Pushing language C Popping language C Pushing language CUDA Popping language CUDA Pushing language Cxx Popping language Cxx Pushing language FC Popping language FC ================================================================================ ================================================================================ Starting Configure Run at Mon Jul 13 15:02:36 2015 Configure Options: --configModules=PETSc.Configure --optionsModule=config.compilerOptions --download-mpich --with-cuda --with-cusp Working directory: /Users/barrysmith/Src/PETSc Machine platform: ('Darwin', 'Barrys-MacBook-Pro.local', '14.4.0', 'Darwin Kernel Version 14.4.0: Thu May 28 11:35:04 PDT 2015; root:xnu-2782.30.5~1/RELEASE_X86_64', 'x86_64', 'i386') Python version: 2.7.6 (default, Sep 9 2014, 15:04:36) [GCC 4.2.1 Compatible Apple LLVM 6.0 (clang-600.0.39)] ================================================================================ Pushing language C Popping language C Pushing language CUDA Popping language CUDA Pushing language Cxx Popping language Cxx Pushing language FC Popping language FC ================================================================================ TEST configureExternalPackagesDir from config.framework(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/framework.py:833) TESTING: configureExternalPackagesDir from config.framework(config/BuildSystem/config/framework.py:833) ================================================================================ TEST configureDebuggers from config.utilities.debuggers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/utilities/debuggers.py:22) TESTING: configureDebuggers from config.utilities.debuggers(config/BuildSystem/config/utilities/debuggers.py:22) Find a default debugger and determine its arguments Checking for program /Users/barrysmith/Src/PETSc/bin/gdb...not found Checking for program gdb...not found Checking for program /Users/barrysmith/bin/gdb...not found Checking for program /usr/local/bin/gdb...not found Checking for program /usr/bin/gdb...not found Checking for program /bin/gdb...not found Checking for program /usr/sbin/gdb...not found Checking for program /sbin/gdb...not found Checking for program /opt/X11/bin/gdb...not found Checking for program /usr/texbin/gdb...not found Checking for program /usr/local/texlive/2014/bin/x86_64-darwin/gdb...not found Checking for program /bin/gdb...not found Checking for program /usr/X11R6/bin/gdb...not found Checking for program /Users/barrysmith/Src/pyjs/bin/gdb...not found Checking for program /Users/barrysmith/gdb...not found Checking for program /Users/barrysmith/Src/PETSc/bin/dbx...not found Checking for program dbx...not found Checking for program /Users/barrysmith/bin/dbx...not found Checking for program /usr/local/bin/dbx...not found Checking for program /usr/bin/dbx...not found Checking for program /bin/dbx...not found Checking for program /usr/sbin/dbx...not found Checking for program /sbin/dbx...not found Checking for program /opt/X11/bin/dbx...not found Checking for program /usr/texbin/dbx...not found Checking for program /usr/local/texlive/2014/bin/x86_64-darwin/dbx...not found Checking for program /bin/dbx...not found Checking for program /usr/X11R6/bin/dbx...not found Checking for program /Users/barrysmith/Src/pyjs/bin/dbx...not found Checking for program /Users/barrysmith/dbx...not found Checking for program /Users/barrysmith/Src/PETSc/bin/xdb...not found Checking for program xdb...not found Checking for program /Users/barrysmith/bin/xdb...not found Checking for program /usr/local/bin/xdb...not found Checking for program /usr/bin/xdb...not found Checking for program /bin/xdb...not found Checking for program /usr/sbin/xdb...not found Checking for program /sbin/xdb...not found Checking for program /opt/X11/bin/xdb...not found Checking for program /usr/texbin/xdb...not found Checking for program /usr/local/texlive/2014/bin/x86_64-darwin/xdb...not found Checking for program /bin/xdb...not found Checking for program /usr/X11R6/bin/xdb...not found Checking for program /Users/barrysmith/Src/pyjs/bin/xdb...not found Checking for program /Users/barrysmith/xdb...not found Checking for program /Users/barrysmith/Src/PETSc/bin/dsymutil...not found Checking for program dsymutil...not found Checking for program /Users/barrysmith/bin/dsymutil...not found Checking for program /usr/local/bin/dsymutil...not found Checking for program /usr/bin/dsymutil...found Defined make macro "DSYMUTIL" to "/usr/bin/dsymutil" Defined make macro "DSYMUTIL" to "/usr/bin/dsymutil" ================================================================================ TEST configureGit from config.sourceControl(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/sourceControl.py:24) TESTING: configureGit from config.sourceControl(config/BuildSystem/config/sourceControl.py:24) Find the Git executable Checking for program /Users/barrysmith/Src/PETSc/bin/git...not found Checking for program git...not found Checking for program /Users/barrysmith/bin/git...not found Checking for program /usr/local/bin/git...not found Checking for program /usr/bin/git...found Defined make macro "GIT" to "git" Executing: git --version stdout: git version 2.3.2 (Apple Git-55) ================================================================================ TEST configureCLanguage from PETSc.options.languages(/Users/barrysmith/Src/PETSc/config/PETSc/options/languages.py:27) TESTING: configureCLanguage from PETSc.options.languages(config/PETSc/options/languages.py:27) Choose whether to compile the PETSc library using a C or C++ compiler C language is C Defined "CLANGUAGE_C" to "1" ================================================================================ TEST configureDirectories from PETSc.options.petscdir(/Users/barrysmith/Src/PETSc/config/PETSc/options/petscdir.py:23) TESTING: configureDirectories from PETSc.options.petscdir(config/PETSc/options/petscdir.py:23) Checks PETSC_DIR and sets if not set Version Information: #define PETSC_VERSION_RELEASE 0 #define PETSC_VERSION_MAJOR 3 #define PETSC_VERSION_MINOR 6 #define PETSC_VERSION_SUBMINOR 0 #define PETSC_VERSION_PATCH 0 #define PETSC_VERSION_DATE "unknown" #define PETSC_VERSION_GIT "unknown" #define PETSC_VERSION_DATE_GIT "unknown" #define PETSC_VERSION_(MAJOR,MINOR,SUBMINOR) \ #define PETSC_VERSION_LT(MAJOR,MINOR,SUBMINOR) \ #define PETSC_VERSION_LE(MAJOR,MINOR,SUBMINOR) \ #define PETSC_VERSION_GT(MAJOR,MINOR,SUBMINOR) \ #define PETSC_VERSION_GE(MAJOR,MINOR,SUBMINOR) \ Defined make macro "DIR" to "/Users/barrysmith/Src/PETSc" ================================================================================ TEST configureInstallationMethod from PETSc.options.petscclone(/Users/barrysmith/Src/PETSc/config/PETSc/options/petscclone.py:20) TESTING: configureInstallationMethod from PETSc.options.petscclone(config/PETSc/options/petscclone.py:20) bin/maint exists. This appears to be a repository clone .git directory exists Executing: cd /Users/barrysmith/Src/PETSc && git describe stdout: v3.6-179-gcfb7fed Executing: cd /Users/barrysmith/Src/PETSc && git log -1 --pretty=format:%H stdout: cfb7fed6c1e94c9d56b4bb5758fa38f8d683b510 Executing: cd /Users/barrysmith/Src/PETSc && git log -1 --pretty=format:%ci stdout: 2015-07-13 14:33:16 -0500 Executing: cd /Users/barrysmith/Src/PETSc && git branch stdout: barry/add-dmdavecgetarrayreadf90/maint barry/error-on-extern-c-of-petscincludes barry/fix-stageevent-idtypes barry/logobjectlifememory barry/maint/fix-snessetupdate-fortran barry/maint/mv-matnullspace-to-mat * barry/master/fix-cuda-extern-c barry/more-tchem-work barry/remove-matmffdaddnullspace/master barry/remove-pcsetup-mg-changeofpreonly/master barry/saws-profile emil/fix-ts-dae-rebased-v2 hongzh/petsc-sa hongzh/ts-matshell-example karpeev/maint/mat-settype-clear maint master next pr192/Fande-Kong/scalable-matincreaseoverlap/master pr345/anriseth/anriseth/ngmres-reset-xm-increase/master Defined "VERSION_GIT" to ""v3.6-179-gcfb7fed"" Defined "VERSION_DATE_GIT" to ""2015-07-13 14:33:16 -0500"" Defined "VERSION_BRANCH_GIT" to ""barry/master/fix-cuda-extern-c"" ================================================================================ TEST getDatafilespath from PETSc.options.dataFilesPath(/Users/barrysmith/Src/PETSc/config/PETSc/options/dataFilesPath.py:29) TESTING: getDatafilespath from PETSc.options.dataFilesPath(config/PETSc/options/dataFilesPath.py:29) Checks what DATAFILESPATH should be ================================================================================ TEST configureArchitecture from PETSc.options.arch(/Users/barrysmith/Src/PETSc/config/PETSc/options/arch.py:25) TESTING: configureArchitecture from PETSc.options.arch(config/PETSc/options/arch.py:25) Checks PETSC_ARCH and sets if not set Defined "ARCH" to ""arch-cuda"" ================================================================================ TEST setInstallDir from PETSc.options.installDir(/Users/barrysmith/Src/PETSc/config/PETSc/options/installDir.py:35) TESTING: setInstallDir from PETSc.options.installDir(config/PETSc/options/installDir.py:35) setup installDir to either prefix or if that is not set to PETSC_DIR/PETSC_ARCH ================================================================================ TEST saveReconfigure from PETSc.options.installDir(/Users/barrysmith/Src/PETSc/config/PETSc/options/installDir.py:74) TESTING: saveReconfigure from PETSc.options.installDir(config/PETSc/options/installDir.py:74) ================================================================================ TEST cleanInstallDir from PETSc.options.installDir(/Users/barrysmith/Src/PETSc/config/PETSc/options/installDir.py:67) TESTING: cleanInstallDir from PETSc.options.installDir(config/PETSc/options/installDir.py:67) ================================================================================ TEST configureInstallDir from PETSc.options.installDir(/Users/barrysmith/Src/PETSc/config/PETSc/options/installDir.py:51) TESTING: configureInstallDir from PETSc.options.installDir(config/PETSc/options/installDir.py:51) Makes installDir subdirectories if it does not exist for both prefix install location and PETSc work install location Changed persistence directory to /Users/barrysmith/Src/PETSc/arch-cuda/lib/petsc/conf ================================================================================ TEST restoreReconfigure from PETSc.options.installDir(/Users/barrysmith/Src/PETSc/config/PETSc/options/installDir.py:87) TESTING: restoreReconfigure from PETSc.options.installDir(config/PETSc/options/installDir.py:87) ================================================================================ TEST setExternalPackagesDir from PETSc.options.externalpackagesdir(/Users/barrysmith/Src/PETSc/config/PETSc/options/externalpackagesdir.py:15) TESTING: setExternalPackagesDir from PETSc.options.externalpackagesdir(config/PETSc/options/externalpackagesdir.py:15) ================================================================================ TEST cleanExternalpackagesDir from PETSc.options.externalpackagesdir(/Users/barrysmith/Src/PETSc/config/PETSc/options/externalpackagesdir.py:22) TESTING: cleanExternalpackagesDir from PETSc.options.externalpackagesdir(config/PETSc/options/externalpackagesdir.py:22) ================================================================================ TEST printEnvVariables from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:1541) TESTING: printEnvVariables from config.setCompilers(config/BuildSystem/config/setCompilers.py:1541) **** printenv **** GIT_PS1_SHOWDIRTYSTATE=1 VERSIONER_PYTHON_PREFER_32_BIT=no MATLABPATH=/Users/barrysmith/Src/PETSc/share/petsc/matlab:/Users/barrysmith/Src/nodal-dg/Codes1.1:/Users/barrysmith/Src/nodal-dg/Codes1.1/CFD2D:/Users/barrysmith/Src/nodal-dg/Codes1.1/ TERM_PROGRAM_VERSION=343.7 LOGNAME=barrysmith USER=barrysmith HOME=/Users/barrysmith PATH=/Users/barrysmith/Src/PETSc/bin::/Users/barrysmith/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:/opt/X11/bin:/usr/texbin:/usr/local/texlive/2014/bin/x86_64-darwin:/bin:/usr/X11R6/bin:/Users/barrysmith/Src/pyjs/bin PS1=\w\[\e[1m\]\[\e[35m\]$(__git_ps1 " (%s)")\[\e[0m\] ${PETSC_ARCH}\n\$ DISPLAY=/private/tmp/com.apple.launchd.RuEJNTE83x/org.macosforge.xquartz:0 TERM_PROGRAM=Apple_Terminal LANG=en_US.UTF-8 TERM=xterm-256color SHELL=/bin/bash TEXINPUTS=/Users/barrysmith/Documents/JedsPresentations/tex-mcs/ANLBlue/:/Users/barrysmith/Documents/JedsPresentations/tex-mcs/ANLBlue/images: VERSIONER_PYTHON_VERSION=2.7 SHLVL=1 SECURITYSESSIONID=18730 PETSC_ARCH=arch-cuda XPC_FLAGS=0x0 GIT_PS1_SHOWUPSTREAM=auto PETSC_DIR=/Users/barrysmith/Src/PETSc _=./configure PETSC_OPTIONS=-malloc_test JENKINS_USERNAME=bsmith TERM_SESSION_ID=11E7B75F-FF01-41DB-86BD-50E8D200017A XPC_SERVICE_NAME=0 SSH_AUTH_SOCK=/private/tmp/com.apple.launchd.OJ2kyhFr8k/Listeners DATAFILESPATH=/Users/barrysmith/Datafiles Apple_PubSub_Socket_Render=/private/tmp/com.apple.launchd.8nfv2JfX8Q/Render TMPDIR=/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/ JENKINS_EMAIL=bsmith@mcs.anl.gov OLDPWD=/Users/barrysmith CLICOLOR= __CF_USER_TEXT_ENCODING=0x1F5:0x0:0x0 PWD=/Users/barrysmith/Src/petsc ================================================================================ TEST resetEnvCompilers from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:1548) TESTING: resetEnvCompilers from config.setCompilers(config/BuildSystem/config/setCompilers.py:1548) ================================================================================ TEST checkEnvCompilers from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:1578) TESTING: checkEnvCompilers from config.setCompilers(config/BuildSystem/config/setCompilers.py:1578) ================================================================================ TEST checkMPICompilerOverride from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:1513) TESTING: checkMPICompilerOverride from config.setCompilers(config/BuildSystem/config/setCompilers.py:1513) Check if --with-mpi-dir is used along with CC CXX or FC compiler options. This usually prevents mpi compilers from being used - so issue a warning ================================================================================ TEST requireMpiLdPath from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:1532) TESTING: requireMpiLdPath from config.setCompilers(config/BuildSystem/config/setCompilers.py:1532) OpenMPI wrappers require LD_LIBRARY_PATH set ================================================================================ TEST checkVendor from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:399) TESTING: checkVendor from config.setCompilers(config/BuildSystem/config/setCompilers.py:399) Determine the compiler vendor Compiler vendor is "" ================================================================================ TEST checkInitialFlags from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:409) TESTING: checkInitialFlags from config.setCompilers(config/BuildSystem/config/setCompilers.py:409) Initialize the compiler and linker flags Pushing language C Initialized CFLAGS to Initialized CFLAGS to Initialized LDFLAGS to Popping language C Pushing language CUDA Initialized CUDAFLAGS to Initialized CUDAFLAGS to Initialized LDFLAGS to Popping language CUDA Pushing language Cxx Initialized CXXFLAGS to Initialized CXX_CXXFLAGS to Initialized LDFLAGS to Popping language Cxx Pushing language FC Initialized FFLAGS to Initialized FFLAGS to Initialized LDFLAGS to Popping language FC Initialized CPPFLAGS to Initialized CUDAPPFLAGS to Initialized CXXCPPFLAGS to Initialized CC_LINKER_FLAGS to [] Initialized CXX_LINKER_FLAGS to [] Initialized FC_LINKER_FLAGS to [] Initialized CUDAC_LINKER_FLAGS to [] Initialized sharedLibraryFlags to [] Initialized dynamicLibraryFlags to [] ================================================================================ TEST checkCCompiler from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:535) TESTING: checkCCompiler from config.setCompilers(config/BuildSystem/config/setCompilers.py:535) Locate a functional C compiler Checking for program /Users/barrysmith/Src/PETSc/bin/gcc...not found Checking for program gcc...not found Checking for program /Users/barrysmith/bin/gcc...not found Checking for program /usr/local/bin/gcc...not found Checking for program /usr/bin/gcc...found Defined make macro "CC" to "gcc" Pushing language C All intermediate test results are stored in /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4 All intermediate test results are stored in /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers Executing: gcc -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Executing: gcc -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Pushing language C Popping language C Pushing language CUDA Popping language CUDA Pushing language Cxx Popping language Cxx Pushing language FC Popping language FC Pushing language C Popping language C Executing: gcc -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o Executing: gcc -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Pushing language C Popping language C Executing: gcc -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -lpetsc-ufod4vtr9mqHvKIQiVAm Possible ERROR while running linker: exit code 256 stderr: ld: library not found for -lpetsc-ufod4vtr9mqHvKIQiVAm clang: error: linker command failed with exit code 1 (use -v to see invocation) Executing: gcc -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Pushing language C Popping language C Executing: gcc -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o Testing executable /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest to see if it can be run Executing: /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest Executing: /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest Popping language C ================================================================================ TEST checkCPreprocessor from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:568) TESTING: checkCPreprocessor from config.setCompilers(config/BuildSystem/config/setCompilers.py:568) Locate a functional C preprocessor Checking for program /Users/barrysmith/Src/PETSc/bin/gcc...not found Checking for program gcc...not found Checking for program /Users/barrysmith/bin/gcc...not found Checking for program /usr/local/bin/gcc...not found Checking for program /usr/bin/gcc...found Defined make macro "CPP" to "gcc -E" Pushing language C Executing: gcc -E -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c stdout: # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c" # 1 "" 1 # 1 "" 3 # 321 "" 3 # 1 "" 1 # 1 "" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/confdefs.h" 1 # 2 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conffix.h" 1 # 3 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c" 2 # 1 "/usr/include/stdlib.h" 1 3 4 # 61 "/usr/include/stdlib.h" 3 4 # 1 "/usr/include/Availability.h" 1 3 4 # 153 "/usr/include/Availability.h" 3 4 # 1 "/usr/include/AvailabilityInternal.h" 1 3 4 # 154 "/usr/include/Availability.h" 2 3 4 # 62 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/_types.h" 1 3 4 # 27 "/usr/include/_types.h" 3 4 # 1 "/usr/include/sys/_types.h" 1 3 4 # 32 "/usr/include/sys/_types.h" 3 4 # 1 "/usr/include/sys/cdefs.h" 1 3 4 # 506 "/usr/include/sys/cdefs.h" 3 4 # 1 "/usr/include/sys/_symbol_aliasing.h" 1 3 4 # 507 "/usr/include/sys/cdefs.h" 2 3 4 # 572 "/usr/include/sys/cdefs.h" 3 4 # 1 "/usr/include/sys/_posix_availability.h" 1 3 4 # 573 "/usr/include/sys/cdefs.h" 2 3 4 # 33 "/usr/include/sys/_types.h" 2 3 4 # 1 "/usr/include/machine/_types.h" 1 3 4 # 32 "/usr/include/machine/_types.h" 3 4 # 1 "/usr/include/i386/_types.h" 1 3 4 # 37 "/usr/include/i386/_types.h" 3 4 typedef signed char __int8_t; typedef unsigned char __uint8_t; typedef short __int16_t; typedef unsigned short __uint16_t; typedef int __int32_t; typedef unsigned int __uint32_t; typedef long long __int64_t; typedef unsigned long long __uint64_t; typedef long __darwin_intptr_t; typedef unsigned int __darwin_natural_t; # 70 "/usr/include/i386/_types.h" 3 4 typedef int __darwin_ct_rune_t; typedef union { char __mbstate8[128]; long long _mbstateL; } __mbstate_t; typedef __mbstate_t __darwin_mbstate_t; typedef long int __darwin_ptrdiff_t; typedef long unsigned int __darwin_size_t; typedef __builtin_va_list __darwin_va_list; typedef int __darwin_wchar_t; typedef __darwin_wchar_t __darwin_rune_t; typedef int __darwin_wint_t; typedef unsigned long __darwin_clock_t; typedef __uint32_t __darwin_socklen_t; typedef long __darwin_ssize_t; typedef long __darwin_time_t; # 33 "/usr/include/machine/_types.h" 2 3 4 # 34 "/usr/include/sys/_types.h" 2 3 4 # 55 "/usr/include/sys/_types.h" 3 4 typedef __int64_t __darwin_blkcnt_t; typedef __int32_t __darwin_blksize_t; typedef __int32_t __darwin_dev_t; typedef unsigned int __darwin_fsblkcnt_t; typedef unsigned int __darwin_fsfilcnt_t; typedef __uint32_t __darwin_gid_t; typedef __uint32_t __darwin_id_t; typedef __uint64_t __darwin_ino64_t; typedef __darwin_ino64_t __darwin_ino_t; typedef __darwin_natural_t __darwin_mach_port_name_t; typedef __darwin_mach_port_name_t __darwin_mach_port_t; typedef __uint16_t __darwin_mode_t; typedef __int64_t __darwin_off_t; typedef __int32_t __darwin_pid_t; typedef __uint32_t __darwin_sigset_t; typedef __int32_t __darwin_suseconds_t; typedef __uint32_t __darwin_uid_t; typedef __uint32_t __darwin_useconds_t; typedef unsigned char __darwin_uuid_t[16]; typedef char __darwin_uuid_string_t[37]; # 1 "/usr/include/sys/_pthread/_pthread_types.h" 1 3 4 # 57 "/usr/include/sys/_pthread/_pthread_types.h" 3 4 struct __darwin_pthread_handler_rec { void (*__routine)(void *); void *__arg; struct __darwin_pthread_handler_rec *__next; }; struct _opaque_pthread_attr_t { long __sig; char __opaque[56]; }; struct _opaque_pthread_cond_t { long __sig; char __opaque[40]; }; struct _opaque_pthread_condattr_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_mutex_t { long __sig; char __opaque[56]; }; struct _opaque_pthread_mutexattr_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_once_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_rwlock_t { long __sig; char __opaque[192]; }; struct _opaque_pthread_rwlockattr_t { long __sig; char __opaque[16]; }; struct _opaque_pthread_t { long __sig; struct __darwin_pthread_handler_rec *__cleanup_stack; char __opaque[8176]; }; typedef struct _opaque_pthread_attr_t __darwin_pthread_attr_t; typedef struct _opaque_pthread_cond_t __darwin_pthread_cond_t; typedef struct _opaque_pthread_condattr_t __darwin_pthread_condattr_t; typedef unsigned long __darwin_pthread_key_t; typedef struct _opaque_pthread_mutex_t __darwin_pthread_mutex_t; typedef struct _opaque_pthread_mutexattr_t __darwin_pthread_mutexattr_t; typedef struct _opaque_pthread_once_t __darwin_pthread_once_t; typedef struct _opaque_pthread_rwlock_t __darwin_pthread_rwlock_t; typedef struct _opaque_pthread_rwlockattr_t __darwin_pthread_rwlockattr_t; typedef struct _opaque_pthread_t *__darwin_pthread_t; # 81 "/usr/include/sys/_types.h" 2 3 4 # 28 "/usr/include/_types.h" 2 3 4 # 39 "/usr/include/_types.h" 3 4 typedef int __darwin_nl_item; typedef int __darwin_wctrans_t; typedef __uint32_t __darwin_wctype_t; # 64 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/wait.h" 1 3 4 # 79 "/usr/include/sys/wait.h" 3 4 typedef enum { P_ALL, P_PID, P_PGID } idtype_t; # 1 "/usr/include/sys/_types/_pid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_pid_t.h" 3 4 typedef __darwin_pid_t pid_t; # 90 "/usr/include/sys/wait.h" 2 3 4 # 1 "/usr/include/sys/_types/_id_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_id_t.h" 3 4 typedef __darwin_id_t id_t; # 91 "/usr/include/sys/wait.h" 2 3 4 # 109 "/usr/include/sys/wait.h" 3 4 # 1 "/usr/include/sys/signal.h" 1 3 4 # 73 "/usr/include/sys/signal.h" 3 4 # 1 "/usr/include/sys/appleapiopts.h" 1 3 4 # 74 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/machine/signal.h" 1 3 4 # 32 "/usr/include/machine/signal.h" 3 4 # 1 "/usr/include/i386/signal.h" 1 3 4 # 39 "/usr/include/i386/signal.h" 3 4 typedef int sig_atomic_t; # 33 "/usr/include/machine/signal.h" 2 3 4 # 82 "/usr/include/sys/signal.h" 2 3 4 # 145 "/usr/include/sys/signal.h" 3 4 # 1 "/usr/include/machine/_mcontext.h" 1 3 4 # 29 "/usr/include/machine/_mcontext.h" 3 4 # 1 "/usr/include/i386/_mcontext.h" 1 3 4 # 33 "/usr/include/i386/_mcontext.h" 3 4 # 1 "/usr/include/mach/i386/_structs.h" 1 3 4 # 43 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_thread_state { unsigned int __eax; unsigned int __ebx; unsigned int __ecx; unsigned int __edx; unsigned int __edi; unsigned int __esi; unsigned int __ebp; unsigned int __esp; unsigned int __ss; unsigned int __eflags; unsigned int __eip; unsigned int __cs; unsigned int __ds; unsigned int __es; unsigned int __fs; unsigned int __gs; }; # 89 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_fp_control { unsigned short __invalid :1, __denorm :1, __zdiv :1, __ovrfl :1, __undfl :1, __precis :1, :2, __pc :2, __rc :2, :1, :3; }; typedef struct __darwin_fp_control __darwin_fp_control_t; # 147 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_fp_status { unsigned short __invalid :1, __denorm :1, __zdiv :1, __ovrfl :1, __undfl :1, __precis :1, __stkflt :1, __errsumm :1, __c0 :1, __c1 :1, __c2 :1, __tos :3, __c3 :1, __busy :1; }; typedef struct __darwin_fp_status __darwin_fp_status_t; # 191 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_mmst_reg { char __mmst_reg[10]; char __mmst_rsrv[6]; }; # 210 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_xmm_reg { char __xmm_reg[16]; }; # 232 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_float_state { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; char __fpu_rsrv4[14*16]; int __fpu_reserved1; }; struct __darwin_i386_avx_state { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; char __fpu_rsrv4[14*16]; int __fpu_reserved1; char __avx_reserved1[64]; struct __darwin_xmm_reg __fpu_ymmh0; struct __darwin_xmm_reg __fpu_ymmh1; struct __darwin_xmm_reg __fpu_ymmh2; struct __darwin_xmm_reg __fpu_ymmh3; struct __darwin_xmm_reg __fpu_ymmh4; struct __darwin_xmm_reg __fpu_ymmh5; struct __darwin_xmm_reg __fpu_ymmh6; struct __darwin_xmm_reg __fpu_ymmh7; }; # 402 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_exception_state { __uint16_t __trapno; __uint16_t __cpu; __uint32_t __err; __uint32_t __faultvaddr; }; # 422 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_debug_state32 { unsigned int __dr0; unsigned int __dr1; unsigned int __dr2; unsigned int __dr3; unsigned int __dr4; unsigned int __dr5; unsigned int __dr6; unsigned int __dr7; }; # 454 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_thread_state64 { __uint64_t __rax; __uint64_t __rbx; __uint64_t __rcx; __uint64_t __rdx; __uint64_t __rdi; __uint64_t __rsi; __uint64_t __rbp; __uint64_t __rsp; __uint64_t __r8; __uint64_t __r9; __uint64_t __r10; __uint64_t __r11; __uint64_t __r12; __uint64_t __r13; __uint64_t __r14; __uint64_t __r15; __uint64_t __rip; __uint64_t __rflags; __uint64_t __cs; __uint64_t __fs; __uint64_t __gs; }; # 509 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_float_state64 { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; struct __darwin_xmm_reg __fpu_xmm8; struct __darwin_xmm_reg __fpu_xmm9; struct __darwin_xmm_reg __fpu_xmm10; struct __darwin_xmm_reg __fpu_xmm11; struct __darwin_xmm_reg __fpu_xmm12; struct __darwin_xmm_reg __fpu_xmm13; struct __darwin_xmm_reg __fpu_xmm14; struct __darwin_xmm_reg __fpu_xmm15; char __fpu_rsrv4[6*16]; int __fpu_reserved1; }; struct __darwin_x86_avx_state64 { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; struct __darwin_xmm_reg __fpu_xmm8; struct __darwin_xmm_reg __fpu_xmm9; struct __darwin_xmm_reg __fpu_xmm10; struct __darwin_xmm_reg __fpu_xmm11; struct __darwin_xmm_reg __fpu_xmm12; struct __darwin_xmm_reg __fpu_xmm13; struct __darwin_xmm_reg __fpu_xmm14; struct __darwin_xmm_reg __fpu_xmm15; char __fpu_rsrv4[6*16]; int __fpu_reserved1; char __avx_reserved1[64]; struct __darwin_xmm_reg __fpu_ymmh0; struct __darwin_xmm_reg __fpu_ymmh1; struct __darwin_xmm_reg __fpu_ymmh2; struct __darwin_xmm_reg __fpu_ymmh3; struct __darwin_xmm_reg __fpu_ymmh4; struct __darwin_xmm_reg __fpu_ymmh5; struct __darwin_xmm_reg __fpu_ymmh6; struct __darwin_xmm_reg __fpu_ymmh7; struct __darwin_xmm_reg __fpu_ymmh8; struct __darwin_xmm_reg __fpu_ymmh9; struct __darwin_xmm_reg __fpu_ymmh10; struct __darwin_xmm_reg __fpu_ymmh11; struct __darwin_xmm_reg __fpu_ymmh12; struct __darwin_xmm_reg __fpu_ymmh13; struct __darwin_xmm_reg __fpu_ymmh14; struct __darwin_xmm_reg __fpu_ymmh15; }; # 751 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_exception_state64 { __uint16_t __trapno; __uint16_t __cpu; __uint32_t __err; __uint64_t __faultvaddr; }; # 771 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_debug_state64 { __uint64_t __dr0; __uint64_t __dr1; __uint64_t __dr2; __uint64_t __dr3; __uint64_t __dr4; __uint64_t __dr5; __uint64_t __dr6; __uint64_t __dr7; }; # 34 "/usr/include/i386/_mcontext.h" 2 3 4 struct __darwin_mcontext32 { struct __darwin_i386_exception_state __es; struct __darwin_i386_thread_state __ss; struct __darwin_i386_float_state __fs; }; struct __darwin_mcontext_avx32 { struct __darwin_i386_exception_state __es; struct __darwin_i386_thread_state __ss; struct __darwin_i386_avx_state __fs; }; # 76 "/usr/include/i386/_mcontext.h" 3 4 struct __darwin_mcontext64 { struct __darwin_x86_exception_state64 __es; struct __darwin_x86_thread_state64 __ss; struct __darwin_x86_float_state64 __fs; }; struct __darwin_mcontext_avx64 { struct __darwin_x86_exception_state64 __es; struct __darwin_x86_thread_state64 __ss; struct __darwin_x86_avx_state64 __fs; }; # 115 "/usr/include/i386/_mcontext.h" 3 4 typedef struct __darwin_mcontext64 *mcontext_t; # 30 "/usr/include/machine/_mcontext.h" 2 3 4 # 146 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_pthread/_pthread_attr_t.h" 1 3 4 # 30 "/usr/include/sys/_pthread/_pthread_attr_t.h" 3 4 typedef __darwin_pthread_attr_t pthread_attr_t; # 148 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_sigaltstack.h" 1 3 4 # 36 "/usr/include/sys/_types/_sigaltstack.h" 3 4 struct __darwin_sigaltstack { void *ss_sp; __darwin_size_t ss_size; int ss_flags; }; typedef struct __darwin_sigaltstack stack_t; # 150 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_ucontext.h" 1 3 4 # 34 "/usr/include/sys/_types/_ucontext.h" 3 4 struct __darwin_ucontext { int uc_onstack; __darwin_sigset_t uc_sigmask; struct __darwin_sigaltstack uc_stack; struct __darwin_ucontext *uc_link; __darwin_size_t uc_mcsize; struct __darwin_mcontext64 *uc_mcontext; }; typedef struct __darwin_ucontext ucontext_t; # 151 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_sigset_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_sigset_t.h" 3 4 typedef __darwin_sigset_t sigset_t; # 154 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_size_t.h" 3 4 typedef __darwin_size_t size_t; # 155 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_uid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uid_t.h" 3 4 typedef __darwin_uid_t uid_t; # 156 "/usr/include/sys/signal.h" 2 3 4 union sigval { int sival_int; void *sival_ptr; }; struct sigevent { int sigev_notify; int sigev_signo; union sigval sigev_value; void (*sigev_notify_function)(union sigval); pthread_attr_t *sigev_notify_attributes; }; typedef struct __siginfo { int si_signo; int si_errno; int si_code; pid_t si_pid; uid_t si_uid; int si_status; void *si_addr; union sigval si_value; long si_band; unsigned long __pad[7]; } siginfo_t; # 268 "/usr/include/sys/signal.h" 3 4 union __sigaction_u { void (*__sa_handler)(int); void (*__sa_sigaction)(int, struct __siginfo *, void *); }; struct __sigaction { union __sigaction_u __sigaction_u; void (*sa_tramp)(void *, int, int, siginfo_t *, void *); sigset_t sa_mask; int sa_flags; }; struct sigaction { union __sigaction_u __sigaction_u; sigset_t sa_mask; int sa_flags; }; # 330 "/usr/include/sys/signal.h" 3 4 typedef void (*sig_t)(int); # 347 "/usr/include/sys/signal.h" 3 4 struct sigvec { void (*sv_handler)(int); int sv_mask; int sv_flags; }; # 366 "/usr/include/sys/signal.h" 3 4 struct sigstack { char *ss_sp; int ss_onstack; }; # 389 "/usr/include/sys/signal.h" 3 4 void (*signal(int, void (*)(int)))(int); # 110 "/usr/include/sys/wait.h" 2 3 4 # 1 "/usr/include/sys/resource.h" 1 3 4 # 72 "/usr/include/sys/resource.h" 3 4 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 1 3 4 # 63 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 3 4 # 1 "/usr/include/stdint.h" 1 3 4 # 18 "/usr/include/stdint.h" 3 4 # 1 "/usr/include/sys/_types/_int8_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int8_t.h" 3 4 typedef signed char int8_t; # 19 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int16_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int16_t.h" 3 4 typedef short int16_t; # 20 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int32_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int32_t.h" 3 4 typedef int int32_t; # 21 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int64_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int64_t.h" 3 4 typedef long long int64_t; # 22 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint8_t.h" 1 3 4 # 31 "/usr/include/_types/_uint8_t.h" 3 4 typedef unsigned char uint8_t; # 24 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint16_t.h" 1 3 4 # 31 "/usr/include/_types/_uint16_t.h" 3 4 typedef unsigned short uint16_t; # 25 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint32_t.h" 1 3 4 # 31 "/usr/include/_types/_uint32_t.h" 3 4 typedef unsigned int uint32_t; # 26 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint64_t.h" 1 3 4 # 31 "/usr/include/_types/_uint64_t.h" 3 4 typedef unsigned long long uint64_t; # 27 "/usr/include/stdint.h" 2 3 4 typedef int8_t int_least8_t; typedef int16_t int_least16_t; typedef int32_t int_least32_t; typedef int64_t int_least64_t; typedef uint8_t uint_least8_t; typedef uint16_t uint_least16_t; typedef uint32_t uint_least32_t; typedef uint64_t uint_least64_t; typedef int8_t int_fast8_t; typedef int16_t int_fast16_t; typedef int32_t int_fast32_t; typedef int64_t int_fast64_t; typedef uint8_t uint_fast8_t; typedef uint16_t uint_fast16_t; typedef uint32_t uint_fast32_t; typedef uint64_t uint_fast64_t; # 1 "/usr/include/sys/_types/_intptr_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_intptr_t.h" 3 4 typedef __darwin_intptr_t intptr_t; # 54 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_uintptr_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uintptr_t.h" 3 4 typedef unsigned long uintptr_t; # 55 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_intmax_t.h" 1 3 4 # 32 "/usr/include/_types/_intmax_t.h" 3 4 typedef long int intmax_t; # 59 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uintmax_t.h" 1 3 4 # 32 "/usr/include/_types/_uintmax_t.h" 3 4 typedef long unsigned int uintmax_t; # 60 "/usr/include/stdint.h" 2 3 4 # 64 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 2 3 4 # 73 "/usr/include/sys/resource.h" 2 3 4 # 1 "/usr/include/sys/_types/_timeval.h" 1 3 4 # 30 "/usr/include/sys/_types/_timeval.h" 3 4 struct timeval { __darwin_time_t tv_sec; __darwin_suseconds_t tv_usec; }; # 81 "/usr/include/sys/resource.h" 2 3 4 typedef __uint64_t rlim_t; # 152 "/usr/include/sys/resource.h" 3 4 struct rusage { struct timeval ru_utime; struct timeval ru_stime; # 163 "/usr/include/sys/resource.h" 3 4 long ru_maxrss; long ru_ixrss; long ru_idrss; long ru_isrss; long ru_minflt; long ru_majflt; long ru_nswap; long ru_inblock; long ru_oublock; long ru_msgsnd; long ru_msgrcv; long ru_nsignals; long ru_nvcsw; long ru_nivcsw; }; # 192 "/usr/include/sys/resource.h" 3 4 typedef void *rusage_info_t; struct rusage_info_v0 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; }; struct rusage_info_v1 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; }; struct rusage_info_v2 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; uint64_t ri_diskio_bytesread; uint64_t ri_diskio_byteswritten; }; struct rusage_info_v3 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; uint64_t ri_diskio_bytesread; uint64_t ri_diskio_byteswritten; uint64_t ri_cpu_time_qos_default; uint64_t ri_cpu_time_qos_maintenance; uint64_t ri_cpu_time_qos_background; uint64_t ri_cpu_time_qos_utility; uint64_t ri_cpu_time_qos_legacy; uint64_t ri_cpu_time_qos_user_initiated; uint64_t ri_cpu_time_qos_user_interactive; uint64_t ri_billed_system_time; uint64_t ri_serviced_system_time; }; typedef struct rusage_info_v3 rusage_info_current; # 325 "/usr/include/sys/resource.h" 3 4 struct rlimit { rlim_t rlim_cur; rlim_t rlim_max; }; # 353 "/usr/include/sys/resource.h" 3 4 struct proc_rlimit_control_wakeupmon { uint32_t wm_flags; int32_t wm_rate; }; # 383 "/usr/include/sys/resource.h" 3 4 int getpriority(int, id_t); int getiopolicy_np(int, int) __attribute__((availability(macosx,introduced=10.5))); int getrlimit(int, struct rlimit *) __asm("_" "getrlimit" ); int getrusage(int, struct rusage *); int setpriority(int, id_t, int); int setiopolicy_np(int, int, int) __attribute__((availability(macosx,introduced=10.5))); int setrlimit(int, const struct rlimit *) __asm("_" "setrlimit" ); # 111 "/usr/include/sys/wait.h" 2 3 4 # 186 "/usr/include/sys/wait.h" 3 4 # 1 "/usr/include/machine/endian.h" 1 3 4 # 35 "/usr/include/machine/endian.h" 3 4 # 1 "/usr/include/i386/endian.h" 1 3 4 # 99 "/usr/include/i386/endian.h" 3 4 # 1 "/usr/include/sys/_endian.h" 1 3 4 # 130 "/usr/include/sys/_endian.h" 3 4 # 1 "/usr/include/libkern/_OSByteOrder.h" 1 3 4 # 66 "/usr/include/libkern/_OSByteOrder.h" 3 4 # 1 "/usr/include/libkern/i386/_OSByteOrder.h" 1 3 4 # 44 "/usr/include/libkern/i386/_OSByteOrder.h" 3 4 static inline __uint16_t _OSSwapInt16( __uint16_t _data ) { return ((__uint16_t)((_data << 8) | (_data >> 8))); } static inline __uint32_t _OSSwapInt32( __uint32_t _data ) { return __builtin_bswap32(_data); } static inline __uint64_t _OSSwapInt64( __uint64_t _data ) { return __builtin_bswap64(_data); } # 67 "/usr/include/libkern/_OSByteOrder.h" 2 3 4 # 131 "/usr/include/sys/_endian.h" 2 3 4 # 100 "/usr/include/i386/endian.h" 2 3 4 # 36 "/usr/include/machine/endian.h" 2 3 4 # 187 "/usr/include/sys/wait.h" 2 3 4 union wait { int w_status; struct { unsigned int w_Termsig:7, w_Coredump:1, w_Retcode:8, w_Filler:16; } w_T; struct { unsigned int w_Stopval:8, w_Stopsig:8, w_Filler:16; } w_S; }; # 248 "/usr/include/sys/wait.h" 3 4 pid_t wait(int *) __asm("_" "wait" ); pid_t waitpid(pid_t, int *, int) __asm("_" "waitpid" ); int waitid(idtype_t, id_t, siginfo_t *, int) __asm("_" "waitid" ); pid_t wait3(int *, int, struct rusage *); pid_t wait4(pid_t, int *, int, struct rusage *); # 66 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/alloca.h" 1 3 4 # 32 "/usr/include/alloca.h" 3 4 void *alloca(size_t); # 68 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_ct_rune_t.h" 1 3 4 # 31 "/usr/include/sys/_types/_ct_rune_t.h" 3 4 typedef __darwin_ct_rune_t ct_rune_t; # 77 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_rune_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_rune_t.h" 3 4 typedef __darwin_rune_t rune_t; # 78 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_wchar_t.h" 1 3 4 # 33 "/usr/include/sys/_types/_wchar_t.h" 3 4 typedef __darwin_wchar_t wchar_t; # 81 "/usr/include/stdlib.h" 2 3 4 typedef struct { int quot; int rem; } div_t; typedef struct { long quot; long rem; } ldiv_t; typedef struct { long long quot; long long rem; } lldiv_t; # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 100 "/usr/include/stdlib.h" 2 3 4 # 117 "/usr/include/stdlib.h" 3 4 extern int __mb_cur_max; # 128 "/usr/include/stdlib.h" 3 4 void abort(void) __attribute__((noreturn)); int abs(int) __attribute__((const)); int atexit(void (*)(void)); double atof(const char *); int atoi(const char *); long atol(const char *); long long atoll(const char *); void *bsearch(const void *, const void *, size_t, size_t, int (*)(const void *, const void *)); void *calloc(size_t, size_t); div_t div(int, int) __attribute__((const)); void exit(int) __attribute__((noreturn)); void free(void *); char *getenv(const char *); long labs(long) __attribute__((const)); ldiv_t ldiv(long, long) __attribute__((const)); long long llabs(long long); lldiv_t lldiv(long long, long long); void *malloc(size_t); int mblen(const char *, size_t); size_t mbstowcs(wchar_t * restrict , const char * restrict, size_t); int mbtowc(wchar_t * restrict, const char * restrict, size_t); int posix_memalign(void **, size_t, size_t) __attribute__((availability(macosx,introduced=10.6))); void qsort(void *, size_t, size_t, int (*)(const void *, const void *)); int rand(void); void *realloc(void *, size_t); void srand(unsigned); double strtod(const char *, char **) __asm("_" "strtod" ); float strtof(const char *, char **) __asm("_" "strtof" ); long strtol(const char *, char **, int); long double strtold(const char *, char **); long long strtoll(const char *, char **, int); unsigned long strtoul(const char *, char **, int); unsigned long long strtoull(const char *, char **, int); int system(const char *) __asm("_" "system" ) __attribute__((availability(macosx,introduced=10.0))); size_t wcstombs(char * restrict, const wchar_t * restrict, size_t); int wctomb(char *, wchar_t); void _Exit(int) __attribute__((noreturn)); long a64l(const char *); double drand48(void); char *ecvt(double, int, int *restrict, int *restrict); double erand48(unsigned short[3]); char *fcvt(double, int, int *restrict, int *restrict); char *gcvt(double, int, char *); int getsubopt(char **, char * const *, char **); int grantpt(int); char *initstate(unsigned, char *, size_t); long jrand48(unsigned short[3]); char *l64a(long); void lcong48(unsigned short[7]); long lrand48(void); char *mktemp(char *); int mkstemp(char *); long mrand48(void); long nrand48(unsigned short[3]); int posix_openpt(int); char *ptsname(int); int putenv(char *) __asm("_" "putenv" ); long random(void); int rand_r(unsigned *); char *realpath(const char * restrict, char * restrict) __asm("_" "realpath" "$DARWIN_EXTSN"); unsigned short *seed48(unsigned short[3]); int setenv(const char *, const char *, int) __asm("_" "setenv" ); void setkey(const char *) __asm("_" "setkey" ); char *setstate(const char *); void srand48(long); void srandom(unsigned); int unlockpt(int); int unsetenv(const char *) __asm("_" "unsetenv" ); # 1 "/usr/include/machine/types.h" 1 3 4 # 35 "/usr/include/machine/types.h" 3 4 # 1 "/usr/include/i386/types.h" 1 3 4 # 81 "/usr/include/i386/types.h" 3 4 typedef unsigned char u_int8_t; typedef unsigned short u_int16_t; typedef unsigned int u_int32_t; typedef unsigned long long u_int64_t; typedef int64_t register_t; # 97 "/usr/include/i386/types.h" 3 4 typedef u_int64_t user_addr_t; typedef u_int64_t user_size_t; typedef int64_t user_ssize_t; typedef int64_t user_long_t; typedef u_int64_t user_ulong_t; typedef int64_t user_time_t; typedef int64_t user_off_t; typedef u_int64_t syscall_arg_t; # 36 "/usr/include/machine/types.h" 2 3 4 # 239 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_dev_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_dev_t.h" 3 4 typedef __darwin_dev_t dev_t; # 241 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_mode_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_mode_t.h" 3 4 typedef __darwin_mode_t mode_t; # 242 "/usr/include/stdlib.h" 2 3 4 u_int32_t arc4random(void); void arc4random_addrandom(unsigned char * , int ); void arc4random_buf(void * , size_t ) __attribute__((availability(macosx,introduced=10.7))); void arc4random_stir(void); u_int32_t arc4random_uniform(u_int32_t ) __attribute__((availability(macosx,introduced=10.7))); int atexit_b(void (^)(void)) __attribute__((availability(macosx,introduced=10.6))); void *bsearch_b(const void *, const void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); char *cgetcap(char *, const char *, int); int cgetclose(void); int cgetent(char **, char **, const char *); int cgetfirst(char **, char **); int cgetmatch(const char *, const char *); int cgetnext(char **, char **); int cgetnum(char *, const char *, long *); int cgetset(const char *); int cgetstr(char *, const char *, char **); int cgetustr(char *, const char *, char **); int daemon(int, int) __asm("_" "daemon" "$1050") __attribute__((availability(macosx,introduced=10.0,deprecated=10.5))); char *devname(dev_t, mode_t); char *devname_r(dev_t, mode_t, char *buf, int len); char *getbsize(int *, long *); int getloadavg(double [], int); const char *getprogname(void); int heapsort(void *, size_t, size_t, int (*)(const void *, const void *)); int heapsort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); int mergesort(void *, size_t, size_t, int (*)(const void *, const void *)); int mergesort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort(void *, size_t, size_t, int (*)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort_r(void *, size_t, size_t, void *, int (*)(void *, const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void qsort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void qsort_r(void *, size_t, size_t, void *, int (*)(void *, const void *, const void *)); int radixsort(const unsigned char **, int, const unsigned char *, unsigned); void setprogname(const char *); int sradixsort(const unsigned char **, int, const unsigned char *, unsigned); void sranddev(void); void srandomdev(void); void *reallocf(void *, size_t); long long strtoq(const char *, char **, int); unsigned long long strtouq(const char *, char **, int); extern char *suboptarg; void *valloc(size_t); # 4 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.c" 2 Preprocess stderr before filtering:: Preprocess stderr after filtering:: Popping language C ================================================================================ TEST checkCUDACompiler from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:609) TESTING: checkCUDACompiler from config.setCompilers(config/BuildSystem/config/setCompilers.py:609) Locate a functional CUDA compiler Checking for program /Users/barrysmith/Src/PETSc/bin/nvcc...not found Checking for program nvcc...not found Checking for program /Users/barrysmith/bin/nvcc...not found Checking for program /usr/local/bin/nvcc...not found Checking for program /usr/bin/nvcc...not found Checking for program /bin/nvcc...not found Checking for program /usr/sbin/nvcc...not found Checking for program /sbin/nvcc...not found Checking for program /opt/X11/bin/nvcc...not found Checking for program /usr/texbin/nvcc...not found Checking for program /usr/local/texlive/2014/bin/x86_64-darwin/nvcc...not found Checking for program /bin/nvcc...not found Checking for program /usr/X11R6/bin/nvcc...not found Checking for program /Users/barrysmith/Src/pyjs/bin/nvcc...not found Checking for program /Users/barrysmith/nvcc...not found Checking for program /Users/barrysmith/Src/PETSc/bin/win32fe/nvcc...not found Checking for program /Users/barrysmith/Src/PETSc/bin/nvcc...not found Checking for program nvcc...not found Checking for program /Users/barrysmith/bin/nvcc...not found Checking for program /usr/local/bin/nvcc...not found Checking for program /usr/bin/nvcc...not found Checking for program /bin/nvcc...not found Checking for program /usr/sbin/nvcc...not found Checking for program /sbin/nvcc...not found Checking for program /opt/X11/bin/nvcc...not found Checking for program /usr/texbin/nvcc...not found Checking for program /usr/local/texlive/2014/bin/x86_64-darwin/nvcc...not found Checking for program /bin/nvcc...not found Checking for program /usr/X11R6/bin/nvcc...not found Checking for program /Users/barrysmith/Src/pyjs/bin/nvcc...not found Checking for program /Users/barrysmith/nvcc...not found Checking for program /Users/barrysmith/Src/PETSc/bin/win32fe/nvcc...not found Checking for program /Developer/NVIDIA/CUDA-6.5/bin/nvcc...found Defined make macro "CUDAC" to "/Developer/NVIDIA/CUDA-6.5/bin/nvcc" Pushing language CUDA Executing: /Developer/NVIDIA/CUDA-6.5/bin/nvcc -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cu Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Popping language CUDA Executing: /Developer/NVIDIA/CUDA-6.5/bin/nvcc --version stdout: nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2014 NVIDIA Corporation Built on Thu_Jul_17_19:13:24_CDT_2014 Cuda compilation tools, release 6.5, V6.5.12 ================================================================================ TEST checkCUDAPreprocessor from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:649) TESTING: checkCUDAPreprocessor from config.setCompilers(config/BuildSystem/config/setCompilers.py:649) Locate a functional CUDA preprocessor Checking for program /Developer/NVIDIA/CUDA-6.5/bin/nvcc...found Defined make macro "CUDAPP" to "/Developer/NVIDIA/CUDA-6.5/bin/nvcc -arch=sm_20 -E" Pushing language CUDA Executing: /Developer/NVIDIA/CUDA-6.5/bin/nvcc -arch=sm_20 -E -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cu stdout: # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cu" # 1 "" 1 # 1 "" 3 # 326 "" 3 # 1 "" 1 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 1 # 59 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/host_config.h" 1 # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 56 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_types.h" 1 # 53 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_types.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/host_defines.h" 1 # 54 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_types.h" 2 enum __attribute__((device_builtin)) cudaRoundMode { cudaRoundNearest, cudaRoundZero, cudaRoundPosInf, cudaRoundMinInf }; # 57 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" 1 # 70 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/limits.h" 1 3 4 # 37 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/limits.h" 3 4 # 1 "/usr/include/limits.h" 1 3 4 # 63 "/usr/include/limits.h" 3 4 # 1 "/usr/include/sys/cdefs.h" 1 3 4 # 506 "/usr/include/sys/cdefs.h" 3 4 # 1 "/usr/include/sys/_symbol_aliasing.h" 1 3 4 # 507 "/usr/include/sys/cdefs.h" 2 3 4 # 572 "/usr/include/sys/cdefs.h" 3 4 # 1 "/usr/include/sys/_posix_availability.h" 1 3 4 # 573 "/usr/include/sys/cdefs.h" 2 3 4 # 64 "/usr/include/limits.h" 2 3 4 # 1 "/usr/include/machine/limits.h" 1 3 4 # 1 "/usr/include/i386/limits.h" 1 3 4 # 40 "/usr/include/i386/limits.h" 3 4 # 1 "/usr/include/i386/_limits.h" 1 3 4 # 41 "/usr/include/i386/limits.h" 2 3 4 # 7 "/usr/include/machine/limits.h" 2 3 4 # 65 "/usr/include/limits.h" 2 3 4 # 1 "/usr/include/sys/syslimits.h" 1 3 4 # 66 "/usr/include/limits.h" 2 3 4 # 38 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/limits.h" 2 3 4 # 71 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" 2 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stddef.h" 1 3 4 # 47 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stddef.h" 3 4 typedef long int ptrdiff_t; # 58 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stddef.h" 3 4 typedef long unsigned int size_t; # 72 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stddef.h" 3 4 typedef long unsigned int rsize_t; # 72 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" 2 # 128 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" enum __attribute__((device_builtin)) cudaError { cudaSuccess = 0, cudaErrorMissingConfiguration = 1, cudaErrorMemoryAllocation = 2, cudaErrorInitializationError = 3, # 163 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorLaunchFailure = 4, # 172 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorPriorLaunchFailure = 5, # 182 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorLaunchTimeout = 6, # 191 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorLaunchOutOfResources = 7, cudaErrorInvalidDeviceFunction = 8, # 206 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorInvalidConfiguration = 9, cudaErrorInvalidDevice = 10, cudaErrorInvalidValue = 11, cudaErrorInvalidPitchValue = 12, cudaErrorInvalidSymbol = 13, cudaErrorMapBufferObjectFailed = 14, cudaErrorUnmapBufferObjectFailed = 15, cudaErrorInvalidHostPointer = 16, cudaErrorInvalidDevicePointer = 17, cudaErrorInvalidTexture = 18, cudaErrorInvalidTextureBinding = 19, cudaErrorInvalidChannelDescriptor = 20, cudaErrorInvalidMemcpyDirection = 21, # 287 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorAddressOfConstant = 22, # 296 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorTextureFetchFailed = 23, # 305 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorTextureNotBound = 24, # 314 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorSynchronizationError = 25, cudaErrorInvalidFilterSetting = 26, cudaErrorInvalidNormSetting = 27, cudaErrorMixedDeviceExecution = 28, cudaErrorCudartUnloading = 29, cudaErrorUnknown = 30, cudaErrorNotYetImplemented = 31, # 363 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorMemoryValueTooLarge = 32, cudaErrorInvalidResourceHandle = 33, cudaErrorNotReady = 34, cudaErrorInsufficientDriver = 35, # 398 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorSetOnActiveProcess = 36, cudaErrorInvalidSurface = 37, cudaErrorNoDevice = 38, cudaErrorECCUncorrectable = 39, cudaErrorSharedObjectSymbolNotFound = 40, cudaErrorSharedObjectInitFailed = 41, cudaErrorUnsupportedLimit = 42, cudaErrorDuplicateVariableName = 43, cudaErrorDuplicateTextureName = 44, cudaErrorDuplicateSurfaceName = 45, # 460 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorDevicesUnavailable = 46, cudaErrorInvalidKernelImage = 47, cudaErrorNoKernelImageForDevice = 48, # 486 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorIncompatibleDriverContext = 49, cudaErrorPeerAccessAlreadyEnabled = 50, cudaErrorPeerAccessNotEnabled = 51, cudaErrorDeviceAlreadyInUse = 54, cudaErrorProfilerDisabled = 55, cudaErrorProfilerNotInitialized = 56, cudaErrorProfilerAlreadyStarted = 57, cudaErrorProfilerAlreadyStopped = 58, cudaErrorAssert = 59, cudaErrorTooManyPeers = 60, cudaErrorHostMemoryAlreadyRegistered = 61, cudaErrorHostMemoryNotRegistered = 62, cudaErrorOperatingSystem = 63, cudaErrorPeerAccessUnsupported = 64, cudaErrorLaunchMaxDepthExceeded = 65, cudaErrorLaunchFileScopedTex = 66, cudaErrorLaunchFileScopedSurf = 67, # 611 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorSyncDepthExceeded = 68, # 623 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorLaunchPendingCountExceeded = 69, cudaErrorNotPermitted = 70, cudaErrorNotSupported = 71, # 643 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorHardwareStackError = 72, cudaErrorIllegalInstruction = 73, # 660 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorMisalignedAddress = 74, # 671 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" cudaErrorInvalidAddressSpace = 75, cudaErrorInvalidPc = 76, cudaErrorIllegalAddress = 77, cudaErrorInvalidPtx = 78, cudaErrorInvalidGraphicsContext = 79, cudaErrorStartupFailure = 0x7f, cudaErrorApiFailureBase = 10000 }; enum __attribute__((device_builtin)) cudaChannelFormatKind { cudaChannelFormatKindSigned = 0, cudaChannelFormatKindUnsigned = 1, cudaChannelFormatKindFloat = 2, cudaChannelFormatKindNone = 3 }; struct __attribute__((device_builtin)) cudaChannelFormatDesc { int x; int y; int z; int w; enum cudaChannelFormatKind f; }; typedef struct cudaArray *cudaArray_t; typedef const struct cudaArray *cudaArray_const_t; struct cudaArray; typedef struct cudaMipmappedArray *cudaMipmappedArray_t; typedef const struct cudaMipmappedArray *cudaMipmappedArray_const_t; struct cudaMipmappedArray; enum __attribute__((device_builtin)) cudaMemoryType { cudaMemoryTypeHost = 1, cudaMemoryTypeDevice = 2 }; enum __attribute__((device_builtin)) cudaMemcpyKind { cudaMemcpyHostToHost = 0, cudaMemcpyHostToDevice = 1, cudaMemcpyDeviceToHost = 2, cudaMemcpyDeviceToDevice = 3, cudaMemcpyDefault = 4 }; struct __attribute__((device_builtin)) cudaPitchedPtr { void *ptr; size_t pitch; size_t xsize; size_t ysize; }; struct __attribute__((device_builtin)) cudaExtent { size_t width; size_t height; size_t depth; }; struct __attribute__((device_builtin)) cudaPos { size_t x; size_t y; size_t z; }; struct __attribute__((device_builtin)) cudaMemcpy3DParms { cudaArray_t srcArray; struct cudaPos srcPos; struct cudaPitchedPtr srcPtr; cudaArray_t dstArray; struct cudaPos dstPos; struct cudaPitchedPtr dstPtr; struct cudaExtent extent; enum cudaMemcpyKind kind; }; struct __attribute__((device_builtin)) cudaMemcpy3DPeerParms { cudaArray_t srcArray; struct cudaPos srcPos; struct cudaPitchedPtr srcPtr; int srcDevice; cudaArray_t dstArray; struct cudaPos dstPos; struct cudaPitchedPtr dstPtr; int dstDevice; struct cudaExtent extent; }; struct cudaGraphicsResource; enum __attribute__((device_builtin)) cudaGraphicsRegisterFlags { cudaGraphicsRegisterFlagsNone = 0, cudaGraphicsRegisterFlagsReadOnly = 1, cudaGraphicsRegisterFlagsWriteDiscard = 2, cudaGraphicsRegisterFlagsSurfaceLoadStore = 4, cudaGraphicsRegisterFlagsTextureGather = 8 }; enum __attribute__((device_builtin)) cudaGraphicsMapFlags { cudaGraphicsMapFlagsNone = 0, cudaGraphicsMapFlagsReadOnly = 1, cudaGraphicsMapFlagsWriteDiscard = 2 }; enum __attribute__((device_builtin)) cudaGraphicsCubeFace { cudaGraphicsCubeFacePositiveX = 0x00, cudaGraphicsCubeFaceNegativeX = 0x01, cudaGraphicsCubeFacePositiveY = 0x02, cudaGraphicsCubeFaceNegativeY = 0x03, cudaGraphicsCubeFacePositiveZ = 0x04, cudaGraphicsCubeFaceNegativeZ = 0x05 }; enum __attribute__((device_builtin)) cudaResourceType { cudaResourceTypeArray = 0x00, cudaResourceTypeMipmappedArray = 0x01, cudaResourceTypeLinear = 0x02, cudaResourceTypePitch2D = 0x03 }; enum __attribute__((device_builtin)) cudaResourceViewFormat { cudaResViewFormatNone = 0x00, cudaResViewFormatUnsignedChar1 = 0x01, cudaResViewFormatUnsignedChar2 = 0x02, cudaResViewFormatUnsignedChar4 = 0x03, cudaResViewFormatSignedChar1 = 0x04, cudaResViewFormatSignedChar2 = 0x05, cudaResViewFormatSignedChar4 = 0x06, cudaResViewFormatUnsignedShort1 = 0x07, cudaResViewFormatUnsignedShort2 = 0x08, cudaResViewFormatUnsignedShort4 = 0x09, cudaResViewFormatSignedShort1 = 0x0a, cudaResViewFormatSignedShort2 = 0x0b, cudaResViewFormatSignedShort4 = 0x0c, cudaResViewFormatUnsignedInt1 = 0x0d, cudaResViewFormatUnsignedInt2 = 0x0e, cudaResViewFormatUnsignedInt4 = 0x0f, cudaResViewFormatSignedInt1 = 0x10, cudaResViewFormatSignedInt2 = 0x11, cudaResViewFormatSignedInt4 = 0x12, cudaResViewFormatHalf1 = 0x13, cudaResViewFormatHalf2 = 0x14, cudaResViewFormatHalf4 = 0x15, cudaResViewFormatFloat1 = 0x16, cudaResViewFormatFloat2 = 0x17, cudaResViewFormatFloat4 = 0x18, cudaResViewFormatUnsignedBlockCompressed1 = 0x19, cudaResViewFormatUnsignedBlockCompressed2 = 0x1a, cudaResViewFormatUnsignedBlockCompressed3 = 0x1b, cudaResViewFormatUnsignedBlockCompressed4 = 0x1c, cudaResViewFormatSignedBlockCompressed4 = 0x1d, cudaResViewFormatUnsignedBlockCompressed5 = 0x1e, cudaResViewFormatSignedBlockCompressed5 = 0x1f, cudaResViewFormatUnsignedBlockCompressed6H = 0x20, cudaResViewFormatSignedBlockCompressed6H = 0x21, cudaResViewFormatUnsignedBlockCompressed7 = 0x22 }; struct __attribute__((device_builtin)) cudaResourceDesc { enum cudaResourceType resType; union { struct { cudaArray_t array; } array; struct { cudaMipmappedArray_t mipmap; } mipmap; struct { void *devPtr; struct cudaChannelFormatDesc desc; size_t sizeInBytes; } linear; struct { void *devPtr; struct cudaChannelFormatDesc desc; size_t width; size_t height; size_t pitchInBytes; } pitch2D; } res; }; struct __attribute__((device_builtin)) cudaResourceViewDesc { enum cudaResourceViewFormat format; size_t width; size_t height; size_t depth; unsigned int firstMipmapLevel; unsigned int lastMipmapLevel; unsigned int firstLayer; unsigned int lastLayer; }; struct __attribute__((device_builtin)) cudaPointerAttributes { enum cudaMemoryType memoryType; # 1011 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" int device; void *devicePointer; void *hostPointer; int isManaged; }; struct __attribute__((device_builtin)) cudaFuncAttributes { size_t sharedSizeBytes; size_t constSizeBytes; size_t localSizeBytes; int maxThreadsPerBlock; int numRegs; int ptxVersion; int binaryVersion; int cacheModeCA; }; enum __attribute__((device_builtin)) cudaFuncCache { cudaFuncCachePreferNone = 0, cudaFuncCachePreferShared = 1, cudaFuncCachePreferL1 = 2, cudaFuncCachePreferEqual = 3 }; enum __attribute__((device_builtin)) cudaSharedMemConfig { cudaSharedMemBankSizeDefault = 0, cudaSharedMemBankSizeFourByte = 1, cudaSharedMemBankSizeEightByte = 2 }; enum __attribute__((device_builtin)) cudaComputeMode { cudaComputeModeDefault = 0, cudaComputeModeExclusive = 1, cudaComputeModeProhibited = 2, cudaComputeModeExclusiveProcess = 3 }; enum __attribute__((device_builtin)) cudaLimit { cudaLimitStackSize = 0x00, cudaLimitPrintfFifoSize = 0x01, cudaLimitMallocHeapSize = 0x02, cudaLimitDevRuntimeSyncDepth = 0x03, cudaLimitDevRuntimePendingLaunchCount = 0x04 }; enum __attribute__((device_builtin)) cudaOutputMode { cudaKeyValuePair = 0x00, cudaCSV = 0x01 }; enum __attribute__((device_builtin)) cudaDeviceAttr { cudaDevAttrMaxThreadsPerBlock = 1, cudaDevAttrMaxBlockDimX = 2, cudaDevAttrMaxBlockDimY = 3, cudaDevAttrMaxBlockDimZ = 4, cudaDevAttrMaxGridDimX = 5, cudaDevAttrMaxGridDimY = 6, cudaDevAttrMaxGridDimZ = 7, cudaDevAttrMaxSharedMemoryPerBlock = 8, cudaDevAttrTotalConstantMemory = 9, cudaDevAttrWarpSize = 10, cudaDevAttrMaxPitch = 11, cudaDevAttrMaxRegistersPerBlock = 12, cudaDevAttrClockRate = 13, cudaDevAttrTextureAlignment = 14, cudaDevAttrGpuOverlap = 15, cudaDevAttrMultiProcessorCount = 16, cudaDevAttrKernelExecTimeout = 17, cudaDevAttrIntegrated = 18, cudaDevAttrCanMapHostMemory = 19, cudaDevAttrComputeMode = 20, cudaDevAttrMaxTexture1DWidth = 21, cudaDevAttrMaxTexture2DWidth = 22, cudaDevAttrMaxTexture2DHeight = 23, cudaDevAttrMaxTexture3DWidth = 24, cudaDevAttrMaxTexture3DHeight = 25, cudaDevAttrMaxTexture3DDepth = 26, cudaDevAttrMaxTexture2DLayeredWidth = 27, cudaDevAttrMaxTexture2DLayeredHeight = 28, cudaDevAttrMaxTexture2DLayeredLayers = 29, cudaDevAttrSurfaceAlignment = 30, cudaDevAttrConcurrentKernels = 31, cudaDevAttrEccEnabled = 32, cudaDevAttrPciBusId = 33, cudaDevAttrPciDeviceId = 34, cudaDevAttrTccDriver = 35, cudaDevAttrMemoryClockRate = 36, cudaDevAttrGlobalMemoryBusWidth = 37, cudaDevAttrL2CacheSize = 38, cudaDevAttrMaxThreadsPerMultiProcessor = 39, cudaDevAttrAsyncEngineCount = 40, cudaDevAttrUnifiedAddressing = 41, cudaDevAttrMaxTexture1DLayeredWidth = 42, cudaDevAttrMaxTexture1DLayeredLayers = 43, cudaDevAttrMaxTexture2DGatherWidth = 45, cudaDevAttrMaxTexture2DGatherHeight = 46, cudaDevAttrMaxTexture3DWidthAlt = 47, cudaDevAttrMaxTexture3DHeightAlt = 48, cudaDevAttrMaxTexture3DDepthAlt = 49, cudaDevAttrPciDomainId = 50, cudaDevAttrTexturePitchAlignment = 51, cudaDevAttrMaxTextureCubemapWidth = 52, cudaDevAttrMaxTextureCubemapLayeredWidth = 53, cudaDevAttrMaxTextureCubemapLayeredLayers = 54, cudaDevAttrMaxSurface1DWidth = 55, cudaDevAttrMaxSurface2DWidth = 56, cudaDevAttrMaxSurface2DHeight = 57, cudaDevAttrMaxSurface3DWidth = 58, cudaDevAttrMaxSurface3DHeight = 59, cudaDevAttrMaxSurface3DDepth = 60, cudaDevAttrMaxSurface1DLayeredWidth = 61, cudaDevAttrMaxSurface1DLayeredLayers = 62, cudaDevAttrMaxSurface2DLayeredWidth = 63, cudaDevAttrMaxSurface2DLayeredHeight = 64, cudaDevAttrMaxSurface2DLayeredLayers = 65, cudaDevAttrMaxSurfaceCubemapWidth = 66, cudaDevAttrMaxSurfaceCubemapLayeredWidth = 67, cudaDevAttrMaxSurfaceCubemapLayeredLayers = 68, cudaDevAttrMaxTexture1DLinearWidth = 69, cudaDevAttrMaxTexture2DLinearWidth = 70, cudaDevAttrMaxTexture2DLinearHeight = 71, cudaDevAttrMaxTexture2DLinearPitch = 72, cudaDevAttrMaxTexture2DMipmappedWidth = 73, cudaDevAttrMaxTexture2DMipmappedHeight = 74, cudaDevAttrComputeCapabilityMajor = 75, cudaDevAttrComputeCapabilityMinor = 76, cudaDevAttrMaxTexture1DMipmappedWidth = 77, cudaDevAttrStreamPrioritiesSupported = 78, cudaDevAttrGlobalL1CacheSupported = 79, cudaDevAttrLocalL1CacheSupported = 80, cudaDevAttrMaxSharedMemoryPerMultiprocessor = 81, cudaDevAttrMaxRegistersPerMultiprocessor = 82, cudaDevAttrManagedMemory = 83, cudaDevAttrIsMultiGpuBoard = 84, cudaDevAttrMultiGpuBoardGroupID = 85 }; struct __attribute__((device_builtin)) cudaDeviceProp { char name[256]; size_t totalGlobalMem; size_t sharedMemPerBlock; int regsPerBlock; int warpSize; size_t memPitch; int maxThreadsPerBlock; int maxThreadsDim[3]; int maxGridSize[3]; int clockRate; size_t totalConstMem; int major; int minor; size_t textureAlignment; size_t texturePitchAlignment; int deviceOverlap; int multiProcessorCount; int kernelExecTimeoutEnabled; int integrated; int canMapHostMemory; int computeMode; int maxTexture1D; int maxTexture1DMipmap; int maxTexture1DLinear; int maxTexture2D[2]; int maxTexture2DMipmap[2]; int maxTexture2DLinear[3]; int maxTexture2DGather[2]; int maxTexture3D[3]; int maxTexture3DAlt[3]; int maxTextureCubemap; int maxTexture1DLayered[2]; int maxTexture2DLayered[3]; int maxTextureCubemapLayered[2]; int maxSurface1D; int maxSurface2D[2]; int maxSurface3D[3]; int maxSurface1DLayered[2]; int maxSurface2DLayered[3]; int maxSurfaceCubemap; int maxSurfaceCubemapLayered[2]; size_t surfaceAlignment; int concurrentKernels; int ECCEnabled; int pciBusID; int pciDeviceID; int pciDomainID; int tccDriver; int asyncEngineCount; int unifiedAddressing; int memoryClockRate; int memoryBusWidth; int l2CacheSize; int maxThreadsPerMultiProcessor; int streamPrioritiesSupported; int globalL1CacheSupported; int localL1CacheSupported; size_t sharedMemPerMultiprocessor; int regsPerMultiprocessor; int managedMemory; int isMultiGpuBoard; int multiGpuBoardGroupID; }; # 1375 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" typedef __attribute__((device_builtin)) struct __attribute__((device_builtin)) cudaIpcEventHandle_st { char reserved[64]; }cudaIpcEventHandle_t; typedef __attribute__((device_builtin)) struct __attribute__((device_builtin)) cudaIpcMemHandle_st { char reserved[64]; }cudaIpcMemHandle_t; # 1397 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_types.h" typedef __attribute__((device_builtin)) enum cudaError cudaError_t; typedef __attribute__((device_builtin)) struct CUstream_st *cudaStream_t; typedef __attribute__((device_builtin)) struct CUevent_st *cudaEvent_t; typedef __attribute__((device_builtin)) struct cudaGraphicsResource *cudaGraphicsResource_t; typedef __attribute__((device_builtin)) struct CUuuid_st cudaUUID_t; typedef __attribute__((device_builtin)) enum cudaOutputMode cudaOutputMode_t; # 58 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_types.h" 1 # 84 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_types.h" enum __attribute__((device_builtin)) cudaSurfaceBoundaryMode { cudaBoundaryModeZero = 0, cudaBoundaryModeClamp = 1, cudaBoundaryModeTrap = 2 }; enum __attribute__((device_builtin)) cudaSurfaceFormatMode { cudaFormatModeForced = 0, cudaFormatModeAuto = 1 }; struct __attribute__((device_builtin)) surfaceReference { struct cudaChannelFormatDesc channelDesc; }; typedef __attribute__((device_builtin)) unsigned long long cudaSurfaceObject_t; # 59 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_types.h" 1 # 84 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_types.h" enum __attribute__((device_builtin)) cudaTextureAddressMode { cudaAddressModeWrap = 0, cudaAddressModeClamp = 1, cudaAddressModeMirror = 2, cudaAddressModeBorder = 3 }; enum __attribute__((device_builtin)) cudaTextureFilterMode { cudaFilterModePoint = 0, cudaFilterModeLinear = 1 }; enum __attribute__((device_builtin)) cudaTextureReadMode { cudaReadModeElementType = 0, cudaReadModeNormalizedFloat = 1 }; struct __attribute__((device_builtin)) textureReference { int normalized; enum cudaTextureFilterMode filterMode; enum cudaTextureAddressMode addressMode[3]; struct cudaChannelFormatDesc channelDesc; int sRGB; unsigned int maxAnisotropy; enum cudaTextureFilterMode mipmapFilterMode; float mipmapLevelBias; float minMipmapLevelClamp; float maxMipmapLevelClamp; int __cudaReserved[15]; }; struct __attribute__((device_builtin)) cudaTextureDesc { enum cudaTextureAddressMode addressMode[3]; enum cudaTextureFilterMode filterMode; enum cudaTextureReadMode readMode; int sRGB; int normalizedCoords; unsigned int maxAnisotropy; enum cudaTextureFilterMode mipmapFilterMode; float mipmapLevelBias; float minMipmapLevelClamp; float maxMipmapLevelClamp; }; typedef __attribute__((device_builtin)) unsigned long long cudaTextureObject_t; # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" 1 # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 2 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" 2 # 96 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" struct __attribute__((device_builtin)) char1 { signed char x; }; struct __attribute__((device_builtin)) uchar1 { unsigned char x; }; struct __attribute__((device_builtin)) __attribute__((aligned(2))) char2 { signed char x, y; }; struct __attribute__((device_builtin)) __attribute__((aligned(2))) uchar2 { unsigned char x, y; }; struct __attribute__((device_builtin)) char3 { signed char x, y, z; }; struct __attribute__((device_builtin)) uchar3 { unsigned char x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(4))) char4 { signed char x, y, z, w; }; struct __attribute__((device_builtin)) __attribute__((aligned(4))) uchar4 { unsigned char x, y, z, w; }; struct __attribute__((device_builtin)) short1 { short x; }; struct __attribute__((device_builtin)) ushort1 { unsigned short x; }; struct __attribute__((device_builtin)) __attribute__((aligned(4))) short2 { short x, y; }; struct __attribute__((device_builtin)) __attribute__((aligned(4))) ushort2 { unsigned short x, y; }; struct __attribute__((device_builtin)) short3 { short x, y, z; }; struct __attribute__((device_builtin)) ushort3 { unsigned short x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(8))) short4 { short x; short y; short z; short w; }; struct __attribute__((device_builtin)) __attribute__((aligned(8))) ushort4 { unsigned short x; unsigned short y; unsigned short z; unsigned short w; }; struct __attribute__((device_builtin)) int1 { int x; }; struct __attribute__((device_builtin)) uint1 { unsigned int x; }; struct __attribute__((device_builtin)) __attribute__((aligned(8))) int2 { int x; int y; }; struct __attribute__((device_builtin)) __attribute__((aligned(8))) uint2 { unsigned int x; unsigned int y; }; struct __attribute__((device_builtin)) int3 { int x, y, z; }; struct __attribute__((device_builtin)) uint3 { unsigned int x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) int4 { int x, y, z, w; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) uint4 { unsigned int x, y, z, w; }; struct __attribute__((device_builtin)) long1 { long int x; }; struct __attribute__((device_builtin)) ulong1 { unsigned long x; }; struct __attribute__((device_builtin)) __attribute__((aligned(2*sizeof(long int)))) long2 { long int x, y; }; struct __attribute__((device_builtin)) __attribute__((aligned(2*sizeof(unsigned long int)))) ulong2 { unsigned long int x, y; }; struct __attribute__((device_builtin)) long3 { long int x, y, z; }; struct __attribute__((device_builtin)) ulong3 { unsigned long int x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) long4 { long int x, y, z, w; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) ulong4 { unsigned long int x, y, z, w; }; struct __attribute__((device_builtin)) float1 { float x; }; # 272 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" struct __attribute__((device_builtin)) __attribute__((aligned(8))) float2 { float x; float y; }; struct __attribute__((device_builtin)) float3 { float x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) float4 { float x, y, z, w; }; struct __attribute__((device_builtin)) longlong1 { long long int x; }; struct __attribute__((device_builtin)) ulonglong1 { unsigned long long int x; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) longlong2 { long long int x, y; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) ulonglong2 { unsigned long long int x, y; }; struct __attribute__((device_builtin)) longlong3 { long long int x, y, z; }; struct __attribute__((device_builtin)) ulonglong3 { unsigned long long int x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) longlong4 { long long int x, y, z ,w; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) ulonglong4 { unsigned long long int x, y, z, w; }; struct __attribute__((device_builtin)) double1 { double x; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) double2 { double x, y; }; struct __attribute__((device_builtin)) double3 { double x, y, z; }; struct __attribute__((device_builtin)) __attribute__((aligned(16))) double4 { double x, y, z, w; }; # 360 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_types.h" typedef __attribute__((device_builtin)) struct char1 char1; typedef __attribute__((device_builtin)) struct uchar1 uchar1; typedef __attribute__((device_builtin)) struct char2 char2; typedef __attribute__((device_builtin)) struct uchar2 uchar2; typedef __attribute__((device_builtin)) struct char3 char3; typedef __attribute__((device_builtin)) struct uchar3 uchar3; typedef __attribute__((device_builtin)) struct char4 char4; typedef __attribute__((device_builtin)) struct uchar4 uchar4; typedef __attribute__((device_builtin)) struct short1 short1; typedef __attribute__((device_builtin)) struct ushort1 ushort1; typedef __attribute__((device_builtin)) struct short2 short2; typedef __attribute__((device_builtin)) struct ushort2 ushort2; typedef __attribute__((device_builtin)) struct short3 short3; typedef __attribute__((device_builtin)) struct ushort3 ushort3; typedef __attribute__((device_builtin)) struct short4 short4; typedef __attribute__((device_builtin)) struct ushort4 ushort4; typedef __attribute__((device_builtin)) struct int1 int1; typedef __attribute__((device_builtin)) struct uint1 uint1; typedef __attribute__((device_builtin)) struct int2 int2; typedef __attribute__((device_builtin)) struct uint2 uint2; typedef __attribute__((device_builtin)) struct int3 int3; typedef __attribute__((device_builtin)) struct uint3 uint3; typedef __attribute__((device_builtin)) struct int4 int4; typedef __attribute__((device_builtin)) struct uint4 uint4; typedef __attribute__((device_builtin)) struct long1 long1; typedef __attribute__((device_builtin)) struct ulong1 ulong1; typedef __attribute__((device_builtin)) struct long2 long2; typedef __attribute__((device_builtin)) struct ulong2 ulong2; typedef __attribute__((device_builtin)) struct long3 long3; typedef __attribute__((device_builtin)) struct ulong3 ulong3; typedef __attribute__((device_builtin)) struct long4 long4; typedef __attribute__((device_builtin)) struct ulong4 ulong4; typedef __attribute__((device_builtin)) struct float1 float1; typedef __attribute__((device_builtin)) struct float2 float2; typedef __attribute__((device_builtin)) struct float3 float3; typedef __attribute__((device_builtin)) struct float4 float4; typedef __attribute__((device_builtin)) struct longlong1 longlong1; typedef __attribute__((device_builtin)) struct ulonglong1 ulonglong1; typedef __attribute__((device_builtin)) struct longlong2 longlong2; typedef __attribute__((device_builtin)) struct ulonglong2 ulonglong2; typedef __attribute__((device_builtin)) struct longlong3 longlong3; typedef __attribute__((device_builtin)) struct ulonglong3 ulonglong3; typedef __attribute__((device_builtin)) struct longlong4 longlong4; typedef __attribute__((device_builtin)) struct ulonglong4 ulonglong4; typedef __attribute__((device_builtin)) struct double1 double1; typedef __attribute__((device_builtin)) struct double2 double2; typedef __attribute__((device_builtin)) struct double3 double3; typedef __attribute__((device_builtin)) struct double4 double4; struct __attribute__((device_builtin)) dim3 { unsigned int x, y, z; __attribute__((host)) __attribute__((device)) dim3(unsigned int vx = 1, unsigned int vy = 1, unsigned int vz = 1) : x(vx), y(vy), z(vz) {} __attribute__((host)) __attribute__((device)) dim3(uint3 v) : x(v.x), y(v.y), z(v.z) {} __attribute__((host)) __attribute__((device)) operator uint3(void) { uint3 t; t.x = x; t.y = y; t.z = z; return t; } }; typedef __attribute__((device_builtin)) struct dim3 dim3; # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 2 # 68 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/channel_descriptor.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/channel_descriptor.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" 1 # 143 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 144 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_device_runtime_api.h" 1 # 145 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" 2 # 174 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern "C" { # 207 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceReset(void); # 224 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaDeviceSynchronize(void); # 309 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceSetLimit(enum cudaLimit limit, size_t value); # 338 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaDeviceGetLimit(size_t *pValue, enum cudaLimit limit); # 369 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaDeviceGetCacheConfig(enum cudaFuncCache *pCacheConfig); # 404 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaDeviceGetStreamPriorityRange(int *leastPriority, int *greatestPriority); # 446 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceSetCacheConfig(enum cudaFuncCache cacheConfig); # 475 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaDeviceGetSharedMemConfig(enum cudaSharedMemConfig *pConfig); # 517 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceSetSharedMemConfig(enum cudaSharedMemConfig config); # 540 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceGetByPCIBusId(int *device, const char *pciBusId); # 567 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceGetPCIBusId(char *pciBusId, int len, int device); # 609 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaIpcGetEventHandle(cudaIpcEventHandle_t *handle, cudaEvent_t event); # 644 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaIpcOpenEventHandle(cudaEvent_t *event, cudaIpcEventHandle_t handle); # 682 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaIpcGetMemHandle(cudaIpcMemHandle_t *handle, void *devPtr); # 732 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaIpcOpenMemHandle(void **devPtr, cudaIpcMemHandle_t handle, unsigned int flags); # 762 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaIpcCloseMemHandle(void *devPtr); # 802 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaThreadExit(void); # 826 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaThreadSynchronize(void); # 885 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaThreadSetLimit(enum cudaLimit limit, size_t value); # 916 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaThreadGetLimit(size_t *pValue, enum cudaLimit limit); # 951 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaThreadGetCacheConfig(enum cudaFuncCache *pCacheConfig); # 997 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaThreadSetCacheConfig(enum cudaFuncCache cacheConfig); # 1051 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaGetLastError(void); # 1092 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaPeekAtLastError(void); # 1107 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) const char* cudaGetErrorName(cudaError_t error); # 1122 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) const char* cudaGetErrorString(cudaError_t error); # 1152 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaGetDeviceCount(int *count); # 1388 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaGetDeviceProperties(struct cudaDeviceProp *prop, int device); # 1548 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaDeviceGetAttribute(int *value, enum cudaDeviceAttr attr, int device); # 1567 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaChooseDevice(int *device, const struct cudaDeviceProp *prop); # 1601 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaSetDevice(int device); # 1618 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaGetDevice(int *device); # 1647 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaSetValidDevices(int *device_arr, int len); # 1707 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaSetDeviceFlags( unsigned int flags ); # 1745 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaStreamCreate(cudaStream_t *pStream); # 1774 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamCreateWithFlags(cudaStream_t *pStream, unsigned int flags); # 1817 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamCreateWithPriority(cudaStream_t *pStream, unsigned int flags, int priority); # 1841 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamGetPriority(cudaStream_t hStream, int *priority); # 1862 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamGetFlags(cudaStream_t hStream, unsigned int *flags); # 1883 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamDestroy(cudaStream_t stream); # 1915 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamWaitEvent(cudaStream_t stream, cudaEvent_t event, unsigned int flags); # 1929 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" typedef void ( *cudaStreamCallback_t)(cudaStream_t stream, cudaError_t status, void *userData); # 1991 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaStreamAddCallback(cudaStream_t stream, cudaStreamCallback_t callback, void *userData, unsigned int flags); # 2011 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaStreamSynchronize(cudaStream_t stream); # 2032 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaStreamQuery(cudaStream_t stream); # 2098 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaStreamAttachMemAsync(cudaStream_t stream, void *devPtr, size_t length, unsigned int flags); # 2134 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaEventCreate(cudaEvent_t *event); # 2168 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaEventCreateWithFlags(cudaEvent_t *event, unsigned int flags); # 2199 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaEventRecord(cudaEvent_t event, cudaStream_t stream = 0); # 2231 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaEventQuery(cudaEvent_t event); # 2263 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaEventSynchronize(cudaEvent_t event); # 2288 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaEventDestroy(cudaEvent_t event); # 2329 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaEventElapsedTime(float *ms, cudaEvent_t start, cudaEvent_t end); # 2376 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaConfigureCall(dim3 gridDim, dim3 blockDim, size_t sharedMem = 0, cudaStream_t stream = 0); # 2403 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaSetupArgument(const void *arg, size_t size, size_t offset); # 2450 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaFuncSetCacheConfig(const void *func, enum cudaFuncCache cacheConfig); # 2501 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaFuncSetSharedMemConfig(const void *func, enum cudaSharedMemConfig config); # 2536 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaLaunch(const void *func); # 2569 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaFuncGetAttributes(struct cudaFuncAttributes *attr, const void *func); # 2591 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaSetDoubleForDevice(double *d); # 2613 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaSetDoubleForHost(double *d); # 2666 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaOccupancyMaxActiveBlocksPerMultiprocessor(int *numBlocks, const void *func, int blockSize, size_t dynamicSMemSize); # 2754 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMallocManaged(void **devPtr, size_t size, unsigned int flags); # 2777 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMalloc(void **devPtr, size_t size); # 2806 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMallocHost(void **ptr, size_t size); # 2845 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMallocPitch(void **devPtr, size_t *pitch, size_t width, size_t height); # 2887 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMallocArray(cudaArray_t *array, const struct cudaChannelFormatDesc *desc, size_t width, size_t height = 0, unsigned int flags = 0); # 2911 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaFree(void *devPtr); # 2931 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaFreeHost(void *ptr); # 2953 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaFreeArray(cudaArray_t array); # 2975 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaFreeMipmappedArray(cudaMipmappedArray_t mipmappedArray); # 3034 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaHostAlloc(void **pHost, size_t size, unsigned int flags); # 3087 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaHostRegister(void *ptr, size_t size, unsigned int flags); # 3106 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaHostUnregister(void *ptr); # 3133 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaHostGetDevicePointer(void **pDevice, void *pHost, unsigned int flags); # 3152 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaHostGetFlags(unsigned int *pFlags, void *pHost); # 3187 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMalloc3D(struct cudaPitchedPtr* pitchedDevPtr, struct cudaExtent extent); # 3322 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMalloc3DArray(cudaArray_t *array, const struct cudaChannelFormatDesc* desc, struct cudaExtent extent, unsigned int flags = 0); # 3443 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMallocMipmappedArray(cudaMipmappedArray_t *mipmappedArray, const struct cudaChannelFormatDesc* desc, struct cudaExtent extent, unsigned int numLevels, unsigned int flags = 0); # 3469 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetMipmappedArrayLevel(cudaArray_t *levelArray, cudaMipmappedArray_const_t mipmappedArray, unsigned int level); # 3566 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy3D(const struct cudaMemcpy3DParms *p); # 3594 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy3DPeer(const struct cudaMemcpy3DPeerParms *p); # 3699 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMemcpy3DAsync(const struct cudaMemcpy3DParms *p, cudaStream_t stream = 0); # 3722 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy3DPeerAsync(const struct cudaMemcpy3DPeerParms *p, cudaStream_t stream = 0); # 3741 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemGetInfo(size_t *free, size_t *total); # 3762 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaArrayGetInfo(struct cudaChannelFormatDesc *desc, struct cudaExtent *extent, unsigned int *flags, cudaArray_t array); # 3797 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy(void *dst, const void *src, size_t count, enum cudaMemcpyKind kind); # 3829 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyPeer(void *dst, int dstDevice, const void *src, int srcDevice, size_t count); # 3863 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyToArray(cudaArray_t dst, size_t wOffset, size_t hOffset, const void *src, size_t count, enum cudaMemcpyKind kind); # 3897 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyFromArray(void *dst, cudaArray_const_t src, size_t wOffset, size_t hOffset, size_t count, enum cudaMemcpyKind kind); # 3932 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyArrayToArray(cudaArray_t dst, size_t wOffsetDst, size_t hOffsetDst, cudaArray_const_t src, size_t wOffsetSrc, size_t hOffsetSrc, size_t count, enum cudaMemcpyKind kind = cudaMemcpyDeviceToDevice); # 3974 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy2D(void *dst, size_t dpitch, const void *src, size_t spitch, size_t width, size_t height, enum cudaMemcpyKind kind); # 4016 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy2DToArray(cudaArray_t dst, size_t wOffset, size_t hOffset, const void *src, size_t spitch, size_t width, size_t height, enum cudaMemcpyKind kind); # 4058 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy2DFromArray(void *dst, size_t dpitch, cudaArray_const_t src, size_t wOffset, size_t hOffset, size_t width, size_t height, enum cudaMemcpyKind kind); # 4098 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy2DArrayToArray(cudaArray_t dst, size_t wOffsetDst, size_t hOffsetDst, cudaArray_const_t src, size_t wOffsetSrc, size_t hOffsetSrc, size_t width, size_t height, enum cudaMemcpyKind kind = cudaMemcpyDeviceToDevice); # 4133 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyToSymbol(const void *symbol, const void *src, size_t count, size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyHostToDevice); # 4168 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyFromSymbol(void *dst, const void *symbol, size_t count, size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyDeviceToHost); # 4211 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMemcpyAsync(void *dst, const void *src, size_t count, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4243 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyPeerAsync(void *dst, int dstDevice, const void *src, int srcDevice, size_t count, cudaStream_t stream = 0); # 4285 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyToArrayAsync(cudaArray_t dst, size_t wOffset, size_t hOffset, const void *src, size_t count, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4327 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyFromArrayAsync(void *dst, cudaArray_const_t src, size_t wOffset, size_t hOffset, size_t count, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4379 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMemcpy2DAsync(void *dst, size_t dpitch, const void *src, size_t spitch, size_t width, size_t height, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4430 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy2DToArrayAsync(cudaArray_t dst, size_t wOffset, size_t hOffset, const void *src, size_t spitch, size_t width, size_t height, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4480 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpy2DFromArrayAsync(void *dst, size_t dpitch, cudaArray_const_t src, size_t wOffset, size_t hOffset, size_t width, size_t height, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4523 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyToSymbolAsync(const void *symbol, const void *src, size_t count, size_t offset, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4566 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemcpyFromSymbolAsync(void *dst, const void *symbol, size_t count, size_t offset, enum cudaMemcpyKind kind, cudaStream_t stream = 0); # 4592 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemset(void *devPtr, int value, size_t count); # 4622 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemset2D(void *devPtr, size_t pitch, int value, size_t width, size_t height); # 4665 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaMemset3D(struct cudaPitchedPtr pitchedDevPtr, int value, struct cudaExtent extent); # 4694 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMemsetAsync(void *devPtr, int value, size_t count, cudaStream_t stream = 0); # 4728 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMemset2DAsync(void *devPtr, size_t pitch, int value, size_t width, size_t height, cudaStream_t stream = 0); # 4775 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaMemset3DAsync(struct cudaPitchedPtr pitchedDevPtr, int value, struct cudaExtent extent, cudaStream_t stream = 0); # 4798 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetSymbolAddress(void **devPtr, const void *symbol); # 4820 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetSymbolSize(size_t *size, const void *symbol); # 4974 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaPointerGetAttributes(struct cudaPointerAttributes *attributes, const void *ptr); # 5012 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceCanAccessPeer(int *canAccessPeer, int device, int peerDevice); # 5049 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceEnablePeerAccess(int peerDevice, unsigned int flags); # 5068 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDeviceDisablePeerAccess(int peerDevice); # 5126 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsUnregisterResource(cudaGraphicsResource_t resource); # 5158 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsResourceSetMapFlags(cudaGraphicsResource_t resource, unsigned int flags); # 5194 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsMapResources(int count, cudaGraphicsResource_t *resources, cudaStream_t stream = 0); # 5226 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsUnmapResources(int count, cudaGraphicsResource_t *resources, cudaStream_t stream = 0); # 5255 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsResourceGetMappedPointer(void **devPtr, size_t *size, cudaGraphicsResource_t resource); # 5289 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsSubResourceGetMappedArray(cudaArray_t *array, cudaGraphicsResource_t resource, unsigned int arrayIndex, unsigned int mipLevel); # 5314 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGraphicsResourceGetMappedMipmappedArray(cudaMipmappedArray_t *mipmappedArray, cudaGraphicsResource_t resource); # 5354 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetChannelDesc(struct cudaChannelFormatDesc *desc, cudaArray_const_t array); # 5389 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) struct cudaChannelFormatDesc cudaCreateChannelDesc(int x, int y, int z, int w, enum cudaChannelFormatKind f); # 5436 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaBindTexture(size_t *offset, const struct textureReference *texref, const void *devPtr, const struct cudaChannelFormatDesc *desc, size_t size = (2147483647 *2U +1U)); # 5487 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaBindTexture2D(size_t *offset, const struct textureReference *texref, const void *devPtr, const struct cudaChannelFormatDesc *desc, size_t width, size_t height, size_t pitch); # 5515 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaBindTextureToArray(const struct textureReference *texref, cudaArray_const_t array, const struct cudaChannelFormatDesc *desc); # 5543 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaBindTextureToMipmappedArray(const struct textureReference *texref, cudaMipmappedArray_const_t mipmappedArray, const struct cudaChannelFormatDesc *desc); # 5564 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaUnbindTexture(const struct textureReference *texref); # 5589 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetTextureAlignmentOffset(size_t *offset, const struct textureReference *texref); # 5614 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetTextureReference(const struct textureReference **texref, const void *symbol); # 5654 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaBindSurfaceToArray(const struct surfaceReference *surfref, cudaArray_const_t array, const struct cudaChannelFormatDesc *desc); # 5673 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetSurfaceReference(const struct surfaceReference **surfref, const void *symbol); # 5888 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaCreateTextureObject(cudaTextureObject_t *pTexObject, const struct cudaResourceDesc *pResDesc, const struct cudaTextureDesc *pTexDesc, const struct cudaResourceViewDesc *pResViewDesc); # 5903 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDestroyTextureObject(cudaTextureObject_t texObject); # 5919 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetTextureObjectResourceDesc(struct cudaResourceDesc *pResDesc, cudaTextureObject_t texObject); # 5935 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetTextureObjectTextureDesc(struct cudaTextureDesc *pTexDesc, cudaTextureObject_t texObject); # 5952 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetTextureObjectResourceViewDesc(struct cudaResourceViewDesc *pResViewDesc, cudaTextureObject_t texObject); # 5989 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaCreateSurfaceObject(cudaSurfaceObject_t *pSurfObject, const struct cudaResourceDesc *pResDesc); # 6004 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDestroySurfaceObject(cudaSurfaceObject_t surfObject); # 6019 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaGetSurfaceObjectResourceDesc(struct cudaResourceDesc *pResDesc, cudaSurfaceObject_t surfObject); # 6046 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) cudaError_t cudaDriverGetVersion(int *driverVersion); # 6063 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" extern __attribute__((host)) __attribute__((cudart_builtin)) cudaError_t cudaRuntimeGetVersion(int *runtimeVersion); extern __attribute__((host)) cudaError_t cudaGetExportTable(const void **ppExportTable, const cudaUUID_t *pExportTableId); # 6204 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime_api.h" } # 63 "/Developer/NVIDIA/CUDA-6.5/bin/../include/channel_descriptor.h" 2 # 107 "/Developer/NVIDIA/CUDA-6.5/bin/../include/channel_descriptor.h" template __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { return cudaCreateChannelDesc(0, 0, 0, 0, cudaChannelFormatKindNone); } static __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDescHalf(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindFloat); } static __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDescHalf1(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindFloat); } static __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDescHalf2(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindFloat); } static __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDescHalf4(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindFloat); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(char) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(signed char) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned char) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(signed char) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned char) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(signed char) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned char) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(signed char) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned char) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(short) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(short) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(short) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(short) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned short) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(int) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned int) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(int) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned int) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(int) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned int) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindUnsigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(int) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindSigned); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(unsigned int) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindUnsigned); } # 379 "/Developer/NVIDIA/CUDA-6.5/bin/../include/channel_descriptor.h" template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(float) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindFloat); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(float) * 8; return cudaCreateChannelDesc(e, 0, 0, 0, cudaChannelFormatKindFloat); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(float) * 8; return cudaCreateChannelDesc(e, e, 0, 0, cudaChannelFormatKindFloat); } template<> __inline__ __attribute__((host)) cudaChannelFormatDesc cudaCreateChannelDesc(void) { int e = (int)sizeof(float) * 8; return cudaCreateChannelDesc(e, e, e, e, cudaChannelFormatKindFloat); } # 69 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_functions.h" 1 # 53 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 54 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_functions.h" 2 # 79 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_functions.h" static __inline__ __attribute__((host)) struct cudaPitchedPtr make_cudaPitchedPtr(void *d, size_t p, size_t xsz, size_t ysz) { struct cudaPitchedPtr s; s.ptr = d; s.pitch = p; s.xsize = xsz; s.ysize = ysz; return s; } # 106 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_functions.h" static __inline__ __attribute__((host)) struct cudaPos make_cudaPos(size_t x, size_t y, size_t z) { struct cudaPos p; p.x = x; p.y = y; p.z = z; return p; } # 132 "/Developer/NVIDIA/CUDA-6.5/bin/../include/driver_functions.h" static __inline__ __attribute__((host)) struct cudaExtent make_cudaExtent(size_t w, size_t h, size_t d) { struct cudaExtent e; e.width = w; e.height = h; e.depth = d; return e; } # 71 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_functions.h" 1 # 59 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_functions.h" 2 # 69 "/Developer/NVIDIA/CUDA-6.5/bin/../include/vector_functions.h" static __inline__ __attribute__((host)) __attribute__((device)) char1 make_char1(signed char x) { char1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uchar1 make_uchar1(unsigned char x) { uchar1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) char2 make_char2(signed char x, signed char y) { char2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uchar2 make_uchar2(unsigned char x, unsigned char y) { uchar2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) char3 make_char3(signed char x, signed char y, signed char z) { char3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uchar3 make_uchar3(unsigned char x, unsigned char y, unsigned char z) { uchar3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) char4 make_char4(signed char x, signed char y, signed char z, signed char w) { char4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uchar4 make_uchar4(unsigned char x, unsigned char y, unsigned char z, unsigned char w) { uchar4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) short1 make_short1(short x) { short1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ushort1 make_ushort1(unsigned short x) { ushort1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) short2 make_short2(short x, short y) { short2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ushort2 make_ushort2(unsigned short x, unsigned short y) { ushort2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) short3 make_short3(short x,short y, short z) { short3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ushort3 make_ushort3(unsigned short x, unsigned short y, unsigned short z) { ushort3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) short4 make_short4(short x, short y, short z, short w) { short4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ushort4 make_ushort4(unsigned short x, unsigned short y, unsigned short z, unsigned short w) { ushort4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) int1 make_int1(int x) { int1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uint1 make_uint1(unsigned int x) { uint1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) int2 make_int2(int x, int y) { int2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uint2 make_uint2(unsigned int x, unsigned int y) { uint2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) int3 make_int3(int x, int y, int z) { int3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uint3 make_uint3(unsigned int x, unsigned int y, unsigned int z) { uint3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) int4 make_int4(int x, int y, int z, int w) { int4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) uint4 make_uint4(unsigned int x, unsigned int y, unsigned int z, unsigned int w) { uint4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) long1 make_long1(long int x) { long1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulong1 make_ulong1(unsigned long int x) { ulong1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) long2 make_long2(long int x, long int y) { long2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulong2 make_ulong2(unsigned long int x, unsigned long int y) { ulong2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) long3 make_long3(long int x, long int y, long int z) { long3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulong3 make_ulong3(unsigned long int x, unsigned long int y, unsigned long int z) { ulong3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) long4 make_long4(long int x, long int y, long int z, long int w) { long4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulong4 make_ulong4(unsigned long int x, unsigned long int y, unsigned long int z, unsigned long int w) { ulong4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) float1 make_float1(float x) { float1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) float2 make_float2(float x, float y) { float2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) float3 make_float3(float x, float y, float z) { float3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) float4 make_float4(float x, float y, float z, float w) { float4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) longlong1 make_longlong1(long long int x) { longlong1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulonglong1 make_ulonglong1(unsigned long long int x) { ulonglong1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) longlong2 make_longlong2(long long int x, long long int y) { longlong2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulonglong2 make_ulonglong2(unsigned long long int x, unsigned long long int y) { ulonglong2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) longlong3 make_longlong3(long long int x, long long int y, long long int z) { longlong3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulonglong3 make_ulonglong3(unsigned long long int x, unsigned long long int y, unsigned long long int z) { ulonglong3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) longlong4 make_longlong4(long long int x, long long int y, long long int z, long long int w) { longlong4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) ulonglong4 make_ulonglong4(unsigned long long int x, unsigned long long int y, unsigned long long int z, unsigned long long int w) { ulonglong4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } static __inline__ __attribute__((host)) __attribute__((device)) double1 make_double1(double x) { double1 t; t.x = x; return t; } static __inline__ __attribute__((host)) __attribute__((device)) double2 make_double2(double x, double y) { double2 t; t.x = x; t.y = y; return t; } static __inline__ __attribute__((host)) __attribute__((device)) double3 make_double3(double x, double y, double z) { double3 t; t.x = x; t.y = y; t.z = z; return t; } static __inline__ __attribute__((host)) __attribute__((device)) double4 make_double4(double x, double y, double z, double w) { double4 t; t.x = x; t.y = y; t.z = z; t.w = w; return t; } # 73 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 # 1 "/usr/include/string.h" 1 3 4 # 61 "/usr/include/string.h" 3 4 # 1 "/usr/include/_types.h" 1 3 4 # 27 "/usr/include/_types.h" 3 4 # 1 "/usr/include/sys/_types.h" 1 3 4 # 33 "/usr/include/sys/_types.h" 3 4 # 1 "/usr/include/machine/_types.h" 1 3 4 # 32 "/usr/include/machine/_types.h" 3 4 # 1 "/usr/include/i386/_types.h" 1 3 4 # 37 "/usr/include/i386/_types.h" 3 4 typedef signed char __int8_t; typedef unsigned char __uint8_t; typedef short __int16_t; typedef unsigned short __uint16_t; typedef int __int32_t; typedef unsigned int __uint32_t; typedef long long __int64_t; typedef unsigned long long __uint64_t; typedef long __darwin_intptr_t; typedef unsigned int __darwin_natural_t; # 70 "/usr/include/i386/_types.h" 3 4 typedef int __darwin_ct_rune_t; typedef union { char __mbstate8[128]; long long _mbstateL; } __mbstate_t; typedef __mbstate_t __darwin_mbstate_t; typedef long int __darwin_ptrdiff_t; typedef long unsigned int __darwin_size_t; typedef __builtin_va_list __darwin_va_list; typedef int __darwin_wchar_t; typedef __darwin_wchar_t __darwin_rune_t; typedef int __darwin_wint_t; typedef unsigned long __darwin_clock_t; typedef __uint32_t __darwin_socklen_t; typedef long __darwin_ssize_t; typedef long __darwin_time_t; # 33 "/usr/include/machine/_types.h" 2 3 4 # 34 "/usr/include/sys/_types.h" 2 3 4 # 55 "/usr/include/sys/_types.h" 3 4 typedef __int64_t __darwin_blkcnt_t; typedef __int32_t __darwin_blksize_t; typedef __int32_t __darwin_dev_t; typedef unsigned int __darwin_fsblkcnt_t; typedef unsigned int __darwin_fsfilcnt_t; typedef __uint32_t __darwin_gid_t; typedef __uint32_t __darwin_id_t; typedef __uint64_t __darwin_ino64_t; typedef __darwin_ino64_t __darwin_ino_t; typedef __darwin_natural_t __darwin_mach_port_name_t; typedef __darwin_mach_port_name_t __darwin_mach_port_t; typedef __uint16_t __darwin_mode_t; typedef __int64_t __darwin_off_t; typedef __int32_t __darwin_pid_t; typedef __uint32_t __darwin_sigset_t; typedef __int32_t __darwin_suseconds_t; typedef __uint32_t __darwin_uid_t; typedef __uint32_t __darwin_useconds_t; typedef unsigned char __darwin_uuid_t[16]; typedef char __darwin_uuid_string_t[37]; # 1 "/usr/include/sys/_pthread/_pthread_types.h" 1 3 4 # 57 "/usr/include/sys/_pthread/_pthread_types.h" 3 4 struct __darwin_pthread_handler_rec { void (*__routine)(void *); void *__arg; struct __darwin_pthread_handler_rec *__next; }; struct _opaque_pthread_attr_t { long __sig; char __opaque[56]; }; struct _opaque_pthread_cond_t { long __sig; char __opaque[40]; }; struct _opaque_pthread_condattr_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_mutex_t { long __sig; char __opaque[56]; }; struct _opaque_pthread_mutexattr_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_once_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_rwlock_t { long __sig; char __opaque[192]; }; struct _opaque_pthread_rwlockattr_t { long __sig; char __opaque[16]; }; struct _opaque_pthread_t { long __sig; struct __darwin_pthread_handler_rec *__cleanup_stack; char __opaque[8176]; }; typedef struct _opaque_pthread_attr_t __darwin_pthread_attr_t; typedef struct _opaque_pthread_cond_t __darwin_pthread_cond_t; typedef struct _opaque_pthread_condattr_t __darwin_pthread_condattr_t; typedef unsigned long __darwin_pthread_key_t; typedef struct _opaque_pthread_mutex_t __darwin_pthread_mutex_t; typedef struct _opaque_pthread_mutexattr_t __darwin_pthread_mutexattr_t; typedef struct _opaque_pthread_once_t __darwin_pthread_once_t; typedef struct _opaque_pthread_rwlock_t __darwin_pthread_rwlock_t; typedef struct _opaque_pthread_rwlockattr_t __darwin_pthread_rwlockattr_t; typedef struct _opaque_pthread_t *__darwin_pthread_t; # 81 "/usr/include/sys/_types.h" 2 3 4 # 28 "/usr/include/_types.h" 2 3 4 # 39 "/usr/include/_types.h" 3 4 typedef int __darwin_nl_item; typedef int __darwin_wctrans_t; typedef __uint32_t __darwin_wctype_t; # 62 "/usr/include/string.h" 2 3 4 # 1 "/usr/include/Availability.h" 1 3 4 # 153 "/usr/include/Availability.h" 3 4 # 1 "/usr/include/AvailabilityInternal.h" 1 3 4 # 154 "/usr/include/Availability.h" 2 3 4 # 64 "/usr/include/string.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 65 "/usr/include/string.h" 2 3 4 # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 66 "/usr/include/string.h" 2 3 4 extern "C" { void *memchr(const void *, int, size_t); int memcmp(const void *, const void *, size_t); void *memcpy(void *, const void *, size_t); void *memmove(void *, const void *, size_t); void *memset(void *, int, size_t); char *strcat(char *, const char *); char *strchr(const char *, int); int strcmp(const char *, const char *); int strcoll(const char *, const char *); char *strcpy(char *, const char *); size_t strcspn(const char *, const char *); char *strerror(int) __asm("_" "strerror" ); size_t strlen(const char *); char *strncat(char *, const char *, size_t); int strncmp(const char *, const char *, size_t); char *strncpy(char *, const char *, size_t); char *strpbrk(const char *, const char *); char *strrchr(const char *, int); size_t strspn(const char *, const char *); char *strstr(const char *, const char *); char *strtok(char *, const char *); size_t strxfrm(char *, const char *, size_t); } # 103 "/usr/include/string.h" 3 4 extern "C" { char *strtok_r(char *, const char *, char **); } # 115 "/usr/include/string.h" 3 4 extern "C" { int strerror_r(int, char *, size_t); char *strdup(const char *); void *memccpy(void *, const void *, int, size_t); } # 129 "/usr/include/string.h" 3 4 extern "C" { char *stpcpy(char *, const char *); char *stpncpy(char *, const char *, size_t) __attribute__((availability(macosx,introduced=10.7))); char *strndup(const char *, size_t) __attribute__((availability(macosx,introduced=10.7))); size_t strnlen(const char *, size_t) __attribute__((availability(macosx,introduced=10.7))); char *strsignal(int sig); } # 1 "/usr/include/sys/_types/_rsize_t.h" 1 3 4 # 142 "/usr/include/string.h" 2 3 4 # 1 "/usr/include/sys/_types/_errno_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_errno_t.h" 3 4 typedef int errno_t; # 143 "/usr/include/string.h" 2 3 4 extern "C" { errno_t memset_s(void *, rsize_t, int, rsize_t) __attribute__((availability(macosx,introduced=10.9))); } # 1 "/usr/include/sys/_types/_ssize_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_ssize_t.h" 3 4 typedef __darwin_ssize_t ssize_t; # 153 "/usr/include/string.h" 2 3 4 extern "C" { void *memmem(const void *, size_t, const void *, size_t) __attribute__((availability(macosx,introduced=10.7))); void memset_pattern4(void *, const void *, size_t) __attribute__((availability(macosx,introduced=10.5))); void memset_pattern8(void *, const void *, size_t) __attribute__((availability(macosx,introduced=10.5))); void memset_pattern16(void *, const void *, size_t) __attribute__((availability(macosx,introduced=10.5))); char *strcasestr(const char *, const char *); char *strnstr(const char *, const char *, size_t); size_t strlcat(char *, const char *, size_t); size_t strlcpy(char *, const char *, size_t); void strmode(int, char *); char *strsep(char **, const char *); void swab(const void * , void * , ssize_t); } # 1 "/usr/include/strings.h" 1 3 4 # 65 "/usr/include/strings.h" 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 66 "/usr/include/strings.h" 2 3 4 extern "C" { int bcmp(const void *, const void *, size_t) ; void bcopy(const void *, void *, size_t) ; void bzero(void *, size_t) ; char *index(const char *, int) ; char *rindex(const char *, int) ; int ffs(int); int strcasecmp(const char *, const char *); int strncasecmp(const char *, const char *, size_t); } extern "C" { int ffsl(long) __attribute__((availability(macosx,introduced=10.5))); int ffsll(long long) __attribute__((availability(macosx,introduced=10.9))); int fls(int) __attribute__((availability(macosx,introduced=10.5))); int flsl(long) __attribute__((availability(macosx,introduced=10.5))); int flsll(long long) __attribute__((availability(macosx,introduced=10.9))); } # 1 "/usr/include/string.h" 1 3 4 # 93 "/usr/include/strings.h" 2 3 4 # 177 "/usr/include/string.h" 2 3 4 # 65 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 # 1 "/usr/include/time.h" 1 3 4 # 67 "/usr/include/time.h" 3 4 # 1 "/usr/include/sys/_types/_clock_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_clock_t.h" 3 4 typedef __darwin_clock_t clock_t; # 68 "/usr/include/time.h" 2 3 4 # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 69 "/usr/include/time.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 70 "/usr/include/time.h" 2 3 4 # 1 "/usr/include/sys/_types/_time_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_time_t.h" 3 4 typedef __darwin_time_t time_t; # 71 "/usr/include/time.h" 2 3 4 # 1 "/usr/include/sys/_types/_timespec.h" 1 3 4 # 30 "/usr/include/sys/_types/_timespec.h" 3 4 struct timespec { __darwin_time_t tv_sec; long tv_nsec; }; # 72 "/usr/include/time.h" 2 3 4 struct tm { int tm_sec; int tm_min; int tm_hour; int tm_mday; int tm_mon; int tm_year; int tm_wday; int tm_yday; int tm_isdst; long tm_gmtoff; char *tm_zone; }; # 96 "/usr/include/time.h" 3 4 extern char *tzname[]; extern int getdate_err; extern long timezone __asm("_" "timezone" ); extern int daylight; extern "C" { char *asctime(const struct tm *); clock_t clock(void) __asm("_" "clock" ); char *ctime(const time_t *); double difftime(time_t, time_t); struct tm *getdate(const char *); struct tm *gmtime(const time_t *); struct tm *localtime(const time_t *); time_t mktime(struct tm *) __asm("_" "mktime" ); size_t strftime(char * , size_t, const char * , const struct tm * ) __asm("_" "strftime" ); char *strptime(const char * , const char * , struct tm * ) __asm("_" "strptime" ); time_t time(time_t *); void tzset(void); char *asctime_r(const struct tm * , char * ); char *ctime_r(const time_t *, char *); struct tm *gmtime_r(const time_t * , struct tm * ); struct tm *localtime_r(const time_t * , struct tm * ); time_t posix2time(time_t); void tzsetwall(void); time_t time2posix(time_t); time_t timelocal(struct tm * const); time_t timegm(struct tm * const); int nanosleep(const struct timespec *, struct timespec *) __asm("_" "nanosleep" ); } # 66 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 extern "C" { extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) clock_t clock(void) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) void* memset(void*, int, size_t) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) void* memcpy(void*, const void*, size_t) ; } # 1 "/usr/include/c++/4.2.1/new" 1 3 # 44 "/usr/include/c++/4.2.1/new" 3 # 1 "/usr/include/c++/4.2.1/cstddef" 1 3 # 49 "/usr/include/c++/4.2.1/cstddef" 3 # 1 "/usr/include/c++/4.2.1/bits/c++config.h" 1 3 # 41 "/usr/include/c++/4.2.1/bits/c++config.h" 3 # 1 "/usr/include/c++/4.2.1/bits/os_defines.h" 1 3 # 61 "/usr/include/c++/4.2.1/bits/os_defines.h" 3 # 1 "/usr/include/unistd.h" 1 3 4 # 72 "/usr/include/unistd.h" 3 4 # 1 "/usr/include/sys/unistd.h" 1 3 4 # 84 "/usr/include/sys/unistd.h" 3 4 # 1 "/usr/include/sys/_types/_posix_vdisable.h" 1 3 4 # 85 "/usr/include/sys/unistd.h" 2 3 4 # 122 "/usr/include/sys/unistd.h" 3 4 # 1 "/usr/include/sys/_types/_seek_set.h" 1 3 4 # 123 "/usr/include/sys/unistd.h" 2 3 4 # 132 "/usr/include/sys/unistd.h" 3 4 struct accessx_descriptor { unsigned int ad_name_offset; int ad_flags; int ad_pad[2]; }; # 179 "/usr/include/sys/unistd.h" 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 180 "/usr/include/sys/unistd.h" 2 3 4 # 1 "/usr/include/_types/_uint64_t.h" 1 3 4 # 31 "/usr/include/_types/_uint64_t.h" 3 4 typedef unsigned long long uint64_t; # 181 "/usr/include/sys/unistd.h" 2 3 4 extern "C" { int getattrlistbulk(int, void *, void *, size_t, uint64_t) __attribute__((availability(macosx,introduced=10.10))); } # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 195 "/usr/include/sys/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_uid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uid_t.h" 3 4 typedef __darwin_uid_t uid_t; # 198 "/usr/include/sys/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_gid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_gid_t.h" 3 4 typedef __darwin_gid_t gid_t; # 199 "/usr/include/sys/unistd.h" 2 3 4 extern "C" { int faccessat(int, const char *, int, int) __attribute__((availability(macosx,introduced=10.10))); int fchownat(int, const char *, uid_t, gid_t, int) __attribute__((availability(macosx,introduced=10.10))); int linkat(int, const char *, int, const char *, int) __attribute__((availability(macosx,introduced=10.10))); ssize_t readlinkat(int, const char *, char *, size_t) __attribute__((availability(macosx,introduced=10.10))); int symlinkat(const char *, int, const char *) __attribute__((availability(macosx,introduced=10.10))); int unlinkat(int, const char *, int) __attribute__((availability(macosx,introduced=10.10))); int getattrlistat(int, const char *, void *, void *, size_t, unsigned long) __attribute__((availability(macosx,introduced=10.10))); } # 73 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_intptr_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_intptr_t.h" 3 4 typedef __darwin_intptr_t intptr_t; # 76 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_off_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_off_t.h" 3 4 typedef __darwin_off_t off_t; # 77 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_pid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_pid_t.h" 3 4 typedef __darwin_pid_t pid_t; # 78 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 81 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_useconds_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_useconds_t.h" 3 4 typedef __darwin_useconds_t useconds_t; # 84 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 85 "/usr/include/unistd.h" 2 3 4 # 423 "/usr/include/unistd.h" 3 4 extern "C" { void _exit(int) __attribute__((noreturn)); int access(const char *, int); unsigned int alarm(unsigned int); int chdir(const char *); int chown(const char *, uid_t, gid_t); int close(int) __asm("_" "close" ); int dup(int); int dup2(int, int); int execl(const char *, const char *, ...); int execle(const char *, const char *, ...); int execlp(const char *, const char *, ...); int execv(const char *, char * const *); int execve(const char *, char * const *, char * const *); int execvp(const char *, char * const *); pid_t fork(void); long fpathconf(int, int); char *getcwd(char *, size_t); gid_t getegid(void); uid_t geteuid(void); gid_t getgid(void); int getgroups(int, gid_t []); char *getlogin(void); pid_t getpgrp(void); pid_t getpid(void); pid_t getppid(void); uid_t getuid(void); int isatty(int); int link(const char *, const char *); off_t lseek(int, off_t, int); long pathconf(const char *, int); int pause(void) __asm("_" "pause" ); int pipe(int [2]); ssize_t read(int, void *, size_t) __asm("_" "read" ); int rmdir(const char *); int setgid(gid_t); int setpgid(pid_t, pid_t); pid_t setsid(void); int setuid(uid_t); unsigned int sleep(unsigned int) __asm("_" "sleep" ); long sysconf(int); pid_t tcgetpgrp(int); int tcsetpgrp(int, pid_t); char *ttyname(int); int ttyname_r(int, char *, size_t) __asm("_" "ttyname_r" ); int unlink(const char *); ssize_t write(int, const void *, size_t) __asm("_" "write" ); } # 500 "/usr/include/unistd.h" 3 4 extern "C" { size_t confstr(int, char *, size_t) __asm("_" "confstr" ); int getopt(int, char * const [], const char *) __asm("_" "getopt" ); extern char *optarg; extern int optind, opterr, optopt; } # 525 "/usr/include/unistd.h" 3 4 extern "C" { __attribute__((deprecated)) void *brk(const void *); int chroot(const char *) ; char *crypt(const char *, const char *); char *ctermid(char *); void encrypt(char *, int) __asm("_" "encrypt" ); int fchdir(int); long gethostid(void); pid_t getpgid(pid_t); pid_t getsid(pid_t); int getdtablesize(void) ; int getpagesize(void) __attribute__((const)) ; char *getpass(const char *) ; char *getwd(char *) ; int lchown(const char *, uid_t, gid_t) __asm("_" "lchown" ); int lockf(int, int, off_t) __asm("_" "lockf" ); int nice(int) __asm("_" "nice" ); ssize_t pread(int, void *, size_t, off_t) __asm("_" "pread" ); ssize_t pwrite(int, const void *, size_t, off_t) __asm("_" "pwrite" ); __attribute__((deprecated)) void *sbrk(int); pid_t setpgrp(void) __asm("_" "setpgrp" ); int setregid(gid_t, gid_t) __asm("_" "setregid" ); int setreuid(uid_t, uid_t) __asm("_" "setreuid" ); void swab(const void * , void * , ssize_t); void sync(void); int truncate(const char *, off_t); useconds_t ualarm(useconds_t, useconds_t); int usleep(useconds_t) __asm("_" "usleep" ); pid_t vfork(void); int fsync(int) __asm("_" "fsync" ); int ftruncate(int, off_t); int getlogin_r(char *, size_t); } # 618 "/usr/include/unistd.h" 3 4 extern "C" { int fchown(int, uid_t, gid_t); int gethostname(char *, size_t); ssize_t readlink(const char * , char * , size_t); int setegid(gid_t); int seteuid(uid_t); int symlink(const char *, const char *); } # 1 "/usr/include/sys/select.h" 1 3 4 # 66 "/usr/include/sys/select.h" 3 4 # 1 "/usr/include/sys/appleapiopts.h" 1 3 4 # 67 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_fd_def.h" 1 3 4 # 45 "/usr/include/sys/_types/_fd_def.h" 3 4 extern "C" { typedef struct fd_set { __int32_t fds_bits[((((1024) % ((sizeof(__int32_t) * 8))) == 0) ? ((1024) / ((sizeof(__int32_t) * 8))) : (((1024) / ((sizeof(__int32_t) * 8))) + 1))]; } fd_set; } static inline int __darwin_fd_isset(int _n, const struct fd_set *_p) { return (_p->fds_bits[(unsigned long)_n/(sizeof(__int32_t) * 8)] & ((__int32_t)(1<<((unsigned long)_n % (sizeof(__int32_t) * 8))))); } # 76 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_timeval.h" 1 3 4 # 30 "/usr/include/sys/_types/_timeval.h" 3 4 struct timeval { __darwin_time_t tv_sec; __darwin_suseconds_t tv_usec; }; # 78 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_suseconds_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_suseconds_t.h" 3 4 typedef __darwin_suseconds_t suseconds_t; # 86 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_sigset_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_sigset_t.h" 3 4 typedef __darwin_sigset_t sigset_t; # 87 "/usr/include/sys/select.h" 2 3 4 # 100 "/usr/include/sys/select.h" 3 4 # 1 "/usr/include/sys/_types/_fd_setsize.h" 1 3 4 # 101 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_fd_set.h" 1 3 4 # 102 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_fd_clr.h" 1 3 4 # 103 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_fd_isset.h" 1 3 4 # 104 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_fd_zero.h" 1 3 4 # 105 "/usr/include/sys/select.h" 2 3 4 # 1 "/usr/include/sys/_types/_fd_copy.h" 1 3 4 # 108 "/usr/include/sys/select.h" 2 3 4 extern "C" { int pselect(int, fd_set * , fd_set * , fd_set * , const struct timespec * , const sigset_t * ) __asm("_" "pselect" "$1050") ; # 1 "/usr/include/sys/_select.h" 1 3 4 # 39 "/usr/include/sys/_select.h" 3 4 int select(int, fd_set * , fd_set * , fd_set * , struct timeval * ) __asm("_" "select" "$1050") ; # 130 "/usr/include/sys/select.h" 2 3 4 } # 634 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_dev_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_dev_t.h" 3 4 typedef __darwin_dev_t dev_t; # 636 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_mode_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_mode_t.h" 3 4 typedef __darwin_mode_t mode_t; # 637 "/usr/include/unistd.h" 2 3 4 # 1 "/usr/include/sys/_types/_uuid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uuid_t.h" 3 4 typedef __darwin_uuid_t uuid_t; # 638 "/usr/include/unistd.h" 2 3 4 extern "C" { void _Exit(int) __attribute__((noreturn)); int accessx_np(const struct accessx_descriptor *, size_t, int *, uid_t); int acct(const char *); int add_profil(char *, size_t, unsigned long, unsigned int); void endusershell(void); int execvP(const char *, const char *, char * const *); char *fflagstostr(unsigned long); int getdomainname(char *, int); int getgrouplist(const char *, int, int *, int *); # 1 "/usr/include/gethostuuid.h" 1 3 4 # 39 "/usr/include/gethostuuid.h" 3 4 int gethostuuid(uuid_t, const struct timespec *) __attribute__((availability(macosx,introduced=10.5))); # 654 "/usr/include/unistd.h" 2 3 4 mode_t getmode(const void *, mode_t); int getpeereid(int, uid_t *, gid_t *); int getsgroups_np(int *, uuid_t); char *getusershell(void); int getwgroups_np(int *, uuid_t); int initgroups(const char *, int); int iruserok(unsigned long, int, const char *, const char *); int iruserok_sa(const void *, int, int, const char *, const char *); int issetugid(void); char *mkdtemp(char *); int mknod(const char *, mode_t, dev_t); int mkpath_np(const char *path, mode_t omode) __attribute__((availability(macosx,introduced=10.8))); int mkstemp(char *); int mkstemps(char *, int); char *mktemp(char *); int nfssvc(int, void *); int profil(char *, size_t, unsigned long, unsigned int); int pthread_setugid_np(uid_t, gid_t); int pthread_getugid_np( uid_t *, gid_t *); int rcmd(char **, int, const char *, const char *, const char *, int *); int rcmd_af(char **, int, const char *, const char *, const char *, int *, int); int reboot(int); int revoke(const char *); int rresvport(int *); int rresvport_af(int *, int); int ruserok(const char *, int, const char *, const char *); int setdomainname(const char *, int); int setgroups(int, const gid_t *); void sethostid(long); int sethostname(const char *, int); void setkey(const char *) __asm("_" "setkey" ); int setlogin(const char *); void *setmode(const char *) __asm("_" "setmode" ); int setrgid(gid_t); int setruid(uid_t); int setsgroups_np(int, const uuid_t); void setusershell(void); int setwgroups_np(int, const uuid_t); int strtofflags(char **, unsigned long *, unsigned long *); int swapon(const char *); int syscall(int, ...); int ttyslot(void); int undelete(const char *); int unwhiteout(const char *); void *valloc(size_t); extern char *suboptarg; int getsubopt(char **, char * const *, char **); int fgetattrlist(int,void*,void*,size_t,unsigned int) __attribute__((availability(macosx,introduced=10.6))); int fsetattrlist(int,void*,void*,size_t,unsigned int) __attribute__((availability(macosx,introduced=10.6))); int getattrlist(const char*,void*,void*,size_t,unsigned int) __asm("_" "getattrlist" ); int setattrlist(const char*,void*,void*,size_t,unsigned int) __asm("_" "setattrlist" ); int exchangedata(const char*,const char*,unsigned int); int getdirentriesattr(int,void*,void*,size_t,unsigned int*,unsigned int*,unsigned int*,unsigned int); # 731 "/usr/include/unistd.h" 3 4 struct fssearchblock; struct searchstate; int searchfs(const char *, struct fssearchblock *, unsigned long *, unsigned int, unsigned int, struct searchstate *); int fsctl(const char *,unsigned long,void*,unsigned int); int ffsctl(int,unsigned long,void*,unsigned int) __attribute__((availability(macosx,introduced=10.6))); int fsync_volume_np(int, int) __attribute__((availability(macosx,introduced=10.8))); int sync_volume_np(const char *, int) __attribute__((availability(macosx,introduced=10.8))); extern int optreset; } # 62 "/usr/include/c++/4.2.1/bits/os_defines.h" 2 3 extern "C" { # 92 "/usr/include/c++/4.2.1/bits/os_defines.h" 3 extern void __dtrace_probe$cxa_runtime$cxa_exception_rethrow$v1(void); extern int __dtrace_isenabled$cxa_runtime$cxa_exception_rethrow$v1(void); extern void __dtrace_probe$cxa_runtime$cxa_exception_throw$v1$766f6964202a(void *); extern int __dtrace_isenabled$cxa_runtime$cxa_exception_throw$v1(void); } # 42 "/usr/include/c++/4.2.1/bits/c++config.h" 2 3 # 1 "/usr/include/c++/4.2.1/bits/cpu_defines.h" 1 3 # 45 "/usr/include/c++/4.2.1/bits/c++config.h" 2 3 # 153 "/usr/include/c++/4.2.1/bits/c++config.h" 3 namespace std { # 165 "/usr/include/c++/4.2.1/bits/c++config.h" 3 } # 51 "/usr/include/c++/4.2.1/cstddef" 2 3 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stddef.h" 1 3 4 # 52 "/usr/include/c++/4.2.1/cstddef" 2 3 namespace std { using ::ptrdiff_t; using ::size_t; } # 45 "/usr/include/c++/4.2.1/new" 2 3 # 1 "/usr/include/c++/4.2.1/exception" 1 3 # 40 "/usr/include/c++/4.2.1/exception" 3 #pragma GCC visibility push(default) extern "C++" { namespace std { # 56 "/usr/include/c++/4.2.1/exception" 3 class exception { public: exception() throw() { } virtual ~exception() throw(); virtual const char* what() const throw(); }; class bad_exception : public exception { public: bad_exception() throw() { } virtual ~bad_exception() throw(); virtual const char* what() const throw(); }; typedef void (*terminate_handler) (); typedef void (*unexpected_handler) (); terminate_handler set_terminate(terminate_handler) throw(); void terminate() __attribute__ ((__noreturn__)); unexpected_handler set_unexpected(unexpected_handler) throw(); void unexpected() __attribute__ ((__noreturn__)); # 112 "/usr/include/c++/4.2.1/exception" 3 bool uncaught_exception() throw(); } namespace __gnu_cxx { # 127 "/usr/include/c++/4.2.1/exception" 3 void __verbose_terminate_handler (); } } #pragma GCC visibility pop # 46 "/usr/include/c++/4.2.1/new" 2 3 #pragma GCC visibility push(default) extern "C++" { namespace std { class bad_alloc : public exception { public: bad_alloc() throw() { } virtual ~bad_alloc() throw(); virtual const char* what() const throw(); }; struct nothrow_t { }; extern const nothrow_t nothrow; typedef void (*new_handler)(); new_handler set_new_handler(new_handler) throw(); } # 99 "/usr/include/c++/4.2.1/new" 3 void* operator new(std::size_t) throw (std::bad_alloc); void* operator new[](std::size_t) throw (std::bad_alloc); void operator delete(void*) throw(); void operator delete[](void*) throw(); void* operator new(std::size_t, const std::nothrow_t&) throw(); void* operator new[](std::size_t, const std::nothrow_t&) throw(); void operator delete(void*, const std::nothrow_t&) throw(); void operator delete[](void*, const std::nothrow_t&) throw(); inline void* operator new(std::size_t, void* __p) throw() { return __p; } inline void* operator new[](std::size_t, void* __p) throw() { return __p; } inline void operator delete (void*, void*) throw() { } inline void operator delete[](void*, void*) throw() { } } #pragma GCC visibility pop # 78 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 # 91 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void* operator new(std:: size_t, void*) throw(); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void* operator new[](std:: size_t, void*) throw(); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void operator delete(void*, void*) throw(); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void operator delete[](void*, void*) throw(); # 1 "/usr/include/stdio.h" 1 3 4 # 71 "/usr/include/stdio.h" 3 4 # 1 "/usr/include/sys/_types/_va_list.h" 1 3 4 # 31 "/usr/include/sys/_types/_va_list.h" 3 4 typedef __darwin_va_list va_list; # 72 "/usr/include/stdio.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 73 "/usr/include/stdio.h" 2 3 4 # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 74 "/usr/include/stdio.h" 2 3 4 # 1 "/usr/include/sys/stdio.h" 1 3 4 # 37 "/usr/include/sys/stdio.h" 3 4 extern "C" { int renameat(int, const char *, int, const char *) __attribute__((availability(macosx,introduced=10.10))); } # 76 "/usr/include/stdio.h" 2 3 4 typedef __darwin_off_t fpos_t; # 88 "/usr/include/stdio.h" 3 4 struct __sbuf { unsigned char *_base; int _size; }; struct __sFILEX; # 122 "/usr/include/stdio.h" 3 4 typedef struct __sFILE { unsigned char *_p; int _r; int _w; short _flags; short _file; struct __sbuf _bf; int _lbfsize; void *_cookie; int (*_close)(void *); int (*_read) (void *, char *, int); fpos_t (*_seek) (void *, fpos_t, int); int (*_write)(void *, const char *, int); struct __sbuf _ub; struct __sFILEX *_extra; int _ur; unsigned char _ubuf[3]; unsigned char _nbuf[1]; struct __sbuf _lb; int _blksize; fpos_t _offset; } FILE; extern "C" { extern FILE *__stdinp; extern FILE *__stdoutp; extern FILE *__stderrp; } # 230 "/usr/include/stdio.h" 3 4 extern "C" { void clearerr(FILE *); int fclose(FILE *); int feof(FILE *); int ferror(FILE *); int fflush(FILE *); int fgetc(FILE *); int fgetpos(FILE * , fpos_t *); char *fgets(char * , int, FILE *); FILE *fopen(const char * , const char * ) __asm("_" "fopen" ); int fprintf(FILE * , const char * , ...) __attribute__((__format__ (__printf__, 2, 3))); int fputc(int, FILE *); int fputs(const char * , FILE * ) __asm("_" "fputs" ); size_t fread(void * , size_t, size_t, FILE * ); FILE *freopen(const char * , const char * , FILE * ) __asm("_" "freopen" ); int fscanf(FILE * , const char * , ...) __attribute__((__format__ (__scanf__, 2, 3))); int fseek(FILE *, long, int); int fsetpos(FILE *, const fpos_t *); long ftell(FILE *); size_t fwrite(const void * , size_t, size_t, FILE * ) __asm("_" "fwrite" ); int getc(FILE *); int getchar(void); char *gets(char *); void perror(const char *); int printf(const char * , ...) __attribute__((__format__ (__printf__, 1, 2))); int putc(int, FILE *); int putchar(int); int puts(const char *); int remove(const char *); int rename (const char *, const char *); void rewind(FILE *); int scanf(const char * , ...) __attribute__((__format__ (__scanf__, 1, 2))); void setbuf(FILE * , char * ); int setvbuf(FILE * , char * , int, size_t); int sprintf(char * , const char * , ...) __attribute__((__format__ (__printf__, 2, 3))); int sscanf(const char * , const char * , ...) __attribute__((__format__ (__scanf__, 2, 3))); FILE *tmpfile(void); __attribute__((deprecated("This function is provided for compatibility reasons only. Due to security concerns inherent in the design of tmpnam(3), it is highly recommended that you use mkstemp(3) instead."))) char *tmpnam(char *); int ungetc(int, FILE *); int vfprintf(FILE * , const char * , va_list) __attribute__((__format__ (__printf__, 2, 0))); int vprintf(const char * , va_list) __attribute__((__format__ (__printf__, 1, 0))); int vsprintf(char * , const char * , va_list) __attribute__((__format__ (__printf__, 2, 0))); } # 292 "/usr/include/stdio.h" 3 4 extern "C" { # 302 "/usr/include/stdio.h" 3 4 FILE *fdopen(int, const char *) __asm("_" "fdopen" ); int fileno(FILE *); } # 314 "/usr/include/stdio.h" 3 4 extern "C" { int pclose(FILE *); FILE *popen(const char *, const char *) __asm("_" "popen" ); } # 336 "/usr/include/stdio.h" 3 4 extern "C" { int __srget(FILE *); int __svfscanf(FILE *, const char *, va_list) __attribute__((__format__ (__scanf__, 2, 0))); int __swbuf(int, FILE *); } inline __attribute__ ((__always_inline__)) int __sputc(int _c, FILE *_p) { if (--_p->_w >= 0 || (_p->_w >= _p->_lbfsize && (char)_c != '\n')) return (*_p->_p++ = _c); else return (__swbuf(_c, _p)); } # 373 "/usr/include/stdio.h" 3 4 extern "C" { void flockfile(FILE *); int ftrylockfile(FILE *); void funlockfile(FILE *); int getc_unlocked(FILE *); int getchar_unlocked(void); int putc_unlocked(int, FILE *); int putchar_unlocked(int); int getw(FILE *); int putw(int, FILE *); __attribute__((deprecated("This function is provided for compatibility reasons only. Due to security concerns inherent in the design of tempnam(3), it is highly recommended that you use mkstemp(3) instead."))) char *tempnam(const char *, const char *) __asm("_" "tempnam" ); } # 413 "/usr/include/stdio.h" 3 4 extern "C" { int fseeko(FILE *, off_t, int); off_t ftello(FILE *); } extern "C" { int snprintf(char * , size_t, const char * , ...) __attribute__((__format__ (__printf__, 3, 4))); int vfscanf(FILE * , const char * , va_list) __attribute__((__format__ (__scanf__, 2, 0))); int vscanf(const char * , va_list) __attribute__((__format__ (__scanf__, 1, 0))); int vsnprintf(char * , size_t, const char * , va_list) __attribute__((__format__ (__printf__, 3, 0))); int vsscanf(const char * , const char * , va_list) __attribute__((__format__ (__scanf__, 2, 0))); } # 438 "/usr/include/stdio.h" 3 4 extern "C" { int dprintf(int, const char * , ...) __attribute__((__format__ (__printf__, 2, 3))) __attribute__((availability(macosx,introduced=10.7))); int vdprintf(int, const char * , va_list) __attribute__((__format__ (__printf__, 2, 0))) __attribute__((availability(macosx,introduced=10.7))); ssize_t getdelim(char ** , size_t * , int, FILE * ) __attribute__((availability(macosx,introduced=10.7))); ssize_t getline(char ** , size_t * , FILE * ) __attribute__((availability(macosx,introduced=10.7))); } extern "C" { extern const int sys_nerr; extern const char *const sys_errlist[]; int asprintf(char ** , const char * , ...) __attribute__((__format__ (__printf__, 2, 3))); char *ctermid_r(char *); char *fgetln(FILE *, size_t *); const char *fmtcheck(const char *, const char *); int fpurge(FILE *); void setbuffer(FILE *, char *, int); int setlinebuf(FILE *); int vasprintf(char ** , const char * , va_list) __attribute__((__format__ (__printf__, 2, 0))); FILE *zopen(const char *, const char *, int); FILE *funopen(const void *, int (*)(void *, char *, int), int (*)(void *, const char *, int), fpos_t (*)(void *, fpos_t, int), int (*)(void *)); } # 99 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 # 1 "/usr/include/stdlib.h" 1 3 4 # 65 "/usr/include/stdlib.h" 3 4 # 1 "/usr/include/sys/wait.h" 1 3 4 # 79 "/usr/include/sys/wait.h" 3 4 typedef enum { P_ALL, P_PID, P_PGID } idtype_t; # 1 "/usr/include/sys/_types/_id_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_id_t.h" 3 4 typedef __darwin_id_t id_t; # 91 "/usr/include/sys/wait.h" 2 3 4 # 109 "/usr/include/sys/wait.h" 3 4 # 1 "/usr/include/sys/signal.h" 1 3 4 # 81 "/usr/include/sys/signal.h" 3 4 # 1 "/usr/include/machine/signal.h" 1 3 4 # 32 "/usr/include/machine/signal.h" 3 4 # 1 "/usr/include/i386/signal.h" 1 3 4 # 39 "/usr/include/i386/signal.h" 3 4 typedef int sig_atomic_t; # 33 "/usr/include/machine/signal.h" 2 3 4 # 82 "/usr/include/sys/signal.h" 2 3 4 # 145 "/usr/include/sys/signal.h" 3 4 # 1 "/usr/include/machine/_mcontext.h" 1 3 4 # 29 "/usr/include/machine/_mcontext.h" 3 4 # 1 "/usr/include/i386/_mcontext.h" 1 3 4 # 33 "/usr/include/i386/_mcontext.h" 3 4 # 1 "/usr/include/mach/i386/_structs.h" 1 3 4 # 43 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_thread_state { unsigned int __eax; unsigned int __ebx; unsigned int __ecx; unsigned int __edx; unsigned int __edi; unsigned int __esi; unsigned int __ebp; unsigned int __esp; unsigned int __ss; unsigned int __eflags; unsigned int __eip; unsigned int __cs; unsigned int __ds; unsigned int __es; unsigned int __fs; unsigned int __gs; }; # 89 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_fp_control { unsigned short __invalid :1, __denorm :1, __zdiv :1, __ovrfl :1, __undfl :1, __precis :1, :2, __pc :2, __rc :2, :1, :3; }; typedef struct __darwin_fp_control __darwin_fp_control_t; # 147 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_fp_status { unsigned short __invalid :1, __denorm :1, __zdiv :1, __ovrfl :1, __undfl :1, __precis :1, __stkflt :1, __errsumm :1, __c0 :1, __c1 :1, __c2 :1, __tos :3, __c3 :1, __busy :1; }; typedef struct __darwin_fp_status __darwin_fp_status_t; # 191 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_mmst_reg { char __mmst_reg[10]; char __mmst_rsrv[6]; }; # 210 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_xmm_reg { char __xmm_reg[16]; }; # 232 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_float_state { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; char __fpu_rsrv4[14*16]; int __fpu_reserved1; }; struct __darwin_i386_avx_state { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; char __fpu_rsrv4[14*16]; int __fpu_reserved1; char __avx_reserved1[64]; struct __darwin_xmm_reg __fpu_ymmh0; struct __darwin_xmm_reg __fpu_ymmh1; struct __darwin_xmm_reg __fpu_ymmh2; struct __darwin_xmm_reg __fpu_ymmh3; struct __darwin_xmm_reg __fpu_ymmh4; struct __darwin_xmm_reg __fpu_ymmh5; struct __darwin_xmm_reg __fpu_ymmh6; struct __darwin_xmm_reg __fpu_ymmh7; }; # 402 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_exception_state { __uint16_t __trapno; __uint16_t __cpu; __uint32_t __err; __uint32_t __faultvaddr; }; # 422 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_debug_state32 { unsigned int __dr0; unsigned int __dr1; unsigned int __dr2; unsigned int __dr3; unsigned int __dr4; unsigned int __dr5; unsigned int __dr6; unsigned int __dr7; }; # 454 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_thread_state64 { __uint64_t __rax; __uint64_t __rbx; __uint64_t __rcx; __uint64_t __rdx; __uint64_t __rdi; __uint64_t __rsi; __uint64_t __rbp; __uint64_t __rsp; __uint64_t __r8; __uint64_t __r9; __uint64_t __r10; __uint64_t __r11; __uint64_t __r12; __uint64_t __r13; __uint64_t __r14; __uint64_t __r15; __uint64_t __rip; __uint64_t __rflags; __uint64_t __cs; __uint64_t __fs; __uint64_t __gs; }; # 509 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_float_state64 { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; struct __darwin_xmm_reg __fpu_xmm8; struct __darwin_xmm_reg __fpu_xmm9; struct __darwin_xmm_reg __fpu_xmm10; struct __darwin_xmm_reg __fpu_xmm11; struct __darwin_xmm_reg __fpu_xmm12; struct __darwin_xmm_reg __fpu_xmm13; struct __darwin_xmm_reg __fpu_xmm14; struct __darwin_xmm_reg __fpu_xmm15; char __fpu_rsrv4[6*16]; int __fpu_reserved1; }; struct __darwin_x86_avx_state64 { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; struct __darwin_xmm_reg __fpu_xmm8; struct __darwin_xmm_reg __fpu_xmm9; struct __darwin_xmm_reg __fpu_xmm10; struct __darwin_xmm_reg __fpu_xmm11; struct __darwin_xmm_reg __fpu_xmm12; struct __darwin_xmm_reg __fpu_xmm13; struct __darwin_xmm_reg __fpu_xmm14; struct __darwin_xmm_reg __fpu_xmm15; char __fpu_rsrv4[6*16]; int __fpu_reserved1; char __avx_reserved1[64]; struct __darwin_xmm_reg __fpu_ymmh0; struct __darwin_xmm_reg __fpu_ymmh1; struct __darwin_xmm_reg __fpu_ymmh2; struct __darwin_xmm_reg __fpu_ymmh3; struct __darwin_xmm_reg __fpu_ymmh4; struct __darwin_xmm_reg __fpu_ymmh5; struct __darwin_xmm_reg __fpu_ymmh6; struct __darwin_xmm_reg __fpu_ymmh7; struct __darwin_xmm_reg __fpu_ymmh8; struct __darwin_xmm_reg __fpu_ymmh9; struct __darwin_xmm_reg __fpu_ymmh10; struct __darwin_xmm_reg __fpu_ymmh11; struct __darwin_xmm_reg __fpu_ymmh12; struct __darwin_xmm_reg __fpu_ymmh13; struct __darwin_xmm_reg __fpu_ymmh14; struct __darwin_xmm_reg __fpu_ymmh15; }; # 751 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_exception_state64 { __uint16_t __trapno; __uint16_t __cpu; __uint32_t __err; __uint64_t __faultvaddr; }; # 771 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_debug_state64 { __uint64_t __dr0; __uint64_t __dr1; __uint64_t __dr2; __uint64_t __dr3; __uint64_t __dr4; __uint64_t __dr5; __uint64_t __dr6; __uint64_t __dr7; }; # 34 "/usr/include/i386/_mcontext.h" 2 3 4 struct __darwin_mcontext32 { struct __darwin_i386_exception_state __es; struct __darwin_i386_thread_state __ss; struct __darwin_i386_float_state __fs; }; struct __darwin_mcontext_avx32 { struct __darwin_i386_exception_state __es; struct __darwin_i386_thread_state __ss; struct __darwin_i386_avx_state __fs; }; # 76 "/usr/include/i386/_mcontext.h" 3 4 struct __darwin_mcontext64 { struct __darwin_x86_exception_state64 __es; struct __darwin_x86_thread_state64 __ss; struct __darwin_x86_float_state64 __fs; }; struct __darwin_mcontext_avx64 { struct __darwin_x86_exception_state64 __es; struct __darwin_x86_thread_state64 __ss; struct __darwin_x86_avx_state64 __fs; }; # 115 "/usr/include/i386/_mcontext.h" 3 4 typedef struct __darwin_mcontext64 *mcontext_t; # 30 "/usr/include/machine/_mcontext.h" 2 3 4 # 146 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_pthread/_pthread_attr_t.h" 1 3 4 # 30 "/usr/include/sys/_pthread/_pthread_attr_t.h" 3 4 typedef __darwin_pthread_attr_t pthread_attr_t; # 148 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_sigaltstack.h" 1 3 4 # 36 "/usr/include/sys/_types/_sigaltstack.h" 3 4 struct __darwin_sigaltstack { void *ss_sp; __darwin_size_t ss_size; int ss_flags; }; typedef struct __darwin_sigaltstack stack_t; # 150 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_ucontext.h" 1 3 4 # 34 "/usr/include/sys/_types/_ucontext.h" 3 4 struct __darwin_ucontext { int uc_onstack; __darwin_sigset_t uc_sigmask; struct __darwin_sigaltstack uc_stack; struct __darwin_ucontext *uc_link; __darwin_size_t uc_mcsize; struct __darwin_mcontext64 *uc_mcontext; }; typedef struct __darwin_ucontext ucontext_t; # 151 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 155 "/usr/include/sys/signal.h" 2 3 4 union sigval { int sival_int; void *sival_ptr; }; struct sigevent { int sigev_notify; int sigev_signo; union sigval sigev_value; void (*sigev_notify_function)(union sigval); pthread_attr_t *sigev_notify_attributes; }; typedef struct __siginfo { int si_signo; int si_errno; int si_code; pid_t si_pid; uid_t si_uid; int si_status; void *si_addr; union sigval si_value; long si_band; unsigned long __pad[7]; } siginfo_t; # 268 "/usr/include/sys/signal.h" 3 4 union __sigaction_u { void (*__sa_handler)(int); void (*__sa_sigaction)(int, struct __siginfo *, void *); }; struct __sigaction { union __sigaction_u __sigaction_u; void (*sa_tramp)(void *, int, int, siginfo_t *, void *); sigset_t sa_mask; int sa_flags; }; struct sigaction { union __sigaction_u __sigaction_u; sigset_t sa_mask; int sa_flags; }; # 330 "/usr/include/sys/signal.h" 3 4 typedef void (*sig_t)(int); # 347 "/usr/include/sys/signal.h" 3 4 struct sigvec { void (*sv_handler)(int); int sv_mask; int sv_flags; }; # 366 "/usr/include/sys/signal.h" 3 4 struct sigstack { char *ss_sp; int ss_onstack; }; # 388 "/usr/include/sys/signal.h" 3 4 extern "C" { void (*signal(int, void (*)(int)))(int); } # 110 "/usr/include/sys/wait.h" 2 3 4 # 1 "/usr/include/sys/resource.h" 1 3 4 # 72 "/usr/include/sys/resource.h" 3 4 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 1 3 4 # 63 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 3 4 # 1 "/usr/include/stdint.h" 1 3 4 # 18 "/usr/include/stdint.h" 3 4 # 1 "/usr/include/sys/_types/_int8_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int8_t.h" 3 4 typedef signed char int8_t; # 19 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int16_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int16_t.h" 3 4 typedef short int16_t; # 20 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int32_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int32_t.h" 3 4 typedef int int32_t; # 21 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int64_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int64_t.h" 3 4 typedef long long int64_t; # 22 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint8_t.h" 1 3 4 # 31 "/usr/include/_types/_uint8_t.h" 3 4 typedef unsigned char uint8_t; # 24 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint16_t.h" 1 3 4 # 31 "/usr/include/_types/_uint16_t.h" 3 4 typedef unsigned short uint16_t; # 25 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint32_t.h" 1 3 4 # 31 "/usr/include/_types/_uint32_t.h" 3 4 typedef unsigned int uint32_t; # 26 "/usr/include/stdint.h" 2 3 4 typedef int8_t int_least8_t; typedef int16_t int_least16_t; typedef int32_t int_least32_t; typedef int64_t int_least64_t; typedef uint8_t uint_least8_t; typedef uint16_t uint_least16_t; typedef uint32_t uint_least32_t; typedef uint64_t uint_least64_t; typedef int8_t int_fast8_t; typedef int16_t int_fast16_t; typedef int32_t int_fast32_t; typedef int64_t int_fast64_t; typedef uint8_t uint_fast8_t; typedef uint16_t uint_fast16_t; typedef uint32_t uint_fast32_t; typedef uint64_t uint_fast64_t; # 1 "/usr/include/sys/_types/_uintptr_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uintptr_t.h" 3 4 typedef unsigned long uintptr_t; # 55 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_intmax_t.h" 1 3 4 # 32 "/usr/include/_types/_intmax_t.h" 3 4 typedef long int intmax_t; # 59 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uintmax_t.h" 1 3 4 # 32 "/usr/include/_types/_uintmax_t.h" 3 4 typedef long unsigned int uintmax_t; # 60 "/usr/include/stdint.h" 2 3 4 # 64 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 2 3 4 # 73 "/usr/include/sys/resource.h" 2 3 4 # 89 "/usr/include/sys/resource.h" 3 4 typedef __uint64_t rlim_t; # 152 "/usr/include/sys/resource.h" 3 4 struct rusage { struct timeval ru_utime; struct timeval ru_stime; # 163 "/usr/include/sys/resource.h" 3 4 long ru_maxrss; long ru_ixrss; long ru_idrss; long ru_isrss; long ru_minflt; long ru_majflt; long ru_nswap; long ru_inblock; long ru_oublock; long ru_msgsnd; long ru_msgrcv; long ru_nsignals; long ru_nvcsw; long ru_nivcsw; }; # 192 "/usr/include/sys/resource.h" 3 4 typedef void *rusage_info_t; struct rusage_info_v0 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; }; struct rusage_info_v1 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; }; struct rusage_info_v2 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; uint64_t ri_diskio_bytesread; uint64_t ri_diskio_byteswritten; }; struct rusage_info_v3 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; uint64_t ri_diskio_bytesread; uint64_t ri_diskio_byteswritten; uint64_t ri_cpu_time_qos_default; uint64_t ri_cpu_time_qos_maintenance; uint64_t ri_cpu_time_qos_background; uint64_t ri_cpu_time_qos_utility; uint64_t ri_cpu_time_qos_legacy; uint64_t ri_cpu_time_qos_user_initiated; uint64_t ri_cpu_time_qos_user_interactive; uint64_t ri_billed_system_time; uint64_t ri_serviced_system_time; }; typedef struct rusage_info_v3 rusage_info_current; # 325 "/usr/include/sys/resource.h" 3 4 struct rlimit { rlim_t rlim_cur; rlim_t rlim_max; }; # 353 "/usr/include/sys/resource.h" 3 4 struct proc_rlimit_control_wakeupmon { uint32_t wm_flags; int32_t wm_rate; }; # 382 "/usr/include/sys/resource.h" 3 4 extern "C" { int getpriority(int, id_t); int getiopolicy_np(int, int) __attribute__((availability(macosx,introduced=10.5))); int getrlimit(int, struct rlimit *) __asm("_" "getrlimit" ); int getrusage(int, struct rusage *); int setpriority(int, id_t, int); int setiopolicy_np(int, int, int) __attribute__((availability(macosx,introduced=10.5))); int setrlimit(int, const struct rlimit *) __asm("_" "setrlimit" ); } # 111 "/usr/include/sys/wait.h" 2 3 4 # 186 "/usr/include/sys/wait.h" 3 4 # 1 "/usr/include/machine/endian.h" 1 3 4 # 35 "/usr/include/machine/endian.h" 3 4 # 1 "/usr/include/i386/endian.h" 1 3 4 # 99 "/usr/include/i386/endian.h" 3 4 # 1 "/usr/include/sys/_endian.h" 1 3 4 # 130 "/usr/include/sys/_endian.h" 3 4 # 1 "/usr/include/libkern/_OSByteOrder.h" 1 3 4 # 66 "/usr/include/libkern/_OSByteOrder.h" 3 4 # 1 "/usr/include/libkern/i386/_OSByteOrder.h" 1 3 4 # 44 "/usr/include/libkern/i386/_OSByteOrder.h" 3 4 static inline __uint16_t _OSSwapInt16( __uint16_t _data ) { return ((__uint16_t)((_data << 8) | (_data >> 8))); } static inline __uint32_t _OSSwapInt32( __uint32_t _data ) { return __builtin_bswap32(_data); } static inline __uint64_t _OSSwapInt64( __uint64_t _data ) { return __builtin_bswap64(_data); } # 67 "/usr/include/libkern/_OSByteOrder.h" 2 3 4 # 131 "/usr/include/sys/_endian.h" 2 3 4 # 100 "/usr/include/i386/endian.h" 2 3 4 # 36 "/usr/include/machine/endian.h" 2 3 4 # 187 "/usr/include/sys/wait.h" 2 3 4 union wait { int w_status; struct { unsigned int w_Termsig:7, w_Coredump:1, w_Retcode:8, w_Filler:16; } w_T; struct { unsigned int w_Stopval:8, w_Stopsig:8, w_Filler:16; } w_S; }; # 247 "/usr/include/sys/wait.h" 3 4 extern "C" { pid_t wait(int *) __asm("_" "wait" ); pid_t waitpid(pid_t, int *, int) __asm("_" "waitpid" ); int waitid(idtype_t, id_t, siginfo_t *, int) __asm("_" "waitid" ); pid_t wait3(int *, int, struct rusage *); pid_t wait4(pid_t, int *, int, struct rusage *); } # 66 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/alloca.h" 1 3 4 # 29 "/usr/include/alloca.h" 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 30 "/usr/include/alloca.h" 2 3 4 extern "C" { void *alloca(size_t); } # 68 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 74 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_ct_rune_t.h" 1 3 4 # 31 "/usr/include/sys/_types/_ct_rune_t.h" 3 4 typedef __darwin_ct_rune_t ct_rune_t; # 77 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_rune_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_rune_t.h" 3 4 typedef __darwin_rune_t rune_t; # 78 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_wchar_t.h" 1 3 4 # 81 "/usr/include/stdlib.h" 2 3 4 typedef struct { int quot; int rem; } div_t; typedef struct { long quot; long rem; } ldiv_t; typedef struct { long long quot; long long rem; } lldiv_t; # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 100 "/usr/include/stdlib.h" 2 3 4 # 117 "/usr/include/stdlib.h" 3 4 extern int __mb_cur_max; # 127 "/usr/include/stdlib.h" 3 4 extern "C" { void abort(void) __attribute__((noreturn)); int abs(int) __attribute__((const)); int atexit(void (*)(void)); double atof(const char *); int atoi(const char *); long atol(const char *); long long atoll(const char *); void *bsearch(const void *, const void *, size_t, size_t, int (*)(const void *, const void *)); void *calloc(size_t, size_t); div_t div(int, int) __attribute__((const)); void exit(int) __attribute__((noreturn)); void free(void *); char *getenv(const char *); long labs(long) __attribute__((const)); ldiv_t ldiv(long, long) __attribute__((const)); long long llabs(long long); lldiv_t lldiv(long long, long long); void *malloc(size_t); int mblen(const char *, size_t); size_t mbstowcs(wchar_t * , const char * , size_t); int mbtowc(wchar_t * , const char * , size_t); int posix_memalign(void **, size_t, size_t) __attribute__((availability(macosx,introduced=10.6))); void qsort(void *, size_t, size_t, int (*)(const void *, const void *)); int rand(void); void *realloc(void *, size_t); void srand(unsigned); double strtod(const char *, char **) __asm("_" "strtod" ); float strtof(const char *, char **) __asm("_" "strtof" ); long strtol(const char *, char **, int); long double strtold(const char *, char **); long long strtoll(const char *, char **, int); unsigned long strtoul(const char *, char **, int); unsigned long long strtoull(const char *, char **, int); int system(const char *) __asm("_" "system" ) __attribute__((availability(macosx,introduced=10.0))); size_t wcstombs(char * , const wchar_t * , size_t); int wctomb(char *, wchar_t); void _Exit(int) __attribute__((noreturn)); long a64l(const char *); double drand48(void); char *ecvt(double, int, int *, int *); double erand48(unsigned short[3]); char *fcvt(double, int, int *, int *); char *gcvt(double, int, char *); int getsubopt(char **, char * const *, char **); int grantpt(int); char *initstate(unsigned, char *, size_t); long jrand48(unsigned short[3]); char *l64a(long); void lcong48(unsigned short[7]); long lrand48(void); char *mktemp(char *); int mkstemp(char *); long mrand48(void); long nrand48(unsigned short[3]); int posix_openpt(int); char *ptsname(int); int putenv(char *) __asm("_" "putenv" ); long random(void); int rand_r(unsigned *); char *realpath(const char * , char * ) __asm("_" "realpath" "$DARWIN_EXTSN"); unsigned short *seed48(unsigned short[3]); int setenv(const char *, const char *, int) __asm("_" "setenv" ); void setkey(const char *) __asm("_" "setkey" ); char *setstate(const char *); void srand48(long); void srandom(unsigned); int unlockpt(int); int unsetenv(const char *) __asm("_" "unsetenv" ); # 1 "/usr/include/machine/types.h" 1 3 4 # 35 "/usr/include/machine/types.h" 3 4 # 1 "/usr/include/i386/types.h" 1 3 4 # 81 "/usr/include/i386/types.h" 3 4 typedef unsigned char u_int8_t; typedef unsigned short u_int16_t; typedef unsigned int u_int32_t; typedef unsigned long long u_int64_t; typedef int64_t register_t; # 97 "/usr/include/i386/types.h" 3 4 typedef u_int64_t user_addr_t; typedef u_int64_t user_size_t; typedef int64_t user_ssize_t; typedef int64_t user_long_t; typedef u_int64_t user_ulong_t; typedef int64_t user_time_t; typedef int64_t user_off_t; typedef u_int64_t syscall_arg_t; # 36 "/usr/include/machine/types.h" 2 3 4 # 239 "/usr/include/stdlib.h" 2 3 4 u_int32_t arc4random(void); void arc4random_addrandom(unsigned char * , int ); void arc4random_buf(void * , size_t ) __attribute__((availability(macosx,introduced=10.7))); void arc4random_stir(void); u_int32_t arc4random_uniform(u_int32_t ) __attribute__((availability(macosx,introduced=10.7))); char *cgetcap(char *, const char *, int); int cgetclose(void); int cgetent(char **, char **, const char *); int cgetfirst(char **, char **); int cgetmatch(const char *, const char *); int cgetnext(char **, char **); int cgetnum(char *, const char *, long *); int cgetset(const char *); int cgetstr(char *, const char *, char **); int cgetustr(char *, const char *, char **); int daemon(int, int) __asm("_" "daemon" "$1050") __attribute__((availability(macosx,introduced=10.0,deprecated=10.5))); char *devname(dev_t, mode_t); char *devname_r(dev_t, mode_t, char *buf, int len); char *getbsize(int *, long *); int getloadavg(double [], int); const char *getprogname(void); int heapsort(void *, size_t, size_t, int (*)(const void *, const void *)); int mergesort(void *, size_t, size_t, int (*)(const void *, const void *)); void psort(void *, size_t, size_t, int (*)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort_r(void *, size_t, size_t, void *, int (*)(void *, const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void qsort_r(void *, size_t, size_t, void *, int (*)(void *, const void *, const void *)); int radixsort(const unsigned char **, int, const unsigned char *, unsigned); void setprogname(const char *); int sradixsort(const unsigned char **, int, const unsigned char *, unsigned); void sranddev(void); void srandomdev(void); void *reallocf(void *, size_t); long long strtoq(const char *, char **, int); unsigned long long strtouq(const char *, char **, int); extern char *suboptarg; void *valloc(size_t); } # 100 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 extern "C" { extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) int printf(const char*, ...); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) int fprintf(FILE*, const char*, ...); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void* malloc(size_t) ; extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void free(void*) ; } # 1 "/usr/include/assert.h" 1 3 4 # 75 "/usr/include/assert.h" 3 4 extern "C" { void __assert_rtn(const char *, const char *, int, const char *) __attribute__((noreturn)); } # 111 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 extern "C" { extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void __assert_rtn( const char *, const char *, int, const char *); # 129 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" } # 145 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void* operator new(std:: size_t) throw(std:: bad_alloc); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void* operator new[](std:: size_t) throw(std:: bad_alloc); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void operator delete(void*) throw(); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) void operator delete[](void*) throw(); # 169 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" 1 # 83 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 84 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" 2 extern "C" { # 149 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) int abs(int) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) long int labs(long int) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) long long int llabs(long long int) ; # 194 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double fabs(double x) ; # 235 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float fabsf(float x) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int min(int, int); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) unsigned int umin(unsigned int, unsigned int); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long long int llmin(long long int, long long int); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) unsigned long long int ullmin(unsigned long long int, unsigned long long int); # 256 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float fminf(float x, float y) ; # 276 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double fmin(double x, double y) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int max(int, int); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) unsigned int umax(unsigned int, unsigned int); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long long int llmax(long long int, long long int); extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) unsigned long long int ullmax(unsigned long long int, unsigned long long int); # 300 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float fmaxf(float x, float y) ; # 320 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double fmax(double, double) ; # 364 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double sin(double x) ; # 397 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double cos(double x) ; # 412 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) void sincos(double x, double *sptr, double *cptr) ; # 428 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) void sincosf(float x, float *sptr, float *cptr) ; # 469 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double tan(double x) ; # 538 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double sqrt(double x) ; # 607 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double rsqrt(double x); # 676 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float rsqrtf(float x); # 728 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double log2(double x) ; # 753 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double exp2(double x) ; # 778 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float exp2f(float x) ; # 802 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double exp10(double x) ; # 824 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float exp10f(float x) ; # 866 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double expm1(double x) ; # 911 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float expm1f(float x) ; # 966 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float log2f(float x) ; # 1020 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double log10(double x) ; # 1091 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double log(double x) ; # 1185 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double log1p(double x) ; # 1282 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float log1pf(float x) ; # 1357 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double floor(double x) ; # 1396 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double exp(double x) ; # 1427 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double cosh(double x) ; # 1457 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double sinh(double x) ; # 1487 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double tanh(double x) ; # 1522 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double acosh(double x) ; # 1560 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float acoshf(float x) ; # 1576 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double asinh(double x) ; # 1592 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float asinhf(float x) ; # 1646 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double atanh(double x) ; # 1700 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float atanhf(float x) ; # 1759 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double ldexp(double x, int exp) ; # 1815 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float ldexpf(float x, int exp) ; # 1867 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double logb(double x) ; # 1922 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float logbf(float x) ; # 1952 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int ilogb(double x) ; # 1982 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int ilogbf(float x) ; # 2058 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double scalbn(double x, int n) ; # 2134 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float scalbnf(float x, int n) ; # 2210 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double scalbln(double x, long int n) ; # 2286 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float scalblnf(float x, long int n) ; # 2364 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double frexp(double x, int *nptr) ; # 2439 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float frexpf(float x, int *nptr) ; # 2453 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double round(double x) ; # 2470 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float roundf(float x) ; # 2488 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long int lround(double x) ; # 2506 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long int lroundf(float x) ; # 2524 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long long int llround(double x) ; # 2542 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long long int llroundf(float x) ; # 2557 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double rint(double x) ; # 2572 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float rintf(float x) ; # 2588 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long int lrint(double x) ; # 2604 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long int lrintf(float x) ; # 2620 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long long int llrint(double x) ; # 2636 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) long long int llrintf(float x) ; # 2689 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double nearbyint(double x) ; # 2742 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float nearbyintf(float x) ; # 2804 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double ceil(double x) ; # 2816 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double trunc(double x) ; # 2831 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float truncf(float x) ; # 2857 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double fdim(double x, double y) ; # 2883 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float fdimf(float x, float y) ; # 2919 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double atan2(double y, double x) ; # 2950 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double atan(double x) ; # 2973 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double acos(double x) ; # 3005 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double asin(double x) ; # 3045 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double hypot(double x, double y) ; # 3095 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double rhypot(double x, double y) ; # 3136 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float hypotf(float x, float y) ; # 3186 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float rhypotf(float x, float y) ; # 3270 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double cbrt(double x) ; # 3356 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float cbrtf(float x) ; # 3408 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double rcbrt(double x); # 3457 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float rcbrtf(float x); # 3517 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double sinpi(double x); # 3577 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float sinpif(float x); # 3629 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double cospi(double x); # 3681 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float cospif(float x); # 3711 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) void sincospi(double x, double *sptr, double *cptr); # 3741 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) void sincospif(float x, float *sptr, float *cptr); # 4049 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double pow(double x, double y) ; # 4105 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double modf(double x, double *iptr) ; # 4164 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double fmod(double x, double y) ; # 4250 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double remainder(double x, double y) ; # 4340 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float remainderf(float x, float y) ; # 4394 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double remquo(double x, double y, int *quo) ; # 4448 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float remquof(float x, float y, int *quo) ; # 4489 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double j0(double x) ; # 4527 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float j0f(float x) ; # 4584 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double j1(double x) ; # 4641 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float j1f(float x) ; # 4680 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double jn(int n, double x) ; # 4719 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float jnf(int n, float x) ; # 4767 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double y0(double x) ; # 4815 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float y0f(float x) ; # 4863 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double y1(double x) ; # 4911 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float y1f(float x) ; # 4960 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double yn(int n, double x) ; # 5009 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float ynf(int n, float x) ; # 5036 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double cyl_bessel_i0(double x) ; # 5062 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float cyl_bessel_i0f(float x) ; # 5089 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double cyl_bessel_i1(double x) ; # 5115 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float cyl_bessel_i1f(float x) ; # 5195 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double erf(double x) ; # 5277 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float erff(float x) ; # 5337 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double erfinv(double y); # 5394 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float erfinvf(float y); # 5429 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double erfc(double x) ; # 5467 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float erfcf(float x) ; # 5595 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double lgamma(double x) ; # 5654 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double erfcinv(double y); # 5710 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float erfcinvf(float y); # 5768 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double normcdfinv(double y); # 5826 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float normcdfinvf(float y); # 5869 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double normcdf(double y); # 5912 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float normcdff(float y); # 5987 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double erfcx(double x); # 6062 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float erfcxf(float x); # 6192 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float lgammaf(float x) ; # 6301 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double tgamma(double x) ; # 6410 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float tgammaf(float x) ; # 6423 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double copysign(double x, double y) ; # 6436 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float copysignf(float x, float y) ; # 6473 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double nextafter(double x, double y) ; # 6510 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float nextafterf(float x, float y) ; # 6526 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double nan(const char *tagp) ; # 6542 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float nanf(const char *tagp) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isinff(float) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isnanf(float) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isfinited(double) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isfinitef(float) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __signbitd(double) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isnand(double) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isinfd(double) ; # 6563 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __signbitf(float) ; # 6718 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) double fma(double x, double y, double z) ; # 6876 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float fmaf(float x, float y, float z) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __signbitl(long double) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isfinite(long double) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isinf(long double) ; extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) int __isnan(long double) ; # 6939 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float acosf(float x) ; # 6979 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float asinf(float x) ; # 7019 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float atanf(float x) ; # 7052 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float atan2f(float y, float x) ; # 7076 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float cosf(float x) ; # 7118 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float sinf(float x) ; # 7160 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float tanf(float x) ; # 7184 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float coshf(float x) ; # 7225 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float sinhf(float x) ; # 7255 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float tanhf(float x) ; # 7306 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float logf(float x) ; # 7356 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float expf(float x) ; # 7407 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float log10f(float x) ; # 7462 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float modff(float x, float *iptr) ; # 7770 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float powf(float x, float y) ; # 7839 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float sqrtf(float x) ; # 7898 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float ceilf(float x) ; # 7970 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float floorf(float x) ; # 8029 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((device_builtin)) float fmodf(float x, float y) ; } # 1 "/usr/include/math.h" 1 3 4 # 33 "/usr/include/math.h" 3 4 extern "C" { # 44 "/usr/include/math.h" 3 4 typedef float float_t; typedef double double_t; # 111 "/usr/include/math.h" 3 4 extern int __math_errhandling(void); # 144 "/usr/include/math.h" 3 4 extern int __fpclassifyf(float); extern int __fpclassifyd(double); extern int __fpclassifyl(long double); # 188 "/usr/include/math.h" 3 4 inline __attribute__ ((__always_inline__)) int __inline_isfinitef(float); inline __attribute__ ((__always_inline__)) int __inline_isfinited(double); inline __attribute__ ((__always_inline__)) int __inline_isfinitel(long double); inline __attribute__ ((__always_inline__)) int __inline_isinff(float); inline __attribute__ ((__always_inline__)) int __inline_isinfd(double); inline __attribute__ ((__always_inline__)) int __inline_isinfl(long double); inline __attribute__ ((__always_inline__)) int __inline_isnanf(float); inline __attribute__ ((__always_inline__)) int __inline_isnand(double); inline __attribute__ ((__always_inline__)) int __inline_isnanl(long double); inline __attribute__ ((__always_inline__)) int __inline_isnormalf(float); inline __attribute__ ((__always_inline__)) int __inline_isnormald(double); inline __attribute__ ((__always_inline__)) int __inline_isnormall(long double); inline __attribute__ ((__always_inline__)) int __inline_signbitf(float); inline __attribute__ ((__always_inline__)) int __inline_signbitd(double); inline __attribute__ ((__always_inline__)) int __inline_signbitl(long double); inline __attribute__ ((__always_inline__)) int __inline_isfinitef(float __x) { return __x == __x && __builtin_fabsf(__x) != __builtin_inff(); } inline __attribute__ ((__always_inline__)) int __inline_isfinited(double __x) { return __x == __x && __builtin_fabs(__x) != __builtin_inf(); } inline __attribute__ ((__always_inline__)) int __inline_isfinitel(long double __x) { return __x == __x && __builtin_fabsl(__x) != __builtin_infl(); } inline __attribute__ ((__always_inline__)) int __inline_isinff(float __x) { return __builtin_fabsf(__x) == __builtin_inff(); } inline __attribute__ ((__always_inline__)) int __inline_isinfd(double __x) { return __builtin_fabs(__x) == __builtin_inf(); } inline __attribute__ ((__always_inline__)) int __inline_isinfl(long double __x) { return __builtin_fabsl(__x) == __builtin_infl(); } inline __attribute__ ((__always_inline__)) int __inline_isnanf(float __x) { return __x != __x; } inline __attribute__ ((__always_inline__)) int __inline_isnand(double __x) { return __x != __x; } inline __attribute__ ((__always_inline__)) int __inline_isnanl(long double __x) { return __x != __x; } inline __attribute__ ((__always_inline__)) int __inline_signbitf(float __x) { union { float __f; unsigned int __u; } __u; __u.__f = __x; return (int)(__u.__u >> 31); } inline __attribute__ ((__always_inline__)) int __inline_signbitd(double __x) { union { double __f; unsigned long long __u; } __u; __u.__f = __x; return (int)(__u.__u >> 63); } inline __attribute__ ((__always_inline__)) int __inline_signbitl(long double __x) { union { long double __ld; struct{ unsigned long long __m; unsigned short __sexp; } __p; } __u; __u.__ld = __x; return (int)(__u.__p.__sexp >> 15); } inline __attribute__ ((__always_inline__)) int __inline_isnormalf(float __x) { return __inline_isfinitef(__x) && __builtin_fabsf(__x) >= 1.17549435e-38F; } inline __attribute__ ((__always_inline__)) int __inline_isnormald(double __x) { return __inline_isfinited(__x) && __builtin_fabs(__x) >= 2.2250738585072014e-308; } inline __attribute__ ((__always_inline__)) int __inline_isnormall(long double __x) { return __inline_isfinitel(__x) && __builtin_fabsl(__x) >= 3.36210314311209350626e-4932L; } # 322 "/usr/include/math.h" 3 4 extern float acosf(float); extern double acos(double); extern long double acosl(long double); extern float asinf(float); extern double asin(double); extern long double asinl(long double); extern float atanf(float); extern double atan(double); extern long double atanl(long double); extern float atan2f(float, float); extern double atan2(double, double); extern long double atan2l(long double, long double); extern float cosf(float); extern double cos(double); extern long double cosl(long double); extern float sinf(float); extern double sin(double); extern long double sinl(long double); extern float tanf(float); extern double tan(double); extern long double tanl(long double); extern float acoshf(float); extern double acosh(double); extern long double acoshl(long double); extern float asinhf(float); extern double asinh(double); extern long double asinhl(long double); extern float atanhf(float); extern double atanh(double); extern long double atanhl(long double); extern float coshf(float); extern double cosh(double); extern long double coshl(long double); extern float sinhf(float); extern double sinh(double); extern long double sinhl(long double); extern float tanhf(float); extern double tanh(double); extern long double tanhl(long double); extern float expf(float); extern double exp(double); extern long double expl(long double); extern float exp2f(float); extern double exp2(double); extern long double exp2l(long double); extern float expm1f(float); extern double expm1(double); extern long double expm1l(long double); extern float logf(float); extern double log(double); extern long double logl(long double); extern float log10f(float); extern double log10(double); extern long double log10l(long double); extern float log2f(float); extern double log2(double); extern long double log2l(long double); extern float log1pf(float); extern double log1p(double); extern long double log1pl(long double); extern float logbf(float); extern double logb(double); extern long double logbl(long double); extern float modff(float, float *); extern double modf(double, double *); extern long double modfl(long double, long double *); extern float ldexpf(float, int); extern double ldexp(double, int); extern long double ldexpl(long double, int); extern float frexpf(float, int *); extern double frexp(double, int *); extern long double frexpl(long double, int *); extern int ilogbf(float); extern int ilogb(double); extern int ilogbl(long double); extern float scalbnf(float, int); extern double scalbn(double, int); extern long double scalbnl(long double, int); extern float scalblnf(float, long int); extern double scalbln(double, long int); extern long double scalblnl(long double, long int); extern float fabsf(float); extern double fabs(double); extern long double fabsl(long double); extern float cbrtf(float); extern double cbrt(double); extern long double cbrtl(long double); extern float hypotf(float, float); extern double hypot(double, double); extern long double hypotl(long double, long double); extern float powf(float, float); extern double pow(double, double); extern long double powl(long double, long double); extern float sqrtf(float); extern double sqrt(double); extern long double sqrtl(long double); extern float erff(float); extern double erf(double); extern long double erfl(long double); extern float erfcf(float); extern double erfc(double); extern long double erfcl(long double); extern float lgammaf(float); extern double lgamma(double); extern long double lgammal(long double); extern float tgammaf(float); extern double tgamma(double); extern long double tgammal(long double); extern float ceilf(float); extern double ceil(double); extern long double ceill(long double); extern float floorf(float); extern double floor(double); extern long double floorl(long double); extern float nearbyintf(float); extern double nearbyint(double); extern long double nearbyintl(long double); extern float rintf(float); extern double rint(double); extern long double rintl(long double); extern long int lrintf(float); extern long int lrint(double); extern long int lrintl(long double); extern float roundf(float); extern double round(double); extern long double roundl(long double); extern long int lroundf(float); extern long int lround(double); extern long int lroundl(long double); extern long long int llrintf(float); extern long long int llrint(double); extern long long int llrintl(long double); extern long long int llroundf(float); extern long long int llround(double); extern long long int llroundl(long double); extern float truncf(float); extern double trunc(double); extern long double truncl(long double); extern float fmodf(float, float); extern double fmod(double, double); extern long double fmodl(long double, long double); extern float remainderf(float, float); extern double remainder(double, double); extern long double remainderl(long double, long double); extern float remquof(float, float, int *); extern double remquo(double, double, int *); extern long double remquol(long double, long double, int *); extern float copysignf(float, float); extern double copysign(double, double); extern long double copysignl(long double, long double); extern float nanf(const char *); extern double nan(const char *); extern long double nanl(const char *); extern float nextafterf(float, float); extern double nextafter(double, double); extern long double nextafterl(long double, long double); extern double nexttoward(double, long double); extern float nexttowardf(float, long double); extern long double nexttowardl(long double, long double); extern float fdimf(float, float); extern double fdim(double, double); extern long double fdiml(long double, long double); extern float fmaxf(float, float); extern double fmax(double, double); extern long double fmaxl(long double, long double); extern float fminf(float, float); extern double fmin(double, double); extern long double fminl(long double, long double); extern float fmaf(float, float, float); extern double fma(double, double, double); extern long double fmal(long double, long double, long double); # 565 "/usr/include/math.h" 3 4 extern float __inff(void) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern double __inf(void) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern long double __infl(void) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern float __nan(void) __attribute__((availability(macosx,introduced=10.0))); # 597 "/usr/include/math.h" 3 4 extern float __exp10f(float) __attribute__((availability(macosx,introduced=10.9))); extern double __exp10(double) __attribute__((availability(macosx,introduced=10.9))); inline __attribute__ ((__always_inline__)) void __sincosf(float __x, float *__sinp, float *__cosp) __attribute__((availability(macosx,introduced=10.9))); inline __attribute__ ((__always_inline__)) void __sincos(double __x, double *__sinp, double *__cosp) __attribute__((availability(macosx,introduced=10.9))); # 614 "/usr/include/math.h" 3 4 extern float __cospif(float) __attribute__((availability(macosx,introduced=10.9))); extern double __cospi(double) __attribute__((availability(macosx,introduced=10.9))); extern float __sinpif(float) __attribute__((availability(macosx,introduced=10.9))); extern double __sinpi(double) __attribute__((availability(macosx,introduced=10.9))); extern float __tanpif(float) __attribute__((availability(macosx,introduced=10.9))); extern double __tanpi(double) __attribute__((availability(macosx,introduced=10.9))); inline __attribute__ ((__always_inline__)) void __sincospif(float __x, float *__sinp, float *__cosp) __attribute__((availability(macosx,introduced=10.9))); inline __attribute__ ((__always_inline__)) void __sincospi(double __x, double *__sinp, double *__cosp) __attribute__((availability(macosx,introduced=10.9))); struct __float2 { float __sinval; float __cosval; }; struct __double2 { double __sinval; double __cosval; }; extern struct __float2 __sincosf_stret(float); extern struct __double2 __sincos_stret(double); extern struct __float2 __sincospif_stret(float); extern struct __double2 __sincospi_stret(double); inline __attribute__ ((__always_inline__)) void __sincosf(float __x, float *__sinp, float *__cosp) { const struct __float2 __stret = __sincosf_stret(__x); *__sinp = __stret.__sinval; *__cosp = __stret.__cosval; } inline __attribute__ ((__always_inline__)) void __sincos(double __x, double *__sinp, double *__cosp) { const struct __double2 __stret = __sincos_stret(__x); *__sinp = __stret.__sinval; *__cosp = __stret.__cosval; } inline __attribute__ ((__always_inline__)) void __sincospif(float __x, float *__sinp, float *__cosp) { const struct __float2 __stret = __sincospif_stret(__x); *__sinp = __stret.__sinval; *__cosp = __stret.__cosval; } inline __attribute__ ((__always_inline__)) void __sincospi(double __x, double *__sinp, double *__cosp) { const struct __double2 __stret = __sincospi_stret(__x); *__sinp = __stret.__sinval; *__cosp = __stret.__cosval; } extern double j0(double) __attribute__((availability(macosx,introduced=10.0))); extern double j1(double) __attribute__((availability(macosx,introduced=10.0))); extern double jn(int, double) __attribute__((availability(macosx,introduced=10.0))); extern double y0(double) __attribute__((availability(macosx,introduced=10.0))); extern double y1(double) __attribute__((availability(macosx,introduced=10.0))); extern double yn(int, double) __attribute__((availability(macosx,introduced=10.0))); extern double scalb(double, double); extern int signgam; # 712 "/usr/include/math.h" 3 4 extern long int rinttol(double) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern long int roundtol(double) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern double drem(double, double) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern int finite(double) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern double gamma(double) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); extern double significand(double) __attribute__((availability(macosx,introduced=10.0,deprecated=10.9))); # 737 "/usr/include/math.h" 3 4 } # 8035 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" 2 # 1 "/usr/include/c++/4.2.1/cmath" 1 3 # 49 "/usr/include/c++/4.2.1/cmath" 3 # 1 "/usr/include/c++/4.2.1/bits/cpp_type_traits.h" 1 3 # 42 "/usr/include/c++/4.2.1/bits/cpp_type_traits.h" 3 # 74 "/usr/include/c++/4.2.1/bits/cpp_type_traits.h" 3 namespace __gnu_cxx { template class __normal_iterator; } namespace std { namespace __detail { typedef char __one; typedef char __two[2]; template __one __test_type(int _Tp::*); template __two& __test_type(...); } struct __true_type { }; struct __false_type { }; template struct __truth_type { typedef __false_type __type; }; template<> struct __truth_type { typedef __true_type __type; }; template struct __traitor { enum { __value = bool(_Sp::__value) || bool(_Tp::__value) }; typedef typename __truth_type<__value>::__type __type; }; template struct __are_same { enum { __value = 0 }; typedef __false_type __type; }; template struct __are_same<_Tp, _Tp> { enum { __value = 1 }; typedef __true_type __type; }; template struct __is_void { enum { __value = 0 }; typedef __false_type __type; }; template<> struct __is_void { enum { __value = 1 }; typedef __true_type __type; }; template struct __is_integer { enum { __value = 0 }; typedef __false_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_integer { enum { __value = 1 }; typedef __true_type __type; }; template struct __is_floating { enum { __value = 0 }; typedef __false_type __type; }; template<> struct __is_floating { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_floating { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_floating { enum { __value = 1 }; typedef __true_type __type; }; template struct __is_pointer { enum { __value = 0 }; typedef __false_type __type; }; template struct __is_pointer<_Tp*> { enum { __value = 1 }; typedef __true_type __type; }; template struct __is_normal_iterator { enum { __value = 0 }; typedef __false_type __type; }; template struct __is_normal_iterator< __gnu_cxx::__normal_iterator<_Iterator, _Container> > { enum { __value = 1 }; typedef __true_type __type; }; template struct __is_arithmetic : public __traitor<__is_integer<_Tp>, __is_floating<_Tp> > { }; template struct __is_fundamental : public __traitor<__is_void<_Tp>, __is_arithmetic<_Tp> > { }; template struct __is_scalar : public __traitor<__is_arithmetic<_Tp>, __is_pointer<_Tp> > { }; # 380 "/usr/include/c++/4.2.1/bits/cpp_type_traits.h" 3 template struct __is_pod { enum { __value = (sizeof(__detail::__test_type<_Tp>(0)) != sizeof(__detail::__one)) }; }; template struct __is_empty { private: template struct __first { }; template struct __second : public _Up { }; public: enum { __value = sizeof(__first<_Tp>) == sizeof(__second<_Tp>) }; }; template struct __is_char { enum { __value = 0 }; typedef __false_type __type; }; template<> struct __is_char { enum { __value = 1 }; typedef __true_type __type; }; template<> struct __is_char { enum { __value = 1 }; typedef __true_type __type; }; } # 52 "/usr/include/c++/4.2.1/cmath" 2 3 # 1 "/usr/include/c++/4.2.1/ext/type_traits.h" 1 3 # 39 "/usr/include/c++/4.2.1/ext/type_traits.h" 3 # 1 "/usr/include/c++/4.2.1/utility" 1 3 # 64 "/usr/include/c++/4.2.1/utility" 3 # 1 "/usr/include/c++/4.2.1/bits/stl_relops.h" 1 3 # 74 "/usr/include/c++/4.2.1/bits/stl_relops.h" 3 namespace std { namespace rel_ops { # 90 "/usr/include/c++/4.2.1/bits/stl_relops.h" 3 template inline bool operator!=(const _Tp& __x, const _Tp& __y) { return !(__x == __y); } # 103 "/usr/include/c++/4.2.1/bits/stl_relops.h" 3 template inline bool operator>(const _Tp& __x, const _Tp& __y) { return __y < __x; } # 116 "/usr/include/c++/4.2.1/bits/stl_relops.h" 3 template inline bool operator<=(const _Tp& __x, const _Tp& __y) { return !(__y < __x); } # 129 "/usr/include/c++/4.2.1/bits/stl_relops.h" 3 template inline bool operator>=(const _Tp& __x, const _Tp& __y) { return !(__x < __y); } } } # 67 "/usr/include/c++/4.2.1/utility" 2 3 # 1 "/usr/include/c++/4.2.1/bits/stl_pair.h" 1 3 # 64 "/usr/include/c++/4.2.1/bits/stl_pair.h" 3 namespace std { template struct pair { typedef _T1 first_type; typedef _T2 second_type; _T1 first; _T2 second; pair() : first(), second() { } pair(const _T1& __a, const _T2& __b) : first(__a), second(__b) { } template pair(const pair<_U1, _U2>& __p) : first(__p.first), second(__p.second) { } }; template inline bool operator==(const pair<_T1, _T2>& __x, const pair<_T1, _T2>& __y) { return __x.first == __y.first && __x.second == __y.second; } template inline bool operator<(const pair<_T1, _T2>& __x, const pair<_T1, _T2>& __y) { return __x.first < __y.first || (!(__y.first < __x.first) && __x.second < __y.second); } template inline bool operator!=(const pair<_T1, _T2>& __x, const pair<_T1, _T2>& __y) { return !(__x == __y); } template inline bool operator>(const pair<_T1, _T2>& __x, const pair<_T1, _T2>& __y) { return __y < __x; } template inline bool operator<=(const pair<_T1, _T2>& __x, const pair<_T1, _T2>& __y) { return !(__y < __x); } template inline bool operator>=(const pair<_T1, _T2>& __x, const pair<_T1, _T2>& __y) { return !(__x < __y); } # 142 "/usr/include/c++/4.2.1/bits/stl_pair.h" 3 template inline pair<_T1, _T2> make_pair(_T1 __x, _T2 __y) { return pair<_T1, _T2>(__x, __y); } } # 68 "/usr/include/c++/4.2.1/utility" 2 3 # 42 "/usr/include/c++/4.2.1/ext/type_traits.h" 2 3 namespace __gnu_cxx { template struct __enable_if { }; template struct __enable_if { typedef _Tp __type; }; template struct __conditional_type { typedef _Iftrue __type; }; template struct __conditional_type { typedef _Iffalse __type; }; template struct __add_unsigned { private: typedef __enable_if::__value, _Tp> __if_type; public: typedef typename __if_type::__type __type; }; template<> struct __add_unsigned { typedef unsigned char __type; }; template<> struct __add_unsigned { typedef unsigned char __type; }; template<> struct __add_unsigned { typedef unsigned short __type; }; template<> struct __add_unsigned { typedef unsigned int __type; }; template<> struct __add_unsigned { typedef unsigned long __type; }; template<> struct __add_unsigned { typedef unsigned long long __type; }; template<> struct __add_unsigned; template<> struct __add_unsigned; template struct __remove_unsigned { private: typedef __enable_if::__value, _Tp> __if_type; public: typedef typename __if_type::__type __type; }; template<> struct __remove_unsigned { typedef signed char __type; }; template<> struct __remove_unsigned { typedef signed char __type; }; template<> struct __remove_unsigned { typedef short __type; }; template<> struct __remove_unsigned { typedef int __type; }; template<> struct __remove_unsigned { typedef long __type; }; template<> struct __remove_unsigned { typedef long long __type; }; template<> struct __remove_unsigned; template<> struct __remove_unsigned; } # 53 "/usr/include/c++/4.2.1/cmath" 2 3 # 82 "/usr/include/c++/4.2.1/cmath" 3 namespace std { template _Tp __cmath_power(_Tp, unsigned int); inline double abs(double __x) { return __builtin_fabs(__x); } inline float abs(float __x) { return __builtin_fabsf(__x); } inline long double abs(long double __x) { return __builtin_fabsl(__x); } using ::acos; inline float acos(float __x) { return __builtin_acosf(__x); } inline long double acos(long double __x) { return __builtin_acosl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type acos(_Tp __x) { return __builtin_acos(__x); } using ::asin; inline float asin(float __x) { return __builtin_asinf(__x); } inline long double asin(long double __x) { return __builtin_asinl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type asin(_Tp __x) { return __builtin_asin(__x); } using ::atan; inline float atan(float __x) { return __builtin_atanf(__x); } inline long double atan(long double __x) { return __builtin_atanl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type atan(_Tp __x) { return __builtin_atan(__x); } using ::atan2; inline float atan2(float __y, float __x) { return __builtin_atan2f(__y, __x); } inline long double atan2(long double __y, long double __x) { return __builtin_atan2l(__y, __x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value && __is_integer<_Up>::__value, double>::__type atan2(_Tp __y, _Up __x) { return __builtin_atan2(__y, __x); } using ::ceil; inline float ceil(float __x) { return __builtin_ceilf(__x); } inline long double ceil(long double __x) { return __builtin_ceill(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type ceil(_Tp __x) { return __builtin_ceil(__x); } using ::cos; inline float cos(float __x) { return __builtin_cosf(__x); } inline long double cos(long double __x) { return __builtin_cosl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type cos(_Tp __x) { return __builtin_cos(__x); } using ::cosh; inline float cosh(float __x) { return __builtin_coshf(__x); } inline long double cosh(long double __x) { return __builtin_coshl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type cosh(_Tp __x) { return __builtin_cosh(__x); } using ::exp; inline float exp(float __x) { return __builtin_expf(__x); } inline long double exp(long double __x) { return __builtin_expl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type exp(_Tp __x) { return __builtin_exp(__x); } using ::fabs; inline float fabs(float __x) { return __builtin_fabsf(__x); } inline long double fabs(long double __x) { return __builtin_fabsl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type fabs(_Tp __x) { return __builtin_fabs(__x); } using ::floor; inline float floor(float __x) { return __builtin_floorf(__x); } inline long double floor(long double __x) { return __builtin_floorl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type floor(_Tp __x) { return __builtin_floor(__x); } using ::fmod; inline float fmod(float __x, float __y) { return __builtin_fmodf(__x, __y); } inline long double fmod(long double __x, long double __y) { return __builtin_fmodl(__x, __y); } using ::frexp; inline float frexp(float __x, int* __exp) { return __builtin_frexpf(__x, __exp); } inline long double frexp(long double __x, int* __exp) { return __builtin_frexpl(__x, __exp); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type frexp(_Tp __x, int* __exp) { return __builtin_frexp(__x, __exp); } using ::ldexp; inline float ldexp(float __x, int __exp) { return __builtin_ldexpf(__x, __exp); } inline long double ldexp(long double __x, int __exp) { return __builtin_ldexpl(__x, __exp); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type ldexp(_Tp __x, int __exp) { return __builtin_ldexp(__x, __exp); } using ::log; inline float log(float __x) { return __builtin_logf(__x); } inline long double log(long double __x) { return __builtin_logl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type log(_Tp __x) { return __builtin_log(__x); } using ::log10; inline float log10(float __x) { return __builtin_log10f(__x); } inline long double log10(long double __x) { return __builtin_log10l(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type log10(_Tp __x) { return __builtin_log10(__x); } using ::modf; inline float modf(float __x, float* __iptr) { return __builtin_modff(__x, __iptr); } inline long double modf(long double __x, long double* __iptr) { return __builtin_modfl(__x, __iptr); } template inline _Tp __pow_helper(_Tp __x, int __n) { return __n < 0 ? _Tp(1)/__cmath_power(__x, -__n) : __cmath_power(__x, __n); } using ::pow; inline float pow(float __x, float __y) { return __builtin_powf(__x, __y); } inline long double pow(long double __x, long double __y) { return __builtin_powl(__x, __y); } inline double pow(double __x, int __i) { return __builtin_powi(__x, __i); } inline float pow(float __x, int __n) { return __builtin_powif(__x, __n); } inline long double pow(long double __x, int __n) { return __builtin_powil(__x, __n); } using ::sin; inline float sin(float __x) { return __builtin_sinf(__x); } inline long double sin(long double __x) { return __builtin_sinl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type sin(_Tp __x) { return __builtin_sin(__x); } using ::sinh; inline float sinh(float __x) { return __builtin_sinhf(__x); } inline long double sinh(long double __x) { return __builtin_sinhl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type sinh(_Tp __x) { return __builtin_sinh(__x); } using ::sqrt; inline float sqrt(float __x) { return __builtin_sqrtf(__x); } inline long double sqrt(long double __x) { return __builtin_sqrtl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type sqrt(_Tp __x) { return __builtin_sqrt(__x); } using ::tan; inline float tan(float __x) { return __builtin_tanf(__x); } inline long double tan(long double __x) { return __builtin_tanl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type tan(_Tp __x) { return __builtin_tan(__x); } using ::tanh; inline float tanh(float __x) { return __builtin_tanhf(__x); } inline long double tanh(long double __x) { return __builtin_tanhl(__x); } template inline typename __gnu_cxx::__enable_if<__is_integer<_Tp>::__value, double>::__type tanh(_Tp __x) { return __builtin_tanh(__x); } } namespace __gnu_cxx { template inline int __capture_fpclassify(_Tp __f) { return ( sizeof(__f) == sizeof(float) ? __fpclassifyf((float)(__f)) : sizeof(__f) == sizeof(double) ? __fpclassifyd((double)(__f)) : __fpclassifyl((long double)(__f))); } template inline int __capture_isfinite(_Tp __f) { return ( sizeof(__f) == sizeof(float) ? __inline_isfinitef((float)(__f)) : sizeof(__f) == sizeof(double) ? __inline_isfinited((double)(__f)) : __inline_isfinitel((long double)(__f))); } template inline int __capture_isinf(_Tp __f) { return ( sizeof(__f) == sizeof(float) ? __inline_isinff((float)(__f)) : sizeof(__f) == sizeof(double) ? __inline_isinfd((double)(__f)) : __inline_isinfl((long double)(__f))); } template inline int __capture_isnan(_Tp __f) { return ( sizeof(__f) == sizeof(float) ? __inline_isnanf((float)(__f)) : sizeof(__f) == sizeof(double) ? __inline_isnand((double)(__f)) : __inline_isnanl((long double)(__f))); } template inline int __capture_isnormal(_Tp __f) { return ( sizeof(__f) == sizeof(float) ? __inline_isnormalf((float)(__f)) : sizeof(__f) == sizeof(double) ? __inline_isnormald((double)(__f)) : __inline_isnormall((long double)(__f))); } template inline int __capture_signbit(_Tp __f) { return ( sizeof(__f) == sizeof(float) ? __inline_signbitf((float)(__f)) : sizeof(__f) == sizeof(double) ? __inline_signbitd((double)(__f)) : __inline_signbitl((long double)(__f))); } template inline int __capture_isgreater(_Tp __f1, _Tp __f2) { return __builtin_isgreater((__f1),(__f2)); } template inline int __capture_isgreaterequal(_Tp __f1, _Tp __f2) { return __builtin_isgreaterequal((__f1),(__f2)); } template inline int __capture_isless(_Tp __f1, _Tp __f2) { return __builtin_isless((__f1),(__f2)); } template inline int __capture_islessequal(_Tp __f1, _Tp __f2) { return __builtin_islessequal((__f1),(__f2)); } template inline int __capture_islessgreater(_Tp __f1, _Tp __f2) { return __builtin_islessgreater((__f1),(__f2)); } template inline int __capture_isunordered(_Tp __f1, _Tp __f2) { return __builtin_isunordered((__f1),(__f2)); } } # 535 "/usr/include/c++/4.2.1/cmath" 3 namespace std { template inline int fpclassify(_Tp __f) { return ::__gnu_cxx::__capture_fpclassify(__f); } template inline int isfinite(_Tp __f) { return ::__gnu_cxx::__capture_isfinite(__f); } template inline int isinf(_Tp __f) { return ::__gnu_cxx::__capture_isinf(__f); } template inline int isnan(_Tp __f) { return ::__gnu_cxx::__capture_isnan(__f); } template inline int isnormal(_Tp __f) { return ::__gnu_cxx::__capture_isnormal(__f); } template inline int signbit(_Tp __f) { return ::__gnu_cxx::__capture_signbit(__f); } template inline int isgreater(_Tp __f1, _Tp __f2) { return ::__gnu_cxx::__capture_isgreater(__f1, __f2); } template inline int isgreaterequal(_Tp __f1, _Tp __f2) { return ::__gnu_cxx::__capture_isgreaterequal(__f1, __f2); } template inline int isless(_Tp __f1, _Tp __f2) { return ::__gnu_cxx::__capture_isless(__f1, __f2); } template inline int islessequal(_Tp __f1, _Tp __f2) { return ::__gnu_cxx::__capture_islessequal(__f1, __f2); } template inline int islessgreater(_Tp __f1, _Tp __f2) { return ::__gnu_cxx::__capture_islessgreater(__f1, __f2); } template inline int isunordered(_Tp __f1, _Tp __f2) { return ::__gnu_cxx::__capture_isunordered(__f1, __f2); } } # 1 "/usr/include/c++/4.2.1/bits/cmath.tcc" 1 3 # 39 "/usr/include/c++/4.2.1/bits/cmath.tcc" 3 namespace std { template inline _Tp __cmath_power(_Tp __x, unsigned int __n) { _Tp __y = __n % 2 ? __x : 1; while (__n >>= 1) { __x = __x * __x; if (__n % 2) __y = __y * __x; } return __y; } } # 598 "/usr/include/c++/4.2.1/cmath" 2 3 # 8039 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" 2 # 1 "/usr/include/c++/4.2.1/cstdlib" 1 3 # 49 "/usr/include/c++/4.2.1/cstdlib" 3 # 104 "/usr/include/c++/4.2.1/cstdlib" 3 namespace std { using ::div_t; using ::ldiv_t; using ::abort; using ::abs; using ::atexit; using ::atof; using ::atoi; using ::atol; using ::bsearch; using ::calloc; using ::div; using ::exit; using ::free; using ::getenv; using ::labs; using ::ldiv; using ::malloc; using ::mblen; using ::mbstowcs; using ::mbtowc; using ::qsort; using ::rand; using ::realloc; using ::srand; using ::strtod; using ::strtol; using ::strtoul; using ::system; using ::wcstombs; using ::wctomb; inline long abs(long __i) { return labs(__i); } inline ldiv_t div(long __i, long __j) { return ldiv(__i, __j); } } # 161 "/usr/include/c++/4.2.1/cstdlib" 3 namespace __gnu_cxx { using ::lldiv_t; using ::_Exit; inline long long abs(long long __x) { return __x >= 0 ? __x : -__x; } using ::llabs; inline lldiv_t div(long long __n, long long __d) { lldiv_t __q; __q.quot = __n / __d; __q.rem = __n % __d; return __q; } using ::lldiv; # 194 "/usr/include/c++/4.2.1/cstdlib" 3 using ::atoll; using ::strtoll; using ::strtoull; using ::strtof; using ::strtold; } namespace std { using ::__gnu_cxx::lldiv_t; using ::__gnu_cxx::_Exit; using ::__gnu_cxx::abs; using ::__gnu_cxx::llabs; using ::__gnu_cxx::div; using ::__gnu_cxx::lldiv; using ::__gnu_cxx::atoll; using ::__gnu_cxx::strtof; using ::__gnu_cxx::strtoll; using ::__gnu_cxx::strtoull; using ::__gnu_cxx::strtold; } # 8040 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" 2 # 8056 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int signbit(float x) { return __signbitf(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int signbit(double x) { return __signbitd(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int signbit(long double x) { return __signbitl(x);} __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isfinite(float x) { return __isfinitef(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isfinite(double x) { return __isfinited(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isfinite(long double x) { return __isfinite(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isnan(float x) { return __isnanf(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isnan(double x) throw() { return __isnand(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isnan(long double x) { return __isnan(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isinf(float x) { return __isinff(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isinf(double x) throw() { return __isinfd(x); } __inline__ __attribute__((always_inline)) __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) int isinf(long double x) { return __isinf(x); } # 8116 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" namespace __gnu_cxx { extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) long long int abs(long long int a); } namespace std { template extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) T __pow_helper(T, int); template extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) T __cmath_power(T, unsigned int); } using std::abs; using std::fabs; using std::ceil; using std::floor; using std::sqrt; using std::pow; using std::log; using std::log10; using std::fmod; using std::modf; using std::exp; using std::frexp; using std::ldexp; using std::asin; using std::sin; using std::sinh; using std::acos; using std::cos; using std::cosh; using std::atan; using std::atan2; using std::tan; using std::tanh; # 8606 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" namespace std { # 8618 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) long int abs(long int); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float abs(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) double abs(double); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float fabs(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float ceil(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float floor(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float sqrt(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float pow(float, float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float pow(float, int); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) double pow(double, int); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float log(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float log10(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float fmod(float, float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float modf(float, float*); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float exp(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float frexp(float, int*); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float ldexp(float, int); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float asin(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float sin(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float sinh(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float acos(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float cos(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float cosh(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float atan(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float atan2(float, float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float tan(float); extern __attribute__((host)) __attribute__((device)) __attribute__((cudart_builtin)) float tanh(float); # 8676 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" } static __inline__ __attribute__((host)) __attribute__((device)) float logb(float a) { return logbf(a); } static __inline__ __attribute__((host)) __attribute__((device)) int ilogb(float a) { return ilogbf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float scalbn(float a, int b) { return scalbnf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float scalbln(float a, long int b) { return scalblnf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float exp2(float a) { return exp2f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float expm1(float a) { return expm1f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float log2(float a) { return log2f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float log1p(float a) { return log1pf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float acosh(float a) { return acoshf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float asinh(float a) { return asinhf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float atanh(float a) { return atanhf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float hypot(float a, float b) { return hypotf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float cbrt(float a) { return cbrtf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float erf(float a) { return erff(a); } static __inline__ __attribute__((host)) __attribute__((device)) float erfc(float a) { return erfcf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float lgamma(float a) { return lgammaf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float tgamma(float a) { return tgammaf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float copysign(float a, float b) { return copysignf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float nextafter(float a, float b) { return nextafterf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float remainder(float a, float b) { return remainderf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float remquo(float a, float b, int *quo) { return remquof(a, b, quo); } static __inline__ __attribute__((host)) __attribute__((device)) float round(float a) { return roundf(a); } static __inline__ __attribute__((host)) __attribute__((device)) long int lround(float a) { return lroundf(a); } static __inline__ __attribute__((host)) __attribute__((device)) long long int llround(float a) { return llroundf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float trunc(float a) { return truncf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float rint(float a) { return rintf(a); } static __inline__ __attribute__((host)) __attribute__((device)) long int lrint(float a) { return lrintf(a); } static __inline__ __attribute__((host)) __attribute__((device)) long long int llrint(float a) { return llrintf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float nearbyint(float a) { return nearbyintf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float fdim(float a, float b) { return fdimf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float fma(float a, float b, float c) { return fmaf(a, b, c); } static __inline__ __attribute__((host)) __attribute__((device)) float fmax(float a, float b) { return fmaxf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) float fmin(float a, float b) { return fminf(a, b); } # 8880 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" static __inline__ __attribute__((host)) __attribute__((device)) float exp10(float a) { return exp10f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float rsqrt(float a) { return rsqrtf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float rcbrt(float a) { return rcbrtf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float sinpi(float a) { return sinpif(a); } static __inline__ __attribute__((host)) __attribute__((device)) float cospi(float a) { return cospif(a); } static __inline__ __attribute__((host)) __attribute__((device)) void sincospi(float a, float *sptr, float *cptr) { sincospif(a, sptr, cptr); } static __inline__ __attribute__((host)) __attribute__((device)) void sincos(float a, float *sptr, float *cptr) { sincosf(a, sptr, cptr); } static __inline__ __attribute__((host)) __attribute__((device)) float j0(float a) { return j0f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float j1(float a) { return j1f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float jn(int n, float a) { return jnf(n, a); } static __inline__ __attribute__((host)) __attribute__((device)) float y0(float a) { return y0f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float y1(float a) { return y1f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float yn(int n, float a) { return ynf(n, a); } static __inline__ __attribute__((host)) __attribute__((device)) float cyl_bessel_i0(float a) { return cyl_bessel_i0f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float cyl_bessel_i1(float a) { return cyl_bessel_i1f(a); } static __inline__ __attribute__((host)) __attribute__((device)) float erfinv(float a) { return erfinvf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float erfcinv(float a) { return erfcinvf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float normcdfinv(float a) { return normcdfinvf(a); } static __inline__ __attribute__((host)) __attribute__((device)) float normcdf(float a) { return normcdff(a); } static __inline__ __attribute__((host)) __attribute__((device)) float erfcx(float a) { return erfcxf(a); } static __inline__ __attribute__((host)) __attribute__((device)) double copysign(double a, float b) { return copysign(a, (double)b); } static __inline__ __attribute__((host)) __attribute__((device)) float copysign(float a, double b) { return copysignf(a, (float)b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned int min(unsigned int a, unsigned int b) { return umin(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned int min(int a, unsigned int b) { return umin((unsigned int)a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned int min(unsigned int a, int b) { return umin(a, (unsigned int)b); } static __inline__ __attribute__((host)) __attribute__((device)) long long int min(long long int a, long long int b) { return llmin(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned long long int min(unsigned long long int a, unsigned long long int b) { return ullmin(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned long long int min(long long int a, unsigned long long int b) { return ullmin((unsigned long long int)a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned long long int min(unsigned long long int a, long long int b) { return ullmin(a, (unsigned long long int)b); } static __inline__ __attribute__((host)) __attribute__((device)) float min(float a, float b) { return fminf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) double min(double a, double b) { return fmin(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) double min(float a, double b) { return fmin((double)a, b); } static __inline__ __attribute__((host)) __attribute__((device)) double min(double a, float b) { return fmin(a, (double)b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned int max(unsigned int a, unsigned int b) { return umax(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned int max(int a, unsigned int b) { return umax((unsigned int)a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned int max(unsigned int a, int b) { return umax(a, (unsigned int)b); } static __inline__ __attribute__((host)) __attribute__((device)) long long int max(long long int a, long long int b) { return llmax(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned long long int max(unsigned long long int a, unsigned long long int b) { return ullmax(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned long long int max(long long int a, unsigned long long int b) { return ullmax((unsigned long long int)a, b); } static __inline__ __attribute__((host)) __attribute__((device)) unsigned long long int max(unsigned long long int a, long long int b) { return ullmax(a, (unsigned long long int)b); } static __inline__ __attribute__((host)) __attribute__((device)) float max(float a, float b) { return fmaxf(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) double max(double a, double b) { return fmax(a, b); } static __inline__ __attribute__((host)) __attribute__((device)) double max(float a, double b) { return fmax((double)a, b); } static __inline__ __attribute__((host)) __attribute__((device)) double max(double a, float b) { return fmax(a, (double)b); } # 14768 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions_dbl_ptx3.h" 1 # 14769 "/Developer/NVIDIA/CUDA-6.5/bin/../include/math_functions.h" 2 # 170 "/Developer/NVIDIA/CUDA-6.5/bin/../include/common_functions.h" 2 # 77 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_surface_types.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_surface_types.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_surface_types.h" 2 # 73 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_surface_types.h" template struct __attribute__((device_builtin_surface_type)) surface : public surfaceReference { __attribute__((host)) surface(void) { channelDesc = cudaCreateChannelDesc(); } __attribute__((host)) surface(struct cudaChannelFormatDesc desc) { channelDesc = desc; } }; template struct __attribute__((device_builtin_surface_type)) surface : public surfaceReference { __attribute__((host)) surface(void) { channelDesc = cudaCreateChannelDesc(); } }; # 78 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_texture_types.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_texture_types.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_texture_types.h" 2 # 73 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_texture_types.h" template struct __attribute__((device_builtin_texture_type)) texture : public textureReference { __attribute__((host)) texture(int norm = 0, enum cudaTextureFilterMode fMode = cudaFilterModePoint, enum cudaTextureAddressMode aMode = cudaAddressModeClamp) { normalized = norm; filterMode = fMode; addressMode[0] = aMode; addressMode[1] = aMode; addressMode[2] = aMode; channelDesc = cudaCreateChannelDesc(); sRGB = 0; } __attribute__((host)) texture(int norm, enum cudaTextureFilterMode fMode, enum cudaTextureAddressMode aMode, struct cudaChannelFormatDesc desc) { normalized = norm; filterMode = fMode; addressMode[0] = aMode; addressMode[1] = aMode; addressMode[2] = aMode; channelDesc = desc; sRGB = 0; } }; # 79 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 71 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern "C" { # 82 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __mulhi(int x, int y); # 92 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __umulhi(unsigned int x, unsigned int y); # 102 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __mul64hi(long long int x, long long int y); # 112 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __umul64hi(unsigned long long int x, unsigned long long int y); # 121 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __int_as_float(int x); # 130 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __float_as_int(float x); extern __attribute__((device)) __attribute__((device_builtin)) void __syncthreads(void); extern __attribute__((device)) __attribute__((device_builtin)) void __prof_trigger(int); extern __attribute__((device)) __attribute__((device_builtin)) void __threadfence(void); extern __attribute__((device)) __attribute__((device_builtin)) void __threadfence_block(void); extern __attribute__((device)) __attribute__((device_builtin)) void __trap(void); extern __attribute__((device)) __attribute__((device_builtin)) void __brkpt(int c = 0); # 159 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __saturatef(float x); # 228 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __sad(int x, int y, unsigned int z); # 296 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __usad(unsigned int x, unsigned int y, unsigned int z); # 306 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __mul24(int x, int y); # 316 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __umul24(unsigned int x, unsigned int y); # 329 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float fdividef(float x, float y); # 404 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fdividef(float x, float y); extern __attribute__((device)) __attribute__((device_builtin)) double fdivide(double x, double y); # 417 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __sinf(float x) ; # 429 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __cosf(float x) ; # 443 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __tanf(float x) ; # 458 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) void __sincosf(float x, float *sptr, float *cptr) ; # 508 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __expf(float x) ; # 540 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __exp10f(float x) ; # 566 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __log2f(float x) ; # 594 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __log10f(float x) ; # 638 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __logf(float x) ; # 681 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) __attribute__((cudart_builtin)) float __powf(float x, float y) ; # 690 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __float2int_rn(float x); # 699 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __float2int_rz(float x); # 708 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __float2int_ru(float); # 717 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __float2int_rd(float x); # 726 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __float2uint_rn(float x); # 735 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __float2uint_rz(float x); # 744 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __float2uint_ru(float x); # 753 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __float2uint_rd(float x); # 762 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __int2float_rn(int x); # 771 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __int2float_rz(int x); # 780 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __int2float_ru(int x); # 789 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __int2float_rd(int x); # 798 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __uint2float_rn(unsigned int x); # 807 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __uint2float_rz(unsigned int x); # 816 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __uint2float_ru(unsigned int x); # 825 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __uint2float_rd(unsigned int x); # 834 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __float2ll_rn(float x); # 843 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __float2ll_rz(float x); # 852 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __float2ll_ru(float x); # 861 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __float2ll_rd(float x); # 870 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __float2ull_rn(float x); # 879 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __float2ull_rz(float x); # 888 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __float2ull_ru(float x); # 897 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __float2ull_rd(float x); # 906 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ll2float_rn(long long int x); # 915 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ll2float_rz(long long int x); # 924 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ll2float_ru(long long int x); # 933 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ll2float_rd(long long int x); # 942 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ull2float_rn(unsigned long long int x); # 951 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ull2float_rz(unsigned long long int x); # 960 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ull2float_ru(unsigned long long int x); # 969 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __ull2float_rd(unsigned long long int x); # 978 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned short __float2half_rn(float x); # 987 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __half2float(unsigned short x); # 999 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fadd_rn(float x, float y); # 1011 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fadd_rz(float x, float y); # 1023 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fadd_ru(float x, float y); # 1035 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fadd_rd(float x, float y); # 1047 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsub_rn(float x, float y); # 1059 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsub_rz(float x, float y); # 1071 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsub_ru(float x, float y); # 1083 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsub_rd(float x, float y); # 1095 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmul_rn(float x, float y); # 1107 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmul_rz(float x, float y); # 1119 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmul_ru(float x, float y); # 1131 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmul_rd(float x, float y); # 1284 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_rn(float x, float y, float z); # 1437 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_rz(float x, float y, float z); # 1590 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_ru(float x, float y, float z); # 1743 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_rd(float x, float y, float z); # 1776 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __frcp_rn(float x); # 1809 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __frcp_rz(float x); # 1842 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __frcp_ru(float x); # 1875 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __frcp_rd(float x); # 1906 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsqrt_rn(float x); # 1937 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsqrt_rz(float x); # 1968 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsqrt_ru(float x); # 1999 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fsqrt_rd(float x); # 2038 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __frsqrt_rn(float x); # 2049 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fdiv_rn(float x, float y); # 2060 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fdiv_rz(float x, float y); # 2071 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fdiv_ru(float x, float y); # 2082 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __fdiv_rd(float x, float y); # 2091 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __clz(int x); # 2102 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __ffs(int x); # 2111 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __popc(unsigned int x); # 2120 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __brev(unsigned int x); # 2129 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __clzll(long long int x); # 2140 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __ffsll(long long int x); # 2151 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __popcll(unsigned long long int x); # 2160 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __brevll(unsigned long long int x); # 2184 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __byte_perm(unsigned int x, unsigned int y, unsigned int s); # 2196 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __hadd(int, int); # 2209 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __rhadd(int, int); # 2221 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uhadd(unsigned int, unsigned int); # 2234 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __urhadd(unsigned int, unsigned int); # 2245 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __double2int_rz(double); # 2254 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __double2uint_rz(double); # 2263 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __double2ll_rz(double); # 2272 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __double2ull_rz(double); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __pm0(void); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __pm1(void); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __pm2(void); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __pm3(void); # 2294 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabs2(unsigned int a); # 2305 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabsss2(unsigned int a); # 2316 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vadd2(unsigned int a, unsigned int b); # 2327 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vaddss2 (unsigned int a, unsigned int b); # 2337 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vaddus2 (unsigned int a, unsigned int b); # 2348 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vavgs2(unsigned int a, unsigned int b); # 2359 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vavgu2(unsigned int a, unsigned int b); # 2370 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vhaddu2(unsigned int a, unsigned int b); # 2381 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpeq2(unsigned int a, unsigned int b); # 2392 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpges2(unsigned int a, unsigned int b); # 2403 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpgeu2(unsigned int a, unsigned int b); # 2414 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpgts2(unsigned int a, unsigned int b); # 2425 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpgtu2(unsigned int a, unsigned int b); # 2436 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmples2(unsigned int a, unsigned int b); # 2448 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpleu2(unsigned int a, unsigned int b); # 2459 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmplts2(unsigned int a, unsigned int b); # 2470 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpltu2(unsigned int a, unsigned int b); # 2481 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpne2(unsigned int a, unsigned int b); # 2492 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabsdiffu2(unsigned int a, unsigned int b); # 2503 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vmaxs2(unsigned int a, unsigned int b); # 2514 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vmaxu2(unsigned int a, unsigned int b); # 2525 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vmins2(unsigned int a, unsigned int b); # 2536 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vminu2(unsigned int a, unsigned int b); # 2547 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vseteq2(unsigned int a, unsigned int b); # 2558 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetges2(unsigned int a, unsigned int b); # 2569 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetgeu2(unsigned int a, unsigned int b); # 2580 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetgts2(unsigned int a, unsigned int b); # 2591 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetgtu2(unsigned int a, unsigned int b); # 2602 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetles2(unsigned int a, unsigned int b); # 2613 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetleu2(unsigned int a, unsigned int b); # 2624 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetlts2(unsigned int a, unsigned int b); # 2635 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetltu2(unsigned int a, unsigned int b); # 2646 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetne2(unsigned int a, unsigned int b); # 2657 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsadu2(unsigned int a, unsigned int b); # 2668 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsub2(unsigned int a, unsigned int b); # 2679 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsubss2 (unsigned int a, unsigned int b); # 2690 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsubus2 (unsigned int a, unsigned int b); # 2700 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vneg2(unsigned int a); # 2710 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vnegss2(unsigned int a); # 2721 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabsdiffs2(unsigned int a, unsigned int b); # 2732 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsads2(unsigned int a, unsigned int b); # 2742 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabs4(unsigned int a); # 2753 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabsss4(unsigned int a); # 2764 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vadd4(unsigned int a, unsigned int b); # 2775 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vaddss4 (unsigned int a, unsigned int b); # 2785 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vaddus4 (unsigned int a, unsigned int b); # 2796 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vavgs4(unsigned int a, unsigned int b); # 2807 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vavgu4(unsigned int a, unsigned int b); # 2818 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vhaddu4(unsigned int a, unsigned int b); # 2829 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpeq4(unsigned int a, unsigned int b); # 2840 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpges4(unsigned int a, unsigned int b); # 2851 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpgeu4(unsigned int a, unsigned int b); # 2862 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpgts4(unsigned int a, unsigned int b); # 2873 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpgtu4(unsigned int a, unsigned int b); # 2884 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmples4(unsigned int a, unsigned int b); # 2895 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpleu4(unsigned int a, unsigned int b); # 2906 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmplts4(unsigned int a, unsigned int b); # 2917 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpltu4(unsigned int a, unsigned int b); # 2928 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vcmpne4(unsigned int a, unsigned int b); # 2939 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabsdiffu4(unsigned int a, unsigned int b); # 2950 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vmaxs4(unsigned int a, unsigned int b); # 2961 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vmaxu4(unsigned int a, unsigned int b); # 2972 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vmins4(unsigned int a, unsigned int b); # 2983 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vminu4(unsigned int a, unsigned int b); # 2994 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vseteq4(unsigned int a, unsigned int b); # 3005 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetles4(unsigned int a, unsigned int b); # 3016 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetleu4(unsigned int a, unsigned int b); # 3027 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetlts4(unsigned int a, unsigned int b); # 3038 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetltu4(unsigned int a, unsigned int b); # 3049 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetges4(unsigned int a, unsigned int b); # 3060 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetgeu4(unsigned int a, unsigned int b); # 3071 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetgts4(unsigned int a, unsigned int b); # 3082 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetgtu4(unsigned int a, unsigned int b); # 3093 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsetne4(unsigned int a, unsigned int b); # 3104 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsadu4(unsigned int a, unsigned int b); # 3115 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsub4(unsigned int a, unsigned int b); # 3126 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsubss4(unsigned int a, unsigned int b); # 3137 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsubus4(unsigned int a, unsigned int b); # 3147 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vneg4(unsigned int a); # 3157 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vnegss4(unsigned int a); # 3168 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vabsdiffs4(unsigned int a, unsigned int b); # 3179 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __vsads4(unsigned int a, unsigned int b); } static __inline__ __attribute__((device)) int mulhi(int a, int b) { return __mulhi(a, b); } static __inline__ __attribute__((device)) unsigned int mulhi(unsigned int a, unsigned int b) { return __umulhi(a, b); } static __inline__ __attribute__((device)) unsigned int mulhi(int a, unsigned int b) { return __umulhi((unsigned int)a, b); } static __inline__ __attribute__((device)) unsigned int mulhi(unsigned int a, int b) { return __umulhi(a, (unsigned int)b); } static __inline__ __attribute__((device)) long long int mul64hi(long long int a, long long int b) { return __mul64hi(a, b); } static __inline__ __attribute__((device)) unsigned long long int mul64hi(unsigned long long int a, unsigned long long int b) { return __umul64hi(a, b); } static __inline__ __attribute__((device)) unsigned long long int mul64hi(long long int a, unsigned long long int b) { return __umul64hi((unsigned long long int)a, b); } static __inline__ __attribute__((device)) unsigned long long int mul64hi(unsigned long long int a, long long int b) { return __umul64hi(a, (unsigned long long int)b); } static __inline__ __attribute__((device)) int float_as_int(float a) { return __float_as_int(a); } static __inline__ __attribute__((device)) float int_as_float(int a) { return __int_as_float(a); } static __inline__ __attribute__((device)) float saturate(float a) { return __saturatef(a); } static __inline__ __attribute__((device)) int mul24(int a, int b) { return __mul24(a, b); } static __inline__ __attribute__((device)) unsigned int umul24(unsigned int a, unsigned int b) { return __umul24(a, b); } static __inline__ __attribute__((device)) void trap(void) { __trap(); } static __inline__ __attribute__((device)) void brkpt(int c = 0) { __brkpt(c); } static __inline__ __attribute__((device)) void syncthreads(void) { __syncthreads(); } static __inline__ __attribute__((device)) void prof_trigger(int e) { if (e == 0) __prof_trigger( 0); else if (e == 1) __prof_trigger( 1); else if (e == 2) __prof_trigger( 2); else if (e == 3) __prof_trigger( 3); else if (e == 4) __prof_trigger( 4); else if (e == 5) __prof_trigger( 5); else if (e == 6) __prof_trigger( 6); else if (e == 7) __prof_trigger( 7); else if (e == 8) __prof_trigger( 8); else if (e == 9) __prof_trigger( 9); else if (e == 10) __prof_trigger(10); else if (e == 11) __prof_trigger(11); else if (e == 12) __prof_trigger(12); else if (e == 13) __prof_trigger(13); else if (e == 14) __prof_trigger(14); else if (e == 15) __prof_trigger(15); } static __inline__ __attribute__((device)) void threadfence(bool global = true) { global ? __threadfence() : __threadfence_block(); } static __inline__ __attribute__((device)) int float2int(float a, enum cudaRoundMode mode = cudaRoundZero) { return mode == cudaRoundNearest ? __float2int_rn(a) : mode == cudaRoundPosInf ? __float2int_ru(a) : mode == cudaRoundMinInf ? __float2int_rd(a) : __float2int_rz(a); } static __inline__ __attribute__((device)) unsigned int float2uint(float a, enum cudaRoundMode mode = cudaRoundZero) { return mode == cudaRoundNearest ? __float2uint_rn(a) : mode == cudaRoundPosInf ? __float2uint_ru(a) : mode == cudaRoundMinInf ? __float2uint_rd(a) : __float2uint_rz(a); } static __inline__ __attribute__((device)) float int2float(int a, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __int2float_rz(a) : mode == cudaRoundPosInf ? __int2float_ru(a) : mode == cudaRoundMinInf ? __int2float_rd(a) : __int2float_rn(a); } static __inline__ __attribute__((device)) float uint2float(unsigned int a, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __uint2float_rz(a) : mode == cudaRoundPosInf ? __uint2float_ru(a) : mode == cudaRoundMinInf ? __uint2float_rd(a) : __uint2float_rn(a); } # 9405 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_11_atomic_functions.h" 1 # 63 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_11_atomic_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 64 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_11_atomic_functions.h" 2 extern "C" { extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicAdd(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicAdd(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicExch(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicExch(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) float __fAtomicExch(float *address, float val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicMin(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicMin(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicMax(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicMax(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicInc(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicDec(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicAnd(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicAnd(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicOr(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicOr(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicXor(int *address, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicXor(unsigned int *address, unsigned int val); extern __attribute__((device)) __attribute__((device_builtin)) int __iAtomicCAS(int *address, int compare, int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __uAtomicCAS(unsigned int *address, unsigned int compare, unsigned int val); } static __inline__ __attribute__((device)) int atomicAdd(int *address, int val) { return __iAtomicAdd(address, val); } static __inline__ __attribute__((device)) unsigned int atomicAdd(unsigned int *address, unsigned int val) { return __uAtomicAdd(address, val); } static __inline__ __attribute__((device)) int atomicSub(int *address, int val) { return __iAtomicAdd(address, (unsigned int)-(int)val); } static __inline__ __attribute__((device)) unsigned int atomicSub(unsigned int *address, unsigned int val) { return __uAtomicAdd(address, (unsigned int)-(int)val); } static __inline__ __attribute__((device)) int atomicExch(int *address, int val) { return __iAtomicExch(address, val); } static __inline__ __attribute__((device)) unsigned int atomicExch(unsigned int *address, unsigned int val) { return __uAtomicExch(address, val); } static __inline__ __attribute__((device)) float atomicExch(float *address, float val) { return __fAtomicExch(address, val); } static __inline__ __attribute__((device)) int atomicMin(int *address, int val) { return __iAtomicMin(address, val); } static __inline__ __attribute__((device)) unsigned int atomicMin(unsigned int *address, unsigned int val) { return __uAtomicMin(address, val); } static __inline__ __attribute__((device)) int atomicMax(int *address, int val) { return __iAtomicMax(address, val); } static __inline__ __attribute__((device)) unsigned int atomicMax(unsigned int *address, unsigned int val) { return __uAtomicMax(address, val); } static __inline__ __attribute__((device)) unsigned int atomicInc(unsigned int *address, unsigned int val) { return __uAtomicInc(address, val); } static __inline__ __attribute__((device)) unsigned int atomicDec(unsigned int *address, unsigned int val) { return __uAtomicDec(address, val); } static __inline__ __attribute__((device)) int atomicAnd(int *address, int val) { return __iAtomicAnd(address, val); } static __inline__ __attribute__((device)) unsigned int atomicAnd(unsigned int *address, unsigned int val) { return __uAtomicAnd(address, val); } static __inline__ __attribute__((device)) int atomicOr(int *address, int val) { return __iAtomicOr(address, val); } static __inline__ __attribute__((device)) unsigned int atomicOr(unsigned int *address, unsigned int val) { return __uAtomicOr(address, val); } static __inline__ __attribute__((device)) int atomicXor(int *address, int val) { return __iAtomicXor(address, val); } static __inline__ __attribute__((device)) unsigned int atomicXor(unsigned int *address, unsigned int val) { return __uAtomicXor(address, val); } static __inline__ __attribute__((device)) int atomicCAS(int *address, int compare, int val) { return __iAtomicCAS(address, compare, val); } static __inline__ __attribute__((device)) unsigned int atomicCAS(unsigned int *address, unsigned int compare, unsigned int val) { return __uAtomicCAS(address, compare, val); } # 9406 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_12_atomic_functions.h" 1 # 63 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_12_atomic_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 64 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_12_atomic_functions.h" 2 extern "C" { extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __ullAtomicAdd(unsigned long long int *address, unsigned long long int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __ullAtomicExch(unsigned long long int *address, unsigned long long int val); extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __ullAtomicCAS(unsigned long long int *address, unsigned long long int compare, unsigned long long int val); extern __attribute__((device)) __attribute__((device_builtin)) int __any(int cond); extern __attribute__((device)) __attribute__((device_builtin)) int __all(int cond); } static __inline__ __attribute__((device)) unsigned long long int atomicAdd(unsigned long long int *address, unsigned long long int val) { return __ullAtomicAdd(address, val); } static __inline__ __attribute__((device)) unsigned long long int atomicExch(unsigned long long int *address, unsigned long long int val) { return __ullAtomicExch(address, val); } static __inline__ __attribute__((device)) unsigned long long int atomicCAS(unsigned long long int *address, unsigned long long int compare, unsigned long long int val) { return __ullAtomicCAS(address, compare, val); } static __inline__ __attribute__((device)) bool any(bool cond) { return (bool)__any((int)cond); } static __inline__ __attribute__((device)) bool all(bool cond) { return (bool)__all((int)cond); } # 9407 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" 1 # 69 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 70 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" 2 extern "C" { # 83 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __double_as_longlong(double x); # 92 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __longlong_as_double(long long int x); # 249 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __fma_rn(double x, double y, double z); # 406 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __fma_rz(double x, double y, double z); # 563 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __fma_ru(double x, double y, double z); # 720 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __fma_rd(double x, double y, double z); # 732 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dadd_rn(double x, double y); # 744 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dadd_rz(double x, double y); # 756 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dadd_ru(double x, double y); # 768 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dadd_rd(double x, double y); # 780 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsub_rn(double x, double y); # 792 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsub_rz(double x, double y); # 804 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsub_ru(double x, double y); # 816 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsub_rd(double x, double y); # 828 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dmul_rn(double x, double y); # 840 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dmul_rz(double x, double y); # 852 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dmul_ru(double x, double y); # 864 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dmul_rd(double x, double y); # 873 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __double2float_rn(double x); # 882 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __double2float_rz(double x); # 891 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __double2float_ru(double x); # 900 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) float __double2float_rd(double x); # 909 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __double2int_rn(double x); # 918 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __double2int_ru(double x); # 927 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __double2int_rd(double x); # 936 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __double2uint_rn(double x); # 945 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __double2uint_ru(double x); # 954 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __double2uint_rd(double x); # 963 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __double2ll_rn(double x); # 972 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __double2ll_ru(double x); # 981 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) long long int __double2ll_rd(double x); # 990 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __double2ull_rn(double x); # 999 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __double2ull_ru(double x); # 1008 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) unsigned long long int __double2ull_rd(double x); extern __attribute__((device)) __attribute__((device_builtin)) double __int2double_rn(int x); extern __attribute__((device)) __attribute__((device_builtin)) double __uint2double_rn(unsigned int x); # 1033 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ll2double_rn(long long int x); # 1042 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ll2double_rz(long long int x); # 1051 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ll2double_ru(long long int x); # 1060 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ll2double_rd(long long int x); # 1069 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ull2double_rn(unsigned long long int x); # 1078 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ull2double_rz(unsigned long long int x); # 1087 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ull2double_ru(unsigned long long int x); # 1096 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ull2double_rd(unsigned long long int x); # 1105 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __double2hiint(double x); # 1114 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) int __double2loint(double x); # 1124 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_13_double_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) double __hiloint2double(int hi, int lo); } static __inline__ __attribute__((device)) double fma(double a, double b, double c, enum cudaRoundMode mode) { return mode == cudaRoundZero ? __fma_rz(a, b, c) : mode == cudaRoundPosInf ? __fma_ru(a, b, c) : mode == cudaRoundMinInf ? __fma_rd(a, b, c) : __fma_rn(a, b, c); } static __inline__ __attribute__((device)) double dmul(double a, double b, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __dmul_rz(a, b) : mode == cudaRoundPosInf ? __dmul_ru(a, b) : mode == cudaRoundMinInf ? __dmul_rd(a, b) : __dmul_rn(a, b); } static __inline__ __attribute__((device)) double dadd(double a, double b, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __dadd_rz(a, b) : mode == cudaRoundPosInf ? __dadd_ru(a, b) : mode == cudaRoundMinInf ? __dadd_rd(a, b) : __dadd_rn(a, b); } static __inline__ __attribute__((device)) double dsub(double a, double b, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __dsub_rz(a, b) : mode == cudaRoundPosInf ? __dsub_ru(a, b) : mode == cudaRoundMinInf ? __dsub_rd(a, b) : __dsub_rn(a, b); } static __inline__ __attribute__((device)) int double2int(double a, enum cudaRoundMode mode = cudaRoundZero) { return mode == cudaRoundNearest ? __double2int_rn(a) : mode == cudaRoundPosInf ? __double2int_ru(a) : mode == cudaRoundMinInf ? __double2int_rd(a) : __double2int_rz(a); } static __inline__ __attribute__((device)) unsigned int double2uint(double a, enum cudaRoundMode mode = cudaRoundZero) { return mode == cudaRoundNearest ? __double2uint_rn(a) : mode == cudaRoundPosInf ? __double2uint_ru(a) : mode == cudaRoundMinInf ? __double2uint_rd(a) : __double2uint_rz(a); } static __inline__ __attribute__((device)) long long int double2ll(double a, enum cudaRoundMode mode = cudaRoundZero) { return mode == cudaRoundNearest ? __double2ll_rn(a) : mode == cudaRoundPosInf ? __double2ll_ru(a) : mode == cudaRoundMinInf ? __double2ll_rd(a) : __double2ll_rz(a); } static __inline__ __attribute__((device)) unsigned long long int double2ull(double a, enum cudaRoundMode mode = cudaRoundZero) { return mode == cudaRoundNearest ? __double2ull_rn(a) : mode == cudaRoundPosInf ? __double2ull_ru(a) : mode == cudaRoundMinInf ? __double2ull_rd(a) : __double2ull_rz(a); } static __inline__ __attribute__((device)) double ll2double(long long int a, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __ll2double_rz(a) : mode == cudaRoundPosInf ? __ll2double_ru(a) : mode == cudaRoundMinInf ? __ll2double_rd(a) : __ll2double_rn(a); } static __inline__ __attribute__((device)) double ull2double(unsigned long long int a, enum cudaRoundMode mode = cudaRoundNearest) { return mode == cudaRoundZero ? __ull2double_rz(a) : mode == cudaRoundPosInf ? __ull2double_ru(a) : mode == cudaRoundMinInf ? __ull2double_rd(a) : __ull2double_rn(a); } static __inline__ __attribute__((device)) double int2double(int a, enum cudaRoundMode mode = cudaRoundNearest) { return (double)a; } static __inline__ __attribute__((device)) double uint2double(unsigned int a, enum cudaRoundMode mode = cudaRoundNearest) { return (double)a; } static __inline__ __attribute__((device)) double float2double(float a, enum cudaRoundMode mode = cudaRoundNearest) { return (double)a; } # 9408 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_atomic_functions.h" 1 # 63 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_atomic_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 64 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_atomic_functions.h" 2 extern "C" { extern __attribute__((device)) __attribute__((device_builtin)) float __fAtomicAdd(float *address, float val); } static __inline__ __attribute__((device)) float atomicAdd(float *address, float val) { return __fAtomicAdd(address, val); } # 9409 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_32_atomic_functions.h" 1 # 9410 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_35_atomic_functions.h" 1 # 9411 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" 1 # 63 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 64 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" 2 extern "C" { extern __attribute__((device)) __attribute__((device_builtin)) void __threadfence_system(void); # 81 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ddiv_rn(double x, double y); # 93 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ddiv_rz(double x, double y); # 105 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ddiv_ru(double x, double y); # 117 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __ddiv_rd(double x, double y); # 151 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __drcp_rn(double x); # 185 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __drcp_rz(double x); # 219 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __drcp_ru(double x); # 253 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __drcp_rd(double x); # 285 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsqrt_rn(double x); # 317 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsqrt_rz(double x); # 349 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsqrt_ru(double x); # 381 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_20_intrinsics.h" extern __attribute__((device)) __attribute__((device_builtin)) double __dsqrt_rd(double x); extern __attribute__((device)) __attribute__((device_builtin)) unsigned int __ballot(int); extern __attribute__((device)) __attribute__((device_builtin)) int __syncthreads_count(int); extern __attribute__((device)) __attribute__((device_builtin)) int __syncthreads_and(int); extern __attribute__((device)) __attribute__((device_builtin)) int __syncthreads_or(int); extern __attribute__((device)) __attribute__((device_builtin)) long long int clock64(void); extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_ieee_rn(float, float, float); extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_ieee_rz(float, float, float); extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_ieee_ru(float, float, float); extern __attribute__((device)) __attribute__((device_builtin)) float __fmaf_ieee_rd(float, float, float); extern __attribute__((device)) __attribute__((device_builtin)) double __rcp64h(double); } static __inline__ __attribute__((device)) unsigned int ballot(bool pred) { return __ballot((int)pred); } static __inline__ __attribute__((device)) int syncthreads_count(bool pred) { return __syncthreads_count((int)pred); } static __inline__ __attribute__((device)) bool syncthreads_and(bool pred) { return (bool)__syncthreads_and((int)pred); } static __inline__ __attribute__((device)) bool syncthreads_or(bool pred) { return (bool)__syncthreads_or((int)pred); } static __inline__ __attribute__((device)) unsigned int __isGlobal(const void *ptr) { unsigned int ret; asm volatile ("{ \n\t" " .reg .pred p; \n\t" " isspacep.global p, %1; \n\t" " selp.u32 %0, 1, 0, p; \n\t" "} \n\t" : "=r"(ret) : "l"(ptr)); return ret; } # 9412 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_30_intrinsics.h" 1 # 9413 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_32_intrinsics.h" 1 # 9414 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/sm_35_intrinsics.h" 1 # 9415 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" 2 # 73 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surf1Dreadc1(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surf1Dreadc2(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surf1Dreadc4(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surf1Dreads1(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surf1Dreads2(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surf1Dreads4(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surf1Dreadu1(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surf1Dreadu2(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surf1Dreadu4(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surf1Dreadl1(surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surf1Dreadl2(surface t, int x, enum cudaSurfaceBoundaryMode mode); # 99 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(T *res, surface surf, int x, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surf1Dreadc1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc1(surf, x, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surf1Dreads1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads1(surf, x, cudaBoundaryModeClamp) : __surf1Dreads1(surf, x, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu2(surf, x, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu4(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu4(surf, x, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surf1Dread(&tmp, surf, x, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(T *res, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surf1Dread(surf, x, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surf1Dreadc1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surf1Dreadc1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadc1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surf1Dreadc1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc1(surf, x, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadc1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc1(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadc2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc2(surf, x, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadc2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc2(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadc4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc4(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc4(surf, x, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadc4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadc4(surf, x, cudaBoundaryModeClamp) : __surf1Dreadc4(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surf1Dreads1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads1(surf, x, cudaBoundaryModeClamp) : __surf1Dreads1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreads1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads1(surf, x, cudaBoundaryModeClamp) : __surf1Dreads1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surf1Dreads1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads1(surf, x, cudaBoundaryModeClamp) : __surf1Dreads1(surf, x, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreads1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads1(surf, x, cudaBoundaryModeClamp) : __surf1Dreads1(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreads2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads2(surf, x, cudaBoundaryModeClamp) : __surf1Dreads2(surf, x, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreads2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads2(surf, x, cudaBoundaryModeClamp) : __surf1Dreads2(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreads4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads4(surf, x, cudaBoundaryModeClamp) : __surf1Dreads4(surf, x, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreads4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreads4(surf, x, cudaBoundaryModeClamp) : __surf1Dreads4(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu2(surf, x, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadu2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu2(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu4(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu4(surf, x, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadu4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu4(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu4(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surf1Dreadl1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadl1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadl1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadl1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadl1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadl1(surf, x, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surf1Dreadl1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadl1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadl1(surf, x, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadl1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadl1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadl1(surf, x, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadl2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadl2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadl2(surf, x, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1Dreadl2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadl2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadl2(surf, x, cudaBoundaryModeTrap )); } # 386 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf1Dreadu1(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu1(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu1(surf, x, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu2(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu2(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu2(surf, x, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surf1Dread(surface surf, int x, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1Dreadu4(surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dreadu4(surf, x, cudaBoundaryModeClamp) : __surf1Dreadu4(surf, x, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 421 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surf2Dreadc1(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surf2Dreadc2(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surf2Dreadc4(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surf2Dreads1(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surf2Dreads2(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surf2Dreads4(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surf2Dreadu1(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surf2Dreadu2(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surf2Dreadu4(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surf2Dreadl1(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surf2Dreadl2(surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); # 447 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(T *res, surface surf, int x, int y, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc1(surf, x, y, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads1(surf, x, y, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu2(surf, x, y, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu4(surf, x, y, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surf2Dread(&tmp, surf, x, y, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(T *res, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surf2Dread(surf, x, y, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc1(surf, x, y, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc1(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadc2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc2(surf, x, y, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadc2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc2(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadc4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc4(surf, x, y, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadc4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadc4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadc4(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads1(surf, x, y, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads1(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreads2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads2(surf, x, y, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreads2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads2(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreads4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads4(surf, x, y, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreads4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreads4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreads4(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu2(surf, x, y, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu2(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu4(surf, x, y, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu4(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadl1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadl1(surf, x, y, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadl1(surf, x, y, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadl1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadl1(surf, x, y, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadl2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadl2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadl2(surf, x, y, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2Dreadl2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadl2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadl2(surf, x, y, cudaBoundaryModeTrap )); } # 734 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu1(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu1(surf, x, y, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu2(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu2(surf, x, y, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surf2Dread(surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dreadu4(surf, x, y, cudaBoundaryModeClamp) : __surf2Dreadu4(surf, x, y, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 769 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surf3Dreadc1(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surf3Dreadc2(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surf3Dreadc4(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surf3Dreads1(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surf3Dreads2(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surf3Dreads4(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surf3Dreadu1(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surf3Dreadu2(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surf3Dreadu4(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surf3Dreadl1(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surf3Dreadl2(surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); # 795 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(T *res, surface surf, int x, int y, int z, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads1(surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surf3Dread(&tmp, surf, x, y, z, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(T *res, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surf3Dread(surf, x, y, z, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc1(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadc2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc2(surf, x, y, z, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadc2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc2(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadc4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc4(surf, x, y, z, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadc4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadc4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadc4(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads1(surf, x, y, z, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads1(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreads2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads2(surf, x, y, z, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreads2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads2(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreads4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads4(surf, x, y, z, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreads4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreads4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreads4(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadl1(surf, x, y, z, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadl2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadl2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadl2(surf, x, y, z, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf3Dreadl2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadl2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadl2(surf, x, y, z, cudaBoundaryModeTrap )); } # 1082 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu1(surf, x, y, z, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu2(surf, x, y, z, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surf3Dread(surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dreadu4(surf, x, y, z, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 1117 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surf1DLayeredreadc1(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surf1DLayeredreadc2(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surf1DLayeredreadc4(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surf1DLayeredreads1(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surf1DLayeredreads2(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surf1DLayeredreads4(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surf1DLayeredreadu1(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surf1DLayeredreadu2(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surf1DLayeredreadu4(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surf1DLayeredreadl1(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surf1DLayeredreadl2(surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); # 1143 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(T *res, surface surf, int x, int layer, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surf1DLayeredread(&tmp, surf, x, layer, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(T *res, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surf1DLayeredread(surf, x, layer, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc1(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc2(surf, x, layer, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc2(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc4(surf, x, layer, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadc4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadc4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadc4(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads1(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads2(surf, x, layer, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads2(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads4(surf, x, layer, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreads4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreads4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreads4(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadl1(surf, x, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadl2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadl2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadl2(surf, x, layer, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadl2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadl2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadl2(surf, x, layer, cudaBoundaryModeTrap )); } # 1430 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu1(surf, x, layer, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu2(surf, x, layer, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surf1DLayeredread(surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredreadu4(surf, x, layer, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 1465 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surf2DLayeredreadc1(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surf2DLayeredreadc2(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surf2DLayeredreadc4(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surf2DLayeredreads1(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surf2DLayeredreads2(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surf2DLayeredreads4(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surf2DLayeredreadu1(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surf2DLayeredreadu2(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surf2DLayeredreadu4(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surf2DLayeredreadl1(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surf2DLayeredreadl2(surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); # 1491 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(T *res, surface surf, int x, int y, int layer, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surf2DLayeredread(&tmp, surf, x, y, layer, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(T *res, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surf2DLayeredread(surf, x, y, layer, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc1(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc2(surf, x, y, layer, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc2(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc4(surf, x, y, layer, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadc4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadc4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadc4(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads1(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads2(surf, x, y, layer, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads2(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads4(surf, x, y, layer, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreads4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreads4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreads4(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadl1(surf, x, y, layer, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadl2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadl2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadl2(surf, x, y, layer, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadl2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadl2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadl2(surf, x, y, layer, cudaBoundaryModeTrap )); } # 1778 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu1(surf, x, y, layer, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu2(surf, x, y, layer, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surf2DLayeredread(surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredreadu4(surf, x, y, layer, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 1813 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surfCubemapreadc1(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surfCubemapreadc2(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surfCubemapreadc4(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surfCubemapreads1(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surfCubemapreads2(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surfCubemapreads4(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surfCubemapreadu1(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surfCubemapreadu2(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surfCubemapreadu4(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surfCubemapreadl1(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surfCubemapreadl2(surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); # 1839 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(T *res, surface surf, int x, int y, int face, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surfCubemapread(&tmp, surf, x, y, face, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(T *res, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surfCubemapread(surf, x, y, face, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc1(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc2(surf, x, y, face, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc2(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc4(surf, x, y, face, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadc4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadc4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadc4(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads1(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreads2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads2(surf, x, y, face, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreads2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads2(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreads4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads4(surf, x, y, face, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreads4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreads4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreads4(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadl1(surf, x, y, face, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadl2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadl2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadl2(surf, x, y, face, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapreadl2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadl2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadl2(surf, x, y, face, cudaBoundaryModeTrap )); } # 2126 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu1(surf, x, y, face, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu2(surf, x, y, face, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surfCubemapread(surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapreadu4(surf, x, y, face, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 2161 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) uchar1 __surfCubemapLayeredreadc1(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar2 __surfCubemapLayeredreadc2(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uchar4 __surfCubemapLayeredreadc4(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort1 __surfCubemapLayeredreads1(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort2 __surfCubemapLayeredreads2(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ushort4 __surfCubemapLayeredreads4(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint1 __surfCubemapLayeredreadu1(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint2 __surfCubemapLayeredreadu2(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) uint4 __surfCubemapLayeredreadu4(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong1 __surfCubemapLayeredreadl1(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) ulonglong2 __surfCubemapLayeredreadl2(surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); # 2188 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(T *res, surface surf, int x, int y, int layerFace, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { (s == 1) ? (void)(*(uchar1 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(*(ushort1*)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(*(uint1 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(*(uint2 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(*(uint4 *)res = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { T tmp; surfCubemapLayeredread(&tmp, surf, x, y, layerFace, (int)sizeof(T), mode); return tmp; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(T *res, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { *res = surfCubemapLayeredread(surf, x, y, layerFace, mode); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return (char)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) signed char surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return (signed char)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return make_char1((signed char)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc1(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { uchar2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc2(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_char2((signed char)tmp.x, (signed char)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc2(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) char4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { uchar4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc4(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_char4((signed char)tmp.x, (signed char)tmp.y, (signed char)tmp.z, (signed char)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadc4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadc4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadc4(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return (short)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return make_short1((signed short)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads1(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { ushort2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads2(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_short2((signed short)tmp.x, (signed short)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads2(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) short4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { ushort4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads4(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_short4((signed short)tmp.x, (signed short)tmp.y, (signed short)tmp.z, (signed short)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreads4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreads4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreads4(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return (int)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return make_int1((signed int)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_int2((int)tmp.x, (int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) int4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_int4((int)tmp.x, (int)tmp.y, (int)tmp.z, (int)tmp.w); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) long long int surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return (long long int)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned long long int surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x; } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return make_longlong1((long long int)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadl1(surf, x, y, layerFace, cudaBoundaryModeTrap )); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) longlong2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { ulonglong2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadl2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadl2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadl2(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_longlong2((long long int)tmp.x, (long long int)tmp.y); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) ulonglong2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadl2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadl2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadl2(surf, x, y, layerFace, cudaBoundaryModeTrap )); } # 2475 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return __int_as_float((int)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float1 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { return make_float1(__int_as_float((int)((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu1(surf, x, y, layerFace, cudaBoundaryModeTrap )).x)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float2 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { uint2 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu2(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_float2(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y)); } template<> __inline__ __attribute__((always_inline)) __attribute__((device)) float4 surfCubemapLayeredread(surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode) { uint4 tmp = ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredreadu4(surf, x, y, layerFace, cudaBoundaryModeTrap )); return make_float4(__int_as_float((int)tmp.x), __int_as_float((int)tmp.y), __int_as_float((int)tmp.z), __int_as_float((int)tmp.w)); } # 2511 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwritec1( uchar1 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwritec2( uchar2 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwritec4( uchar4 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwrites1( ushort1 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwrites2( ushort2 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwrites4( ushort4 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwriteu1( uint1 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwriteu2( uint2 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwriteu4( uint4 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwritel1(ulonglong1 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1Dwritel2(ulonglong2 val, surface t, int x, enum cudaSurfaceBoundaryMode mode); # 2537 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(T val, surface surf, int x, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1Dwritec1(tmp.c1, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec1(tmp.c1, surf, x, cudaBoundaryModeClamp) : __surf1Dwritec1(tmp.c1, surf, x, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1Dwrites1(tmp.s1, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites1(tmp.s1, surf, x, cudaBoundaryModeClamp) : __surf1Dwrites1(tmp.s1, surf, x, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(tmp.u1, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(tmp.u1, surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(tmp.u1, surf, x, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1Dwriteu2(tmp.u2, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu2(tmp.u2, surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu2(tmp.u2, surf, x, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1Dwriteu4(tmp.u4, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu4(tmp.u4, surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu4(tmp.u4, surf, x, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(T val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surf1Dwrite(val, surf, x, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec1(make_uchar1((unsigned char)val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec1(make_uchar1((unsigned char)val), surf, x, cudaBoundaryModeClamp) : __surf1Dwritec1(make_uchar1((unsigned char)val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(signed char val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec1(make_uchar1((unsigned char)val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec1(make_uchar1((unsigned char)val), surf, x, cudaBoundaryModeClamp) : __surf1Dwritec1(make_uchar1((unsigned char)val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned char val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec1(make_uchar1(val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec1(make_uchar1(val), surf, x, cudaBoundaryModeClamp) : __surf1Dwritec1(make_uchar1(val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec1(make_uchar1((unsigned char)val.x), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec1(make_uchar1((unsigned char)val.x), surf, x, cudaBoundaryModeClamp) : __surf1Dwritec1(make_uchar1((unsigned char)val.x), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uchar1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec1(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec1(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwritec1(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, cudaBoundaryModeClamp) : __surf1Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uchar2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec2(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec2(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwritec2(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, cudaBoundaryModeClamp) : __surf1Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uchar4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritec4(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritec4(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwritec4(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites1(make_ushort1((unsigned short)val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites1(make_ushort1((unsigned short)val), surf, x, cudaBoundaryModeClamp) : __surf1Dwrites1(make_ushort1((unsigned short)val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned short val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites1(make_ushort1(val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites1(make_ushort1(val), surf, x, cudaBoundaryModeClamp) : __surf1Dwrites1(make_ushort1(val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites1(make_ushort1((unsigned short)val.x), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites1(make_ushort1((unsigned short)val.x), surf, x, cudaBoundaryModeClamp) : __surf1Dwrites1(make_ushort1((unsigned short)val.x), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ushort1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites1(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites1(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwrites1(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, cudaBoundaryModeClamp) : __surf1Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ushort2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites2(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites2(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwrites2(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, cudaBoundaryModeClamp) : __surf1Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ushort4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwrites4(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwrites4(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwrites4(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(make_uint1((unsigned int)val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(make_uint1((unsigned int)val), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(make_uint1((unsigned int)val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned int val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(make_uint1(val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(make_uint1(val), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(make_uint1(val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(make_uint1((unsigned int)val.x), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(make_uint1((unsigned int)val.x), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(make_uint1((unsigned int)val.x), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uint1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uint2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu2(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu2(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu2(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uint4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu4(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu4(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu4(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(long long int val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, cudaBoundaryModeClamp) : __surf1Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned long long int val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritel1(make_ulonglong1(val), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritel1(make_ulonglong1(val), surf, x, cudaBoundaryModeClamp) : __surf1Dwritel1(make_ulonglong1(val), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(longlong1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, cudaBoundaryModeClamp) : __surf1Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ulonglong1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritel1(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritel1(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwritel1(val, surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(longlong2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, cudaBoundaryModeClamp) : __surf1Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ulonglong2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwritel2(val, surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwritel2(val, surf, x, cudaBoundaryModeClamp) : __surf1Dwritel2(val, surf, x, cudaBoundaryModeTrap )); } # 2765 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float1 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float2 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float4 val, surface surf, int x, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, cudaBoundaryModeClamp) : __surf1Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, cudaBoundaryModeTrap )); } # 2793 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwritec1( uchar1 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwritec2( uchar2 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwritec4( uchar4 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwrites1( ushort1 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwrites2( ushort2 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwrites4( ushort4 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwriteu1( uint1 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwriteu2( uint2 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwriteu4( uint4 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwritel1(ulonglong1 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2Dwritel2(ulonglong2 val, surface t, int x, int y, enum cudaSurfaceBoundaryMode mode); # 2819 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(T val, surface surf, int x, int y, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2Dwritec1(tmp.c1, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec1(tmp.c1, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec1(tmp.c1, surf, x, y, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2Dwrites1(tmp.s1, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites1(tmp.s1, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites1(tmp.s1, surf, x, y, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(tmp.u1, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(tmp.u1, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(tmp.u1, surf, x, y, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2Dwriteu2(tmp.u2, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu2(tmp.u2, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu2(tmp.u2, surf, x, y, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2Dwriteu4(tmp.u4, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu4(tmp.u4, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu4(tmp.u4, surf, x, y, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(T val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surf2Dwrite(val, surf, x, y, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec1(make_uchar1((unsigned char)val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec1(make_uchar1((unsigned char)val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec1(make_uchar1((unsigned char)val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(signed char val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec1(make_uchar1((unsigned char)val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec1(make_uchar1((unsigned char)val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec1(make_uchar1((unsigned char)val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned char val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec1(make_uchar1(val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec1(make_uchar1(val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec1(make_uchar1(val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec1(make_uchar1((unsigned char)val.x), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec1(make_uchar1((unsigned char)val.x), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec1(make_uchar1((unsigned char)val.x), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uchar1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec1(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec1(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec1(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uchar2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec2(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec2(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec2(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uchar4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritec4(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritec4(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritec4(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites1(make_ushort1((unsigned short)val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites1(make_ushort1((unsigned short)val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites1(make_ushort1((unsigned short)val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned short val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites1(make_ushort1(val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites1(make_ushort1(val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites1(make_ushort1(val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites1(make_ushort1((unsigned short)val.x), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites1(make_ushort1((unsigned short)val.x), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites1(make_ushort1((unsigned short)val.x), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ushort1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites1(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites1(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites1(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ushort2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites2(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites2(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites2(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ushort4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwrites4(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwrites4(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwrites4(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(make_uint1((unsigned int)val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(make_uint1((unsigned int)val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(make_uint1((unsigned int)val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned int val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(make_uint1(val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(make_uint1(val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(make_uint1(val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(make_uint1((unsigned int)val.x), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(make_uint1((unsigned int)val.x), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(make_uint1((unsigned int)val.x), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uint1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uint2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu2(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu2(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu2(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uint4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu4(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu4(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu4(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(long long int val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned long long int val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritel1(make_ulonglong1(val), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritel1(make_ulonglong1(val), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritel1(make_ulonglong1(val), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(longlong1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ulonglong1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritel1(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritel1(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritel1(val, surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(longlong2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ulonglong2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwritel2(val, surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwritel2(val, surf, x, y, cudaBoundaryModeClamp) : __surf2Dwritel2(val, surf, x, y, cudaBoundaryModeTrap )); } # 3047 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float1 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float2 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float4 val, surface surf, int x, int y, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, cudaBoundaryModeClamp) : __surf2Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, cudaBoundaryModeTrap )); } # 3075 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwritec1( uchar1 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwritec2( uchar2 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwritec4( uchar4 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwrites1( ushort1 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwrites2( ushort2 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwrites4( ushort4 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwriteu1( uint1 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwriteu2( uint2 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwriteu4( uint4 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwritel1(ulonglong1 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf3Dwritel2(ulonglong2 val, surface t, int x, int y, int z, enum cudaSurfaceBoundaryMode mode); # 3101 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(T val, surface surf, int x, int y, int z, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surf3Dwritec1(tmp.c1, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec1(tmp.c1, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec1(tmp.c1, surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surf3Dwrites1(tmp.s1, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites1(tmp.s1, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites1(tmp.s1, surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(tmp.u1, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(tmp.u1, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(tmp.u1, surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surf3Dwriteu2(tmp.u2, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu2(tmp.u2, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu2(tmp.u2, surf, x, y, z, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surf3Dwriteu4(tmp.u4, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu4(tmp.u4, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu4(tmp.u4, surf, x, y, z, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(T val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surf3Dwrite(val, surf, x, y, z, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec1(make_uchar1((unsigned char)val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec1(make_uchar1((unsigned char)val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec1(make_uchar1((unsigned char)val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(signed char val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec1(make_uchar1((unsigned char)val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec1(make_uchar1((unsigned char)val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec1(make_uchar1((unsigned char)val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned char val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec1(make_uchar1(val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec1(make_uchar1(val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec1(make_uchar1(val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec1(make_uchar1((unsigned char)val.x), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec1(make_uchar1((unsigned char)val.x), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec1(make_uchar1((unsigned char)val.x), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uchar1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec1(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec1(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec1(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uchar2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec2(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec2(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec2(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uchar4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritec4(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritec4(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritec4(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites1(make_ushort1((unsigned short)val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites1(make_ushort1((unsigned short)val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites1(make_ushort1((unsigned short)val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned short val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites1(make_ushort1(val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites1(make_ushort1(val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites1(make_ushort1(val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites1(make_ushort1((unsigned short)val.x), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites1(make_ushort1((unsigned short)val.x), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites1(make_ushort1((unsigned short)val.x), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ushort1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites1(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites1(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites1(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ushort2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites2(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites2(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites2(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ushort4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwrites4(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwrites4(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwrites4(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(make_uint1((unsigned int)val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(make_uint1((unsigned int)val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(make_uint1((unsigned int)val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned int val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(make_uint1(val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(make_uint1(val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(make_uint1(val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(make_uint1((unsigned int)val.x), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(make_uint1((unsigned int)val.x), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(make_uint1((unsigned int)val.x), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uint1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uint2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu2(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu2(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu2(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uint4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu4(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu4(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu4(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(long long int val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned long long int val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritel1(make_ulonglong1(val), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritel1(make_ulonglong1(val), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritel1(make_ulonglong1(val), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(longlong1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ulonglong1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritel1(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritel1(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritel1(val, surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(longlong2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ulonglong2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwritel2(val, surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwritel2(val, surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwritel2(val, surf, x, y, z, cudaBoundaryModeTrap )); } # 3329 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float1 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float2 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, z, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float4 val, surface surf, int x, int y, int z, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf3Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, z, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf3Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, z, cudaBoundaryModeClamp) : __surf3Dwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, z, cudaBoundaryModeTrap )); } # 3357 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwritec1( uchar1 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwritec2( uchar2 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwritec4( uchar4 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwrites1( ushort1 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwrites2( ushort2 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwrites4( ushort4 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwriteu1( uint1 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwriteu2( uint2 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwriteu4( uint4 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwritel1(ulonglong1 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf1DLayeredwritel2(ulonglong2 val, surface t, int x, int layer, enum cudaSurfaceBoundaryMode mode); # 3383 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(T val, surface surf, int x, int layer, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec1(tmp.c1, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec1(tmp.c1, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec1(tmp.c1, surf, x, layer, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites1(tmp.s1, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites1(tmp.s1, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites1(tmp.s1, surf, x, layer, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(tmp.u1, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(tmp.u1, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(tmp.u1, surf, x, layer, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu2(tmp.u2, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu2(tmp.u2, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu2(tmp.u2, surf, x, layer, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu4(tmp.u4, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu4(tmp.u4, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu4(tmp.u4, surf, x, layer, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(T val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surf1DLayeredwrite(val, surf, x, layer, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(signed char val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned char val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec1(make_uchar1(val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec1(make_uchar1(val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec1(make_uchar1(val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uchar1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec1(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec1(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec1(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uchar2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec2(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec2(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec2(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uchar4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritec4(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritec4(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritec4(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites1(make_ushort1((unsigned short)val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites1(make_ushort1((unsigned short)val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites1(make_ushort1((unsigned short)val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned short val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites1(make_ushort1(val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites1(make_ushort1(val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites1(make_ushort1(val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ushort1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites1(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites1(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites1(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ushort2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites2(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites2(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites2(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ushort4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwrites4(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwrites4(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwrites4(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(make_uint1((unsigned int)val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned int val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(make_uint1(val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(make_uint1(val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(make_uint1(val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uint1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uint2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu2(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu2(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu2(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uint4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu4(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu4(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu4(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(long long int val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned long long int val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritel1(make_ulonglong1(val), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritel1(make_ulonglong1(val), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritel1(make_ulonglong1(val), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(longlong1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ulonglong1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritel1(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritel1(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritel1(val, surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(longlong2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ulonglong2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwritel2(val, surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwritel2(val, surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwritel2(val, surf, x, layer, cudaBoundaryModeTrap )); } # 3611 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float1 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float2 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float4 val, surface surf, int x, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf1DLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf1DLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, layer, cudaBoundaryModeClamp) : __surf1DLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, layer, cudaBoundaryModeTrap )); } # 3639 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwritec1( uchar1 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwritec2( uchar2 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwritec4( uchar4 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwrites1( ushort1 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwrites2( ushort2 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwrites4( ushort4 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwriteu1( uint1 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwriteu2( uint2 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwriteu4( uint4 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwritel1(ulonglong1 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surf2DLayeredwritel2(ulonglong2 val, surface t, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode); # 3665 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(T val, surface surf, int x, int y, int layer, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec1(tmp.c1, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec1(tmp.c1, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec1(tmp.c1, surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites1(tmp.s1, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites1(tmp.s1, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites1(tmp.s1, surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(tmp.u1, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(tmp.u1, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(tmp.u1, surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu2(tmp.u2, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu2(tmp.u2, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu2(tmp.u2, surf, x, y, layer, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu4(tmp.u4, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu4(tmp.u4, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu4(tmp.u4, surf, x, y, layer, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(T val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surf2DLayeredwrite(val, surf, x, y, layer, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(signed char val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned char val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec1(make_uchar1(val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec1(make_uchar1(val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec1(make_uchar1(val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uchar1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec1(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec1(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec1(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uchar2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec2(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec2(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec2(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uchar4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritec4(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritec4(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritec4(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites1(make_ushort1((unsigned short)val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites1(make_ushort1((unsigned short)val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites1(make_ushort1((unsigned short)val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned short val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites1(make_ushort1(val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites1(make_ushort1(val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites1(make_ushort1(val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ushort1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites1(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites1(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites1(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ushort2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites2(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites2(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites2(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ushort4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwrites4(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwrites4(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwrites4(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(make_uint1((unsigned int)val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned int val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(make_uint1(val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(make_uint1(val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(make_uint1(val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uint1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uint2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu2(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu2(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu2(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uint4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu4(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu4(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu4(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(long long int val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned long long int val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritel1(make_ulonglong1(val), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritel1(make_ulonglong1(val), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritel1(make_ulonglong1(val), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(longlong1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ulonglong1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritel1(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritel1(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritel1(val, surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(longlong2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ulonglong2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwritel2(val, surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwritel2(val, surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwritel2(val, surf, x, y, layer, cudaBoundaryModeTrap )); } # 3893 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float1 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float2 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, layer, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float4 val, surface surf, int x, int y, int layer, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surf2DLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, layer, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surf2DLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, layer, cudaBoundaryModeClamp) : __surf2DLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, layer, cudaBoundaryModeTrap )); } # 3920 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwritec1( uchar1 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwritec2( uchar2 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwritec4( uchar4 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwrites1( ushort1 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwrites2( ushort2 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwrites4( ushort4 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwriteu1( uint1 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwriteu2( uint2 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwriteu4( uint4 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwritel1(ulonglong1 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapwritel2(ulonglong2 val, surface t, int x, int y, int face, enum cudaSurfaceBoundaryMode mode); # 3947 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(T val, surface surf, int x, int y, int face, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapwritec1(tmp.c1, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec1(tmp.c1, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec1(tmp.c1, surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapwrites1(tmp.s1, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites1(tmp.s1, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites1(tmp.s1, surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(tmp.u1, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(tmp.u1, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(tmp.u1, surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu2(tmp.u2, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu2(tmp.u2, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu2(tmp.u2, surf, x, y, face, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu4(tmp.u4, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu4(tmp.u4, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu4(tmp.u4, surf, x, y, face, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(T val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surfCubemapwrite(val, surf, x, y, face, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec1(make_uchar1((unsigned char)val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec1(make_uchar1((unsigned char)val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec1(make_uchar1((unsigned char)val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(signed char val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec1(make_uchar1((unsigned char)val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec1(make_uchar1((unsigned char)val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec1(make_uchar1((unsigned char)val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned char val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec1(make_uchar1(val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec1(make_uchar1(val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec1(make_uchar1(val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec1(make_uchar1((unsigned char)val.x), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec1(make_uchar1((unsigned char)val.x), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec1(make_uchar1((unsigned char)val.x), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uchar1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec1(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec1(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec1(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uchar2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec2(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec2(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec2(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uchar4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritec4(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritec4(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritec4(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites1(make_ushort1((unsigned short)val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites1(make_ushort1((unsigned short)val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites1(make_ushort1((unsigned short)val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned short val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites1(make_ushort1(val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites1(make_ushort1(val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites1(make_ushort1(val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites1(make_ushort1((unsigned short)val.x), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites1(make_ushort1((unsigned short)val.x), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites1(make_ushort1((unsigned short)val.x), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ushort1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites1(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites1(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites1(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ushort2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites2(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites2(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites2(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ushort4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwrites4(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwrites4(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwrites4(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(make_uint1((unsigned int)val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(make_uint1((unsigned int)val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(make_uint1((unsigned int)val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned int val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(make_uint1(val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(make_uint1(val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(make_uint1(val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(make_uint1((unsigned int)val.x), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(make_uint1((unsigned int)val.x), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(make_uint1((unsigned int)val.x), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uint1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uint2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu2(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu2(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu2(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uint4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu4(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu4(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu4(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(long long int val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned long long int val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritel1(make_ulonglong1(val), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritel1(make_ulonglong1(val), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritel1(make_ulonglong1(val), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(longlong1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ulonglong1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritel1(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritel1(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritel1(val, surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(longlong2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ulonglong2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwritel2(val, surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwritel2(val, surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwritel2(val, surf, x, y, face, cudaBoundaryModeTrap )); } # 4175 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float1 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float2 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, face, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float4 val, surface surf, int x, int y, int face, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, face, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, face, cudaBoundaryModeClamp) : __surfCubemapwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, face, cudaBoundaryModeTrap )); } # 4202 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwritec1( uchar1 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwritec2( uchar2 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwritec4( uchar4 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwrites1( ushort1 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwrites2( ushort2 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwrites4( ushort4 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwriteu1( uint1 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwriteu2( uint2 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwriteu4( uint4 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwritel1(ulonglong1 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); extern __attribute__((device)) __attribute__((device_builtin)) void __surfCubemapLayeredwritel2(ulonglong2 val, surface t, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode); # 4229 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(T val, surface surf, int x, int y, int layerFace, int s, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { union { T val; uchar1 c1; ushort1 s1; uint1 u1; uint2 u2; uint4 u4; } tmp; tmp.val = val; (s == 1) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec1(tmp.c1, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec1(tmp.c1, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec1(tmp.c1, surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 2) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites1(tmp.s1, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites1(tmp.s1, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites1(tmp.s1, surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 4) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(tmp.u1, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(tmp.u1, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(tmp.u1, surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 8) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu2(tmp.u2, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu2(tmp.u2, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu2(tmp.u2, surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (s == 16) ? (void)(((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu4(tmp.u4, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu4(tmp.u4, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu4(tmp.u4, surf, x, y, layerFace, cudaBoundaryModeTrap ))) : (void)0; } template static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(T val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) {; surfCubemapLayeredwrite(val, surf, x, y, layerFace, (int)sizeof(T), mode); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(signed char val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned char val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec1(make_uchar1(val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec1(make_uchar1(val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec1(make_uchar1(val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec1(make_uchar1((unsigned char)val.x), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uchar1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec1(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec1(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec1(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec2(make_uchar2((unsigned char)val.x, (unsigned char)val.y), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uchar2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec2(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec2(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec2(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec4(make_uchar4((unsigned char)val.x, (unsigned char)val.y, (unsigned char)val.z, (unsigned char)val.w), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uchar4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritec4(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritec4(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritec4(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites1(make_ushort1((unsigned short)val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites1(make_ushort1((unsigned short)val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites1(make_ushort1((unsigned short)val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned short val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites1(make_ushort1(val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites1(make_ushort1(val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites1(make_ushort1(val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites1(make_ushort1((unsigned short)val.x), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ushort1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites1(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites1(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites1(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites2(make_ushort2((unsigned short)val.x, (unsigned short)val.y), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ushort2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites2(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites2(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites2(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites4(make_ushort4((unsigned short)val.x, (unsigned short)val.y, (unsigned short)val.z, (unsigned short)val.w), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ushort4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwrites4(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwrites4(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwrites4(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(make_uint1((unsigned int)val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned int val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(make_uint1(val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(make_uint1(val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(make_uint1(val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(make_uint1((unsigned int)val.x), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uint1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu2(make_uint2((unsigned int)val.x, (unsigned int)val.y), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uint2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu2(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu2(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu2(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu4(make_uint4((unsigned int)val.x, (unsigned int)val.y, (unsigned int)val.z, (unsigned int)val.w), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uint4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu4(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu4(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu4(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(long long int val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritel1(make_ulonglong1((unsigned long long int)val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned long long int val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritel1(make_ulonglong1(val), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritel1(make_ulonglong1(val), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritel1(make_ulonglong1(val), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(longlong1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritel1(make_ulonglong1((unsigned long long int)val.x), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ulonglong1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritel1(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritel1(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritel1(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(longlong2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritel2(make_ulonglong2((unsigned long long int)val.x, (unsigned long long int)val.y), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ulonglong2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwritel2(val, surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwritel2(val, surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwritel2(val, surf, x, y, layerFace, cudaBoundaryModeTrap )); } # 4457 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val)), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float1 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu1(make_uint1((unsigned int)__float_as_int(val.x)), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float2 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu2(make_uint2((unsigned int)__float_as_int(val.x), __float_as_int((unsigned int)val.y)), surf, x, y, layerFace, cudaBoundaryModeTrap )); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float4 val, surface surf, int x, int y, int layerFace, enum cudaSurfaceBoundaryMode mode = cudaBoundaryModeTrap) { ((mode == cudaBoundaryModeZero) ? __surfCubemapLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, layerFace, cudaBoundaryModeZero ) : (mode == cudaBoundaryModeClamp) ? __surfCubemapLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, layerFace, cudaBoundaryModeClamp) : __surfCubemapLayeredwriteu4(make_uint4((unsigned int)__float_as_int(val.x), (unsigned int)__float_as_int(val.y), (unsigned int)__float_as_int(val.z), (unsigned int)__float_as_int(val.w)), surf, x, y, layerFace, cudaBoundaryModeTrap )); } # 9416 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" 1 # 61 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 62 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" 2 # 74 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchi(texture t, int4 i); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchi(texture t, int4 i); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchi(texture t, int4 i); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetch(texture t, float4 i, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetch(texture t, float4 i, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetch(texture t, float4 i, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchc(texture t, float4 i); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchc(texture t, float4 i); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchc(texture t, float4 i); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchl(texture t, float4 i, int l, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchl(texture t, float4 i, int l, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchl(texture t, float4 i, int l, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchlc(texture t, float4 i, int l); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchlc(texture t, float4 i, int l); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchlc(texture t, float4 i, int l); static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 359 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1Dfetch(texture t, int x) { float4 v = __ftexfetchi(t, make_int4(x, 0, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1Dfetch(texture t, int x) { float4 v = __ftexfetchi(t, make_int4(x, 0, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1Dfetch(texture t, int x) { float4 v = __ftexfetchi(t, make_int4(x, 0, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1Dfetch(texture t, int x) { float4 v = __ftexfetchi(t, make_int4(x, 0, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1Dfetch(texture t, int x) { int4 v = __itexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1Dfetch(texture t, int x) { uint4 v = __utexfetchi(t, make_int4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 814 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1D(texture t, float x) { float4 v = __ftexfetch(t, make_float4(x, 0, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1D(texture t, float x) { float4 v = __ftexfetch(t, make_float4(x, 0, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1D(texture t, float x) { float4 v = __ftexfetch(t, make_float4(x, 0, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1D(texture t, float x) { float4 v = __ftexfetch(t, make_float4(x, 0, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1D(texture t, float x) { int4 v = __itexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1D(texture t, float x) { uint4 v = __utexfetch(t, make_float4(x, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 1263 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2D(texture t, float x, float y) { float4 v = __ftexfetch(t, make_float4(x, y, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2D(texture t, float x, float y) { float4 v = __ftexfetch(t, make_float4(x, y, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2D(texture t, float x, float y) { float4 v = __ftexfetch(t, make_float4(x, y, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2D(texture t, float x, float y) { float4 v = __ftexfetch(t, make_float4(x, y, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2D(texture t, float x, float y) { int4 v = __itexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2D(texture t, float x, float y) { uint4 v = __utexfetch(t, make_float4(x, y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_uint4(v.x, v.y, v.z, v.w); } # 1712 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayered(texture t, float x, int layer) { float4 v = __ftexfetchl(t, make_float4(x, 0, 0, 0), layer); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayered(texture t, float x, int layer) { float4 v = __ftexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayered(texture t, float x, int layer) { float4 v = __ftexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayered(texture t, float x, int layer) { float4 v = __ftexfetchl(t, make_float4(x, 0, 0, 0), layer); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayered(texture t, float x, int layer) { int4 v = __itexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayered(texture t, float x, int layer) { uint4 v = __utexfetchl(t, make_float4(x, 0, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); return make_uint4(v.x, v.y, v.z, v.w); } # 2161 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayered(texture t, float x, float y, int layer) { float4 v = __ftexfetchl(t, make_float4(x, y, 0, 0), layer); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayered(texture t, float x, float y, int layer) { float4 v = __ftexfetchl(t, make_float4(x, y, 0, 0), layer); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayered(texture t, float x, float y, int layer) { float4 v = __ftexfetchl(t, make_float4(x, y, 0, 0), layer); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayered(texture t, float x, float y, int layer) { float4 v = __ftexfetchl(t, make_float4(x, y, 0, 0), layer); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayered(texture t, float x, float y, int layer) { int4 v = __itexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayered(texture t, float x, float y, int layer) { uint4 v = __utexfetchl(t, make_float4(x, y, 0, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 2610 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3D(texture t, float x, float y, float z) { float4 v = __ftexfetch(t, make_float4(x, y, z, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3D(texture t, float x, float y, float z) { float4 v = __ftexfetch(t, make_float4(x, y, z, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3D(texture t, float x, float y, float z) { float4 v = __ftexfetch(t, make_float4(x, y, z, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3D(texture t, float x, float y, float z) { float4 v = __ftexfetch(t, make_float4(x, y, z, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3D(texture t, float x, float y, float z) { int4 v = __itexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3D(texture t, float x, float y, float z) { uint4 v = __utexfetch(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 3059 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemap(texture t, float x, float y, float z) { float4 v = __ftexfetchc(t, make_float4(x, y, z, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemap(texture t, float x, float y, float z) { float4 v = __ftexfetchc(t, make_float4(x, y, z, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemap(texture t, float x, float y, float z) { float4 v = __ftexfetchc(t, make_float4(x, y, z, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemap(texture t, float x, float y, float z) { float4 v = __ftexfetchc(t, make_float4(x, y, z, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemap(texture t, float x, float y, float z) { int4 v = __itexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemap(texture t, float x, float y, float z) { uint4 v = __utexfetchc(t, make_float4(x, y, z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); return make_uint4(v.x, v.y, v.z, v.w); } # 3508 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayered(texture t, float x, float y, float z, int layer) { float4 v = __ftexfetchlc(t, make_float4(x, y, z, 0), layer); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayered(texture t, float x, float y, float z, int layer) { float4 v = __ftexfetchlc(t, make_float4(x, y, z, 0), layer); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayered(texture t, float x, float y, float z, int layer) { float4 v = __ftexfetchlc(t, make_float4(x, y, z, 0), layer); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayered(texture t, float x, float y, float z, int layer) { float4 v = __ftexfetchlc(t, make_float4(x, y, z, 0), layer); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayered(texture t, float x, float y, float z, int layer) { int4 v = __itexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayered(texture t, float x, float y, float z, int layer) { uint4 v = __utexfetchlc(t, make_float4(x, y, z, 0), layer); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } # 3785 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itex2Dgather(texture t, float2 i, int c = comp); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utex2Dgather(texture t, float2 i, int c = comp); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftex2Dgather(texture t, float2 i, int c = comp); # 3807 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { int4 v = __itex2Dgather<3>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); } else if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_char4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { uint4 v = __utex2Dgather<3>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); } else if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_uchar4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { int4 v = __itex2Dgather<3>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); } else if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_short4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { uint4 v = __utex2Dgather<3>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); } else if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_ushort4(v.x, v.y, v.z, v.w); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return v; } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return v; } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return v; } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return v; } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return v; } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return v; } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { int4 v = __itex2Dgather<3>(t, make_float2(x, y)); return v; } else if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return v; } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return v; } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { uint4 v = __utex2Dgather<3>(t, make_float2(x, y)); return v; } else if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return v; } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return v; } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { float4 v = __ftex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { float4 v = __ftex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { float4 v = __ftex2Dgather<1>(t, make_float2(x, y)); return v; } else { float4 v = __ftex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { float4 v = __ftex2Dgather<2>(t, make_float2(x, y)); return v; } else if (comp == 1) { float4 v = __ftex2Dgather<1>(t, make_float2(x, y)); return v; } else { float4 v = __ftex2Dgather<0>(t, make_float2(x, y)); return v; }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { float4 v = __ftex2Dgather<3>(t, make_float2(x, y)); return v; } else if (comp == 2) { float4 v = __ftex2Dgather<2>(t, make_float2(x, y)); return v; } else if (comp == 1) { float4 v = __ftex2Dgather<1>(t, make_float2(x, y)); return v; } else { float4 v = __ftex2Dgather<0>(t, make_float2(x, y)); return v; }; } # 3994 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { int4 v = __itex2Dgather<3>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { uint4 v = __utex2Dgather<3>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { int4 v = __itex2Dgather<3>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 2) { int4 v = __itex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { int4 v = __itex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { int4 v = __itex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2Dgather(texture t, float x, float y, int comp = 0) { if (comp == 3) { uint4 v = __utex2Dgather<3>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 2) { uint4 v = __utex2Dgather<2>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else if (comp == 1) { uint4 v = __utex2Dgather<1>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); } else { uint4 v = __utex2Dgather<0>(t, make_float2(x, y)); return make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); }; } template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchlod(texture t, float4 i, float level, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchlod(texture t, float4 i, float level, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchlod(texture t, float4 i, float level, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchlodc(texture t, float4 i, float level); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchlodc(texture t, float4 i, float level); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchlodc(texture t, float4 i, float level); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchlodl(texture t, float4 i, int l, float level, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchlodl(texture t, float4 i, int l, float level, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchlodl(texture t, float4 i, int l, float level, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchlodlc(texture t, float4 i, int l, float level); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchlodlc(texture t, float4 i, int l, float level); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchlodlc(texture t, float4 i, int l, float level); static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_uint4(v.x, v.y, v.z, v.w); } # 4393 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLod(texture t, float x, float level) { float4 v = __ftexfetchlod(t, make_float4(x, 0, 0, 0), level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLod(texture t, float x, float level) { float4 v = __ftexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLod(texture t, float x, float level) { float4 v = __ftexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLod(texture t, float x, float level) { float4 v = __ftexfetchlod(t, make_float4(x, 0, 0, 0), level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLod(texture t, float x, float level) { int4 v = __itexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLod(texture t, float x, float level) { uint4 v = __utexfetchlod(t, make_float4(x, 0, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); return make_uint4(v.x, v.y, v.z, v.w); } # 4842 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLod(texture t, float x, float y, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, 0, 0), level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLod(texture t, float x, float y, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, 0, 0), level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLod(texture t, float x, float y, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, 0, 0), level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLod(texture t, float x, float y, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, 0, 0), level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLod(texture t, float x, float y, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLod(texture t, float x, float y, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, 0, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_uint4(v.x, v.y, v.z, v.w); } # 5291 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredLod(texture t, float x, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredLod(texture t, float x, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredLod(texture t, float x, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredLod(texture t, float x, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredLod(texture t, float x, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredLod(texture t, float x, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, 0, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_uint4(v.x, v.y, v.z, v.w); } # 5740 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredLod(texture t, float x, float y, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { float4 v = __ftexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { int4 v = __itexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredLod(texture t, float x, float y, int layer, float level) { uint4 v = __utexfetchlodl(t, make_float4(x, y, 0, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); return make_uint4(v.x, v.y, v.z, v.w); } # 6189 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, z, 0), level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, z, 0), level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, z, 0), level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlod(t, make_float4(x, y, z, 0), level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlod(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); return make_uint4(v.x, v.y, v.z, v.w); } # 6638 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlodc(t, make_float4(x, y, z, 0), level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlodc(t, make_float4(x, y, z, 0), level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlodc(t, make_float4(x, y, z, 0), level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLod(texture t, float x, float y, float z, float level) { float4 v = __ftexfetchlodc(t, make_float4(x, y, z, 0), level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLod(texture t, float x, float y, float z, float level) { int4 v = __itexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLod(texture t, float x, float y, float z, float level) { uint4 v = __utexfetchlodc(t, make_float4(x, y, z, 0), level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_uint4(v.x, v.y, v.z, v.w); } # 7087 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { float4 v = __ftexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { float4 v = __ftexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { float4 v = __ftexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { float4 v = __ftexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { int4 v = __itexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 texCubemapLayeredLod(texture t, float x, float y, float z, int layer, float level) { uint4 v = __utexfetchlodlc(t, make_float4(x, y, z, 0), layer, level); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchgrad(texture t, float4 i, float4 dPdx, float4 dPdy, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchgrad(texture t, float4 i, float4 dPdx, float4 dPdy, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchgrad(texture t, float4 i, float4 dPdx, float4 dPdy, int d = texType); template extern __attribute__((device)) __attribute__((device_builtin)) uint4 __utexfetchgradl(texture t, float4 i, int l, float4 dPdx, float4 dPdy, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) int4 __itexfetchgradl(texture t, float4 i, int l, float4 dPdx, float4 dPdy, int d = (texType & 0xF)); template extern __attribute__((device)) __attribute__((device_builtin)) float4 __ftexfetchgradl(texture t, float4 i, int l, float4 dPdx, float4 dPdy, int d = (texType & 0xF)); static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 7550 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DGrad(texture t, float x, float dPdx, float dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DGrad(texture t, float x, float dPdx, float dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, 0, 0, 0), make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 7999 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DGrad(texture t, float x, float y, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, 0, 0), make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 8448 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex1DLayeredGrad(texture t, float x, int layer, float dPdx, float dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, 0, 0, 0), layer, make_float4(dPdx, 0, 0, 0), make_float4(dPdy, 0, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 8897 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 v = __ftexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 v = __itexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex2DLayeredGrad(texture t, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 v = __utexfetchgradl(t, make_float4(x, y, 0, 0), layer, make_float4(dPdx.x, dPdx.y, 0, 0), make_float4(dPdy.x, dPdy.y, 0, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) signed char tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (signed char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned char tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (unsigned char)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) char1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_char1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_uchar1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_char2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_uchar2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) char4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_char4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uchar4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_uchar4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned short tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (unsigned short)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) short1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_short1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_ushort1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_short2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_ushort2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) short4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_short4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) ushort4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_ushort4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) unsigned int tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return (unsigned int)v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) int1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_int1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_uint1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_int2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_uint2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) int4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_int4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) uint4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_uint4(v.x, v.y, v.z, v.w); } # 9346 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_fetch_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return v.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_float1(v.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_float2(v.x, v.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 v = __ftexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); return make_float4(v.x, v.y, v.z, v.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return w.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float1 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float1(w.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float2 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float2(w.x, w.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 v = __itexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) float4 tex3DGrad(texture t, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 v = __utexfetchgrad(t, make_float4(x, y, z, 0), make_float4(dPdx.x, dPdx.y, dPdx.z, 0), make_float4(dPdy.x, dPdy.y, dPdy.z, 0)); float4 w = make_float4(__int_as_float(v.x), __int_as_float(v.y), __int_as_float(v.z), __int_as_float(v.w)); return make_float4(w.x, w.y, w.z, w.w); } # 9417 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" 1 # 59 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" 2 # 70 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(char *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(signed char *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(char1 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(char2 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(char4 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(unsigned char *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(uchar1 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(uchar2 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(uchar4 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(short *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(short1 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(short2 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(short4 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(unsigned short *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(ushort1 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(ushort2 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(ushort4 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(int *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(int1 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(int2 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(int4 *retVal, cudaTextureObject_t texObject, int x) { int4 tmp; asm volatile ("tex.1d.v4.s32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(unsigned int *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(uint1 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(uint2 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(uint4 *retVal, cudaTextureObject_t texObject, int x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 334 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(float *retVal, cudaTextureObject_t texObject, int x) { float4 tmp; asm volatile ("tex.1d.v4.f32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(x)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(float1 *retVal, cudaTextureObject_t texObject, int x) { float4 tmp; asm volatile ("tex.1d.v4.f32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(float2 *retVal, cudaTextureObject_t texObject, int x) { float4 tmp; asm volatile ("tex.1d.v4.f32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1Dfetch(float4 *retVal, cudaTextureObject_t texObject, int x) { float4 tmp; asm volatile ("tex.1d.v4.f32.s32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(x)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1Dfetch(cudaTextureObject_t texObject, int x) { T ret; tex1Dfetch(&ret, texObject, x); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(char *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(signed char *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(char1 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(char2 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(char4 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(unsigned char *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(uchar1 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(uchar2 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(uchar4 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(short *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(short1 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(short2 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(short4 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(unsigned short *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(ushort1 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(ushort2 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(ushort4 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(int *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(int1 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(int2 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(int4 *retVal, cudaTextureObject_t texObject, float x) { int4 tmp; asm volatile ("tex.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(unsigned int *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(uint1 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(uint2 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(uint4 *retVal, cudaTextureObject_t texObject, float x) { uint4 tmp; asm volatile ("tex.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 646 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(float *retVal, cudaTextureObject_t texObject, float x) { float4 tmp; asm volatile ("tex.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(float1 *retVal, cudaTextureObject_t texObject, float x) { float4 tmp; asm volatile ("tex.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(float2 *retVal, cudaTextureObject_t texObject, float x) { float4 tmp; asm volatile ("tex.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1D(float4 *retVal, cudaTextureObject_t texObject, float x) { float4 tmp; asm volatile ("tex.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1D(cudaTextureObject_t texObject, float x) { T ret; tex1D(&ret, texObject, x); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(char *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(signed char *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(char1 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(char2 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(char4 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(short *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(short1 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(short2 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(short4 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(int *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(int1 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(int2 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(int4 *retVal, cudaTextureObject_t texObject, float x, float y) { int4 tmp; asm volatile ("tex.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(uint1 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(uint2 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(uint4 *retVal, cudaTextureObject_t texObject, float x, float y) { uint4 tmp; asm volatile ("tex.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 958 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(float *retVal, cudaTextureObject_t texObject, float x, float y) { float4 tmp; asm volatile ("tex.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(float1 *retVal, cudaTextureObject_t texObject, float x, float y) { float4 tmp; asm volatile ("tex.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(float2 *retVal, cudaTextureObject_t texObject, float x, float y) { float4 tmp; asm volatile ("tex.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2D(float4 *retVal, cudaTextureObject_t texObject, float x, float y) { float4 tmp; asm volatile ("tex.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2D(cudaTextureObject_t texObject, float x, float y) { T ret; tex2D(&ret, texObject, x, y); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(char *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(short *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(int *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 1270 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(float *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3D(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex3D(cudaTextureObject_t texObject, float x, float y, float z) { T ret; tex3D(&ret, texObject, x, y, z); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(char *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(signed char *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(char1 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(char2 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(char4 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(unsigned char *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(uchar1 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(uchar2 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(uchar4 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(short *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(short1 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(short2 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(short4 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(unsigned short *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(ushort1 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(ushort2 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(ushort4 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(int *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(int1 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(int2 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(int4 *retVal, cudaTextureObject_t texObject, float x, int layer) { int4 tmp; asm volatile ("tex.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(unsigned int *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(uint1 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(uint2 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(uint4 *retVal, cudaTextureObject_t texObject, float x, int layer) { uint4 tmp; asm volatile ("tex.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 1582 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(float *retVal, cudaTextureObject_t texObject, float x, int layer) { float4 tmp; asm volatile ("tex.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(float1 *retVal, cudaTextureObject_t texObject, float x, int layer) { float4 tmp; asm volatile ("tex.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(float2 *retVal, cudaTextureObject_t texObject, float x, int layer) { float4 tmp; asm volatile ("tex.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayered(float4 *retVal, cudaTextureObject_t texObject, float x, int layer) { float4 tmp; asm volatile ("tex.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1DLayered(cudaTextureObject_t texObject, float x, int layer) { T ret; tex1DLayered(&ret, texObject, x, layer); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(char *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(signed char *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(char1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(char2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(char4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(short *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(short1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(short2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(short4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(int *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(int1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(int2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(int4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { int4 tmp; asm volatile ("tex.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { uint4 tmp; asm volatile ("tex.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 1894 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(float *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { float4 tmp; asm volatile ("tex.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(float1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { float4 tmp; asm volatile ("tex.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(float2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { float4 tmp; asm volatile ("tex.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayered(float4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer) { float4 tmp; asm volatile ("tex.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2DLayered(cudaTextureObject_t texObject, float x, float y, int layer) { T ret; tex2DLayered(&ret, texObject, x, y, layer); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(char *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(short *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(int *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { int4 tmp; asm volatile ("tex.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { uint4 tmp; asm volatile ("tex.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 2206 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(float *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemap(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z) { float4 tmp; asm volatile ("tex.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T texCubemap(cudaTextureObject_t texObject, float x, float y, float z) { T ret; texCubemap(&ret, texObject, x, y, z); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(char *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(short *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(int *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { int4 tmp; asm volatile ("tex.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { uint4 tmp; asm volatile ("tex.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 2518 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(float *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { float4 tmp; asm volatile ("tex.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { float4 tmp; asm volatile ("tex.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { float4 tmp; asm volatile ("tex.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayered(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer) { float4 tmp; asm volatile ("tex.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T texCubemapLayered(cudaTextureObject_t texObject, float x, float y, float z, int layer) { T ret; texCubemapLayered(&ret, texObject, x, y, z, layer); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(char *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(signed char *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(char1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(char2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(char4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(short *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(short1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(short2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(short4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(int *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(int1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(int2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(int4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(long *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (long)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(long1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_long1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(long2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_long2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(long4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { int4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_long4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(unsigned long *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (unsigned long)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(ulong1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_ulong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(ulong2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_ulong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(ulong4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { uint4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_ulong4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(float *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { float4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(float1 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { float4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(float2 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { float4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2Dgather(float4 *retVal, cudaTextureObject_t texObject, float x, float y, int comp = 0) { float4 tmp; if (comp == 0) { asm volatile ("tld4.r.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 1) { asm volatile ("tld4.g.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 2) { asm volatile ("tld4.b.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } else if (comp == 3) { asm volatile ("tld4.a.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2Dgather(cudaTextureObject_t to, float x, float y, int comp = 0) { T ret; tex2Dgather(&ret, to, x, y, comp); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(char *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(signed char *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(char1 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(char2 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(char4 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(short *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(short1 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(short2 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(short4 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(int *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(int1 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(int2 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(int4 *retVal, cudaTextureObject_t texObject, float x, float level) { int4 tmp; asm volatile ("tex.level.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(uint1 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(uint2 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(uint4 *retVal, cudaTextureObject_t texObject, float x, float level) { uint4 tmp; asm volatile ("tex.level.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 3540 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(float *retVal, cudaTextureObject_t texObject, float x, float level) { float4 tmp; asm volatile ("tex.level.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(float1 *retVal, cudaTextureObject_t texObject, float x, float level) { float4 tmp; asm volatile ("tex.level.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(float2 *retVal, cudaTextureObject_t texObject, float x, float level) { float4 tmp; asm volatile ("tex.level.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLod(float4 *retVal, cudaTextureObject_t texObject, float x, float level) { float4 tmp; asm volatile ("tex.level.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], %6;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1DLod(cudaTextureObject_t texObject, float x, float level) { T ret; tex1DLod(&ret, texObject, x, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(char *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(short *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(int *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { int4 tmp; asm volatile ("tex.level.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { uint4 tmp; asm volatile ("tex.level.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 3852 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(float *retVal, cudaTextureObject_t texObject, float x, float y, float level) { float4 tmp; asm volatile ("tex.level.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { float4 tmp; asm volatile ("tex.level.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { float4 tmp; asm volatile ("tex.level.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLod(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float level) { float4 tmp; asm volatile ("tex.level.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2DLod(cudaTextureObject_t texObject, float x, float y, float level) { T ret; tex2DLod(&ret, texObject, x, y, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(short *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(int *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 4164 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(float *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DLod(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex3DLod(cudaTextureObject_t texObject, float x, float y, float z, float level) { T ret; tex3DLod(&ret, texObject, x, y, z, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(char *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(signed char *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(char1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(char2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(char4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(short *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(short1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(short2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(short4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(int *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(int1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(int2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(int4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { int4 tmp; asm volatile ("tex.level.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(uint1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(uint2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(uint4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 4476 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(float *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { float4 tmp; asm volatile ("tex.level.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(float1 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { float4 tmp; asm volatile ("tex.level.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(float2 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { float4 tmp; asm volatile ("tex.level.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredLod(float4 *retVal, cudaTextureObject_t texObject, float x, int layer, float level) { float4 tmp; asm volatile ("tex.level.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], %7;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1DLayeredLod(cudaTextureObject_t texObject, float x, int layer, float level) { T ret; tex1DLayeredLod(&ret, texObject, x, layer, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(char *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(signed char *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(char1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(char2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(char4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(short *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(short1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(short2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(short4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(int *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(int1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(int2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(int4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { int4 tmp; asm volatile ("tex.level.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { uint4 tmp; asm volatile ("tex.level.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 4788 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(float *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { float4 tmp; asm volatile ("tex.level.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(float1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { float4 tmp; asm volatile ("tex.level.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(float2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { float4 tmp; asm volatile ("tex.level.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredLod(float4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float level) { float4 tmp; asm volatile ("tex.level.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2DLayeredLod(cudaTextureObject_t texObject, float x, float y, int layer, float level) { T ret; tex2DLayeredLod(&ret, texObject, x, y, layer, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(short *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(int *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { int4 tmp; asm volatile ("tex.level.cube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { uint4 tmp; asm volatile ("tex.level.cube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 5100 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(float *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLod(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float level) { float4 tmp; asm volatile ("tex.level.cube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], %8;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T texCubemapLod(cudaTextureObject_t texObject, float x, float y, float z, float level) { T ret; texCubemapLod(&ret, texObject, x, y, z, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(char *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(short *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(int *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { int4 tmp; asm volatile ("tex.level.acube.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { uint4 tmp; asm volatile ("tex.level.acube.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 5412 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(float *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { float4 tmp; asm volatile ("tex.level.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { float4 tmp; asm volatile ("tex.level.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { float4 tmp; asm volatile ("tex.level.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void texCubemapLayeredLod(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { float4 tmp; asm volatile ("tex.level.acube.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %8}], %9;" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(z), "f"(level)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T texCubemapLayeredLod(cudaTextureObject_t texObject, float x, float y, float z, int layer, float level) { T ret; texCubemapLayeredLod(&ret, texObject, x, y, z, layer, level); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(char *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(signed char *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(char1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(char2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(char4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(unsigned char *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(uchar1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(uchar2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(uchar4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(short *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(short1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(short2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(short4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(unsigned short *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(ushort1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(ushort2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(ushort4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(int *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(int1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(int2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(int4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(unsigned int *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(uint1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(uint2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(uint4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 5724 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(float *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(float1 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(float2 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DGrad(float4 *retVal, cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5}], {%6}, {%7};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1DGrad(cudaTextureObject_t texObject, float x, float dPdx, float dPdy) { T ret; tex1DGrad(&ret, texObject, x, dPdx, dPdy); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(char *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(short *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(int *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 6036 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(float *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DGrad(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7, %8}, {%9, %10};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2DGrad(cudaTextureObject_t texObject, float x, float y, float2 dPdx, float2 dPdy) { T ret; tex2DGrad(&ret, texObject, x, y, dPdx, dPdy); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(signed char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(char1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(char2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(char4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(short *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(short1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(short2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(short4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(int *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(int1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(int2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(int4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { int4 tmp; asm volatile ("tex.grad.3d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { uint4 tmp; asm volatile ("tex.grad.3d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 6348 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(float *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 tmp; asm volatile ("tex.grad.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(float1 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 tmp; asm volatile ("tex.grad.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(float2 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 tmp; asm volatile ("tex.grad.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex3DGrad(float4 *retVal, cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { float4 tmp; asm volatile ("tex.grad.3d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9, %10, %10}, {%11, %12, %13, %13};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "f"(x), "f"(y), "f"(z), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdx.z), "f"(dPdy.x), "f"(dPdy.y), "f"(dPdy.z)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex3DGrad(cudaTextureObject_t texObject, float x, float y, float z, float4 dPdx, float4 dPdy) { T ret; tex3DGrad(&ret, texObject, x, y, z, dPdx, dPdy); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(char *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(signed char *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(char1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(char2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(char4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(unsigned char *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(uchar1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(uchar2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(uchar4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(short *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(short1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(short2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(short4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(unsigned short *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(ushort1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(ushort2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(ushort4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(int *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(int1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(int2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(int4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { int4 tmp; asm volatile ("tex.grad.a1d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(unsigned int *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(uint1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(uint2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(uint4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { uint4 tmp; asm volatile ("tex.grad.a1d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 6660 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(float *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(float1 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(float2 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex1DLayeredGrad(float4 *retVal, cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { float4 tmp; asm volatile ("tex.grad.a1d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6}], {%7}, {%8};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(dPdx), "f"(dPdy)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex1DLayeredGrad(cudaTextureObject_t texObject, float x, int layer, float dPdx, float dPdy) { T ret; tex1DLayeredGrad(&ret, texObject, x, layer, dPdx, dPdy); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(char *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (char)tmp.x; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(signed char *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (signed char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(char1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(char2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(char4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(unsigned char *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (unsigned char)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(uchar1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(uchar2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(uchar4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(short *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(short1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(short2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(short4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(unsigned short *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (unsigned short)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(ushort1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(ushort2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(ushort4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(int *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(int1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(int2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(int4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { int4 tmp; asm volatile ("tex.grad.a2d.v4.s32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(unsigned int *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (unsigned int)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(uint1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(uint2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(uint4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { uint4 tmp; asm volatile ("tex.grad.a2d.v4.u32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } # 6972 "/Developer/NVIDIA/CUDA-6.5/bin/../include/texture_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(float *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = (float)(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(float1 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(float2 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void tex2DLayeredGrad(float4 *retVal, cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { float4 tmp; asm volatile ("tex.grad.a2d.v4.f32.f32 {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}], {%8, %9}, {%10, %11};" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(texObject), "r"(layer), "f"(x), "f"(y), "f"(dPdx.x), "f"(dPdx.y), "f"(dPdy.x), "f"(dPdy.y)); *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T tex2DLayeredGrad(cudaTextureObject_t texObject, float x, float y, int layer, float2 dPdx, float2 dPdy) { T ret; tex2DLayeredGrad(&ret, texObject, x, y, layer, dPdx, dPdy); return ret; } # 9418 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_indirect_functions.h" 1 # 59 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_indirect_functions.h" # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/builtin_types.h" 1 # 60 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_indirect_functions.h" 2 # 70 "/Developer/NVIDIA/CUDA-6.5/bin/../include/surface_indirect_functions.h" static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(char *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b8.trap {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b8.clamp {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b8.zero {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b8.trap {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b8.clamp {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b8.zero {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b8.trap {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b8.clamp {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b8.zero {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b8.trap {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b8.clamp {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b8.zero {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b8.trap {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b8.clamp {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b8.zero {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(short *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b16.trap {%0}, [%1, {%2}];" : "=h"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b16.clamp {%0}, [%1, {%2}];" : "=h"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b16.zero {%0}, [%1, {%2}];" : "=h"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b16.trap {%0}, [%1, {%2}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b16.clamp {%0}, [%1, {%2}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b16.zero {%0}, [%1, {%2}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b16.trap {%0}, [%1, {%2}];" : "=h"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b16.clamp {%0}, [%1, {%2}];" : "=h"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b16.zero {%0}, [%1, {%2}];" : "=h"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b16.trap {%0}, [%1, {%2}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b16.clamp {%0}, [%1, {%2}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b16.zero {%0}, [%1, {%2}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(int *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b32.trap {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b32.clamp {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b32.zero {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b32.trap {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b32.clamp {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b32.zero {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b32.trap {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b32.clamp {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b32.zero {%0}, [%1, {%2}];" : "=r"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b32.trap {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b32.clamp {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b32.zero {%0}, [%1, {%2}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(long long *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b64.trap {%0}, [%1, {%2}];" : "=l"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b64.clamp {%0}, [%1, {%2}];" : "=l"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b64.zero {%0}, [%1, {%2}];" : "=l"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b64.trap {%0}, [%1, {%2}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b64.clamp {%0}, [%1, {%2}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b64.zero {%0}, [%1, {%2}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b64.trap {%0}, [%1, {%2}];" : "=l"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b64.clamp {%0}, [%1, {%2}];" : "=l"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b64.zero {%0}, [%1, {%2}];" : "=l"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b64.trap {%0}, [%1, {%2}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b64.clamp {%0}, [%1, {%2}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b64.zero {%0}, [%1, {%2}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(float *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b32.trap {%0}, [%1, {%2}];" : "=f"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b32.clamp {%0}, [%1, {%2}];" : "=f"(tmp) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b32.zero {%0}, [%1, {%2}];" : "=f"(tmp) : "l"(surfObject), "r"(x)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.b32.trap {%0}, [%1, {%2}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.b32.clamp {%0}, [%1, {%2}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.b32.zero {%0}, [%1, {%2}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b8.trap {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b8.clamp {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b8.zero {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b8.trap {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b8.clamp {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b8.zero {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b16.trap {%0, %1}, [%2, {%3}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b16.clamp {%0, %1}, [%2, {%3}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b16.zero {%0, %1}, [%2, {%3}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b16.trap {%0, %1}, [%2, {%3}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b16.clamp {%0, %1}, [%2, {%3}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b16.zero {%0, %1}, [%2, {%3}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b32.trap {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b32.clamp {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b32.zero {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b32.trap {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b32.clamp {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b32.zero {%0, %1}, [%2, {%3}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b64.trap {%0, %1}, [%2, {%3}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b64.clamp {%0, %1}, [%2, {%3}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b64.zero {%0, %1}, [%2, {%3}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b64.trap {%0, %1}, [%2, {%3}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b64.clamp {%0, %1}, [%2, {%3}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b64.zero {%0, %1}, [%2, {%3}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v2.b32.trap {%0, %1}, [%2, {%3}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v2.b32.clamp {%0, %1}, [%2, {%3}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v2.b32.zero {%0, %1}, [%2, {%3}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.1d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.1d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.1d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf1Dread(cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surf1Dread(&ret, surfObject, x, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(char *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(short *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(int *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(float *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b32.trap {%0}, [%1, {%2, %3}];" : "=f"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b32.clamp {%0}, [%1, {%2, %3}];" : "=f"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b32.zero {%0}, [%1, {%2, %3}];" : "=f"(tmp) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.b32.trap {%0}, [%1, {%2, %3}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.b32.clamp {%0}, [%1, {%2, %3}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.b32.zero {%0}, [%1, {%2, %3}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b8.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b8.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b8.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b8.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b16.trap {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b16.zero {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b16.trap {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b16.zero {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b32.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b32.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b32.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b32.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b64.trap {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b64.zero {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b64.trap {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b64.zero {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v2.b32.trap {%0, %1}, [%2, {%3, %4}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v2.b32.zero {%0, %1}, [%2, {%3, %4}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x), "r"(y)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf2Dread(cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surf2Dread(&ret, surfObject, x, y, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(float *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.3d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.3d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.3d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(x), "r"(y), "r"(z)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf3Dread(cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surf3Dread(&ret, surfObject, x, y, z, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(char *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b8.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b8.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b8.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(short *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b16.trap {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b16.clamp {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b16.zero {%0}, [%1, {%2, %3}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(int *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b32.trap {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b32.clamp {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b32.zero {%0}, [%1, {%2, %3}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(long long *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b64.trap {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b64.clamp {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b64.zero {%0}, [%1, {%2, %3}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(float *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b32.trap {%0}, [%1, {%2, %3}];" : "=f"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b32.clamp {%0}, [%1, {%2, %3}];" : "=f"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b32.zero {%0}, [%1, {%2, %3}];" : "=f"(tmp) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.b32.trap {%0}, [%1, {%2, %3}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.b32.clamp {%0}, [%1, {%2, %3}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.b32.zero {%0}, [%1, {%2, %3}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b8.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b8.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b8.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b8.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b8.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b8.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b16.trap {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b16.clamp {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b16.zero {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b16.trap {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b16.clamp {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b16.zero {%0, %1}, [%2, {%3, %4}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b32.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b32.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b32.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b32.trap {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b32.clamp {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b32.zero {%0, %1}, [%2, {%3, %4}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b64.trap {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b64.clamp {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b64.zero {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b64.trap {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b64.clamp {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b64.zero {%0, %1}, [%2, {%3, %4}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v2.b32.trap {%0, %1}, [%2, {%3, %4}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v2.b32.clamp {%0, %1}, [%2, {%3, %4}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v2.b32.zero {%0, %1}, [%2, {%3, %4}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a1d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a1d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a1d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf1DLayeredread(cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surf1DLayeredread(&ret, surfObject, x, layer, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(float *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layer), "r"(x), "r"(y)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surf2DLayeredread(cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surf2DLayeredread(&ret, surfObject, x, y, layer, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(float *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(face), "r"(x), "r"(y)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surfCubemapread(cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surfCubemapread(&ret, surfObject, face, x, y, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(signed char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (signed char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(char1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_char1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(unsigned char *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (unsigned char)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(uchar1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b8.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b8.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b8.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_uchar1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(short1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_short1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(unsigned short *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned short tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (unsigned short)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(ushort1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b16.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b16.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b16.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=h"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_ushort1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(int1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_int1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(unsigned int *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned int tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (unsigned int)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(uint1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=r"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_uint1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(longlong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_longlong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(unsigned long long *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { unsigned long long tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (unsigned long long)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(ulonglong1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b64.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b64.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b64.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=l"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_ulonglong1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(float *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = (float)(tmp); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(float1 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float1 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.b32.trap {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.b32.clamp {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.b32.zero {%0}, [%1, {%2, %3, %4, %4}];" : "=f"(tmp.x) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_float1(tmp.x); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(char2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_char2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(uchar2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b8.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b8.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b8.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_uchar2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(short2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_short2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(ushort2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b16.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b16.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b16.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=h"(tmp.x), "=h"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_ushort2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(int2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_int2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(uint2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=r"(tmp.x), "=r"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_uint2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(longlong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { longlong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_longlong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(ulonglong2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ulonglong2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b64.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b64.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b64.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=l"(tmp.x), "=l"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_ulonglong2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(float2 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float2 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v2.b32.trap {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v2.b32.clamp {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v2.b32.zero {%0, %1}, [%2, {%3, %4, %5, %5}];" : "=f"(tmp.x), "=f"(tmp.y) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_float2(tmp.x, tmp.y); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(char4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_char4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(uchar4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b8.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b8.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b8.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_uchar4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(short4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { short4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_short4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(ushort4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { ushort4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b16.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b16.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b16.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=h"(tmp.x), "=h"(tmp.y), "=h"(tmp.z), "=h"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_ushort4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(int4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { int4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_int4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(uint4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { uint4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=r"(tmp.x), "=r"(tmp.y), "=r"(tmp.z), "=r"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_uint4(tmp.x, tmp.y, tmp.z, tmp.w); } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredread(float4 *retVal, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { float4 tmp; if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("suld.b.a2d.v4.b32.trap {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("suld.b.a2d.v4.b32.clamp {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("suld.b.a2d.v4.b32.zero {%0, %1, %2, %3}, [%4, {%5, %6, %7, %7}];" : "=f"(tmp.x), "=f"(tmp.y), "=f"(tmp.z), "=f"(tmp.w) : "l"(surfObject), "r"(layerface), "r"(x), "r"(y)); } *retVal = make_float4(tmp.x, tmp.y, tmp.z, tmp.w); } template static __inline__ __attribute__((always_inline)) __attribute__((device)) T surfCubemapLayeredread(cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { T ret; surfCubemapLayeredread(&ret, surfObject, x, y, z, layerface, boundaryMode); return ret; } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b8.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b8.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b8.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(signed char data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b8.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b8.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b8.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b8.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b8.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b8.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b8.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b8.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b8.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b8.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b8.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b8.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b16.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b16.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b16.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b16.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b16.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b16.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b16.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b16.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b16.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b16.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b16.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b16.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b32.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b32.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b32.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b32.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b32.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b32.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b32.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b32.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b32.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b32.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b32.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b32.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(long long data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b64.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b64.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b64.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b64.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b64.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b64.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b64.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b64.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b64.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b64.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b64.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b64.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b32.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b32.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b32.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float1 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.b32.trap [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.b32.clamp [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.b32.zero [%0, {%1}], {%2};" : : "l"(surfObject), "r"(x), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b8.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b8.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b8.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b8.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b8.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b8.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b16.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b16.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b16.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b16.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b16.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b16.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b32.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b32.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b32.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b32.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b32.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b32.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b64.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b64.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b64.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b64.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b64.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b64.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float2 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v2.b32.trap [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v2.b32.clamp [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v2.b32.zero [%0, {%1}], {%2, %3};" : : "l"(surfObject), "r"(x), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(char4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b8.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b8.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b8.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b8.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b8.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b8.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(short4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b16.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b16.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b16.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b16.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b16.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b16.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(int4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b32.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b32.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b32.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b32.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b32.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b32.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1Dwrite(float4 data, cudaSurfaceObject_t surfObject, int x, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.1d.v4.b32.trap [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.1d.v4.b32.clamp [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.1d.v4.b32.zero [%0, {%1}], {%2, %3, %4, %5};" : : "l"(surfObject), "r"(x), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(signed char data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(long long data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float1 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b8.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b8.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b8.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b8.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b8.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b8.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b16.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b16.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b16.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b16.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b16.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b16.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b32.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b32.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b32.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b32.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b32.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b32.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b64.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b64.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b64.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b64.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b64.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b64.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float2 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v2.b32.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v2.b32.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v2.b32.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(char4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b8.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b8.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b8.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b8.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b8.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b8.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(short4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b16.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b16.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b16.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b16.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b16.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b16.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(int4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b32.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b32.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b32.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b32.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b32.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b32.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2Dwrite(float4 data, cudaSurfaceObject_t surfObject, int x, int y, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.2d.v4.b32.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.2d.v4.b32.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.2d.v4.b32.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(signed char data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(long long data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(char4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(short4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(int4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf3Dwrite(float4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.3d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.3d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.3d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(x), "r"(y), "r"(z), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(signed char data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b8.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b8.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b8.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b16.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b16.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b16.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(long long data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b64.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b64.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b64.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float1 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.b32.trap [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.b32.clamp [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.b32.zero [%0, {%1, %2}], {%3};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b8.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b8.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b8.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b8.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b8.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b8.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b16.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b16.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b16.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b16.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b16.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b16.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b32.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b32.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b32.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b32.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b32.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b32.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b64.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b64.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b64.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b64.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b64.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b64.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float2 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v2.b32.trap [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v2.b32.clamp [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v2.b32.zero [%0, {%1, %2}], {%3, %4};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(char4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b8.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b8.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b8.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b8.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b8.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b8.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(short4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b16.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b16.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b16.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b16.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b16.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b16.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(int4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b32.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b32.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b32.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b32.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b32.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b32.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf1DLayeredwrite(float4 data, cudaSurfaceObject_t surfObject, int x, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a1d.v4.b32.trap [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a1d.v4.b32.clamp [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a1d.v4.b32.zero [%0, {%1, %2}], {%3, %4, %5, %6};" : : "l"(surfObject), "r"(layer), "r"(x), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(signed char data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(long long data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float1 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float2 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(char4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(short4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(int4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surf2DLayeredwrite(float4 data, cudaSurfaceObject_t surfObject, int x, int y, int layer, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layer), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(signed char data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(long long data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float1 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float2 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(char4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(short4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(int4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapwrite(float4 data, cudaSurfaceObject_t surfObject, int x, int y, int face, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(face), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(signed char data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned char data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uchar1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b8.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b8.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b8.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned short data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ushort1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b16.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b16.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b16.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned int data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uint1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(long long data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(longlong1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(unsigned long long data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ulonglong1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b64.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b64.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b64.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float1 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.b32.trap [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.b32.clamp [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.b32.zero [%0, {%1, %2, %3, %3}], {%4};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uchar2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ushort2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uint2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(longlong2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ulonglong2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b64.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b64.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b64.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "l"(data.x), "l"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float2 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v2.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v2.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v2.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x), "f"(data.y)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(char4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((int)data.x), "r"((int)data.y), "r"((int)data.z), "r"((int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uchar4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b8.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b8.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b8.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"((unsigned int)data.x), "r"((unsigned int)data.y), "r"((unsigned int)data.z), "r"((unsigned int)data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(short4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(ushort4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b16.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b16.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b16.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "h"(data.x), "h"(data.y), "h"(data.z), "h"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(int4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(uint4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "r"(data.x), "r"(data.y), "r"(data.z), "r"(data.w)); } } static __inline__ __attribute__((always_inline)) __attribute__((device)) void surfCubemapLayeredwrite(float4 data, cudaSurfaceObject_t surfObject, int x, int y, int z, int layerface, cudaSurfaceBoundaryMode boundaryMode = cudaBoundaryModeTrap) { if (boundaryMode == cudaBoundaryModeTrap) { asm volatile ("sust.b.a2d.v4.b32.trap [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeClamp) { asm volatile ("sust.b.a2d.v4.b32.clamp [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } else if (boundaryMode == cudaBoundaryModeZero) { asm volatile ("sust.b.a2d.v4.b32.zero [%0, {%1, %2, %3, %3}], {%4, %5, %6, %7};" : : "l"(surfObject), "r"(layerface), "r"(x), "r"(y), "f"(data.x), "f"(data.y), "f"(data.z), "f"(data.w)); } } # 9419 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_functions.h" 2 # 80 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 1 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_launch_parameters.h" 1 # 63 "/Developer/NVIDIA/CUDA-6.5/bin/../include/device_launch_parameters.h" extern "C" { uint3 __attribute__((device_builtin)) extern const threadIdx; uint3 __attribute__((device_builtin)) extern const blockIdx; dim3 __attribute__((device_builtin)) extern const blockDim; dim3 __attribute__((device_builtin)) extern const gridDim; int __attribute__((device_builtin)) extern const warpSize; } # 81 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" 2 # 92 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" namespace { # 123 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaSetupArgument( T arg, size_t offset ) { return ::cudaSetupArgument((const void*)&arg, sizeof(T), offset); } # 162 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" static __inline__ __attribute__((host)) cudaError_t cudaEventCreate( cudaEvent_t *event, unsigned int flags ) { return ::cudaEventCreateWithFlags(event, flags); } # 225 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" __inline__ __attribute__((host)) cudaError_t cudaMallocHost( void **ptr, size_t size, unsigned int flags ) { return ::cudaHostAlloc(ptr, size, flags); } template __inline__ __attribute__((host)) cudaError_t cudaHostAlloc( T **ptr, size_t size, unsigned int flags ) { return ::cudaHostAlloc((void**)(void*)ptr, size, flags); } template __inline__ __attribute__((host)) cudaError_t cudaHostGetDevicePointer( T **pDevice, void *pHost, unsigned int flags ) { return ::cudaHostGetDevicePointer((void**)(void*)pDevice, pHost, flags); } # 323 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaMallocManaged( T **devPtr, size_t size, unsigned int flags = 0x01 ) { return ::cudaMallocManaged((void**)(void*)devPtr, size, flags); } # 399 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaStreamAttachMemAsync( cudaStream_t stream, T *devPtr, size_t length = 0, unsigned int flags = 0x04 ) { return ::cudaStreamAttachMemAsync(stream, (void*)devPtr, length, flags); } template __inline__ __attribute__((host)) cudaError_t cudaMalloc( T **devPtr, size_t size ) { return ::cudaMalloc((void**)(void*)devPtr, size); } template __inline__ __attribute__((host)) cudaError_t cudaMallocHost( T **ptr, size_t size, unsigned int flags = 0 ) { return cudaMallocHost((void**)(void*)ptr, size, flags); } template __inline__ __attribute__((host)) cudaError_t cudaMallocPitch( T **devPtr, size_t *pitch, size_t width, size_t height ) { return ::cudaMallocPitch((void**)(void*)devPtr, pitch, width, height); } # 475 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaMemcpyToSymbol( const T &symbol, const void *src, size_t count, size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyHostToDevice ) { return ::cudaMemcpyToSymbol((const void*)&symbol, src, count, offset, kind); } # 527 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaMemcpyToSymbolAsync( const T &symbol, const void *src, size_t count, size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyHostToDevice, cudaStream_t stream = 0 ) { return ::cudaMemcpyToSymbolAsync((const void*)&symbol, src, count, offset, kind, stream); } # 573 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaMemcpyFromSymbol( void *dst, const T &symbol, size_t count, size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyDeviceToHost ) { return ::cudaMemcpyFromSymbol(dst, (const void*)&symbol, count, offset, kind); } # 625 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaMemcpyFromSymbolAsync( void *dst, const T &symbol, size_t count, size_t offset = 0, enum cudaMemcpyKind kind = cudaMemcpyDeviceToHost, cudaStream_t stream = 0 ) { return ::cudaMemcpyFromSymbolAsync(dst, (const void*)&symbol, count, offset, kind, stream); } # 658 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaGetSymbolAddress( void **devPtr, const T &symbol ) { return ::cudaGetSymbolAddress(devPtr, (const void*)&symbol); } # 687 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaGetSymbolSize( size_t *size, const T &symbol ) { return ::cudaGetSymbolSize(size, (const void*)&symbol); } # 730 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTexture( size_t *offset, const struct texture &tex, const void *devPtr, const struct cudaChannelFormatDesc &desc, size_t size = (2147483647 *2U +1U) ) { return ::cudaBindTexture(offset, &tex, devPtr, &desc, size); } # 775 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTexture( size_t *offset, const struct texture &tex, const void *devPtr, size_t size = (2147483647 *2U +1U) ) { return cudaBindTexture(offset, tex, devPtr, tex.channelDesc, size); } # 831 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTexture2D( size_t *offset, const struct texture &tex, const void *devPtr, const struct cudaChannelFormatDesc &desc, size_t width, size_t height, size_t pitch ) { return ::cudaBindTexture2D(offset, &tex, devPtr, &desc, width, height, pitch); } # 889 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTexture2D( size_t *offset, const struct texture &tex, const void *devPtr, size_t width, size_t height, size_t pitch ) { return ::cudaBindTexture2D(offset, &tex, devPtr, &tex.channelDesc, width, height, pitch); } # 931 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTextureToArray( const struct texture &tex, cudaArray_const_t array, const struct cudaChannelFormatDesc &desc ) { return ::cudaBindTextureToArray(&tex, array, &desc); } # 969 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTextureToArray( const struct texture &tex, cudaArray_const_t array ) { struct cudaChannelFormatDesc desc; cudaError_t err = ::cudaGetChannelDesc(&desc, array); return err == cudaSuccess ? cudaBindTextureToArray(tex, array, desc) : err; } # 1010 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTextureToMipmappedArray( const struct texture &tex, cudaMipmappedArray_const_t mipmappedArray, const struct cudaChannelFormatDesc &desc ) { return ::cudaBindTextureToMipmappedArray(&tex, mipmappedArray, &desc); } # 1048 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindTextureToMipmappedArray( const struct texture &tex, cudaMipmappedArray_const_t mipmappedArray ) { struct cudaChannelFormatDesc desc; cudaArray_t levelArray; cudaError_t err = ::cudaGetMipmappedArrayLevel(&levelArray, mipmappedArray, 0); if (err != cudaSuccess) { return err; } err = ::cudaGetChannelDesc(&desc, levelArray); return err == cudaSuccess ? cudaBindTextureToMipmappedArray(tex, mipmappedArray, desc) : err; } # 1087 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaUnbindTexture( const struct texture &tex ) { return ::cudaUnbindTexture(&tex); } # 1121 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaGetTextureAlignmentOffset( size_t *offset, const struct texture &tex ) { return ::cudaGetTextureAlignmentOffset(offset, &tex); } # 1174 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaFuncSetCacheConfig( T *func, enum cudaFuncCache cacheConfig ) { return ::cudaFuncSetCacheConfig((const void*)func, cacheConfig); } template __inline__ __attribute__((host)) cudaError_t cudaFuncSetSharedMemConfig( T *func, enum cudaSharedMemConfig config ) { return ::cudaFuncSetSharedMemConfig((const void*)func, config); } # 1216 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaOccupancyMaxActiveBlocksPerMultiprocessor( int *numBlocks, T func, int blockSize, size_t dynamicSMemSize) { return ::cudaOccupancyMaxActiveBlocksPerMultiprocessor(numBlocks, (const void*)func, blockSize, dynamicSMemSize); } class __cudaOccupancyB2DHelper { size_t n; public: inline __attribute__((host)) __cudaOccupancyB2DHelper(size_t n) : n(n) {} inline __attribute__((host)) size_t operator()(int) { return n; } }; # 1270 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaOccupancyMaxPotentialBlockSize( int *minGridSize, int *blockSize, T func, size_t dynamicSMemSize = 0, int blockSizeLimit = 0) { return cudaOccupancyMaxPotentialBlockSizeVariableSMem(minGridSize, blockSize, func, __cudaOccupancyB2DHelper(dynamicSMemSize), blockSizeLimit); } # 1309 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaOccupancyMaxPotentialBlockSizeVariableSMem( int *minGridSize, int *blockSize, T func, UnaryFunction blockSizeToDynamicSMemSize, int blockSizeLimit = 0) { cudaError_t status; int device; struct cudaFuncAttributes attr; int maxThreadsPerMultiProcessor; int warpSize; int devMaxThreadsPerBlock; int multiProcessorCount; int funcMaxThreadsPerBlock; int occupancyLimit; int granularity; int maxBlockSize = 0; int numBlocks = 0; int maxOccupancy = 0; int blockSizeToTryAligned; int blockSizeToTry; int blockSizeLimitAligned; int occupancyInBlocks; int occupancyInThreads; int dynamicSMemSize; if (!minGridSize || !blockSize || !func) { return cudaErrorInvalidValue; } status = ::cudaGetDevice(&device); if (status != cudaSuccess) { return status; } status = cudaDeviceGetAttribute( &maxThreadsPerMultiProcessor, cudaDevAttrMaxThreadsPerMultiProcessor, device); if (status != cudaSuccess) { return status; } status = cudaDeviceGetAttribute( &warpSize, cudaDevAttrWarpSize, device); if (status != cudaSuccess) { return status; } status = cudaDeviceGetAttribute( &devMaxThreadsPerBlock, cudaDevAttrMaxThreadsPerBlock, device); if (status != cudaSuccess) { return status; } status = cudaDeviceGetAttribute( &multiProcessorCount, cudaDevAttrMultiProcessorCount, device); if (status != cudaSuccess) { return status; } status = cudaFuncGetAttributes(&attr, func); if (status != cudaSuccess) { return status; } funcMaxThreadsPerBlock = attr.maxThreadsPerBlock; occupancyLimit = maxThreadsPerMultiProcessor; granularity = warpSize; if (blockSizeLimit == 0) { blockSizeLimit = devMaxThreadsPerBlock; } if (devMaxThreadsPerBlock < blockSizeLimit) { blockSizeLimit = devMaxThreadsPerBlock; } if (funcMaxThreadsPerBlock < blockSizeLimit) { blockSizeLimit = funcMaxThreadsPerBlock; } blockSizeLimitAligned = ((blockSizeLimit + (granularity - 1)) / granularity) * granularity; for (blockSizeToTryAligned = blockSizeLimitAligned; blockSizeToTryAligned > 0; blockSizeToTryAligned -= granularity) { if (blockSizeLimit < blockSizeToTryAligned) { blockSizeToTry = blockSizeLimit; } else { blockSizeToTry = blockSizeToTryAligned; } dynamicSMemSize = blockSizeToDynamicSMemSize(blockSizeToTry); status = cudaOccupancyMaxActiveBlocksPerMultiprocessor( &occupancyInBlocks, func, blockSizeToTry, dynamicSMemSize); if (status != cudaSuccess) { return status; } occupancyInThreads = blockSizeToTry * occupancyInBlocks; if (occupancyInThreads > maxOccupancy) { maxBlockSize = blockSizeToTry; numBlocks = occupancyInBlocks; maxOccupancy = occupancyInThreads; } if (occupancyLimit == maxOccupancy) { break; } } *minGridSize = numBlocks * multiProcessorCount; *blockSize = maxBlockSize; return status; } # 1505 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaLaunch( T *func ) { return ::cudaLaunch((const void*)func); } # 1543 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaFuncGetAttributes( struct cudaFuncAttributes *attr, T *entry ) { return ::cudaFuncGetAttributes(attr, (const void*)entry); } # 1572 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindSurfaceToArray( const struct surface &surf, cudaArray_const_t array, const struct cudaChannelFormatDesc &desc ) { return ::cudaBindSurfaceToArray(&surf, array, &desc); } # 1601 "/Developer/NVIDIA/CUDA-6.5/bin/../include/cuda_runtime.h" template __inline__ __attribute__((host)) cudaError_t cudaBindSurfaceToArray( const struct surface &surf, cudaArray_const_t array ) { struct cudaChannelFormatDesc desc; cudaError_t err = ::cudaGetChannelDesc(&desc, array); return err == cudaSuccess ? cudaBindSurfaceToArray(surf, array, desc) : err; } } # 6 "" 2 # 1 "" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cu" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/confdefs.h" 1 # 2 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cu" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conffix.h" 1 extern "C" { } # 3 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cu" 2 __attribute__((global)) void testFunction() {return;}; Preprocess stderr before filtering:: Preprocess stderr after filtering:: Popping language CUDA ================================================================================ TEST checkCxxCompiler from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:761) TESTING: checkCxxCompiler from config.setCompilers(config/BuildSystem/config/setCompilers.py:761) Locate a functional Cxx compiler Checking for program /Users/barrysmith/Src/PETSc/bin/g++...not found Checking for program g++...not found Checking for program /Users/barrysmith/bin/g++...not found Checking for program /usr/local/bin/g++...not found Checking for program /usr/bin/g++...found Defined make macro "CXX" to "g++" Pushing language Cxx Executing: g++ -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Executing: g++ -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Pushing language C Popping language C Pushing language CUDA Popping language CUDA Pushing language Cxx Popping language Cxx Pushing language FC Popping language FC Pushing language CXX Popping language CXX Executing: g++ -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o Executing: g++ -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Pushing language CXX Popping language CXX Executing: g++ -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -lpetsc-ufod4vtr9mqHvKIQiVAm Possible ERROR while running linker: exit code 256 stderr: ld: library not found for -lpetsc-ufod4vtr9mqHvKIQiVAm clang: error: linker command failed with exit code 1 (use -v to see invocation) Executing: g++ -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc Successful compile: Source: #include "confdefs.h" #include "conffix.h" int main() { ; return 0; } Pushing language CXX Popping language CXX Executing: g++ -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o Testing executable /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest to see if it can be run Executing: /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest Executing: /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest Popping language Cxx ================================================================================ TEST checkCxxPreprocessor from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:799) TESTING: checkCxxPreprocessor from config.setCompilers(config/BuildSystem/config/setCompilers.py:799) Locate a functional Cxx preprocessor Checking for program /Users/barrysmith/Src/PETSc/bin/g++...not found Checking for program g++...not found Checking for program /Users/barrysmith/bin/g++...not found Checking for program /usr/local/bin/g++...not found Checking for program /usr/bin/g++...found Defined make macro "CXXCPP" to "g++ -E" Pushing language Cxx Executing: g++ -E -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc stdout: # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc" # 1 "" 1 # 1 "" 3 # 326 "" 3 # 1 "" 1 # 1 "" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/confdefs.h" 1 # 2 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc" 2 # 1 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conffix.h" 1 extern "C" { } # 3 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc" 2 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/cstdlib" 1 3 # 85 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/cstdlib" 3 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config" 1 3 # 16 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config" 3 # 227 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config" 3 typedef __char16_t char16_t; typedef __char32_t char32_t; # 360 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config" 3 namespace std { inline namespace __1 { } } # 537 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config" 3 template struct __static_assert_test; template <> struct __static_assert_test {}; template struct __static_assert_check {}; # 86 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/cstdlib" 2 3 # 1 "/usr/include/stdlib.h" 1 3 4 # 61 "/usr/include/stdlib.h" 3 4 # 1 "/usr/include/Availability.h" 1 3 4 # 153 "/usr/include/Availability.h" 3 4 # 1 "/usr/include/AvailabilityInternal.h" 1 3 4 # 154 "/usr/include/Availability.h" 2 3 4 # 62 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/_types.h" 1 3 4 # 27 "/usr/include/_types.h" 3 4 # 1 "/usr/include/sys/_types.h" 1 3 4 # 32 "/usr/include/sys/_types.h" 3 4 # 1 "/usr/include/sys/cdefs.h" 1 3 4 # 506 "/usr/include/sys/cdefs.h" 3 4 # 1 "/usr/include/sys/_symbol_aliasing.h" 1 3 4 # 507 "/usr/include/sys/cdefs.h" 2 3 4 # 572 "/usr/include/sys/cdefs.h" 3 4 # 1 "/usr/include/sys/_posix_availability.h" 1 3 4 # 573 "/usr/include/sys/cdefs.h" 2 3 4 # 33 "/usr/include/sys/_types.h" 2 3 4 # 1 "/usr/include/machine/_types.h" 1 3 4 # 32 "/usr/include/machine/_types.h" 3 4 # 1 "/usr/include/i386/_types.h" 1 3 4 # 37 "/usr/include/i386/_types.h" 3 4 typedef signed char __int8_t; typedef unsigned char __uint8_t; typedef short __int16_t; typedef unsigned short __uint16_t; typedef int __int32_t; typedef unsigned int __uint32_t; typedef long long __int64_t; typedef unsigned long long __uint64_t; typedef long __darwin_intptr_t; typedef unsigned int __darwin_natural_t; # 70 "/usr/include/i386/_types.h" 3 4 typedef int __darwin_ct_rune_t; typedef union { char __mbstate8[128]; long long _mbstateL; } __mbstate_t; typedef __mbstate_t __darwin_mbstate_t; typedef long int __darwin_ptrdiff_t; typedef long unsigned int __darwin_size_t; typedef __builtin_va_list __darwin_va_list; typedef int __darwin_wchar_t; typedef __darwin_wchar_t __darwin_rune_t; typedef int __darwin_wint_t; typedef unsigned long __darwin_clock_t; typedef __uint32_t __darwin_socklen_t; typedef long __darwin_ssize_t; typedef long __darwin_time_t; # 33 "/usr/include/machine/_types.h" 2 3 4 # 34 "/usr/include/sys/_types.h" 2 3 4 # 55 "/usr/include/sys/_types.h" 3 4 typedef __int64_t __darwin_blkcnt_t; typedef __int32_t __darwin_blksize_t; typedef __int32_t __darwin_dev_t; typedef unsigned int __darwin_fsblkcnt_t; typedef unsigned int __darwin_fsfilcnt_t; typedef __uint32_t __darwin_gid_t; typedef __uint32_t __darwin_id_t; typedef __uint64_t __darwin_ino64_t; typedef __darwin_ino64_t __darwin_ino_t; typedef __darwin_natural_t __darwin_mach_port_name_t; typedef __darwin_mach_port_name_t __darwin_mach_port_t; typedef __uint16_t __darwin_mode_t; typedef __int64_t __darwin_off_t; typedef __int32_t __darwin_pid_t; typedef __uint32_t __darwin_sigset_t; typedef __int32_t __darwin_suseconds_t; typedef __uint32_t __darwin_uid_t; typedef __uint32_t __darwin_useconds_t; typedef unsigned char __darwin_uuid_t[16]; typedef char __darwin_uuid_string_t[37]; # 1 "/usr/include/sys/_pthread/_pthread_types.h" 1 3 4 # 57 "/usr/include/sys/_pthread/_pthread_types.h" 3 4 struct __darwin_pthread_handler_rec { void (*__routine)(void *); void *__arg; struct __darwin_pthread_handler_rec *__next; }; struct _opaque_pthread_attr_t { long __sig; char __opaque[56]; }; struct _opaque_pthread_cond_t { long __sig; char __opaque[40]; }; struct _opaque_pthread_condattr_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_mutex_t { long __sig; char __opaque[56]; }; struct _opaque_pthread_mutexattr_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_once_t { long __sig; char __opaque[8]; }; struct _opaque_pthread_rwlock_t { long __sig; char __opaque[192]; }; struct _opaque_pthread_rwlockattr_t { long __sig; char __opaque[16]; }; struct _opaque_pthread_t { long __sig; struct __darwin_pthread_handler_rec *__cleanup_stack; char __opaque[8176]; }; typedef struct _opaque_pthread_attr_t __darwin_pthread_attr_t; typedef struct _opaque_pthread_cond_t __darwin_pthread_cond_t; typedef struct _opaque_pthread_condattr_t __darwin_pthread_condattr_t; typedef unsigned long __darwin_pthread_key_t; typedef struct _opaque_pthread_mutex_t __darwin_pthread_mutex_t; typedef struct _opaque_pthread_mutexattr_t __darwin_pthread_mutexattr_t; typedef struct _opaque_pthread_once_t __darwin_pthread_once_t; typedef struct _opaque_pthread_rwlock_t __darwin_pthread_rwlock_t; typedef struct _opaque_pthread_rwlockattr_t __darwin_pthread_rwlockattr_t; typedef struct _opaque_pthread_t *__darwin_pthread_t; # 81 "/usr/include/sys/_types.h" 2 3 4 # 28 "/usr/include/_types.h" 2 3 4 # 39 "/usr/include/_types.h" 3 4 typedef int __darwin_nl_item; typedef int __darwin_wctrans_t; typedef __uint32_t __darwin_wctype_t; # 64 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/wait.h" 1 3 4 # 79 "/usr/include/sys/wait.h" 3 4 typedef enum { P_ALL, P_PID, P_PGID } idtype_t; # 1 "/usr/include/sys/_types/_pid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_pid_t.h" 3 4 typedef __darwin_pid_t pid_t; # 90 "/usr/include/sys/wait.h" 2 3 4 # 1 "/usr/include/sys/_types/_id_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_id_t.h" 3 4 typedef __darwin_id_t id_t; # 91 "/usr/include/sys/wait.h" 2 3 4 # 109 "/usr/include/sys/wait.h" 3 4 # 1 "/usr/include/sys/signal.h" 1 3 4 # 73 "/usr/include/sys/signal.h" 3 4 # 1 "/usr/include/sys/appleapiopts.h" 1 3 4 # 74 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/machine/signal.h" 1 3 4 # 32 "/usr/include/machine/signal.h" 3 4 # 1 "/usr/include/i386/signal.h" 1 3 4 # 39 "/usr/include/i386/signal.h" 3 4 typedef int sig_atomic_t; # 33 "/usr/include/machine/signal.h" 2 3 4 # 82 "/usr/include/sys/signal.h" 2 3 4 # 145 "/usr/include/sys/signal.h" 3 4 # 1 "/usr/include/machine/_mcontext.h" 1 3 4 # 29 "/usr/include/machine/_mcontext.h" 3 4 # 1 "/usr/include/i386/_mcontext.h" 1 3 4 # 33 "/usr/include/i386/_mcontext.h" 3 4 # 1 "/usr/include/mach/i386/_structs.h" 1 3 4 # 43 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_thread_state { unsigned int __eax; unsigned int __ebx; unsigned int __ecx; unsigned int __edx; unsigned int __edi; unsigned int __esi; unsigned int __ebp; unsigned int __esp; unsigned int __ss; unsigned int __eflags; unsigned int __eip; unsigned int __cs; unsigned int __ds; unsigned int __es; unsigned int __fs; unsigned int __gs; }; # 89 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_fp_control { unsigned short __invalid :1, __denorm :1, __zdiv :1, __ovrfl :1, __undfl :1, __precis :1, :2, __pc :2, __rc :2, :1, :3; }; typedef struct __darwin_fp_control __darwin_fp_control_t; # 147 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_fp_status { unsigned short __invalid :1, __denorm :1, __zdiv :1, __ovrfl :1, __undfl :1, __precis :1, __stkflt :1, __errsumm :1, __c0 :1, __c1 :1, __c2 :1, __tos :3, __c3 :1, __busy :1; }; typedef struct __darwin_fp_status __darwin_fp_status_t; # 191 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_mmst_reg { char __mmst_reg[10]; char __mmst_rsrv[6]; }; # 210 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_xmm_reg { char __xmm_reg[16]; }; # 232 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_float_state { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; char __fpu_rsrv4[14*16]; int __fpu_reserved1; }; struct __darwin_i386_avx_state { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; char __fpu_rsrv4[14*16]; int __fpu_reserved1; char __avx_reserved1[64]; struct __darwin_xmm_reg __fpu_ymmh0; struct __darwin_xmm_reg __fpu_ymmh1; struct __darwin_xmm_reg __fpu_ymmh2; struct __darwin_xmm_reg __fpu_ymmh3; struct __darwin_xmm_reg __fpu_ymmh4; struct __darwin_xmm_reg __fpu_ymmh5; struct __darwin_xmm_reg __fpu_ymmh6; struct __darwin_xmm_reg __fpu_ymmh7; }; # 402 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_i386_exception_state { __uint16_t __trapno; __uint16_t __cpu; __uint32_t __err; __uint32_t __faultvaddr; }; # 422 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_debug_state32 { unsigned int __dr0; unsigned int __dr1; unsigned int __dr2; unsigned int __dr3; unsigned int __dr4; unsigned int __dr5; unsigned int __dr6; unsigned int __dr7; }; # 454 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_thread_state64 { __uint64_t __rax; __uint64_t __rbx; __uint64_t __rcx; __uint64_t __rdx; __uint64_t __rdi; __uint64_t __rsi; __uint64_t __rbp; __uint64_t __rsp; __uint64_t __r8; __uint64_t __r9; __uint64_t __r10; __uint64_t __r11; __uint64_t __r12; __uint64_t __r13; __uint64_t __r14; __uint64_t __r15; __uint64_t __rip; __uint64_t __rflags; __uint64_t __cs; __uint64_t __fs; __uint64_t __gs; }; # 509 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_float_state64 { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; struct __darwin_xmm_reg __fpu_xmm8; struct __darwin_xmm_reg __fpu_xmm9; struct __darwin_xmm_reg __fpu_xmm10; struct __darwin_xmm_reg __fpu_xmm11; struct __darwin_xmm_reg __fpu_xmm12; struct __darwin_xmm_reg __fpu_xmm13; struct __darwin_xmm_reg __fpu_xmm14; struct __darwin_xmm_reg __fpu_xmm15; char __fpu_rsrv4[6*16]; int __fpu_reserved1; }; struct __darwin_x86_avx_state64 { int __fpu_reserved[2]; struct __darwin_fp_control __fpu_fcw; struct __darwin_fp_status __fpu_fsw; __uint8_t __fpu_ftw; __uint8_t __fpu_rsrv1; __uint16_t __fpu_fop; __uint32_t __fpu_ip; __uint16_t __fpu_cs; __uint16_t __fpu_rsrv2; __uint32_t __fpu_dp; __uint16_t __fpu_ds; __uint16_t __fpu_rsrv3; __uint32_t __fpu_mxcsr; __uint32_t __fpu_mxcsrmask; struct __darwin_mmst_reg __fpu_stmm0; struct __darwin_mmst_reg __fpu_stmm1; struct __darwin_mmst_reg __fpu_stmm2; struct __darwin_mmst_reg __fpu_stmm3; struct __darwin_mmst_reg __fpu_stmm4; struct __darwin_mmst_reg __fpu_stmm5; struct __darwin_mmst_reg __fpu_stmm6; struct __darwin_mmst_reg __fpu_stmm7; struct __darwin_xmm_reg __fpu_xmm0; struct __darwin_xmm_reg __fpu_xmm1; struct __darwin_xmm_reg __fpu_xmm2; struct __darwin_xmm_reg __fpu_xmm3; struct __darwin_xmm_reg __fpu_xmm4; struct __darwin_xmm_reg __fpu_xmm5; struct __darwin_xmm_reg __fpu_xmm6; struct __darwin_xmm_reg __fpu_xmm7; struct __darwin_xmm_reg __fpu_xmm8; struct __darwin_xmm_reg __fpu_xmm9; struct __darwin_xmm_reg __fpu_xmm10; struct __darwin_xmm_reg __fpu_xmm11; struct __darwin_xmm_reg __fpu_xmm12; struct __darwin_xmm_reg __fpu_xmm13; struct __darwin_xmm_reg __fpu_xmm14; struct __darwin_xmm_reg __fpu_xmm15; char __fpu_rsrv4[6*16]; int __fpu_reserved1; char __avx_reserved1[64]; struct __darwin_xmm_reg __fpu_ymmh0; struct __darwin_xmm_reg __fpu_ymmh1; struct __darwin_xmm_reg __fpu_ymmh2; struct __darwin_xmm_reg __fpu_ymmh3; struct __darwin_xmm_reg __fpu_ymmh4; struct __darwin_xmm_reg __fpu_ymmh5; struct __darwin_xmm_reg __fpu_ymmh6; struct __darwin_xmm_reg __fpu_ymmh7; struct __darwin_xmm_reg __fpu_ymmh8; struct __darwin_xmm_reg __fpu_ymmh9; struct __darwin_xmm_reg __fpu_ymmh10; struct __darwin_xmm_reg __fpu_ymmh11; struct __darwin_xmm_reg __fpu_ymmh12; struct __darwin_xmm_reg __fpu_ymmh13; struct __darwin_xmm_reg __fpu_ymmh14; struct __darwin_xmm_reg __fpu_ymmh15; }; # 751 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_exception_state64 { __uint16_t __trapno; __uint16_t __cpu; __uint32_t __err; __uint64_t __faultvaddr; }; # 771 "/usr/include/mach/i386/_structs.h" 3 4 struct __darwin_x86_debug_state64 { __uint64_t __dr0; __uint64_t __dr1; __uint64_t __dr2; __uint64_t __dr3; __uint64_t __dr4; __uint64_t __dr5; __uint64_t __dr6; __uint64_t __dr7; }; # 34 "/usr/include/i386/_mcontext.h" 2 3 4 struct __darwin_mcontext32 { struct __darwin_i386_exception_state __es; struct __darwin_i386_thread_state __ss; struct __darwin_i386_float_state __fs; }; struct __darwin_mcontext_avx32 { struct __darwin_i386_exception_state __es; struct __darwin_i386_thread_state __ss; struct __darwin_i386_avx_state __fs; }; # 76 "/usr/include/i386/_mcontext.h" 3 4 struct __darwin_mcontext64 { struct __darwin_x86_exception_state64 __es; struct __darwin_x86_thread_state64 __ss; struct __darwin_x86_float_state64 __fs; }; struct __darwin_mcontext_avx64 { struct __darwin_x86_exception_state64 __es; struct __darwin_x86_thread_state64 __ss; struct __darwin_x86_avx_state64 __fs; }; # 115 "/usr/include/i386/_mcontext.h" 3 4 typedef struct __darwin_mcontext64 *mcontext_t; # 30 "/usr/include/machine/_mcontext.h" 2 3 4 # 146 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_pthread/_pthread_attr_t.h" 1 3 4 # 30 "/usr/include/sys/_pthread/_pthread_attr_t.h" 3 4 typedef __darwin_pthread_attr_t pthread_attr_t; # 148 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_sigaltstack.h" 1 3 4 # 36 "/usr/include/sys/_types/_sigaltstack.h" 3 4 struct __darwin_sigaltstack { void *ss_sp; __darwin_size_t ss_size; int ss_flags; }; typedef struct __darwin_sigaltstack stack_t; # 150 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_ucontext.h" 1 3 4 # 34 "/usr/include/sys/_types/_ucontext.h" 3 4 struct __darwin_ucontext { int uc_onstack; __darwin_sigset_t uc_sigmask; struct __darwin_sigaltstack uc_stack; struct __darwin_ucontext *uc_link; __darwin_size_t uc_mcsize; struct __darwin_mcontext64 *uc_mcontext; }; typedef struct __darwin_ucontext ucontext_t; # 151 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_sigset_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_sigset_t.h" 3 4 typedef __darwin_sigset_t sigset_t; # 154 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_size_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_size_t.h" 3 4 typedef __darwin_size_t size_t; # 155 "/usr/include/sys/signal.h" 2 3 4 # 1 "/usr/include/sys/_types/_uid_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uid_t.h" 3 4 typedef __darwin_uid_t uid_t; # 156 "/usr/include/sys/signal.h" 2 3 4 union sigval { int sival_int; void *sival_ptr; }; struct sigevent { int sigev_notify; int sigev_signo; union sigval sigev_value; void (*sigev_notify_function)(union sigval); pthread_attr_t *sigev_notify_attributes; }; typedef struct __siginfo { int si_signo; int si_errno; int si_code; pid_t si_pid; uid_t si_uid; int si_status; void *si_addr; union sigval si_value; long si_band; unsigned long __pad[7]; } siginfo_t; # 268 "/usr/include/sys/signal.h" 3 4 union __sigaction_u { void (*__sa_handler)(int); void (*__sa_sigaction)(int, struct __siginfo *, void *); }; struct __sigaction { union __sigaction_u __sigaction_u; void (*sa_tramp)(void *, int, int, siginfo_t *, void *); sigset_t sa_mask; int sa_flags; }; struct sigaction { union __sigaction_u __sigaction_u; sigset_t sa_mask; int sa_flags; }; # 330 "/usr/include/sys/signal.h" 3 4 typedef void (*sig_t)(int); # 347 "/usr/include/sys/signal.h" 3 4 struct sigvec { void (*sv_handler)(int); int sv_mask; int sv_flags; }; # 366 "/usr/include/sys/signal.h" 3 4 struct sigstack { char *ss_sp; int ss_onstack; }; # 388 "/usr/include/sys/signal.h" 3 4 extern "C" { void (*signal(int, void (*)(int)))(int); } # 110 "/usr/include/sys/wait.h" 2 3 4 # 1 "/usr/include/sys/resource.h" 1 3 4 # 72 "/usr/include/sys/resource.h" 3 4 # 1 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 1 3 4 # 63 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 3 4 # 1 "/usr/include/stdint.h" 1 3 4 # 18 "/usr/include/stdint.h" 3 4 # 1 "/usr/include/sys/_types/_int8_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int8_t.h" 3 4 typedef signed char int8_t; # 19 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int16_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int16_t.h" 3 4 typedef short int16_t; # 20 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int32_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int32_t.h" 3 4 typedef int int32_t; # 21 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_int64_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_int64_t.h" 3 4 typedef long long int64_t; # 22 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint8_t.h" 1 3 4 # 31 "/usr/include/_types/_uint8_t.h" 3 4 typedef unsigned char uint8_t; # 24 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint16_t.h" 1 3 4 # 31 "/usr/include/_types/_uint16_t.h" 3 4 typedef unsigned short uint16_t; # 25 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint32_t.h" 1 3 4 # 31 "/usr/include/_types/_uint32_t.h" 3 4 typedef unsigned int uint32_t; # 26 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uint64_t.h" 1 3 4 # 31 "/usr/include/_types/_uint64_t.h" 3 4 typedef unsigned long long uint64_t; # 27 "/usr/include/stdint.h" 2 3 4 typedef int8_t int_least8_t; typedef int16_t int_least16_t; typedef int32_t int_least32_t; typedef int64_t int_least64_t; typedef uint8_t uint_least8_t; typedef uint16_t uint_least16_t; typedef uint32_t uint_least32_t; typedef uint64_t uint_least64_t; typedef int8_t int_fast8_t; typedef int16_t int_fast16_t; typedef int32_t int_fast32_t; typedef int64_t int_fast64_t; typedef uint8_t uint_fast8_t; typedef uint16_t uint_fast16_t; typedef uint32_t uint_fast32_t; typedef uint64_t uint_fast64_t; # 1 "/usr/include/sys/_types/_intptr_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_intptr_t.h" 3 4 typedef __darwin_intptr_t intptr_t; # 54 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/sys/_types/_uintptr_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_uintptr_t.h" 3 4 typedef unsigned long uintptr_t; # 55 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_intmax_t.h" 1 3 4 # 32 "/usr/include/_types/_intmax_t.h" 3 4 typedef long int intmax_t; # 59 "/usr/include/stdint.h" 2 3 4 # 1 "/usr/include/_types/_uintmax_t.h" 1 3 4 # 32 "/usr/include/_types/_uintmax_t.h" 3 4 typedef long unsigned int uintmax_t; # 60 "/usr/include/stdint.h" 2 3 4 # 64 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../lib/clang/6.1.0/include/stdint.h" 2 3 4 # 73 "/usr/include/sys/resource.h" 2 3 4 # 1 "/usr/include/sys/_types/_timeval.h" 1 3 4 # 30 "/usr/include/sys/_types/_timeval.h" 3 4 struct timeval { __darwin_time_t tv_sec; __darwin_suseconds_t tv_usec; }; # 81 "/usr/include/sys/resource.h" 2 3 4 typedef __uint64_t rlim_t; # 152 "/usr/include/sys/resource.h" 3 4 struct rusage { struct timeval ru_utime; struct timeval ru_stime; # 163 "/usr/include/sys/resource.h" 3 4 long ru_maxrss; long ru_ixrss; long ru_idrss; long ru_isrss; long ru_minflt; long ru_majflt; long ru_nswap; long ru_inblock; long ru_oublock; long ru_msgsnd; long ru_msgrcv; long ru_nsignals; long ru_nvcsw; long ru_nivcsw; }; # 192 "/usr/include/sys/resource.h" 3 4 typedef void *rusage_info_t; struct rusage_info_v0 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; }; struct rusage_info_v1 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; }; struct rusage_info_v2 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; uint64_t ri_diskio_bytesread; uint64_t ri_diskio_byteswritten; }; struct rusage_info_v3 { uint8_t ri_uuid[16]; uint64_t ri_user_time; uint64_t ri_system_time; uint64_t ri_pkg_idle_wkups; uint64_t ri_interrupt_wkups; uint64_t ri_pageins; uint64_t ri_wired_size; uint64_t ri_resident_size; uint64_t ri_phys_footprint; uint64_t ri_proc_start_abstime; uint64_t ri_proc_exit_abstime; uint64_t ri_child_user_time; uint64_t ri_child_system_time; uint64_t ri_child_pkg_idle_wkups; uint64_t ri_child_interrupt_wkups; uint64_t ri_child_pageins; uint64_t ri_child_elapsed_abstime; uint64_t ri_diskio_bytesread; uint64_t ri_diskio_byteswritten; uint64_t ri_cpu_time_qos_default; uint64_t ri_cpu_time_qos_maintenance; uint64_t ri_cpu_time_qos_background; uint64_t ri_cpu_time_qos_utility; uint64_t ri_cpu_time_qos_legacy; uint64_t ri_cpu_time_qos_user_initiated; uint64_t ri_cpu_time_qos_user_interactive; uint64_t ri_billed_system_time; uint64_t ri_serviced_system_time; }; typedef struct rusage_info_v3 rusage_info_current; # 325 "/usr/include/sys/resource.h" 3 4 struct rlimit { rlim_t rlim_cur; rlim_t rlim_max; }; # 353 "/usr/include/sys/resource.h" 3 4 struct proc_rlimit_control_wakeupmon { uint32_t wm_flags; int32_t wm_rate; }; # 382 "/usr/include/sys/resource.h" 3 4 extern "C" { int getpriority(int, id_t); int getiopolicy_np(int, int) __attribute__((availability(macosx,introduced=10.5))); int getrlimit(int, struct rlimit *) __asm("_" "getrlimit" ); int getrusage(int, struct rusage *); int setpriority(int, id_t, int); int setiopolicy_np(int, int, int) __attribute__((availability(macosx,introduced=10.5))); int setrlimit(int, const struct rlimit *) __asm("_" "setrlimit" ); } # 111 "/usr/include/sys/wait.h" 2 3 4 # 186 "/usr/include/sys/wait.h" 3 4 # 1 "/usr/include/machine/endian.h" 1 3 4 # 35 "/usr/include/machine/endian.h" 3 4 # 1 "/usr/include/i386/endian.h" 1 3 4 # 99 "/usr/include/i386/endian.h" 3 4 # 1 "/usr/include/sys/_endian.h" 1 3 4 # 130 "/usr/include/sys/_endian.h" 3 4 # 1 "/usr/include/libkern/_OSByteOrder.h" 1 3 4 # 66 "/usr/include/libkern/_OSByteOrder.h" 3 4 # 1 "/usr/include/libkern/i386/_OSByteOrder.h" 1 3 4 # 44 "/usr/include/libkern/i386/_OSByteOrder.h" 3 4 static inline __uint16_t _OSSwapInt16( __uint16_t _data ) { return ((__uint16_t)((_data << 8) | (_data >> 8))); } static inline __uint32_t _OSSwapInt32( __uint32_t _data ) { return __builtin_bswap32(_data); } static inline __uint64_t _OSSwapInt64( __uint64_t _data ) { return __builtin_bswap64(_data); } # 67 "/usr/include/libkern/_OSByteOrder.h" 2 3 4 # 131 "/usr/include/sys/_endian.h" 2 3 4 # 100 "/usr/include/i386/endian.h" 2 3 4 # 36 "/usr/include/machine/endian.h" 2 3 4 # 187 "/usr/include/sys/wait.h" 2 3 4 union wait { int w_status; struct { unsigned int w_Termsig:7, w_Coredump:1, w_Retcode:8, w_Filler:16; } w_T; struct { unsigned int w_Stopval:8, w_Stopsig:8, w_Filler:16; } w_S; }; # 247 "/usr/include/sys/wait.h" 3 4 extern "C" { pid_t wait(int *) __asm("_" "wait" ); pid_t waitpid(pid_t, int *, int) __asm("_" "waitpid" ); int waitid(idtype_t, id_t, siginfo_t *, int) __asm("_" "waitid" ); pid_t wait3(int *, int, struct rusage *); pid_t wait4(pid_t, int *, int, struct rusage *); } # 66 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/alloca.h" 1 3 4 # 31 "/usr/include/alloca.h" 3 4 extern "C" { void *alloca(size_t); } # 68 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_ct_rune_t.h" 1 3 4 # 31 "/usr/include/sys/_types/_ct_rune_t.h" 3 4 typedef __darwin_ct_rune_t ct_rune_t; # 77 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_rune_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_rune_t.h" 3 4 typedef __darwin_rune_t rune_t; # 78 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_wchar_t.h" 1 3 4 # 81 "/usr/include/stdlib.h" 2 3 4 typedef struct { int quot; int rem; } div_t; typedef struct { long quot; long rem; } ldiv_t; typedef struct { long long quot; long long rem; } lldiv_t; # 1 "/usr/include/sys/_types/_null.h" 1 3 4 # 100 "/usr/include/stdlib.h" 2 3 4 # 117 "/usr/include/stdlib.h" 3 4 extern int __mb_cur_max; # 127 "/usr/include/stdlib.h" 3 4 extern "C" { void abort(void) __attribute__((noreturn)); int abs(int) __attribute__((const)); int atexit(void (*)(void)); double atof(const char *); int atoi(const char *); long atol(const char *); long long atoll(const char *); void *bsearch(const void *, const void *, size_t, size_t, int (*)(const void *, const void *)); void *calloc(size_t, size_t); div_t div(int, int) __attribute__((const)); void exit(int) __attribute__((noreturn)); void free(void *); char *getenv(const char *); long labs(long) __attribute__((const)); ldiv_t ldiv(long, long) __attribute__((const)); long long llabs(long long); lldiv_t lldiv(long long, long long); void *malloc(size_t); int mblen(const char *, size_t); size_t mbstowcs(wchar_t * , const char * , size_t); int mbtowc(wchar_t * , const char * , size_t); int posix_memalign(void **, size_t, size_t) __attribute__((availability(macosx,introduced=10.6))); void qsort(void *, size_t, size_t, int (*)(const void *, const void *)); int rand(void); void *realloc(void *, size_t); void srand(unsigned); double strtod(const char *, char **) __asm("_" "strtod" ); float strtof(const char *, char **) __asm("_" "strtof" ); long strtol(const char *, char **, int); long double strtold(const char *, char **); long long strtoll(const char *, char **, int); unsigned long strtoul(const char *, char **, int); unsigned long long strtoull(const char *, char **, int); int system(const char *) __asm("_" "system" ) __attribute__((availability(macosx,introduced=10.0))); size_t wcstombs(char * , const wchar_t * , size_t); int wctomb(char *, wchar_t); void _Exit(int) __attribute__((noreturn)); long a64l(const char *); double drand48(void); char *ecvt(double, int, int *, int *); double erand48(unsigned short[3]); char *fcvt(double, int, int *, int *); char *gcvt(double, int, char *); int getsubopt(char **, char * const *, char **); int grantpt(int); char *initstate(unsigned, char *, size_t); long jrand48(unsigned short[3]); char *l64a(long); void lcong48(unsigned short[7]); long lrand48(void); char *mktemp(char *); int mkstemp(char *); long mrand48(void); long nrand48(unsigned short[3]); int posix_openpt(int); char *ptsname(int); int putenv(char *) __asm("_" "putenv" ); long random(void); int rand_r(unsigned *); char *realpath(const char * , char * ) __asm("_" "realpath" "$DARWIN_EXTSN"); unsigned short *seed48(unsigned short[3]); int setenv(const char *, const char *, int) __asm("_" "setenv" ); void setkey(const char *) __asm("_" "setkey" ); char *setstate(const char *); void srand48(long); void srandom(unsigned); int unlockpt(int); int unsetenv(const char *) __asm("_" "unsetenv" ); # 1 "/usr/include/machine/types.h" 1 3 4 # 35 "/usr/include/machine/types.h" 3 4 # 1 "/usr/include/i386/types.h" 1 3 4 # 81 "/usr/include/i386/types.h" 3 4 typedef unsigned char u_int8_t; typedef unsigned short u_int16_t; typedef unsigned int u_int32_t; typedef unsigned long long u_int64_t; typedef int64_t register_t; # 97 "/usr/include/i386/types.h" 3 4 typedef u_int64_t user_addr_t; typedef u_int64_t user_size_t; typedef int64_t user_ssize_t; typedef int64_t user_long_t; typedef u_int64_t user_ulong_t; typedef int64_t user_time_t; typedef int64_t user_off_t; typedef u_int64_t syscall_arg_t; # 36 "/usr/include/machine/types.h" 2 3 4 # 239 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_dev_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_dev_t.h" 3 4 typedef __darwin_dev_t dev_t; # 241 "/usr/include/stdlib.h" 2 3 4 # 1 "/usr/include/sys/_types/_mode_t.h" 1 3 4 # 30 "/usr/include/sys/_types/_mode_t.h" 3 4 typedef __darwin_mode_t mode_t; # 242 "/usr/include/stdlib.h" 2 3 4 u_int32_t arc4random(void); void arc4random_addrandom(unsigned char * , int ); void arc4random_buf(void * , size_t ) __attribute__((availability(macosx,introduced=10.7))); void arc4random_stir(void); u_int32_t arc4random_uniform(u_int32_t ) __attribute__((availability(macosx,introduced=10.7))); int atexit_b(void (^)(void)) __attribute__((availability(macosx,introduced=10.6))); void *bsearch_b(const void *, const void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); char *cgetcap(char *, const char *, int); int cgetclose(void); int cgetent(char **, char **, const char *); int cgetfirst(char **, char **); int cgetmatch(const char *, const char *); int cgetnext(char **, char **); int cgetnum(char *, const char *, long *); int cgetset(const char *); int cgetstr(char *, const char *, char **); int cgetustr(char *, const char *, char **); int daemon(int, int) __asm("_" "daemon" "$1050") __attribute__((availability(macosx,introduced=10.0,deprecated=10.5))); char *devname(dev_t, mode_t); char *devname_r(dev_t, mode_t, char *buf, int len); char *getbsize(int *, long *); int getloadavg(double [], int); const char *getprogname(void); int heapsort(void *, size_t, size_t, int (*)(const void *, const void *)); int heapsort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); int mergesort(void *, size_t, size_t, int (*)(const void *, const void *)); int mergesort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort(void *, size_t, size_t, int (*)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void psort_r(void *, size_t, size_t, void *, int (*)(void *, const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void qsort_b(void *, size_t, size_t, int (^)(const void *, const void *)) __attribute__((availability(macosx,introduced=10.6))); void qsort_r(void *, size_t, size_t, void *, int (*)(void *, const void *, const void *)); int radixsort(const unsigned char **, int, const unsigned char *, unsigned); void setprogname(const char *); int sradixsort(const unsigned char **, int, const unsigned char *, unsigned); void sranddev(void); void srandomdev(void); void *reallocf(void *, size_t); long long strtoq(const char *, char **, int); unsigned long long strtouq(const char *, char **, int); extern char *suboptarg; void *valloc(size_t); } # 87 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/cstdlib" 2 3 # 93 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/cstdlib" 3 namespace std {inline namespace __1 { using ::size_t; using ::div_t; using ::ldiv_t; using ::lldiv_t; using ::atof; using ::atoi; using ::atol; using ::atoll; using ::strtod; using ::strtof; using ::strtold; using ::strtol; using ::strtoll; using ::strtoul; using ::strtoull; using ::rand; using ::srand; using ::calloc; using ::free; using ::malloc; using ::realloc; using ::abort; using ::atexit; using ::exit; using ::_Exit; using ::getenv; using ::system; using ::bsearch; using ::qsort; using ::abs; using ::labs; using ::llabs; using ::div; using ::ldiv; using ::lldiv; using ::mblen; using ::mbtowc; using ::wctomb; using ::mbstowcs; using ::wcstombs; # 159 "/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/cstdlib" 3 inline __attribute__ ((__visibility__("hidden"), __always_inline__)) long abs( long __x) throw() {return labs(__x);} inline __attribute__ ((__visibility__("hidden"), __always_inline__)) long long abs(long long __x) throw() {return llabs(__x);} inline __attribute__ ((__visibility__("hidden"), __always_inline__)) ldiv_t div( long __x, long __y) throw() {return ldiv(__x, __y);} inline __attribute__ ((__visibility__("hidden"), __always_inline__)) lldiv_t div(long long __x, long long __y) throw() {return lldiv(__x, __y);} } } # 4 "/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.cc" 2 Preprocess stderr before filtering:: Preprocess stderr after filtering:: Popping language Cxx ================================================================================ TEST checkFortranCompiler from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:916) TESTING: checkFortranCompiler from config.setCompilers(config/BuildSystem/config/setCompilers.py:916) Locate a functional Fortran compiler Checking for program /Users/barrysmith/Src/PETSc/bin/gfortran...not found Checking for program gfortran...not found Checking for program /Users/barrysmith/bin/gfortran...not found Checking for program /usr/local/bin/gfortran...found Defined make macro "FC" to "gfortran" Pushing language FC Executing: gfortran -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.F Successful compile: Source: program main end Executing: gfortran -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.F Successful compile: Source: program main end Pushing language C Popping language C Pushing language CUDA Popping language CUDA Pushing language Cxx Popping language Cxx Pushing language FC Popping language FC Pushing language FC Popping language FC Executing: gfortran -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o Executing: gfortran -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.F Successful compile: Source: program main end Pushing language FC Popping language FC Executing: gfortran -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -lpetsc-ufod4vtr9mqHvKIQiVAm Possible ERROR while running linker: exit code 256 stderr: ld: library not found for -lpetsc-ufod4vtr9mqHvKIQiVAm collect2: error: ld returned 1 exit status Executing: gfortran -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.F Successful compile: Source: program main end Pushing language FC Popping language FC Executing: gfortran -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o Testing executable /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest to see if it can be run Executing: /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest Executing: /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest Popping language FC ================================================================================ TEST checkFortranComments from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:937) TESTING: checkFortranComments from config.setCompilers(config/BuildSystem/config/setCompilers.py:937) Make sure fortran comment "!" works Pushing language FC Executing: gfortran -c -o /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.o -I/var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers /var/folders/c1/ldz_dt8n2r3dtwv_chp5pfr40000gn/T/petsc-YWhch4/config.setCompilers/conftest.F Successful compile: Source: ! comment program main end Fortran comments can use ! in column 1 Popping language FC ================================================================================ TEST checkPIC from config.setCompilers(/Users/barrysmith/Src/PETSc/config/BuildSystem/config/setCompilers.py:1000) TESTING: checkPIC from config.setCompilers(config/BuildSystem/config/setCompilers.py:1000) Determine the PIC option for each compiler - There needs to be a test that checks that the functionality is actually working Pushing language C Executing: gcc --help stdout: OVERVIEW: clang LLVM compiler USAGE: clang [options] OPTIONS: -### Print (but do not run) the commands to run for this compilation --analyze Run the static analyzer -arcmt-migrate-emit-errors Emit ARC errors even if the migrator can fix them -arcmt-migrate-report-output Output path for the plist report -cxx-isystem Add directory to the C++ SYSTEM include search path -c Only run preprocess, compile, and assemble steps -dD Print macro definitions in -E mode in addition to normal output -dependency-dot Filename to write DOT-formatted header dependencies to -dependency-file Filename (or -) to write dependency output to -dM Print macro definitions in -E mode instead of normal output -emit-ast Emit Clang AST files for source inputs -emit-llvm Use the LLVM representation for assembler and object files -E Only run the preprocessor -faltivec Enable AltiVec vector initializer syntax -fansi-escape-codes Use ANSI escape codes for diagnostics -fapinotes-cache-path= Specify the API notes cache path -fapinotes Enable external API notes support -fapple-kext Use Apple's kernel extensions ABI -fapple-pragma-pack Enable Apple gcc-compatible #pragma pack handling -fapplication-extension Restrict code to those available for App Extensions -fblocks Enable the 'blocks' language feature -fborland-extensions Accept non-standard constructs supported by the Borland compiler -fbuild-session-file= Use the last modification time of as the build session timestamp -fbuild-session-timestamp=