[petsc-users] Combining SUPERLU_DIST with CUDA fails

Mon Dec 20 14:46:12 CST 2021

  Hmm, the fix should now be supplying a -DCMAKE_CUDA_FLAGS to this cmake command (line 48 at https://gitlab.com/petsc/petsc/-/merge_requests/4635/diffs) I do not see that flag being set inside the configure.log so I am guessing you didn't get the complete fix.

Executing: /usr/bin/cmake .. -DCMAKE_INSTALL_PREFIX=/opt/petsc -DCMAKE_INSTALL_NAME_DIR:STRING="/opt/petsc/lib" -DCMAKE_INSTALL_LIBDIR:STRING="lib" -DCMAKE_VERBOSE_MAKEFILE=1 -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER="/opt/intel/oneapi/mpi/2021.5.0/bin/mpicc" -DMPI_C_COMPILER="/opt/intel/oneapi/mpi/2021.5.0/bin/mpicc" -DCMAKE_AR=/usr/bin/ar -DCMAKE_RANLIB=/usr/bin/ranlib -DCMAKE_C_FLAGS:STRING="-mavx2 -march=native -O3 -fPIC -fopenmp" -DCMAKE_C_FLAGS_DEBUG:STRING="-mavx2 -march=native -O3 -fPIC -fopenmp" -DCMAKE_C_FLAGS_RELEASE:STRING="-mavx2 -march=native -O3 -fPIC -fopenmp" -DCMAKE_CXX_COMPILER="/opt/intel/oneapi/mpi/2021.5.0/bin/mpicxx" -DMPI_CXX_COMPILER="/opt/intel/oneapi/mpi/2021.5.0/bin/mpicxx" -DCMAKE_CXX_FLAGS:STRING="-mavx2 -march=native -O3 -fopenmp -fPIC -std=gnu++17 -fopenmp" -DCMAKE_CXX_FLAGS_DEBUG:STRING="-mavx2 -march=native -O3 -fopenmp -fPIC -std=gnu++17 -fopenmp" -DCMAKE_CXX_FLAGS_RELEASE:STRING="-mavx2 -march=native -O3 -fopenmp -fPIC -std=gnu++17 -fopenmp" -DCMAKE_Fortran_COMPILER="/opt/intel/oneapi/mpi/2021.5.0/bin/mpifc" -DMPI_Fortran_COMPILER="/opt/intel/oneapi/mpi/2021.5.0/bin/mpifc" -DCMAKE_Fortran_FLAGS:STRING="-mavx2 -march=native -O3 -fPIC -fopenmp -fallow-argument-mismatch" -DCMAKE_Fortran_FLAGS_DEBUG:STRING="-mavx2 -march=native -O3 -fPIC -fopenmp -fallow-argument-mismatch" -DCMAKE_Fortran_FLAGS_RELEASE:STRING="-mavx2 -march=native -O3 -fPIC -fopenmp -fallow-argument-mismatch" -DCMAKE_EXE_LINKER_FLAGS:STRING=" -fopenmp -fopenmp" -DBUILD_SHARED_LIBS:BOOL=ON -DTPL_ENABLE_CUDALIB=TRUE -DTPL_CUDA_LIBRARIES="-Wl,-rpath,/usr/local/cuda-11.5/lib64 -L/usr/local/cuda-11.5/lib64 -lcudart -lcufft -lcublas -lcusparse -lcusolver -lcurand -L/usr/local/cuda-11.5/lib64/stubs -lcuda" -DCUDA_ARCH_FLAGS="-I/usr/local/cuda-11.5/include -arch=sm_61 -DDEBUGlevel=0 -DPRNTlevel=0" -DUSE_XSDK_DEFAULTS=YES -DTPL_BLAS_LIBRARIES="-lopenblas -Wl,-rpath,/usr/local/cuda-11.5/lib64 -L/usr/local/cuda-11.5/lib64 -lcudart -lcufft -lcublas -lcusparse -lcusolver -lcurand -L/usr/local/cuda-11.5/lib64/stubs -lcuda -lm -lstdc++ -ldl -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib/release -L/opt/intel/oneapi/mpi/2021.5.0/lib/release -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib -L/opt/intel/oneapi/mpi/2021.5.0/lib -lmpifort -lmpi -lrt -lpthread -lgfortran -lm -Wl,-rpath,/usr/lib64/gcc/x86_64-suse-linux/11 -L/usr/lib64/gcc/x86_64-suse-linux/11 -Wl,-rpath,/opt/intel/oneapi/vpl/2022.0.0/lib -L/opt/intel/oneapi/vpl/2022.0.0/lib -Wl,-rpath,/opt/intel/oneapi/tbb/2021.5.0/lib/intel64/gcc4.8 -L/opt/intel/oneapi/tbb/2021.5.0/lib/intel64/gcc4.8 -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/libfabric/lib -L/opt/intel/oneapi/mpi/2021.5.0/libfabric/lib -Wl,-rpath,/opt/intel/oneapi/mkl/2022.0.1/lib/intel64 -L/opt/intel/oneapi/mkl/2022.0.1/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/ipp/2021.5.1/lib/intel64 -L/opt/intel/oneapi/ipp/2021.5.1/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/ippcp/2021.5.0/lib/intel64 -L/opt/intel/oneapi/ippcp/2021.5.0/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/dnnl/2022.0.1/cpu_dpcpp_gpu_dpcpp/lib -L/opt/intel/oneapi/dnnl/2022.0.1/cpu_dpcpp_gpu_dpcpp/lib -Wl,-rpath,/opt/intel/oneapi/dal/2021.5.1/lib/intel64 -L/opt/intel/oneapi/dal/2021.5.1/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/compiler/2022.0.1/linux/compiler/lib/intel64_lin -L/opt/intel/oneapi/compiler/2022.0.1/linux/compiler/lib/intel64_lin -Wl,-rpath,/opt/intel/oneapi/compiler/2022.0.1/linux/lib -L/opt/intel/oneapi/compiler/2022.0.1/linux/lib -Wl,-rpath,/opt/intel/oneapi/clck/2021.5.0/lib/intel64 -L/opt/intel/oneapi/clck/2021.5.0/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/ccl/2021.5.0/lib/cpu_gpu_dpcpp -L/opt/intel/oneapi/ccl/2021.5.0/lib/cpu_gpu_dpcpp -Wl,-rpath,/usr/x86_64-suse-linux/lib -L/usr/x86_64-suse-linux/lib -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib/release -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib -lgfortran -lm -lgcc_s -lquadmath" -DTPL_LAPACK_LIBRARIES="-lopenblas -Wl,-rpath,/usr/local/cuda-11.5/lib64 -L/usr/local/cuda-11.5/lib64 -lcudart -lcufft -lcublas -lcusparse -lcusolver -lcurand -L/usr/local/cuda-11.5/lib64/stubs -lcuda -lm -lstdc++ -ldl -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib/release -L/opt/intel/oneapi/mpi/2021.5.0/lib/release -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib -L/opt/intel/oneapi/mpi/2021.5.0/lib -lmpifort -lmpi -lrt -lpthread -lgfortran -lm -Wl,-rpath,/usr/lib64/gcc/x86_64-suse-linux/11 -L/usr/lib64/gcc/x86_64-suse-linux/11 -Wl,-rpath,/opt/intel/oneapi/vpl/2022.0.0/lib -L/opt/intel/oneapi/vpl/2022.0.0/lib -Wl,-rpath,/opt/intel/oneapi/tbb/2021.5.0/lib/intel64/gcc4.8 -L/opt/intel/oneapi/tbb/2021.5.0/lib/intel64/gcc4.8 -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/libfabric/lib -L/opt/intel/oneapi/mpi/2021.5.0/libfabric/lib -Wl,-rpath,/opt/intel/oneapi/mkl/2022.0.1/lib/intel64 -L/opt/intel/oneapi/mkl/2022.0.1/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/ipp/2021.5.1/lib/intel64 -L/opt/intel/oneapi/ipp/2021.5.1/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/ippcp/2021.5.0/lib/intel64 -L/opt/intel/oneapi/ippcp/2021.5.0/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/dnnl/2022.0.1/cpu_dpcpp_gpu_dpcpp/lib -L/opt/intel/oneapi/dnnl/2022.0.1/cpu_dpcpp_gpu_dpcpp/lib -Wl,-rpath,/opt/intel/oneapi/dal/2021.5.1/lib/intel64 -L/opt/intel/oneapi/dal/2021.5.1/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/compiler/2022.0.1/linux/compiler/lib/intel64_lin -L/opt/intel/oneapi/compiler/2022.0.1/linux/compiler/lib/intel64_lin -Wl,-rpath,/opt/intel/oneapi/compiler/2022.0.1/linux/lib -L/opt/intel/oneapi/compiler/2022.0.1/linux/lib -Wl,-rpath,/opt/intel/oneapi/clck/2021.5.0/lib/intel64 -L/opt/intel/oneapi/clck/2021.5.0/lib/intel64 -Wl,-rpath,/opt/intel/oneapi/ccl/2021.5.0/lib/cpu_gpu_dpcpp -L/opt/intel/oneapi/ccl/2021.5.0/lib/cpu_gpu_dpcpp -Wl,-rpath,/usr/x86_64-suse-linux/lib -L/usr/x86_64-suse-linux/lib -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib/release -Wl,-rpath,/opt/intel/oneapi/mpi/2021.5.0/lib -lgfortran -lm -lgcc_s -lquadmath" -Denable_parmetislib=FALSE -DTPL_ENABLE_PARMETISLIB=FALSE -DXSDK_ENABLE_Fortran=ON -Denable_tests=0 -Denable_examples=0 -DMPI_C_COMPILE_FLAGS:STRING="" -DMPI_C_INCLUDE_PATH:STRING="" -DMPI_C_HEADER_DIR:STRING="" -DMPI_C_LIBRARIES:STRING=""

> On Dec 20, 2021, at 2:59 PM, Roland Richter <roland.richter at ntnu.no> wrote:
> 
> I introduced the changes from that patch directly, without checking out. Is that insufficient?
> 
> Regards,
> 
> Roland
> 
> Am 20.12.2021 um 20:38 schrieb Barry Smith:
>> 
>>   Are you sure you have the correct PETSc branch? From configure.log it has
>> 
>>             Defined "VERSION_GIT" to ""v3.16.2-466-g959e1fce86""
>>             Defined "VERSION_DATE_GIT" to ""2021-12-18 11:17:24 -0600""
>>             Defined "VERSION_BRANCH_GIT" to ""master""
>> 
>> It should have balay/slu-without-omp-3 for the branch.
>> 
>> 
>> 
>>> On Dec 20, 2021, at 10:50 AM, Roland Richter <roland.richter at ntnu.no <mailto:roland.richter at ntnu.no>> wrote:
>>> 
>>> In that case it fails with
>>> 
>>> ~/Downloads/git-files/petsc/mpich-complex-linux-gcc-demo/externalpackages/git.superlu_dist/SRC/cublas_utils.h:22:10: fatal error: cublas_v2.h: No such file or directory
>>> 
>>> even though this header is available. I assume some header paths are not set correctly?
>>> 
>>> Thanks,
>>> 
>>> regards,
>>> 
>>> Roland
>>> 
>>> Am 20.12.21 um 16:29 schrieb Barry Smith:
>>>> 
>>>>   Please try the branch balay/slu-without-omp-3  It is in MR https://gitlab.com/petsc/petsc/-/merge_requests/4635 <https://gitlab.com/petsc/petsc/-/merge_requests/4635>
>>>> 
>>>> 
>>>> 
>>>>> On Dec 20, 2021, at 8:14 AM, Roland Richter <roland.richter at ntnu.no <mailto:roland.richter at ntnu.no>> wrote:
>>>>> 
>>>>> Hei,
>>>>> 
>>>>> I tried to combine CUDA with superlu_dist in petsc using the following configure-line:
>>>>> 
>>>>> ./configure PETSC_ARCH=mpich-complex-linux-gcc-demo --CC=/opt/intel/oneapi/mpi/2021.5.0/bin/mpicc --CXX=/opt/intel/oneapi/mpi/2021.5.0/bin/mpicxx --FC=/opt/intel/oneapi/mpi/2021.5.0/bin/mpifc --CFLAGS="-mavx2 -march=native -O3" --CXXFLAGS="-mavx2 -march=native -O3" --FFLAGS="-mavx2 -march=native -O3" --CUDAFLAGS=-allow-unsupported-compiler --CUDA-CXX=g++ --prefix=/opt/petsc --with-blaslapack=1 --with-mpi=1 --with-scalar-type=complex --download-suitesparse=1 --with-cuda --with-debugging=0 --with-openmp --download-superlu_dist --force
>>>>> 
>>>>> but the configure-step fails with several errors correlated with CUDA and superlu_dist, the first one being
>>>>> 
>>>>> cublas_utils.c:21:37: error: ‘CUDART_VERSION’ undeclared (first use in this function); did you mean ‘CUDA_VERSION’?
>>>>>    21 |     printf("CUDA version:   v %d\n",CUDART_VERSION);
>>>>>       |                                     ^~~~~~~~~~~~~~
>>>>>       |                                     CUDA_VERSION
>>>>> 
>>>>> Compiling superlu_dist separately works, though (including CUDA).
>>>>> 
>>>>> Is there a bug somewhere in the configure-routine? I attached the full configure-log.
>>>>> 
>>>>> Thanks!
>>>>> 
>>>>> Regards,
>>>>> 
>>>>> Roland
>>>>> 
>>>>> <configure.log>
>>>> 
>>> <configure.log>
>> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20211220/bc7bfe68/attachment-0001.html>