[petsc-dev] First call to cudaMalloc or cudaFree is very slow on summit

Matthew Knepley knepley at gmail.com
Sat Feb 8 17:03:04 CST 2020


On Sat, Feb 8, 2020 at 4:34 PM Zhang, Hong via petsc-dev <
petsc-dev at mcs.anl.gov> wrote:

> I did some further investigation. The overhead persists for both the PETSc
> shared library and the static library. In the previous example, it does not
> call any PETSc function, the first CUDA function becomes very slow when it
> is linked to the petsc so. This indicates that the slowdown occurs if the
> symbol (cudafree)is searched through the petsc so, but does not occur if
> the symbol is found directly in the cuda runtime lib.
>
> So the issue has nothing to do with the dynamic linker. The following
> example can be used to easily reproduce the problem (cudaFree(0) always
> takes ~7.5 seconds).
>

1) This should go to OLCF admin as Jeff suggests

2) Just to make sure I understand, a static executable with this code is
still slow on the cudaFree(), since CUDA is a shared library by default.

I think we should try:

  a) Forcing a full static link, if possible

  b) Asking OLCF about link resolution order

It sounds like a similar thing I have seen in the past where link
resolution order can exponentially increase load time.

  Thanks,

     Matt


> bash-4.2$ cat ex_simple_petsc.c
> #include <time.h>
> #include <cuda_runtime.h>
> #include <stdio.h>
> #include <petscmat.h>
>
> int main(int argc,char **args)
> {
>   clock_t start,s1,s2,s3;
>   double  cputime;
>   double  *init,tmp[100] = {0};
>   PetscErrorCode ierr=0;
>
>   ierr = PetscInitialize(&argc,&args,(char*)0,NULL);if (ierr) return ierr;
>   start = clock();
>   cudaFree(0);
>   s1 = clock();
>   cudaMalloc((void **)&init,100*sizeof(double));
>   s2 = clock();
>   cudaMemcpy(init,tmp,100*sizeof(double),cudaMemcpyHostToDevice);
>   s3 = clock();
>   printf("free time =%lf malloc time =%lf copy time =%lf\n",((double) (s1
> - start)) / CLOCKS_PER_SEC,((double) (s2 - s1)) / CLOCKS_PER_SEC,((double)
> (s3 - s2)) / CLOCKS_PER_SEC);
>   ierr = PetscFinalize();
>   return ierr;
> }
>
> Hong
>
> On Feb 7, 2020, at 3:09 PM, Zhang, Hong <hongzhang at anl.gov> wrote:
>
> Note that the overhead was triggered by the first call to a CUDA function.
> So it seems that the first CUDA function triggered loading petsc so (if
> petsc so is linked), which is slow on the summit file system.
>
> Hong
>
> On Feb 7, 2020, at 2:54 PM, Zhang, Hong via petsc-dev <
> petsc-dev at mcs.anl.gov> wrote:
>
> Linking any other shared library does not slow down the execution. The
> PETSc shared library is the only one causing trouble.
>
> Here are the ldd output for two different versions. For the first version,
> I removed -lpetsc and it ran very fast. The second (slow) version was
> linked to petsc so.
>
> bash-4.2$ ldd ex_simple
>         linux-vdso64.so.1 =>  (0x0000200000050000)
>         liblapack.so.0 =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/liblapack.so.0
> (0x0000200000070000)
>         libblas.so.0 =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libblas.so.0
> (0x00002000009b0000)
>         libhdf5hl_fortran.so.100 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5hl_fortran.so.100
> (0x0000200000e80000)
>         libhdf5_fortran.so.100 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5_fortran.so.100
> (0x0000200000ed0000)
>         libhdf5_hl.so.100 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5_hl.so.100
> (0x0000200000f50000)
>         libhdf5.so.103 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5.so.103
> (0x0000200000fb0000)
>         libX11.so.6 => /usr/lib64/libX11.so.6 (0x00002000015e0000)
>         libcufft.so.10 => /sw/summit/cuda/10.1.168/lib64/libcufft.so.10
> (0x0000200001770000)
>         libcublas.so.10 => /sw/summit/cuda/10.1.168/lib64/libcublas.so.10
> (0x0000200009b00000)
>         libcudart.so.10.1 =>
> /sw/summit/cuda/10.1.168/lib64/libcudart.so.10.1 (0x000020000d950000)
>         libcusparse.so.10 =>
> /sw/summit/cuda/10.1.168/lib64/libcusparse.so.10 (0x000020000d9f0000)
>         libcusolver.so.10 =>
> /sw/summit/cuda/10.1.168/lib64/libcusolver.so.10 (0x0000200012f50000)
>         libstdc++.so.6 => /usr/lib64/libstdc++.so.6 (0x000020001dc40000)
>         libdl.so.2 => /usr/lib64/libdl.so.2 (0x000020001ddd0000)
>         libpthread.so.0 => /usr/lib64/libpthread.so.0 (0x000020001de00000)
>         libmpiprofilesupport.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpiprofilesupport.so.3
> (0x000020001de40000)
>         libmpi_ibm_usempi.so =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpi_ibm_usempi.so
> (0x000020001de70000)
>         libmpi_ibm_mpifh.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpi_ibm_mpifh.so.3
> (0x000020001dea0000)
>         libmpi_ibm.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpi_ibm.so.3
> (0x000020001df40000)
>         libpgf90rtl.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf90rtl.so
> (0x000020001e0b0000)
>         libpgf90.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf90.so
> (0x000020001e0f0000)
>         libpgf90_rpm1.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf90_rpm1.so
> (0x000020001e6a0000)
>         libpgf902.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf902.so
> (0x000020001e6d0000)
>         libpgftnrtl.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgftnrtl.so
> (0x000020001e700000)
>         libatomic.so.1 => /usr/lib64/libatomic.so.1 (0x000020001e730000)
>         libpgkomp.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgkomp.so
> (0x000020001e760000)
>         libomp.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libomp.so
> (0x000020001e790000)
>         libomptarget.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libomptarget.so
> (0x000020001e880000)
>         libpgmath.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgmath.so
> (0x000020001e8b0000)
>         libpgc.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgc.so
> (0x000020001e9d0000)
>         librt.so.1 => /usr/lib64/librt.so.1 (0x000020001eb40000)
>         libm.so.6 => /usr/lib64/libm.so.6 (0x000020001eb70000)
>         libgcc_s.so.1 => /usr/lib64/libgcc_s.so.1 (0x000020001ec60000)
>         libc.so.6 => /usr/lib64/libc.so.6 (0x000020001eca0000)
>         libz.so.1 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/zlib-1.2.11-2htm7ws4hgrthi5tyjnqxtjxgpfklxsc/lib/libz.so.1
> (0x000020001ee90000)
>         libxcb.so.1 => /usr/lib64/libxcb.so.1 (0x000020001eef0000)
>         /lib64/ld64.so.2 (0x0000200000000000)
>         libcublasLt.so.10 =>
> /sw/summit/cuda/10.1.168/lib64/libcublasLt.so.10 (0x000020001ef40000)
>         libutil.so.1 => /usr/lib64/libutil.so.1 (0x0000200020e50000)
>         libhwloc_ompi.so.15 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libhwloc_ompi.so.15
> (0x0000200020e80000)
>         libevent-2.1.so.6 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libevent-2.1.so.6
> (0x0000200020ef0000)
>         libevent_pthreads-2.1.so.6 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libevent_pthreads-2.1.so.6
> (0x0000200020f70000)
>         libopen-rte.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libopen-rte.so.3
> (0x0000200020fa0000)
>         libopen-pal.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libopen-pal.so.3
> (0x00002000210b0000)
>         libXau.so.6 => /usr/lib64/libXau.so.6 (0x00002000211a0000)
>
>
> bash-4.2$ ldd ex_simple_slow
>         linux-vdso64.so.1 =>  (0x0000200000050000)
>         libpetsc.so.3.012 =>
> /autofs/nccs-svm1_home1/hongzh/Projects/petsc/arch-olcf-summit-sell-opt/lib/libpetsc.so.3.012
> (0x0000200000070000)
>         liblapack.so.0 =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/liblapack.so.0
> (0x0000200002be0000)
>         libblas.so.0 =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libblas.so.0
> (0x0000200003520000)
>         libhdf5hl_fortran.so.100 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5hl_fortran.so.100
> (0x00002000039f0000)
>         libhdf5_fortran.so.100 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5_fortran.so.100
> (0x0000200003a40000)
>         libhdf5_hl.so.100 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5_hl.so.100
> (0x0000200003ac0000)
>         libhdf5.so.103 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/hdf5-1.10.3-pgiul2yf4auv7krecd72t6vupd7e3qgn/lib/libhdf5.so.103
> (0x0000200003b20000)
>         libX11.so.6 => /usr/lib64/libX11.so.6 (0x0000200004150000)
>         libcufft.so.10 => /sw/summit/cuda/10.1.168/lib64/libcufft.so.10
> (0x00002000042e0000)
>         libcublas.so.10 => /sw/summit/cuda/10.1.168/lib64/libcublas.so.10
> (0x000020000c670000)
>         libcudart.so.10.1 =>
> /sw/summit/cuda/10.1.168/lib64/libcudart.so.10.1 (0x00002000104c0000)
>         libcusparse.so.10 =>
> /sw/summit/cuda/10.1.168/lib64/libcusparse.so.10 (0x0000200010560000)
>         libcusolver.so.10 =>
> /sw/summit/cuda/10.1.168/lib64/libcusolver.so.10 (0x0000200015ac0000)
>         libstdc++.so.6 => /usr/lib64/libstdc++.so.6 (0x00002000207b0000)
>         libdl.so.2 => /usr/lib64/libdl.so.2 (0x0000200020940000)
>         libpthread.so.0 => /usr/lib64/libpthread.so.0 (0x0000200020970000)
>         libmpiprofilesupport.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpiprofilesupport.so.3
> (0x00002000209b0000)
>         libmpi_ibm_usempi.so =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpi_ibm_usempi.so
> (0x00002000209e0000)
>         libmpi_ibm_mpifh.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpi_ibm_mpifh.so.3
> (0x0000200020a10000)
>         libmpi_ibm.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libmpi_ibm.so.3
> (0x0000200020ab0000)
>         libpgf90rtl.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf90rtl.so
> (0x0000200020c20000)
>         libpgf90.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf90.so
> (0x0000200020c60000)
>         libpgf90_rpm1.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf90_rpm1.so
> (0x0000200021210000)
>         libpgf902.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgf902.so
> (0x0000200021240000)
>         libpgftnrtl.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgftnrtl.so
> (0x0000200021270000)
>         libatomic.so.1 => /usr/lib64/libatomic.so.1 (0x00002000212a0000)
>         libpgkomp.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgkomp.so
> (0x00002000212d0000)
>         libomp.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libomp.so
> (0x0000200021300000)
>         libomptarget.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libomptarget.so
> (0x00002000213f0000)
>         libpgmath.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgmath.so
> (0x0000200021420000)
>         libpgc.so =>
> /autofs/nccs-svm1_sw/summit/.swci/0-core/opt/spack/20180914/linux-rhel7-ppc64le/gcc-4.8.5/pgi-19.4-6acz4xyqjlpoaonjiiqjme2aknrfnzoy/linuxpower/19.4/lib/libpgc.so
> (0x0000200021540000)
>         librt.so.1 => /usr/lib64/librt.so.1 (0x00002000216b0000)
>         libm.so.6 => /usr/lib64/libm.so.6 (0x00002000216e0000)
>         libgcc_s.so.1 => /usr/lib64/libgcc_s.so.1 (0x00002000217d0000)
>         libc.so.6 => /usr/lib64/libc.so.6 (0x0000200021810000)
>         libz.so.1 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/zlib-1.2.11-2htm7ws4hgrthi5tyjnqxtjxgpfklxsc/lib/libz.so.1
> (0x0000200021a10000)
>         libxcb.so.1 => /usr/lib64/libxcb.so.1 (0x0000200021a60000)
>         /lib64/ld64.so.2 (0x0000200000000000)
>         libcublasLt.so.10 =>
> /sw/summit/cuda/10.1.168/lib64/libcublasLt.so.10 (0x0000200021ab0000)
>         libutil.so.1 => /usr/lib64/libutil.so.1 (0x00002000239c0000)
>         libhwloc_ompi.so.15 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libhwloc_ompi.so.15
> (0x00002000239f0000)
>         libevent-2.1.so.6 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libevent-2.1.so.6
> (0x0000200023a60000)
>         libevent_pthreads-2.1.so.6 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libevent_pthreads-2.1.so.6
> (0x0000200023ae0000)
>         libopen-rte.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libopen-rte.so.3
> (0x0000200023b10000)
>         libopen-pal.so.3 =>
> /autofs/nccs-svm1_sw/summit/.swci/1-compute/opt/spack/20180914/linux-rhel7-ppc64le/pgi-19.4/spectrum-mpi-10.3.0.1-20190611-4ymaahbai7ehhw4rves5jjiwon2laz3a/lib/libopen-pal.so.3
> (0x0000200023c20000)
>         libXau.so.6 => /usr/lib64/libXau.so.6 (0x0000200023d10000)
>
>
> On Feb 7, 2020, at 2:31 PM, Smith, Barry F. <bsmith at mcs.anl.gov> wrote:
>
>
>  ldd -o on the executable of both linkings of your code.
>
>  My guess is that without PETSc it is linking the static version of the
> needed libraries and with PETSc the shared. And, in typical fashion, the
> shared libraries are off on some super slow file system so take a long time
> to be loaded and linked in on demand.
>
>   Still a performance bug in Summit.
>
>   Barry
>
>
> On Feb 7, 2020, at 12:23 PM, Zhang, Hong via petsc-dev <
> petsc-dev at mcs.anl.gov> wrote:
>
> Hi all,
>
> Previously I have noticed that the first call to a CUDA function such as
> cudaMalloc and cudaFree in PETSc takes a long time (7.5 seconds) on summit.
> Then I prepared a simple example as attached to help OCLF reproduce the
> problem. It turned out that the problem was  caused by PETSc. The
> 7.5-second overhead can be observed only when the PETSc lib is linked. If I
> do not link PETSc, it runs normally. Does anyone have any idea why this
> happens and how to fix it?
>
> Hong (Mr.)
>
> bash-4.2$ cat ex_simple.c
> #include <time.h>
> #include <cuda_runtime.h>
> #include <stdio.h>
>
> int main(int argc,char **args)
> {
> clock_t start,s1,s2,s3;
> double  cputime;
> double   *init,tmp[100] = {0};
>
> start = clock();
> cudaFree(0);
> s1 = clock();
> cudaMalloc((void **)&init,100*sizeof(double));
> s2 = clock();
> cudaMemcpy(init,tmp,100*sizeof(double),cudaMemcpyHostToDevice);
> s3 = clock();
> printf("free time =%lf malloc time =%lf copy time =%lf\n",((double) (s1 -
> start)) / CLOCKS_PER_SEC,((double) (s2 - s1)) / CLOCKS_PER_SEC,((double)
> (s3 - s2)) / CLOCKS_PER_SEC);
>
> return 0;
> }
>
>
>
>
>
>
>

-- 
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener

https://www.cse.buffalo.edu/~knepley/ <http://www.cse.buffalo.edu/~knepley/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20200208/f86a0c19/attachment-0001.html>


More information about the petsc-dev mailing list