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.
<bsm...@mcs.anl.gov<mailto:bsm...@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@mcs.anl.gov<mailto:petsc-dev@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;
}
