tu-c0r2n78 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 1 device=1 binding=--interleave=2,3 tu-c0r2n78 - 1 device=1 binding=--interleave=2,3 tu-c0r2n87 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 2 device=2 binding=--interleave=4,5 tu-c0r2n93 - 0 device=0 binding=--interleave=0,1 tu-c0r2n84 - 0 device=0 binding=--interleave=0,1 tu-c0r2n87 - 1 device=1 binding=--interleave=2,3 tu-c0r2n75 - 3 device=3 binding=--interleave=6,7 tu-c0r2n78 - 2 device=2 binding=--interleave=4,5 tu-c0r2n72 - 1 device=1 binding=--interleave=2,3 tu-c0r2n72 - 0 device=0 binding=--interleave=0,1 tu-c0r2n93 - 1 device=1 binding=--interleave=2,3 tu-c0r2n90 - 0 device=0 binding=--interleave=0,1 tu-c0r2n84 - 2 device=2 binding=--interleave=4,5 tu-c0r2n78 - 3 device=3 binding=--interleave=6,7 tu-c0r2n72 - 2 device=2 binding=--interleave=4,5 tu-c0r2n72 - 3 device=3 binding=--interleave=6,7 tu-c0r2n87 - 2 device=2 binding=--interleave=4,5 tu-c0r2n84 - 3 device=3 binding=--interleave=6,7 tu-c0r2n84 - 1 device=1 binding=--interleave=2,3 tu-c0r2n90 - 1 device=1 binding=--interleave=2,3 tu-c0r2n93 - 3 device=3 binding=--interleave=6,7 tu-c0r2n87 - 3 device=3 binding=--interleave=6,7 tu-c0r2n93 - 2 device=2 binding=--interleave=4,5 tu-c0r2n90 - 2 device=2 binding=--interleave=4,5 tu-c0r2n90 - 3 device=3 binding=--interleave=6,7 tu-c0r2n81 - 2 device=2 binding=--interleave=4,5 tu-c0r2n81 - 0 device=0 binding=--interleave=0,1 tu-c0r2n81 - 3 device=3 binding=--interleave=6,7 tu-c0r2n81 - 1 device=1 binding=--interleave=2,3 OPENMPI detected AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no OPENMPI detected AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no OPENMPI detected AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no OPENMPI detected AcceleratorCudaInit[0]: ======================== AcceleratorCudaInit[0]: Device Number : 0 AcceleratorCudaInit[0]: ======================== AcceleratorCudaInit[0]: Device identifier: NVIDIA A100-SXM4-40GB AcceleratorCudaInit[0]: totalGlobalMem: 42505273344 AcceleratorCudaInit[0]: managedMemory: 1 AcceleratorCudaInit[0]: isMultiGpuBoard: 0 AcceleratorCudaInit[0]: warpSize: 32 AcceleratorCudaInit[0]: pciBusID: 3 AcceleratorCudaInit[0]: pciDeviceID: 0 AcceleratorCudaInit[0]: maxGridSize (2147483647,65535,65535) AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no OPENMPI detected OPENMPI detected AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no OPENMPI detected OPENMPI detected AcceleratorCudaInit[0]: ======================== AcceleratorCudaInit[0]: Device Number : 0 AcceleratorCudaInit[0]: ======================== AcceleratorCudaInit[0]: Device identifier: NVIDIA A100-SXM4-40GB AcceleratorCudaInit[0]: totalGlobalMem: 42505273344 AcceleratorCudaInit[0]: managedMemory: 1 AcceleratorCudaInit[0]: isMultiGpuBoard: 0 AcceleratorCudaInit[0]: warpSize: 32 AcceleratorCudaInit[0]: pciBusID: 3 AcceleratorCudaInit[0]: pciDeviceID: 0 AcceleratorCudaInit[0]: maxGridSize (2147483647,65535,65535) AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no AcceleratorCudaInit: using default device AcceleratorCudaInit: assume user either uses AcceleratorCudaInit: a) IBM jsrun, or AcceleratorCudaInit: b) invokes through a wrapping script to set CUDA_VISIBLE_DEVICES, UCX_NET_DEVICES, and numa binding AcceleratorCudaInit: Configure options --enable-setdevice=no local rank 1 device 0 bus id: 0000:44:00.0 local rank 3 device 0 bus id: 0000:C4:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 2 device 0 bus id: 0000:84:00.0 SharedMemoryMpi: World communicator of size 32 SharedMemoryMpi: Node communicator of size 4 0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14f000000000 for comms buffers Setting up IPC __|__|__|__|__|__|__|__|__|__|__|__|__|__|__ __|__|__|__|__|__|__|__|__|__|__|__|__|__|__ __|_ | | | | | | | | | | | | _|__ __|_ _|__ __|_ GGGG RRRR III DDDD _|__ __|_ G R R I D D _|__ __|_ G R R I D D _|__ __|_ G GG RRRR I D D _|__ __|_ G G R R I D D _|__ __|_ GGGG R R III DDDD _|__ __|_ _|__ __|__|__|__|__|__|__|__|__|__|__|__|__|__|__ __|__|__|__|__|__|__|__|__|__|__|__|__|__|__ | | | | | | | | | | | | | | Copyright (C) 2015 Peter Boyle, Azusa Yamaguchi, Guido Cossu, Antonin Portelli and other authors This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. Current Grid git commit hash=188d2c7a4dc77807b545f5f2813cdb589b9e44ca: (HEAD -> develop, gh/develop, gh/HEAD) uncommited changes Grid : Message : ================================================ Grid : Message : MPI is initialised and logging filters activated Grid : Message : ================================================ Grid : Message : Requested 2147483648 byte stencil comms buffers Grid : Message : MemoryManager Cache 34004218675 bytes Grid : Message : MemoryManager::Init() setting up Grid : Message : MemoryManager::Init() cache pool for recent allocations: SMALL 8 LARGE 2 Grid : Message : MemoryManager::Init() Non unified: Caching accelerator data in dedicated memory Grid : Message : MemoryManager::Init() Using cudaMalloc Grid : Message : 1.349976 s : Grid Layout Grid : Message : 1.349980 s : Global lattice size : 48 48 48 48 Grid : Message : 1.349988 s : OpenMP threads : 4 Grid : Message : 1.349991 s : MPI tasks : 2 2 2 4 Grid : Message : 1.361731 s : Making s innermost grids Grid : Message : 1.377917 s : Initialising 4d RNG Grid : Message : 1.394034 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.394060 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 1.597020 s : Initialising 5d RNG Grid : Message : 1.823564 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 1.823607 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 4.476607 s : Initialised RNGs Grid : Message : 5.204784 s : Drawing gauge field Grid : Message : 5.318953 s : Random gauge initialised Grid : Message : 5.328973 s : Setting up Cshift based reference Grid : Message : 10.884921 s : ***************************************************************** Grid : Message : 10.884946 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 10.884947 s : ***************************************************************** Grid : Message : 10.884948 s : ***************************************************************** Grid : Message : 10.884949 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 10.884950 s : * Vectorising space-time by 8 Grid : Message : 10.884951 s : * VComplexF size is 64 B Grid : Message : 10.884952 s : * SINGLE precision Grid : Message : 10.884953 s : * Using Overlapped Comms/Compute Grid : Message : 10.884954 s : * Using GENERIC Nc WilsonKernels Grid : Message : 10.884955 s : ***************************************************************** Grid : Message : 11.498515 s : Called warmup Grid : Message : 160.334905 s : Called Dw 30000 times in 1.48836e+08 us Grid : Message : 160.334966 s : mflop/s = 2.25981e+07 Grid : Message : 160.334968 s : mflop/s per rank = 706191 Grid : Message : 160.334970 s : mflop/s per node = 2.82476e+06 Grid : Message : 160.334972 s : RF GiB/s (base 2) = 45918.8 Grid : Message : 160.334974 s : mem GiB/s (base 2) = 28699.3 Grid : Message : 160.336049 s : norm diff 1.05759e-13 Grid : Message : 160.353852 s : #### Dhop calls report Grid : Message : 160.353859 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 160.353863 s : WilsonFermion5D TotalTime /Calls : 2481.93 us Grid : Message : 160.353865 s : WilsonFermion5D CommTime /Calls : 1556.12 us Grid : Message : 160.353867 s : WilsonFermion5D FaceTime /Calls : 420.84 us Grid : Message : 160.353869 s : WilsonFermion5D ComputeTime1/Calls : 2.90742 us Grid : Message : 160.353871 s : WilsonFermion5D ComputeTime2/Calls : 518.391 us Grid : Message : 160.353945 s : Average mflops/s per call : 1.81556e+10 Grid : Message : 160.353948 s : Average mflops/s per call per rank : 5.67363e+08 Grid : Message : 160.353950 s : Average mflops/s per call per node : 2.26945e+09 Grid : Message : 160.353952 s : Average mflops/s per call (full) : 2.29967e+07 Grid : Message : 160.353954 s : Average mflops/s per call per rank (full): 718646 Grid : Message : 160.353956 s : Average mflops/s per call per node (full): 2.87458e+06 Grid : Message : 160.353958 s : WilsonFermion5D Stencil Grid : Message : 160.353959 s : WilsonFermion5D StencilEven Grid : Message : 160.353960 s : WilsonFermion5D StencilOdd Grid : Message : 160.353961 s : WilsonFermion5D Stencil Reporti() Grid : Message : 160.353962 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 160.353963 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 169.450973 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 169.451002 s : Called DwDag Grid : Message : 169.451003 s : norm dag result 12.0422 Grid : Message : 169.459099 s : norm dag ref 12.0422 Grid : Message : 169.465313 s : norm dag diff 7.13141e-14 Grid : Message : 169.480865 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 169.545779 s : src_e0.499992 Grid : Message : 169.617290 s : src_o0.500008 Grid : Message : 169.634651 s : ********************************************************* Grid : Message : 169.634656 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 169.634659 s : * Vectorising space-time by 8 Grid : Message : 169.634661 s : * SINGLE precision Grid : Message : 169.634663 s : * Using Overlapped Comms/Compute Grid : Message : 169.634664 s : * Using GENERIC Nc WilsonKernels Grid : Message : 169.634665 s : ********************************************************* Grid : Message : 249.808092 s : Deo mflop/s = 2.09787e+07 Grid : Message : 249.808124 s : Deo mflop/s per rank 655584 Grid : Message : 249.808126 s : Deo mflop/s per node 2.62234e+06 Grid : Message : 249.808129 s : #### Dhop calls report Grid : Message : 249.808131 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 249.808133 s : WilsonFermion5D TotalTime /Calls : 2672.23 us Grid : Message : 249.808135 s : WilsonFermion5D CommTime /Calls : 1622.82 us Grid : Message : 249.808137 s : WilsonFermion5D FaceTime /Calls : 517.669 us Grid : Message : 249.808139 s : WilsonFermion5D ComputeTime1/Calls : 5.04733 us Grid : Message : 249.808141 s : WilsonFermion5D ComputeTime2/Calls : 557.101 us Grid : Message : 249.808166 s : Average mflops/s per call : 1.04805e+10 Grid : Message : 249.808170 s : Average mflops/s per call per rank : 3.27515e+08 Grid : Message : 249.808173 s : Average mflops/s per call per node : 1.31006e+09 Grid : Message : 249.808176 s : Average mflops/s per call (full) : 2.1359e+07 Grid : Message : 249.808180 s : Average mflops/s per call per rank (full): 667467 Grid : Message : 249.808182 s : Average mflops/s per call per node (full): 2.66987e+06 Grid : Message : 249.808186 s : WilsonFermion5D Stencil Grid : Message : 249.808188 s : WilsonFermion5D StencilEven Grid : Message : 249.808191 s : WilsonFermion5D StencilOdd Grid : Message : 249.808194 s : WilsonFermion5D Stencil Reporti() Grid : Message : 249.808195 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 249.808197 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 249.834153 s : r_e6.02129 Grid : Message : 249.837114 s : r_o6.02097 Grid : Message : 249.839935 s : res12.0423 Grid : Message : 249.951239 s : norm diff 0 Grid : Message : 250.995330 s : norm diff even 0 Grid : Message : 250.171057 s : norm diff odd 0