tu-c0r2n72 - 0 device=0 binding=--interleave=0,1 tu-c0r2n72 - 1 device=1 binding=--interleave=2,3 tu-c0r2n72 - 2 device=2 binding=--interleave=4,5 tu-c0r2n72 - 3 device=3 binding=--interleave=6,7 tu-c0r2n78 - 1 device=1 binding=--interleave=2,3 tu-c0r2n78 - 3 device=3 binding=--interleave=6,7 tu-c0r2n78 - 0 device=0 binding=--interleave=0,1 tu-c0r2n93 - 1 device=1 binding=--interleave=2,3 tu-c0r2n78 - 2 device=2 binding=--interleave=4,5 tu-c0r2n93 - 3 device=3 binding=--interleave=6,7 tu-c0r2n93 - 0 device=0 binding=--interleave=0,1 tu-c0r2n93 - 2 device=2 binding=--interleave=4,5 tu-c0r2n75 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 1 device=1 binding=--interleave=2,3 tu-c0r2n75 - 2 device=2 binding=--interleave=4,5 tu-c0r2n75 - 3 device=3 binding=--interleave=6,7 tu-c0r2n90 - 2 device=2 binding=--interleave=4,5 tu-c0r2n90 - 0 device=0 binding=--interleave=0,1 tu-c0r2n90 - 3 device=3 binding=--interleave=6,7 tu-c0r2n90 - 1 device=1 binding=--interleave=2,3 tu-c0r2n87 - 2 device=2 binding=--interleave=4,5 tu-c0r2n87 - 1 device=1 binding=--interleave=2,3 tu-c0r2n87 - 3 device=3 binding=--interleave=6,7 tu-c0r2n87 - 0 device=0 binding=--interleave=0,1 tu-c0r2n84 - 0 device=0 binding=--interleave=0,1 tu-c0r2n84 - 1 device=1 binding=--interleave=2,3 tu-c0r2n84 - 3 device=3 binding=--interleave=6,7 tu-c0r2n84 - 2 device=2 binding=--interleave=4,5 tu-c0r2n81 - 0 device=0 binding=--interleave=0,1 tu-c0r2n81 - 2 device=2 binding=--interleave=4,5 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 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 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 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 1 device 0 bus id: 0000:44:00.0 AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 3 device 0 bus id: 0000:C4:00.0 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 0x152620000000 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 : 1.410572 s : Grid Layout Grid : Message : 1.410577 s : Global lattice size : 48 48 48 48 Grid : Message : 1.410584 s : OpenMP threads : 4 Grid : Message : 1.410587 s : MPI tasks : 2 2 2 4 Grid : Message : 1.422069 s : Making s innermost grids Grid : Message : 1.436430 s : Initialising 4d RNG Grid : Message : 1.452786 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.452812 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 1.695535 s : Initialising 5d RNG Grid : Message : 1.935719 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 1.935757 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 4.571993 s : Initialised RNGs Grid : Message : 5.434592 s : Drawing gauge field Grid : Message : 5.528101 s : Random gauge initialised Grid : Message : 5.533830 s : Setting up Cshift based reference Grid : Message : 10.460627 s : ***************************************************************** Grid : Message : 10.460652 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 10.460653 s : ***************************************************************** Grid : Message : 10.460654 s : ***************************************************************** Grid : Message : 10.460655 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 10.460656 s : * Vectorising space-time by 8 Grid : Message : 10.460657 s : * VComplexF size is 64 B Grid : Message : 10.460658 s : * SINGLE precision Grid : Message : 10.460659 s : * Using Overlapped Comms/Compute Grid : Message : 10.460660 s : * Using GENERIC Nc WilsonKernels Grid : Message : 10.460661 s : ***************************************************************** Grid : Message : 10.959809 s : Called warmup Grid : Message : 91.127659 s : Called Dw 30000 times in 8.01675e+07 us Grid : Message : 91.127722 s : mflop/s = 4.19548e+07 Grid : Message : 91.127724 s : mflop/s per rank = 1.31109e+06 Grid : Message : 91.127726 s : mflop/s per node = 5.24435e+06 Grid : Message : 91.127728 s : RF GiB/s (base 2) = 85251.2 Grid : Message : 91.127730 s : mem GiB/s (base 2) = 53282 Grid : Message : 91.128311 s : norm diff 1.05759e-13 Grid : Message : 91.137629 s : #### Dhop calls report Grid : Message : 91.137637 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 91.137641 s : WilsonFermion5D TotalTime /Calls : 1337.27 us Grid : Message : 91.137643 s : WilsonFermion5D CommTime /Calls : 912.752 us Grid : Message : 91.137645 s : WilsonFermion5D FaceTime /Calls : 206.848 us Grid : Message : 91.137647 s : WilsonFermion5D ComputeTime1/Calls : 2.86259 us Grid : Message : 91.137649 s : WilsonFermion5D ComputeTime2/Calls : 230.59 us Grid : Message : 91.137676 s : Average mflops/s per call : 1.78188e+10 Grid : Message : 91.137680 s : Average mflops/s per call per rank : 5.56837e+08 Grid : Message : 91.137683 s : Average mflops/s per call per node : 2.22735e+09 Grid : Message : 91.137687 s : Average mflops/s per call (full) : 4.26809e+07 Grid : Message : 91.137692 s : Average mflops/s per call per rank (full): 1.33378e+06 Grid : Message : 91.137696 s : Average mflops/s per call per node (full): 5.33512e+06 Grid : Message : 91.137699 s : WilsonFermion5D Stencil Grid : Message : 91.137701 s : WilsonFermion5D StencilEven Grid : Message : 91.137703 s : WilsonFermion5D StencilOdd Grid : Message : 91.137705 s : WilsonFermion5D Stencil Reporti() Grid : Message : 91.137707 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 91.137709 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 99.779635 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 99.779660 s : Called DwDag Grid : Message : 99.779661 s : norm dag result 12.0422 Grid : Message : 99.782195 s : norm dag ref 12.0422 Grid : Message : 99.785016 s : norm dag diff 7.13141e-14 Grid : Message : 99.794656 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 99.850492 s : src_e0.499992 Grid : Message : 99.930831 s : src_o0.500008 Grid : Message : 99.947976 s : ********************************************************* Grid : Message : 99.947980 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 99.947981 s : * Vectorising space-time by 8 Grid : Message : 99.947982 s : * SINGLE precision Grid : Message : 99.947984 s : * Using Overlapped Comms/Compute Grid : Message : 99.947986 s : * Using GENERIC Nc WilsonKernels Grid : Message : 99.947988 s : ********************************************************* Grid : Message : 142.276655 s : Deo mflop/s = 3.97388e+07 Grid : Message : 142.276688 s : Deo mflop/s per rank 1.24184e+06 Grid : Message : 142.276690 s : Deo mflop/s per node 4.96735e+06 Grid : Message : 142.276693 s : #### Dhop calls report Grid : Message : 142.276695 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 142.276697 s : WilsonFermion5D TotalTime /Calls : 1410.77 us Grid : Message : 142.276699 s : WilsonFermion5D CommTime /Calls : 945.198 us Grid : Message : 142.276701 s : WilsonFermion5D FaceTime /Calls : 261.44 us Grid : Message : 142.276703 s : WilsonFermion5D ComputeTime1/Calls : 4.86137 us Grid : Message : 142.276705 s : WilsonFermion5D ComputeTime2/Calls : 228.589 us Grid : Message : 142.276730 s : Average mflops/s per call : 1.01877e+10 Grid : Message : 142.276734 s : Average mflops/s per call per rank : 3.18364e+08 Grid : Message : 142.276737 s : Average mflops/s per call per node : 1.27346e+09 Grid : Message : 142.276740 s : Average mflops/s per call (full) : 4.04575e+07 Grid : Message : 142.276745 s : Average mflops/s per call per rank (full): 1.2643e+06 Grid : Message : 142.276748 s : Average mflops/s per call per node (full): 5.05719e+06 Grid : Message : 142.276752 s : WilsonFermion5D Stencil Grid : Message : 142.276755 s : WilsonFermion5D StencilEven Grid : Message : 142.276756 s : WilsonFermion5D StencilOdd Grid : Message : 142.276757 s : WilsonFermion5D Stencil Reporti() Grid : Message : 142.276759 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 142.276763 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 142.296665 s : r_e6.02129 Grid : Message : 142.298370 s : r_o6.02097 Grid : Message : 142.299632 s : res12.0423 Grid : Message : 142.405123 s : norm diff 0 Grid : Message : 142.533313 s : norm diff even 0 Grid : Message : 142.613424 s : norm diff odd 0