tu-c0r1n72 - 0 device=0 binding=--interleave=0,1 tu-c0r1n75 - 0 device=0 binding=--interleave=0,1 tu-c0r1n72 - 1 device=1 binding=--interleave=2,3 tu-c0r1n93 - 0 device=0 binding=--interleave=0,1 tu-c0r1n84 - 0 device=0 binding=--interleave=0,1 tu-c0r1n72 - 2 device=2 binding=--interleave=4,5 tu-c0r1n72 - 3 device=3 binding=--interleave=6,7 tu-c0r1n93 - 1 device=1 binding=--interleave=2,3 tu-c0r1n75 - 1 device=1 binding=--interleave=2,3 tu-c0r1n93 - 2 device=2 binding=--interleave=4,5 tu-c0r1n84 - 2 device=2 binding=--interleave=4,5 tu-c0r1n93 - 3 device=3 binding=--interleave=6,7 tu-c0r1n84 - 3 device=3 binding=--interleave=6,7 tu-c0r1n84 - 1 device=1 binding=--interleave=2,3 tu-c0r1n75 - 2 device=2 binding=--interleave=4,5 tu-c0r1n75 - 3 device=3 binding=--interleave=6,7 tu-c0r1n87 - 0 device=0 binding=--interleave=0,1 tu-c0r1n87 - 1 device=1 binding=--interleave=2,3 tu-c0r1n87 - 3 device=3 binding=--interleave=6,7 tu-c0r1n87 - 2 device=2 binding=--interleave=4,5 tu-c0r1n81 - 0 device=0 binding=--interleave=0,1 tu-c0r1n81 - 2 device=2 binding=--interleave=4,5 tu-c0r1n81 - 1 device=1 binding=--interleave=2,3 tu-c0r1n81 - 3 device=3 binding=--interleave=6,7 tu-c0r1n78 - 0 device=0 binding=--interleave=0,1 tu-c0r1n78 - 2 device=2 binding=--interleave=4,5 tu-c0r1n78 - 3 device=3 binding=--interleave=6,7 tu-c0r1n78 - 1 device=1 binding=--interleave=2,3 tu-c0r1n90 - 0 device=0 binding=--interleave=0,1 tu-c0r1n90 - 2 device=2 binding=--interleave=4,5 tu-c0r1n90 - 1 device=1 binding=--interleave=2,3 tu-c0r1n90 - 3 device=3 binding=--interleave=6,7 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: 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: 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: 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: ================================================ local rank 3 device 0 bus id: 0000:C4:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 1 device 0 bus id: 0000:44:00.0 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 0x1520a0000000 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 : 1.451132 s : Grid Layout Grid : Message : 1.451136 s : Global lattice size : 64 64 64 128 Grid : Message : 1.451141 s : OpenMP threads : 4 Grid : Message : 1.451143 s : MPI tasks : 2 2 2 4 Grid : Message : 1.490207 s : Making s innermost grids Grid : Message : 1.546698 s : Initialising 4d RNG Grid : Message : 1.639951 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.639978 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 2.448983 s : Initialising 5d RNG Grid : Message : 3.857910 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 3.857941 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 20.528379 s : Initialised RNGs Grid : Message : 24.642198 s : Drawing gauge field Grid : Message : 25.370279 s : Random gauge initialised Grid : Message : 25.386364 s : Setting up Cshift based reference Grid : Message : 54.680530 s : ***************************************************************** Grid : Message : 54.680554 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 54.680555 s : ***************************************************************** Grid : Message : 54.680556 s : ***************************************************************** Grid : Message : 54.680557 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 54.680558 s : * Vectorising space-time by 8 Grid : Message : 54.680559 s : * VComplexF size is 64 B Grid : Message : 54.680560 s : * SINGLE precision Grid : Message : 54.680563 s : * Using Overlapped Comms/Compute Grid : Message : 54.680564 s : * Using GENERIC Nc WilsonKernels Grid : Message : 54.680565 s : ***************************************************************** Grid : Message : 56.720636 s : Called warmup Grid : Message : 341.354661 s : Called Dw 30000 times in 2.84633e+08 us Grid : Message : 341.354717 s : mflop/s = 7.46929e+07 Grid : Message : 341.354719 s : mflop/s per rank = 2.33415e+06 Grid : Message : 341.354721 s : mflop/s per node = 9.33662e+06 Grid : Message : 341.354723 s : RF GiB/s (base 2) = 151774 Grid : Message : 341.354725 s : mem GiB/s (base 2) = 94858.9 Grid : Message : 341.358222 s : norm diff 1.07359e-13 Grid : Message : 341.408574 s : #### Dhop calls report Grid : Message : 341.408581 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 341.408584 s : WilsonFermion5D TotalTime /Calls : 4747.94 us Grid : Message : 341.408586 s : WilsonFermion5D CommTime /Calls : 3238.54 us Grid : Message : 341.408588 s : WilsonFermion5D FaceTime /Calls : 477.179 us Grid : Message : 341.408590 s : WilsonFermion5D ComputeTime1/Calls : 5.20729 us Grid : Message : 341.408592 s : WilsonFermion5D ComputeTime2/Calls : 1046.27 us Grid : Message : 341.408654 s : Average mflops/s per call : 6.22503e+10 Grid : Message : 341.408657 s : Average mflops/s per call per rank : 1.94532e+09 Grid : Message : 341.408659 s : Average mflops/s per call per node : 7.78129e+09 Grid : Message : 341.408661 s : Average mflops/s per call (full) : 7.59861e+07 Grid : Message : 341.408664 s : Average mflops/s per call per rank (full): 2.37457e+06 Grid : Message : 341.408666 s : Average mflops/s per call per node (full): 9.49826e+06 Grid : Message : 341.408668 s : WilsonFermion5D Stencil Grid : Message : 341.408669 s : WilsonFermion5D StencilEven Grid : Message : 341.408672 s : WilsonFermion5D StencilOdd Grid : Message : 341.408674 s : WilsonFermion5D Stencil Reporti() Grid : Message : 341.408676 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 341.408678 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 396.742581 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 396.742602 s : Called DwDag Grid : Message : 396.742603 s : norm dag result 12.0421 Grid : Message : 396.756893 s : norm dag ref 12.0421 Grid : Message : 396.773260 s : norm dag diff 7.28475e-14 Grid : Message : 396.816075 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 397.193717 s : src_e0.499997 Grid : Message : 397.577696 s : src_o0.500003 Grid : Message : 397.675628 s : ********************************************************* Grid : Message : 397.675631 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 397.675632 s : * Vectorising space-time by 8 Grid : Message : 397.675633 s : * SINGLE precision Grid : Message : 397.675634 s : * Using Overlapped Comms/Compute Grid : Message : 397.675635 s : * Using GENERIC Nc WilsonKernels Grid : Message : 397.675636 s : ********************************************************* Grid : Message : 540.232805 s : Deo mflop/s = 7.45971e+07 Grid : Message : 540.232832 s : Deo mflop/s per rank 2.33116e+06 Grid : Message : 540.232834 s : Deo mflop/s per node 9.32463e+06 Grid : Message : 540.232837 s : #### Dhop calls report Grid : Message : 540.232839 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 540.232841 s : WilsonFermion5D TotalTime /Calls : 4751.62 us Grid : Message : 540.232843 s : WilsonFermion5D CommTime /Calls : 3173.44 us Grid : Message : 540.232845 s : WilsonFermion5D FaceTime /Calls : 604.695 us Grid : Message : 540.232847 s : WilsonFermion5D ComputeTime1/Calls : 6.28629 us Grid : Message : 540.232849 s : WilsonFermion5D ComputeTime2/Calls : 999.947 us Grid : Message : 540.232870 s : Average mflops/s per call : 5.14652e+10 Grid : Message : 540.232874 s : Average mflops/s per call per rank : 1.60829e+09 Grid : Message : 540.232878 s : Average mflops/s per call per node : 6.43315e+09 Grid : Message : 540.232881 s : Average mflops/s per call (full) : 7.59272e+07 Grid : Message : 540.232884 s : Average mflops/s per call per rank (full): 2.37273e+06 Grid : Message : 540.232887 s : Average mflops/s per call per node (full): 9.49091e+06 Grid : Message : 540.232890 s : WilsonFermion5D Stencil Grid : Message : 540.232892 s : WilsonFermion5D StencilEven Grid : Message : 540.232893 s : WilsonFermion5D StencilOdd Grid : Message : 540.232896 s : WilsonFermion5D Stencil Reporti() Grid : Message : 540.232897 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 540.232900 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 540.304917 s : r_e6.02113 Grid : Message : 540.311850 s : r_o6.02101 Grid : Message : 540.318515 s : res12.0421 Grid : Message : 540.994922 s : norm diff 0 Grid : Message : 541.747359 s : norm diff even 0 Grid : Message : 542.139558 s : norm diff odd 0