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-c0r2n87 - 0 device=0 binding=--interleave=0,1 tu-c0r2n87 - 1 device=1 binding=--interleave=2,3 tu-c0r2n87 - 2 device=2 binding=--interleave=4,5 tu-c0r2n87 - 3 device=3 binding=--interleave=6,7 tu-c0r2n78 - 2 device=2 binding=--interleave=4,5 tu-c0r2n78 - 1 device=1 binding=--interleave=2,3 tu-c0r2n78 - 3 device=3 binding=--interleave=6,7 tu-c0r2n75 - 2 device=2 binding=--interleave=4,5 tu-c0r2n93 - 3 device=3 binding=--interleave=6,7 tu-c0r2n78 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 1 device=1 binding=--interleave=2,3 tu-c0r2n75 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 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-c0r2n93 - 1 device=1 binding=--interleave=2,3 tu-c0r2n90 - 0 device=0 binding=--interleave=0,1 tu-c0r2n90 - 1 device=1 binding=--interleave=2,3 tu-c0r2n90 - 2 device=2 binding=--interleave=4,5 tu-c0r2n90 - 3 device=3 binding=--interleave=6,7 tu-c0r2n81 - 3 device=3 binding=--interleave=6,7 tu-c0r2n81 - 0 device=0 binding=--interleave=0,1 tu-c0r2n81 - 1 device=1 binding=--interleave=2,3 tu-c0r2n84 - 0 device=0 binding=--interleave=0,1 tu-c0r2n84 - 3 device=3 binding=--interleave=6,7 tu-c0r2n84 - 2 device=2 binding=--interleave=4,5 tu-c0r2n84 - 1 device=1 binding=--interleave=2,3 tu-c0r2n81 - 2 device=2 binding=--interleave=4,5 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 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 AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 1 device 0 bus id: 0000:44:00.0 local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 2 device 0 bus id: 0000:84:00.0 local rank 3 device 0 bus id: 0000:C4:00.0 SharedMemoryMpi: World communicator of size 32 SharedMemoryMpi: Node communicator of size 4 0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14e4a0000000 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 : 1.474568 s : Grid Layout Grid : Message : 1.474573 s : Global lattice size : 64 64 64 128 Grid : Message : 1.474578 s : OpenMP threads : 4 Grid : Message : 1.474581 s : MPI tasks : 2 2 2 4 Grid : Message : 1.514258 s : Making s innermost grids Grid : Message : 1.560200 s : Initialising 4d RNG Grid : Message : 1.655910 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.655945 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 2.737949 s : Initialising 5d RNG Grid : Message : 4.166371 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 4.166415 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 20.865068 s : Initialised RNGs Grid : Message : 24.815048 s : Drawing gauge field Grid : Message : 25.519468 s : Random gauge initialised Grid : Message : 25.534247 s : Setting up Cshift based reference Grid : Message : 55.918672 s : ***************************************************************** Grid : Message : 55.918699 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 55.918700 s : ***************************************************************** Grid : Message : 55.918701 s : ***************************************************************** Grid : Message : 55.918702 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 55.918703 s : * Vectorising space-time by 8 Grid : Message : 55.918704 s : * VComplexF size is 64 B Grid : Message : 55.918705 s : * SINGLE precision Grid : Message : 55.918708 s : * Using Overlapped Comms/Compute Grid : Message : 55.918709 s : * Using GENERIC Nc WilsonKernels Grid : Message : 55.918710 s : ***************************************************************** Grid : Message : 58.166130 s : Called warmup Grid : Message : 513.353136 s : Called Dw 30000 times in 4.55335e+08 us Grid : Message : 513.353214 s : mflop/s = 4.66911e+07 Grid : Message : 513.353216 s : mflop/s per rank = 1.4591e+06 Grid : Message : 513.353222 s : mflop/s per node = 5.83639e+06 Grid : Message : 513.353224 s : RF GiB/s (base 2) = 94875.2 Grid : Message : 513.353226 s : mem GiB/s (base 2) = 59297 Grid : Message : 513.357916 s : norm diff 1.07359e-13 Grid : Message : 513.425968 s : #### Dhop calls report Grid : Message : 513.425975 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 513.425981 s : WilsonFermion5D TotalTime /Calls : 7592.71 us Grid : Message : 513.425984 s : WilsonFermion5D CommTime /Calls : 5677.65 us Grid : Message : 513.425989 s : WilsonFermion5D FaceTime /Calls : 632.501 us Grid : Message : 513.425993 s : WilsonFermion5D ComputeTime1/Calls : 4.95133 us Grid : Message : 513.425995 s : WilsonFermion5D ComputeTime2/Calls : 1295.98 us Grid : Message : 513.426077 s : Average mflops/s per call : 6.47134e+10 Grid : Message : 513.426083 s : Average mflops/s per call per rank : 2.02229e+09 Grid : Message : 513.426086 s : Average mflops/s per call per node : 8.08917e+09 Grid : Message : 513.426090 s : Average mflops/s per call (full) : 4.75163e+07 Grid : Message : 513.426094 s : Average mflops/s per call per rank (full): 1.48488e+06 Grid : Message : 513.426098 s : Average mflops/s per call per node (full): 5.93953e+06 Grid : Message : 513.426101 s : WilsonFermion5D Stencil Grid : Message : 513.426103 s : WilsonFermion5D StencilEven Grid : Message : 513.426105 s : WilsonFermion5D StencilOdd Grid : Message : 513.426107 s : WilsonFermion5D Stencil Reporti() Grid : Message : 513.426109 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 513.426111 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 570.311255 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 570.311281 s : Called DwDag Grid : Message : 570.311282 s : norm dag result 12.0421 Grid : Message : 570.330548 s : norm dag ref 12.0421 Grid : Message : 570.354108 s : norm dag diff 7.28475e-14 Grid : Message : 570.413668 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 570.792618 s : src_e0.499997 Grid : Message : 571.179594 s : src_o0.500003 Grid : Message : 571.278540 s : ********************************************************* Grid : Message : 571.278544 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 571.278546 s : * Vectorising space-time by 8 Grid : Message : 571.278547 s : * SINGLE precision Grid : Message : 571.278548 s : * Using Overlapped Comms/Compute Grid : Message : 571.278549 s : * Using GENERIC Nc WilsonKernels Grid : Message : 571.278550 s : ********************************************************* Grid : Message : 805.842599 s : Deo mflop/s = 4.53282e+07 Grid : Message : 805.842638 s : Deo mflop/s per rank 1.41651e+06 Grid : Message : 805.842640 s : Deo mflop/s per node 5.66603e+06 Grid : Message : 805.842643 s : #### Dhop calls report Grid : Message : 805.842645 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 805.842647 s : WilsonFermion5D TotalTime /Calls : 7818.41 us Grid : Message : 805.842649 s : WilsonFermion5D CommTime /Calls : 5486.69 us Grid : Message : 805.842651 s : WilsonFermion5D FaceTime /Calls : 754.164 us Grid : Message : 805.842653 s : WilsonFermion5D ComputeTime1/Calls : 6.10816 us Grid : Message : 805.842655 s : WilsonFermion5D ComputeTime2/Calls : 1601.11 us Grid : Message : 805.842675 s : Average mflops/s per call : 5.34469e+10 Grid : Message : 805.842678 s : Average mflops/s per call per rank : 1.67022e+09 Grid : Message : 805.842680 s : Average mflops/s per call per node : 6.68087e+09 Grid : Message : 805.842682 s : Average mflops/s per call (full) : 4.61446e+07 Grid : Message : 805.842684 s : Average mflops/s per call per rank (full): 1.44202e+06 Grid : Message : 805.842686 s : Average mflops/s per call per node (full): 5.76807e+06 Grid : Message : 805.842688 s : WilsonFermion5D Stencil Grid : Message : 805.842689 s : WilsonFermion5D StencilEven Grid : Message : 805.842690 s : WilsonFermion5D StencilOdd Grid : Message : 805.842691 s : WilsonFermion5D Stencil Reporti() Grid : Message : 805.842692 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 805.842693 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 805.929673 s : r_e6.02113 Grid : Message : 805.939576 s : r_o6.02101 Grid : Message : 805.949321 s : res12.0421 Grid : Message : 806.629060 s : norm diff 0 Grid : Message : 807.441602 s : norm diff even 0 Grid : Message : 807.841320 s : norm diff odd 0