tu-c0r1n00 - 0 device=0 binding=--interleave=0,1 tu-c0r1n00 - 1 device=1 binding=--interleave=2,3 tu-c0r2n09 - 0 device=0 binding=--interleave=0,1 tu-c0r2n15 - 0 device=0 binding=--interleave=0,1 tu-c0r1n15 - 0 device=0 binding=--interleave=0,1 tu-c0r2n06 - 0 device=0 binding=--interleave=0,1 tu-c0r2n21 - 0 device=0 binding=--interleave=0,1 tu-c0r1n18 - 0 device=0 binding=--interleave=0,1 tu-c0r2n12 - 0 device=0 binding=--interleave=0,1 tu-c0r1n06 - 0 device=0 binding=--interleave=0,1 tu-c0r2n21 - 1 device=1 binding=--interleave=2,3 tu-c0r1n00 - 2 device=2 binding=--interleave=4,5 tu-c0r2n15 - 1 device=1 binding=--interleave=2,3 tu-c0r1n09 - 0 device=0 binding=--interleave=0,1 tu-c0r2n06 - 1 device=1 binding=--interleave=2,3 tu-c0r1n09 - 1 device=1 binding=--interleave=2,3 tu-c0r2n03 - 0 device=0 binding=--interleave=0,1 tu-c0r1n06 - 1 device=1 binding=--interleave=2,3 tu-c0r1n00 - 3 device=3 binding=--interleave=6,7 tu-c0r2n18 - 0 device=0 binding=--interleave=0,1 tu-c0r1n21 - 0 device=0 binding=--interleave=0,1 tu-c0r1n12 - 0 device=0 binding=--interleave=0,1 tu-c0r1n18 - 1 device=1 binding=--interleave=2,3 tu-c0r2n18 - 1 device=1 binding=--interleave=2,3 tu-c0r1n21 - 1 device=1 binding=--interleave=2,3 tu-c0r1n15 - 1 device=1 binding=--interleave=2,3 tu-c0r2n03 - 1 device=1 binding=--interleave=2,3 tu-c0r2n15 - 2 device=2 binding=--interleave=4,5 tu-c0r2n09 - 1 device=1 binding=--interleave=2,3 tu-c0r1n12 - 2 device=2 binding=--interleave=4,5 tu-c0r2n06 - 3 device=3 binding=--interleave=6,7 tu-c0r1n06 - 3 device=3 binding=--interleave=6,7 tu-c0r2n12 - 1 device=1 binding=--interleave=2,3 tu-c0r2n15 - 3 device=3 binding=--interleave=6,7 tu-c0r2n12 - 2 device=2 binding=--interleave=4,5 tu-c0r1n12 - 1 device=1 binding=--interleave=2,3 tu-c0r1n09 - 3 device=3 binding=--interleave=6,7 tu-c0r1n06 - 2 device=2 binding=--interleave=4,5 tu-c0r2n03 - 2 device=2 binding=--interleave=4,5 tu-c0r2n12 - 3 device=3 binding=--interleave=6,7 tu-c0r1n12 - 3 device=3 binding=--interleave=6,7 tu-c0r2n03 - 3 device=3 binding=--interleave=6,7 tu-c0r1n15 - 2 device=2 binding=--interleave=4,5 tu-c0r2n09 - 3 device=3 binding=--interleave=6,7 tu-c0r1n15 - 3 device=3 binding=--interleave=6,7 tu-c0r2n09 - 2 device=2 binding=--interleave=4,5 tu-c0r1n18 - 2 device=2 binding=--interleave=4,5 tu-c0r2n06 - 2 device=2 binding=--interleave=4,5 tu-c0r2n21 - 3 device=3 binding=--interleave=6,7 tu-c0r1n09 - 2 device=2 binding=--interleave=4,5 tu-c0r1n21 - 3 device=3 binding=--interleave=6,7 tu-c0r1n18 - 3 device=3 binding=--interleave=6,7 tu-c0r2n21 - 2 device=2 binding=--interleave=4,5 tu-c0r1n21 - 2 device=2 binding=--interleave=4,5 tu-c0r2n18 - 2 device=2 binding=--interleave=4,5 tu-c0r2n18 - 3 device=3 binding=--interleave=6,7 tu-c0r2n00 - 0 device=0 binding=--interleave=0,1 tu-c0r2n00 - 2 device=2 binding=--interleave=4,5 tu-c0r2n00 - 1 device=1 binding=--interleave=2,3 tu-c0r2n00 - 3 device=3 binding=--interleave=6,7 tu-c0r1n03 - 0 device=0 binding=--interleave=0,1 tu-c0r1n03 - 1 device=1 binding=--interleave=2,3 tu-c0r1n03 - 2 device=2 binding=--interleave=4,5 tu-c0r1n03 - 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: 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 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 local rank 3 device 0 bus id: 0000:C4:00.0 local rank 1 device 0 bus id: 0000:44:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ local rank 2 device 0 bus id: 0000:84:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ SharedMemoryMpi: World communicator of size 64 SharedMemoryMpi: Node communicator of size 4 0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x150d60000000 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 : 1.593675 s : Grid Layout Grid : Message : 1.593680 s : Global lattice size : 48 48 48 96 Grid : Message : 1.593685 s : OpenMP threads : 4 Grid : Message : 1.593687 s : MPI tasks : 2 2 2 8 Grid : Message : 1.607673 s : Making s innermost grids Grid : Message : 1.623783 s : Initialising 4d RNG Grid : Message : 1.638916 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.638939 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 1.932095 s : Initialising 5d RNG Grid : Message : 2.158141 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 2.158172 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 7.432614 s : Initialised RNGs Grid : Message : 8.603775 s : Drawing gauge field Grid : Message : 8.725893 s : Random gauge initialised Grid : Message : 8.732015 s : Setting up Cshift based reference Grid : Message : 14.272870 s : ***************************************************************** Grid : Message : 14.272893 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 14.272895 s : ***************************************************************** Grid : Message : 14.272896 s : ***************************************************************** Grid : Message : 14.272897 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 14.272898 s : * Vectorising space-time by 8 Grid : Message : 14.272899 s : * VComplexF size is 64 B Grid : Message : 14.272900 s : * SINGLE precision Grid : Message : 14.272901 s : * Using Overlapped Comms/Compute Grid : Message : 14.272902 s : * Using GENERIC Nc WilsonKernels Grid : Message : 14.272903 s : ***************************************************************** Grid : Message : 14.886734 s : Called warmup Grid : Message : 158.804470 s : Called Dw 30000 times in 1.43193e+08 us Grid : Message : 158.805140 s : mflop/s = 4.69772e+07 Grid : Message : 158.805160 s : mflop/s per rank = 734019 Grid : Message : 158.805180 s : mflop/s per node = 2.93608e+06 Grid : Message : 158.805200 s : RF GiB/s (base 2) = 95456.6 Grid : Message : 158.805220 s : mem GiB/s (base 2) = 59660.4 Grid : Message : 158.814620 s : norm diff 1.05775e-13 Grid : Message : 158.972370 s : #### Dhop calls report Grid : Message : 158.972450 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 158.972490 s : WilsonFermion5D TotalTime /Calls : 2388.06 us Grid : Message : 158.972510 s : WilsonFermion5D CommTime /Calls : 1575.62 us Grid : Message : 158.972550 s : WilsonFermion5D FaceTime /Calls : 375.65 us Grid : Message : 158.972580 s : WilsonFermion5D ComputeTime1/Calls : 3.01515 us Grid : Message : 158.972610 s : WilsonFermion5D ComputeTime2/Calls : 449.92 us Grid : Message : 158.973560 s : Average mflops/s per call : 3.64228e+10 Grid : Message : 158.973630 s : Average mflops/s per call per rank : 5.69106e+08 Grid : Message : 158.973650 s : Average mflops/s per call per node : 2.27642e+09 Grid : Message : 158.973670 s : Average mflops/s per call (full) : 4.78012e+07 Grid : Message : 158.973690 s : Average mflops/s per call per rank (full): 746893 Grid : Message : 158.973730 s : Average mflops/s per call per node (full): 2.98757e+06 Grid : Message : 158.973780 s : WilsonFermion5D Stencil Grid : Message : 158.973800 s : WilsonFermion5D StencilEven Grid : Message : 158.973820 s : WilsonFermion5D StencilOdd Grid : Message : 158.973840 s : WilsonFermion5D Stencil Reporti() Grid : Message : 158.973860 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 158.973890 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 167.165389 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 167.165414 s : Called DwDag Grid : Message : 167.165415 s : norm dag result 12.0422 Grid : Message : 167.170657 s : norm dag ref 12.0422 Grid : Message : 167.176361 s : norm dag diff 7.28899e-14 Grid : Message : 167.190620 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 167.250165 s : src_e0.5 Grid : Message : 167.327808 s : src_o0.5 Grid : Message : 167.345291 s : ********************************************************* Grid : Message : 167.345295 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 167.345297 s : * Vectorising space-time by 8 Grid : Message : 167.345301 s : * SINGLE precision Grid : Message : 167.345304 s : * Using Overlapped Comms/Compute Grid : Message : 167.345306 s : * Using GENERIC Nc WilsonKernels Grid : Message : 167.345308 s : ********************************************************* Grid : Message : 244.469764 s : Deo mflop/s = 4.36158e+07 Grid : Message : 244.469792 s : Deo mflop/s per rank 681497 Grid : Message : 244.469794 s : Deo mflop/s per node 2.72599e+06 Grid : Message : 244.469797 s : #### Dhop calls report Grid : Message : 244.469799 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 244.469801 s : WilsonFermion5D TotalTime /Calls : 2570.62 us Grid : Message : 244.469803 s : WilsonFermion5D CommTime /Calls : 1628.82 us Grid : Message : 244.469805 s : WilsonFermion5D FaceTime /Calls : 477.644 us Grid : Message : 244.469807 s : WilsonFermion5D ComputeTime1/Calls : 5.02017 us Grid : Message : 244.469809 s : WilsonFermion5D ComputeTime2/Calls : 489.415 us Grid : Message : 244.469833 s : Average mflops/s per call : 2.09965e+10 Grid : Message : 244.469841 s : Average mflops/s per call per rank : 3.28071e+08 Grid : Message : 244.469850 s : Average mflops/s per call per node : 1.31228e+09 Grid : Message : 244.469857 s : Average mflops/s per call (full) : 4.44065e+07 Grid : Message : 244.469860 s : Average mflops/s per call per rank (full): 693852 Grid : Message : 244.469864 s : Average mflops/s per call per node (full): 2.77541e+06 Grid : Message : 244.469869 s : WilsonFermion5D Stencil Grid : Message : 244.469870 s : WilsonFermion5D StencilEven Grid : Message : 244.469871 s : WilsonFermion5D StencilOdd Grid : Message : 244.469877 s : WilsonFermion5D Stencil Reporti() Grid : Message : 244.469880 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 244.469882 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 244.495050 s : r_e6.02106 Grid : Message : 244.498215 s : r_o6.0211 Grid : Message : 244.500710 s : res12.0422 Grid : Message : 244.602254 s : norm diff 0 Grid : Message : 244.751039 s : norm diff even 0 Grid : Message : 244.822925 s : norm diff odd 0