tu-c0r2n75 - 0 device=0 binding=--interleave=0,1 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-c0r2n78 - 0 device=0 binding=--interleave=0,1 tu-c0r2n72 - 3 device=3 binding=--interleave=6,7 tu-c0r2n87 - 0 device=0 binding=--interleave=0,1 tu-c0r2n90 - 0 device=0 binding=--interleave=0,1 tu-c0r2n75 - 1 device=1 binding=--interleave=2,3 tu-c0r2n93 - 0 device=0 binding=--interleave=0,1 tu-c0r2n93 - 1 device=1 binding=--interleave=2,3 tu-c0r2n75 - 2 device=2 binding=--interleave=4,5 tu-c0r2n87 - 1 device=1 binding=--interleave=2,3 tu-c0r2n78 - 1 device=1 binding=--interleave=2,3 tu-c0r2n90 - 1 device=1 binding=--interleave=2,3 tu-c0r2n90 - 2 device=2 binding=--interleave=4,5 tu-c0r2n87 - 2 device=2 binding=--interleave=4,5 tu-c0r2n90 - 3 device=3 binding=--interleave=6,7 tu-c0r2n75 - 3 device=3 binding=--interleave=6,7 tu-c0r2n93 - 3 device=3 binding=--interleave=6,7 tu-c0r2n78 - 2 device=2 binding=--interleave=4,5 tu-c0r2n78 - 3 device=3 binding=--interleave=6,7 tu-c0r2n93 - 2 device=2 binding=--interleave=4,5 tu-c0r2n87 - 3 device=3 binding=--interleave=6,7 tu-c0r2n84 - 0 device=0 binding=--interleave=0,1 tu-c0r2n81 - 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 tu-c0r2n81 - 1 device=1 binding=--interleave=2,3 tu-c0r2n81 - 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: 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 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[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: ================================================ 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 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 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 0x14ad80000000 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 : 1.505659 s : Grid Layout Grid : Message : 1.505663 s : Global lattice size : 48 48 48 48 Grid : Message : 1.505668 s : OpenMP threads : 4 Grid : Message : 1.505670 s : MPI tasks : 2 2 2 4 Grid : Message : 1.518438 s : Making s innermost grids Grid : Message : 1.534800 s : Initialising 4d RNG Grid : Message : 1.550569 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.550592 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 1.676427 s : Initialising 5d RNG Grid : Message : 1.906322 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 1.906349 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 4.519684 s : Initialised RNGs Grid : Message : 5.502398 s : Drawing gauge field Grid : Message : 5.604246 s : Random gauge initialised Grid : Message : 5.608268 s : Setting up Cshift based reference Grid : Message : 10.579707 s : ***************************************************************** Grid : Message : 10.579731 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 10.579732 s : ***************************************************************** Grid : Message : 10.579733 s : ***************************************************************** Grid : Message : 10.579734 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 10.579735 s : * Vectorising space-time by 8 Grid : Message : 10.579736 s : * VComplexF size is 64 B Grid : Message : 10.579738 s : * SINGLE precision Grid : Message : 10.579740 s : * Using Overlapped Comms/Compute Grid : Message : 10.579741 s : * Using GENERIC Nc WilsonKernels Grid : Message : 10.579742 s : ***************************************************************** Grid : Message : 11.153250 s : Called warmup Grid : Message : 92.203682 s : Called Dw 30000 times in 8.1188e+07 us Grid : Message : 92.203725 s : mflop/s = 4.14275e+07 Grid : Message : 92.203727 s : mflop/s per rank = 1.29461e+06 Grid : Message : 92.203729 s : mflop/s per node = 5.17843e+06 Grid : Message : 92.203731 s : RF GiB/s (base 2) = 84179.6 Grid : Message : 92.203733 s : mem GiB/s (base 2) = 52612.3 Grid : Message : 92.204309 s : norm diff 1.05759e-13 Grid : Message : 92.213851 s : #### Dhop calls report Grid : Message : 92.213858 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 92.213861 s : WilsonFermion5D TotalTime /Calls : 1354.33 us Grid : Message : 92.213863 s : WilsonFermion5D CommTime /Calls : 926.2 us Grid : Message : 92.213865 s : WilsonFermion5D FaceTime /Calls : 210.317 us Grid : Message : 92.213867 s : WilsonFermion5D ComputeTime1/Calls : 2.80804 us Grid : Message : 92.213869 s : WilsonFermion5D ComputeTime2/Calls : 230.82 us Grid : Message : 92.213894 s : Average mflops/s per call : 1.77993e+10 Grid : Message : 92.213897 s : Average mflops/s per call per rank : 5.56229e+08 Grid : Message : 92.213899 s : Average mflops/s per call per node : 2.22491e+09 Grid : Message : 92.213901 s : Average mflops/s per call (full) : 4.21434e+07 Grid : Message : 92.213904 s : Average mflops/s per call per rank (full): 1.31698e+06 Grid : Message : 92.213906 s : Average mflops/s per call per node (full): 5.26793e+06 Grid : Message : 92.213908 s : WilsonFermion5D Stencil Grid : Message : 92.213909 s : WilsonFermion5D StencilEven Grid : Message : 92.213910 s : WilsonFermion5D StencilOdd Grid : Message : 92.213911 s : WilsonFermion5D Stencil Reporti() Grid : Message : 92.213913 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 92.213914 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 100.886206 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 100.886234 s : Called DwDag Grid : Message : 100.886235 s : norm dag result 12.0422 Grid : Message : 100.888442 s : norm dag ref 12.0422 Grid : Message : 100.891333 s : norm dag diff 7.13141e-14 Grid : Message : 100.902321 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 100.967918 s : src_e0.499992 Grid : Message : 101.318450 s : src_o0.500008 Grid : Message : 101.482910 s : ********************************************************* Grid : Message : 101.483020 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 101.483060 s : * Vectorising space-time by 8 Grid : Message : 101.483080 s : * SINGLE precision Grid : Message : 101.483090 s : * Using Overlapped Comms/Compute Grid : Message : 101.483120 s : * Using GENERIC Nc WilsonKernels Grid : Message : 101.483150 s : ********************************************************* Grid : Message : 144.642010 s : Deo mflop/s = 3.91041e+07 Grid : Message : 144.642330 s : Deo mflop/s per rank 1.222e+06 Grid : Message : 144.642360 s : Deo mflop/s per node 4.88801e+06 Grid : Message : 144.642390 s : #### Dhop calls report Grid : Message : 144.642410 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 144.642430 s : WilsonFermion5D TotalTime /Calls : 1433.68 us Grid : Message : 144.642450 s : WilsonFermion5D CommTime /Calls : 953.13 us Grid : Message : 144.642470 s : WilsonFermion5D FaceTime /Calls : 274.841 us Grid : Message : 144.642490 s : WilsonFermion5D ComputeTime1/Calls : 5.01543 us Grid : Message : 144.642510 s : WilsonFermion5D ComputeTime2/Calls : 230.018 us Grid : Message : 144.642760 s : Average mflops/s per call : 1.0231e+10 Grid : Message : 144.642790 s : Average mflops/s per call per rank : 3.19718e+08 Grid : Message : 144.642810 s : Average mflops/s per call per node : 1.27887e+09 Grid : Message : 144.642840 s : Average mflops/s per call (full) : 3.98109e+07 Grid : Message : 144.642870 s : Average mflops/s per call per rank (full): 1.24409e+06 Grid : Message : 144.642900 s : Average mflops/s per call per node (full): 4.97637e+06 Grid : Message : 144.642920 s : WilsonFermion5D Stencil Grid : Message : 144.642930 s : WilsonFermion5D StencilEven Grid : Message : 144.642950 s : WilsonFermion5D StencilOdd Grid : Message : 144.642960 s : WilsonFermion5D Stencil Reporti() Grid : Message : 144.642970 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 144.642980 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 144.838260 s : r_e6.02129 Grid : Message : 144.854890 s : r_o6.02097 Grid : Message : 144.867680 s : res12.0423 Grid : Message : 144.198002 s : norm diff 0 Grid : Message : 144.320996 s : norm diff even 0 Grid : Message : 144.389371 s : norm diff odd 0