tu-c0r1n00 - 0 device=0 binding=--interleave=0,1 tu-c0r1n00 - 1 device=1 binding=--interleave=2,3 tu-c0r1n00 - 2 device=2 binding=--interleave=4,5 tu-c0r1n00 - 3 device=3 binding=--interleave=6,7 tu-c0r2n09 - 2 device=2 binding=--interleave=4,5 tu-c0r2n09 - 1 device=1 binding=--interleave=2,3 tu-c0r2n09 - 0 device=0 binding=--interleave=0,1 tu-c0r2n09 - 3 device=3 binding=--interleave=6,7 tu-c0r2n21 - 1 device=1 binding=--interleave=2,3 tu-c0r2n21 - 3 device=3 binding=--interleave=6,7 tu-c0r2n21 - 0 device=0 binding=--interleave=0,1 tu-c0r2n21 - 2 device=2 binding=--interleave=4,5 tu-c0r2n15 - 2 device=2 binding=--interleave=4,5 tu-c0r2n15 - 0 device=0 binding=--interleave=0,1 tu-c0r2n15 - 1 device=1 binding=--interleave=2,3 tu-c0r2n15 - 3 device=3 binding=--interleave=6,7 tu-c0r1n09 - 1 device=1 binding=--interleave=2,3 tu-c0r1n09 - 3 device=3 binding=--interleave=6,7 tu-c0r1n09 - 0 device=0 binding=--interleave=0,1 tu-c0r1n09 - 2 device=2 binding=--interleave=4,5 tu-c0r2n06 - 0 device=0 binding=--interleave=0,1 tu-c0r2n06 - 2 device=2 binding=--interleave=4,5 tu-c0r2n06 - 3 device=3 binding=--interleave=6,7 tu-c0r2n06 - 1 device=1 binding=--interleave=2,3 tu-c0r1n21 - 2 device=2 binding=--interleave=4,5 tu-c0r1n21 - 1 device=1 binding=--interleave=2,3 tu-c0r1n21 - 0 device=0 binding=--interleave=0,1 tu-c0r1n21 - 3 device=3 binding=--interleave=6,7 tu-c0r1n06 - 3 device=3 binding=--interleave=6,7 tu-c0r1n06 - 0 device=0 binding=--interleave=0,1 tu-c0r1n06 - 1 device=1 binding=--interleave=2,3 tu-c0r1n06 - 2 device=2 binding=--interleave=4,5 tu-c0r1n18 - 1 device=1 binding=--interleave=2,3 tu-c0r2n12 - 3 device=3 binding=--interleave=6,7 tu-c0r2n12 - 2 device=2 binding=--interleave=4,5 tu-c0r1n18 - 0 device=0 binding=--interleave=0,1 tu-c0r1n18 - 2 device=2 binding=--interleave=4,5 tu-c0r1n12 - 3 device=3 binding=--interleave=6,7 tu-c0r2n12 - 0 device=0 binding=--interleave=0,1 tu-c0r1n18 - 3 device=3 binding=--interleave=6,7 tu-c0r2n12 - 1 device=1 binding=--interleave=2,3 tu-c0r1n12 - 2 device=2 binding=--interleave=4,5 tu-c0r1n12 - 0 device=0 binding=--interleave=0,1 tu-c0r1n12 - 1 device=1 binding=--interleave=2,3 tu-c0r2n00 - 0 device=0 binding=--interleave=0,1 tu-c0r2n00 - 2 device=2 binding=--interleave=4,5 tu-c0r1n03 - 0 device=0 binding=--interleave=0,1 tu-c0r1n03 - 1 device=1 binding=--interleave=2,3 tu-c0r1n03 - 3 device=3 binding=--interleave=6,7 tu-c0r1n03 - 2 device=2 binding=--interleave=4,5 tu-c0r2n00 - 3 device=3 binding=--interleave=6,7 tu-c0r2n00 - 1 device=1 binding=--interleave=2,3 tu-c0r2n03 - 3 device=3 binding=--interleave=6,7 tu-c0r2n03 - 2 device=2 binding=--interleave=4,5 tu-c0r2n03 - 0 device=0 binding=--interleave=0,1 tu-c0r2n03 - 1 device=1 binding=--interleave=2,3 tu-c0r2n18 - 1 device=1 binding=--interleave=2,3 tu-c0r2n18 - 3 device=3 binding=--interleave=6,7 tu-c0r2n18 - 0 device=0 binding=--interleave=0,1 tu-c0r2n18 - 2 device=2 binding=--interleave=4,5 tu-c0r1n15 - 2 device=2 binding=--interleave=4,5 tu-c0r1n15 - 3 device=3 binding=--interleave=6,7 tu-c0r1n15 - 1 device=1 binding=--interleave=2,3 tu-c0r1n15 - 0 device=0 binding=--interleave=0,1 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 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 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 2 device 0 bus id: 0000:84:00.0 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 0x149f80000000 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 : 1.666464 s : Grid Layout Grid : Message : 1.666469 s : Global lattice size : 64 64 64 256 Grid : Message : 1.666476 s : OpenMP threads : 4 Grid : Message : 1.666479 s : MPI tasks : 2 2 2 8 Grid : Message : 1.710843 s : Making s innermost grids Grid : Message : 1.758250 s : Initialising 4d RNG Grid : Message : 1.849911 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.849939 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 3.444355 s : Initialising 5d RNG Grid : Message : 4.924559 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 4.924593 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 38.347249 s : Initialised RNGs Grid : Message : 43.165089 s : Drawing gauge field Grid : Message : 44.224280 s : Random gauge initialised Grid : Message : 44.351720 s : Setting up Cshift based reference Grid : Message : 73.296796 s : ***************************************************************** Grid : Message : 73.296823 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 73.296825 s : ***************************************************************** Grid : Message : 73.296826 s : ***************************************************************** Grid : Message : 73.296827 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 73.296828 s : * Vectorising space-time by 8 Grid : Message : 73.296829 s : * VComplexF size is 64 B Grid : Message : 73.296830 s : * SINGLE precision Grid : Message : 73.296833 s : * Using Overlapped Comms/Compute Grid : Message : 73.296834 s : * Using GENERIC Nc WilsonKernels Grid : Message : 73.296835 s : ***************************************************************** Grid : Message : 75.370833 s : Called warmup Grid : Message : 368.103333 s : Called Dw 30000 times in 2.92732e+08 us Grid : Message : 368.103404 s : mflop/s = 1.45253e+08 Grid : Message : 368.103406 s : mflop/s per rank = 2.26958e+06 Grid : Message : 368.103408 s : mflop/s per node = 9.0783e+06 Grid : Message : 368.103410 s : RF GiB/s (base 2) = 295150 Grid : Message : 368.103412 s : mem GiB/s (base 2) = 184469 Grid : Message : 368.106910 s : norm diff 1.06407e-13 Grid : Message : 368.157795 s : #### Dhop calls report Grid : Message : 368.157802 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 368.157806 s : WilsonFermion5D TotalTime /Calls : 4882.81 us Grid : Message : 368.157808 s : WilsonFermion5D CommTime /Calls : 3403.06 us Grid : Message : 368.157810 s : WilsonFermion5D FaceTime /Calls : 493.196 us Grid : Message : 368.157812 s : WilsonFermion5D ComputeTime1/Calls : 5.0686 us Grid : Message : 368.157814 s : WilsonFermion5D ComputeTime2/Calls : 999.831 us Grid : Message : 368.157846 s : Average mflops/s per call : 1.24406e+11 Grid : Message : 368.157850 s : Average mflops/s per call per rank : 1.94385e+09 Grid : Message : 368.157852 s : Average mflops/s per call per node : 7.77541e+09 Grid : Message : 368.157854 s : Average mflops/s per call (full) : 1.47774e+08 Grid : Message : 368.157859 s : Average mflops/s per call per rank (full): 2.30897e+06 Grid : Message : 368.157862 s : Average mflops/s per call per node (full): 9.2359e+06 Grid : Message : 368.157864 s : WilsonFermion5D Stencil Grid : Message : 368.157867 s : WilsonFermion5D StencilEven Grid : Message : 368.157870 s : WilsonFermion5D StencilOdd Grid : Message : 368.157871 s : WilsonFermion5D Stencil Reporti() Grid : Message : 368.157873 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 368.157874 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 423.518844 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 423.518868 s : Called DwDag Grid : Message : 423.518869 s : norm dag result 12.0421 Grid : Message : 423.550302 s : norm dag ref 12.0421 Grid : Message : 423.567002 s : norm dag diff 7.21924e-14 Grid : Message : 423.609090 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 424.201170 s : src_e0.499998 Grid : Message : 424.418954 s : src_o0.500002 Grid : Message : 424.545114 s : ********************************************************* Grid : Message : 424.545116 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 424.545117 s : * Vectorising space-time by 8 Grid : Message : 424.545119 s : * SINGLE precision Grid : Message : 424.545120 s : * Using Overlapped Comms/Compute Grid : Message : 424.545121 s : * Using GENERIC Nc WilsonKernels Grid : Message : 424.545122 s : ********************************************************* Grid : Message : 571.385541 s : Deo mflop/s = 1.44858e+08 Grid : Message : 571.385571 s : Deo mflop/s per rank 2.26341e+06 Grid : Message : 571.385574 s : Deo mflop/s per node 9.05363e+06 Grid : Message : 571.385583 s : #### Dhop calls report Grid : Message : 571.385586 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 571.385591 s : WilsonFermion5D TotalTime /Calls : 4894.37 us Grid : Message : 571.385594 s : WilsonFermion5D CommTime /Calls : 3328.54 us Grid : Message : 571.385598 s : WilsonFermion5D FaceTime /Calls : 627.369 us Grid : Message : 571.385601 s : WilsonFermion5D ComputeTime1/Calls : 5.84787 us Grid : Message : 571.385605 s : WilsonFermion5D ComputeTime2/Calls : 962.498 us Grid : Message : 571.385628 s : Average mflops/s per call : 1.03941e+11 Grid : Message : 571.385633 s : Average mflops/s per call per rank : 1.62408e+09 Grid : Message : 571.385637 s : Average mflops/s per call per node : 6.49633e+09 Grid : Message : 571.385641 s : Average mflops/s per call (full) : 1.47426e+08 Grid : Message : 571.385644 s : Average mflops/s per call per rank (full): 2.30352e+06 Grid : Message : 571.385646 s : Average mflops/s per call per node (full): 9.2141e+06 Grid : Message : 571.385648 s : WilsonFermion5D Stencil Grid : Message : 571.385649 s : WilsonFermion5D StencilEven Grid : Message : 571.385651 s : WilsonFermion5D StencilOdd Grid : Message : 571.385653 s : WilsonFermion5D Stencil Reporti() Grid : Message : 571.385656 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 571.385658 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 571.460329 s : r_e6.02108 Grid : Message : 571.468166 s : r_o6.02101 Grid : Message : 571.474988 s : res12.0421 Grid : Message : 572.962590 s : norm diff 0 Grid : Message : 572.945739 s : norm diff even 0 Grid : Message : 573.409309 s : norm diff odd 0