tu-c0r1n24 - 0 device=0 binding=--interleave=0,1 tu-c0r1n24 - 1 device=1 binding=--interleave=2,3 tu-c0r1n24 - 2 device=2 binding=--interleave=4,5 tu-c0r1n24 - 3 device=3 binding=--interleave=6,7 tu-c0r2n27 - 0 device=0 binding=--interleave=0,1 tu-c0r2n27 - 1 device=1 binding=--interleave=2,3 tu-c0r2n27 - 2 device=2 binding=--interleave=4,5 tu-c0r2n27 - 3 device=3 binding=--interleave=6,7 tu-c0r1n66 - 2 device=2 binding=--interleave=4,5 tu-c0r1n66 - 0 device=0 binding=--interleave=0,1 tu-c0r1n66 - 3 device=3 binding=--interleave=6,7 tu-c0r1n66 - 1 device=1 binding=--interleave=2,3 tu-c0r2n33 - 1 device=1 binding=--interleave=2,3 tu-c0r2n33 - 0 device=0 binding=--interleave=0,1 tu-c0r2n33 - 3 device=3 binding=--interleave=6,7 tu-c0r2n33 - 2 device=2 binding=--interleave=4,5 tu-c0r2n30 - 3 device=3 binding=--interleave=6,7 tu-c0r2n30 - 0 device=0 binding=--interleave=0,1 tu-c0r2n30 - 2 device=2 binding=--interleave=4,5 tu-c0r2n30 - 1 device=1 binding=--interleave=2,3 tu-c0r2n24 - 2 device=2 binding=--interleave=4,5 tu-c0r2n60 - 2 device=2 binding=--interleave=4,5 tu-c0r2n24 - 3 device=3 binding=--interleave=6,7 tu-c0r2n66 - 2 device=2 binding=--interleave=4,5 tu-c0r2n60 - 3 device=3 binding=--interleave=6,7 tu-c0r2n60 - 0 device=0 binding=--interleave=0,1 tu-c0r2n60 - 1 device=1 binding=--interleave=2,3 tu-c0r2n66 - 0 device=0 binding=--interleave=0,1 tu-c0r2n66 - 1 device=1 binding=--interleave=2,3 tu-c0r2n66 - 3 device=3 binding=--interleave=6,7 tu-c0r2n24 - 1 device=1 binding=--interleave=2,3 tu-c0r2n24 - 0 device=0 binding=--interleave=0,1 tu-c0r1n69 - 0 device=0 binding=--interleave=0,1 tu-c0r1n69 - 1 device=1 binding=--interleave=2,3 tu-c0r1n69 - 3 device=3 binding=--interleave=6,7 tu-c0r1n69 - 2 device=2 binding=--interleave=4,5 tu-c0r1n27 - 0 device=0 binding=--interleave=0,1 tu-c0r1n27 - 1 device=1 binding=--interleave=2,3 tu-c0r1n27 - 2 device=2 binding=--interleave=4,5 tu-c0r1n27 - 3 device=3 binding=--interleave=6,7 tu-c0r2n69 - 0 device=0 binding=--interleave=0,1 tu-c0r2n69 - 3 device=3 binding=--interleave=6,7 tu-c0r2n69 - 1 device=1 binding=--interleave=2,3 tu-c0r2n69 - 2 device=2 binding=--interleave=4,5 tu-c0r1n63 - 1 device=1 binding=--interleave=2,3 tu-c0r1n63 - 3 device=3 binding=--interleave=6,7 tu-c0r1n63 - 0 device=0 binding=--interleave=0,1 tu-c0r1n63 - 2 device=2 binding=--interleave=4,5 tu-c0r2n63 - 2 device=2 binding=--interleave=4,5 tu-c0r2n63 - 0 device=0 binding=--interleave=0,1 tu-c0r2n63 - 1 device=1 binding=--interleave=2,3 tu-c0r2n63 - 3 device=3 binding=--interleave=6,7 tu-c0r1n60 - 3 device=3 binding=--interleave=6,7 tu-c0r1n60 - 1 device=1 binding=--interleave=2,3 tu-c0r1n60 - 0 device=0 binding=--interleave=0,1 tu-c0r1n60 - 2 device=2 binding=--interleave=4,5 tu-c0r1n30 - 0 device=0 binding=--interleave=0,1 tu-c0r1n30 - 2 device=2 binding=--interleave=4,5 tu-c0r1n30 - 1 device=1 binding=--interleave=2,3 tu-c0r1n30 - 3 device=3 binding=--interleave=6,7 tu-c0r1n33 - 1 device=1 binding=--interleave=2,3 tu-c0r1n33 - 2 device=2 binding=--interleave=4,5 tu-c0r1n33 - 0 device=0 binding=--interleave=0,1 tu-c0r1n33 - 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[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: 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 2 device 0 bus id: 0000:84:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ local rank 1 device 0 bus id: 0000:44:00.0 local rank 3 device 0 bus id: 0000:C4:00.0 SharedMemoryMpi: World communicator of size 64 SharedMemoryMpi: Node communicator of size 4 0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14d220000000 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 : 1.250946 s : Grid Layout Grid : Message : 1.250950 s : Global lattice size : 64 64 64 256 Grid : Message : 1.250955 s : OpenMP threads : 4 Grid : Message : 1.250958 s : MPI tasks : 2 2 2 8 Grid : Message : 1.291834 s : Making s innermost grids Grid : Message : 1.362491 s : Initialising 4d RNG Grid : Message : 1.470580 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.470607 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 3.136601 s : Initialising 5d RNG Grid : Message : 4.577128 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 4.577160 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 38.133308 s : Initialised RNGs Grid : Message : 43.538534 s : Drawing gauge field Grid : Message : 44.356868 s : Random gauge initialised Grid : Message : 44.371603 s : Setting up Cshift based reference Grid : Message : 74.150990 s : ***************************************************************** Grid : Message : 74.151012 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 74.151014 s : ***************************************************************** Grid : Message : 74.151015 s : ***************************************************************** Grid : Message : 74.151016 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 74.151017 s : * Vectorising space-time by 8 Grid : Message : 74.151018 s : * VComplexF size is 64 B Grid : Message : 74.151019 s : * SINGLE precision Grid : Message : 74.151021 s : * Using Overlapped Comms/Compute Grid : Message : 74.151022 s : * Using GENERIC Nc WilsonKernels Grid : Message : 74.151023 s : ***************************************************************** Grid : Message : 76.256746 s : Called warmup Grid : Message : 405.232813 s : Called Dw 30000 times in 3.28975e+08 us Grid : Message : 405.232876 s : mflop/s = 1.29251e+08 Grid : Message : 405.232878 s : mflop/s per rank = 2.01954e+06 Grid : Message : 405.232880 s : mflop/s per node = 8.07816e+06 Grid : Message : 405.232882 s : RF GiB/s (base 2) = 262634 Grid : Message : 405.232886 s : mem GiB/s (base 2) = 164146 Grid : Message : 405.236402 s : norm diff 1.06407e-13 Grid : Message : 405.291726 s : #### Dhop calls report Grid : Message : 405.291733 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 405.291736 s : WilsonFermion5D TotalTime /Calls : 5486.83 us Grid : Message : 405.291738 s : WilsonFermion5D CommTime /Calls : 3976.2 us Grid : Message : 405.291740 s : WilsonFermion5D FaceTime /Calls : 595.539 us Grid : Message : 405.291742 s : WilsonFermion5D ComputeTime1/Calls : 4.55948 us Grid : Message : 405.291744 s : WilsonFermion5D ComputeTime2/Calls : 928.596 us Grid : Message : 405.291756 s : Average mflops/s per call : 1.27217e+11 Grid : Message : 405.291759 s : Average mflops/s per call per rank : 1.98777e+09 Grid : Message : 405.291761 s : Average mflops/s per call per node : 7.95107e+09 Grid : Message : 405.291766 s : Average mflops/s per call (full) : 1.31507e+08 Grid : Message : 405.291768 s : Average mflops/s per call per rank (full): 2.05479e+06 Grid : Message : 405.291770 s : Average mflops/s per call per node (full): 8.21917e+06 Grid : Message : 405.291772 s : WilsonFermion5D Stencil Grid : Message : 405.291773 s : WilsonFermion5D StencilEven Grid : Message : 405.291775 s : WilsonFermion5D StencilOdd Grid : Message : 405.291776 s : WilsonFermion5D Stencil Reporti() Grid : Message : 405.291777 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 405.291778 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 460.970342 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 460.970364 s : Called DwDag Grid : Message : 460.970365 s : norm dag result 12.0421 Grid : Message : 460.985461 s : norm dag ref 12.0421 Grid : Message : 461.376700 s : norm dag diff 7.21924e-14 Grid : Message : 461.543960 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 461.469894 s : src_e0.499998 Grid : Message : 461.884229 s : src_o0.500002 Grid : Message : 462.306898 s : ********************************************************* Grid : Message : 462.306905 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 462.306907 s : * Vectorising space-time by 8 Grid : Message : 462.306910 s : * SINGLE precision Grid : Message : 462.306912 s : * Using Overlapped Comms/Compute Grid : Message : 462.306914 s : * Using GENERIC Nc WilsonKernels Grid : Message : 462.306916 s : ********************************************************* Grid : Message : 633.595622 s : Deo mflop/s = 1.24158e+08 Grid : Message : 633.595651 s : Deo mflop/s per rank 1.93996e+06 Grid : Message : 633.595654 s : Deo mflop/s per node 7.75986e+06 Grid : Message : 633.595660 s : #### Dhop calls report Grid : Message : 633.595663 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 633.595667 s : WilsonFermion5D TotalTime /Calls : 5709.29 us Grid : Message : 633.595672 s : WilsonFermion5D CommTime /Calls : 4083.27 us Grid : Message : 633.595676 s : WilsonFermion5D FaceTime /Calls : 705.086 us Grid : Message : 633.595679 s : WilsonFermion5D ComputeTime1/Calls : 5.73021 us Grid : Message : 633.595683 s : WilsonFermion5D ComputeTime2/Calls : 946.623 us Grid : Message : 633.595705 s : Average mflops/s per call : 1.07059e+11 Grid : Message : 633.595710 s : Average mflops/s per call per rank : 1.6728e+09 Grid : Message : 633.595713 s : Average mflops/s per call per node : 6.6912e+09 Grid : Message : 633.595716 s : Average mflops/s per call (full) : 1.26383e+08 Grid : Message : 633.595719 s : Average mflops/s per call per rank (full): 1.97473e+06 Grid : Message : 633.595722 s : Average mflops/s per call per node (full): 7.89891e+06 Grid : Message : 633.595725 s : WilsonFermion5D Stencil Grid : Message : 633.595727 s : WilsonFermion5D StencilEven Grid : Message : 633.595729 s : WilsonFermion5D StencilOdd Grid : Message : 633.595731 s : WilsonFermion5D Stencil Reporti() Grid : Message : 633.595733 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 633.595735 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 633.672780 s : r_e6.02108 Grid : Message : 633.681183 s : r_o6.02101 Grid : Message : 633.688805 s : res12.0421 Grid : Message : 634.337211 s : norm diff 0 Grid : Message : 635.176714 s : norm diff even 0 Grid : Message : 635.571579 s : norm diff odd 0