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-c0r2n30 - 3 device=3 binding=--interleave=6,7 tu-c0r2n30 - 2 device=2 binding=--interleave=4,5 tu-c0r2n30 - 0 device=0 binding=--interleave=0,1 tu-c0r2n27 - 0 device=0 binding=--interleave=0,1 tu-c0r2n27 - 2 device=2 binding=--interleave=4,5 tu-c0r2n27 - 1 device=1 binding=--interleave=2,3 tu-c0r2n27 - 3 device=3 binding=--interleave=6,7 tu-c0r2n30 - 1 device=1 binding=--interleave=2,3 tu-c0r2n33 - 1 device=1 binding=--interleave=2,3 tu-c0r2n33 - 2 device=2 binding=--interleave=4,5 tu-c0r2n33 - 0 device=0 binding=--interleave=0,1 tu-c0r2n33 - 3 device=3 binding=--interleave=6,7 tu-c0r2n24 - 3 device=3 binding=--interleave=6,7 tu-c0r1n66 - 2 device=2 binding=--interleave=4,5 tu-c0r1n66 - 3 device=3 binding=--interleave=6,7 tu-c0r1n66 - 0 device=0 binding=--interleave=0,1 tu-c0r1n66 - 1 device=1 binding=--interleave=2,3 tu-c0r2n60 - 0 device=0 binding=--interleave=0,1 tu-c0r2n60 - 2 device=2 binding=--interleave=4,5 tu-c0r2n60 - 1 device=1 binding=--interleave=2,3 tu-c0r2n60 - 3 device=3 binding=--interleave=6,7 tu-c0r2n24 - 2 device=2 binding=--interleave=4,5 tu-c0r2n24 - 0 device=0 binding=--interleave=0,1 tu-c0r2n24 - 1 device=1 binding=--interleave=2,3 tu-c0r2n66 - 3 device=3 binding=--interleave=6,7 tu-c0r2n66 - 0 device=0 binding=--interleave=0,1 tu-c0r2n66 - 1 device=1 binding=--interleave=2,3 tu-c0r2n66 - 2 device=2 binding=--interleave=4,5 tu-c0r2n69 - 3 device=3 binding=--interleave=6,7 tu-c0r2n69 - 2 device=2 binding=--interleave=4,5 tu-c0r2n69 - 1 device=1 binding=--interleave=2,3 tu-c0r2n69 - 0 device=0 binding=--interleave=0,1 tu-c0r1n27 - 0 device=0 binding=--interleave=0,1 tu-c0r1n27 - 3 device=3 binding=--interleave=6,7 tu-c0r1n27 - 1 device=1 binding=--interleave=2,3 tu-c0r1n27 - 2 device=2 binding=--interleave=4,5 tu-c0r1n69 - 0 device=0 binding=--interleave=0,1 tu-c0r1n69 - 3 device=3 binding=--interleave=6,7 tu-c0r1n69 - 1 device=1 binding=--interleave=2,3 tu-c0r1n69 - 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-c0r1n63 - 0 device=0 binding=--interleave=0,1 tu-c0r1n63 - 3 device=3 binding=--interleave=6,7 tu-c0r1n63 - 1 device=1 binding=--interleave=2,3 tu-c0r1n63 - 2 device=2 binding=--interleave=4,5 tu-c0r1n60 - 2 device=2 binding=--interleave=4,5 tu-c0r1n60 - 0 device=0 binding=--interleave=0,1 tu-c0r1n60 - 1 device=1 binding=--interleave=2,3 tu-c0r1n60 - 3 device=3 binding=--interleave=6,7 tu-c0r1n30 - 0 device=0 binding=--interleave=0,1 tu-c0r1n30 - 3 device=3 binding=--interleave=6,7 tu-c0r1n30 - 1 device=1 binding=--interleave=2,3 tu-c0r1n30 - 2 device=2 binding=--interleave=4,5 tu-c0r1n33 - 1 device=1 binding=--interleave=2,3 tu-c0r1n33 - 2 device=2 binding=--interleave=4,5 tu-c0r1n33 - 3 device=3 binding=--interleave=6,7 tu-c0r1n33 - 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: 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: 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: ================================================ 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: ================================================ 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 64 SharedMemoryMpi: Node communicator of size 4 0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x1502a0000000 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 : 1.452796 s : Grid Layout Grid : Message : 1.452800 s : Global lattice size : 64 64 64 256 Grid : Message : 1.452808 s : OpenMP threads : 4 Grid : Message : 1.452812 s : MPI tasks : 2 2 2 8 Grid : Message : 1.494442 s : Making s innermost grids Grid : Message : 1.551242 s : Initialising 4d RNG Grid : Message : 1.646765 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.646794 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 3.503070 s : Initialising 5d RNG Grid : Message : 4.943585 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 4.943617 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 38.387959 s : Initialised RNGs Grid : Message : 42.192942 s : Drawing gauge field Grid : Message : 42.724298 s : Random gauge initialised Grid : Message : 42.737493 s : Setting up Cshift based reference Grid : Message : 72.115680 s : ***************************************************************** Grid : Message : 72.115705 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 72.115707 s : ***************************************************************** Grid : Message : 72.115709 s : ***************************************************************** Grid : Message : 72.115710 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 72.115713 s : * Vectorising space-time by 8 Grid : Message : 72.115715 s : * VComplexF size is 64 B Grid : Message : 72.115717 s : * SINGLE precision Grid : Message : 72.115719 s : * Using Overlapped Comms/Compute Grid : Message : 72.115721 s : * Using GENERIC Nc WilsonKernels Grid : Message : 72.115722 s : ***************************************************************** Grid : Message : 74.872260 s : Called warmup Grid : Message : 352.731659 s : Called Dw 30000 times in 2.78644e+08 us Grid : Message : 352.731729 s : mflop/s = 1.52597e+08 Grid : Message : 352.731731 s : mflop/s per rank = 2.38432e+06 Grid : Message : 352.731733 s : mflop/s per node = 9.53729e+06 Grid : Message : 352.731735 s : RF GiB/s (base 2) = 310073 Grid : Message : 352.731737 s : mem GiB/s (base 2) = 193796 Grid : Message : 352.735278 s : norm diff 1.06407e-13 Grid : Message : 352.781927 s : #### Dhop calls report Grid : Message : 352.781934 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 352.781937 s : WilsonFermion5D TotalTime /Calls : 4646.99 us Grid : Message : 352.781939 s : WilsonFermion5D CommTime /Calls : 3149.98 us Grid : Message : 352.781941 s : WilsonFermion5D FaceTime /Calls : 467.151 us Grid : Message : 352.781943 s : WilsonFermion5D ComputeTime1/Calls : 4.70368 us Grid : Message : 352.781945 s : WilsonFermion5D ComputeTime2/Calls : 1042.84 us Grid : Message : 352.781976 s : Average mflops/s per call : 1.262e+11 Grid : Message : 352.781980 s : Average mflops/s per call per rank : 1.97187e+09 Grid : Message : 352.781982 s : Average mflops/s per call per node : 7.88748e+09 Grid : Message : 352.781984 s : Average mflops/s per call (full) : 1.55273e+08 Grid : Message : 352.781990 s : Average mflops/s per call per rank (full): 2.42615e+06 Grid : Message : 352.781994 s : Average mflops/s per call per node (full): 9.70459e+06 Grid : Message : 352.781998 s : WilsonFermion5D Stencil Grid : Message : 352.782001 s : WilsonFermion5D StencilEven Grid : Message : 352.782003 s : WilsonFermion5D StencilOdd Grid : Message : 352.782005 s : WilsonFermion5D Stencil Reporti() Grid : Message : 352.782006 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 352.782009 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 408.185372 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 408.185396 s : Called DwDag Grid : Message : 408.185397 s : norm dag result 12.0421 Grid : Message : 408.208484 s : norm dag ref 12.0421 Grid : Message : 408.223701 s : norm dag diff 7.21924e-14 Grid : Message : 408.264555 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 408.617122 s : src_e0.499998 Grid : Message : 409.480320 s : src_o0.500002 Grid : Message : 409.167040 s : ********************************************************* Grid : Message : 409.167043 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 409.167044 s : * Vectorising space-time by 8 Grid : Message : 409.167046 s : * SINGLE precision Grid : Message : 409.167047 s : * Using Overlapped Comms/Compute Grid : Message : 409.167048 s : * Using GENERIC Nc WilsonKernels Grid : Message : 409.167049 s : ********************************************************* Grid : Message : 544.822916 s : Deo mflop/s = 1.56784e+08 Grid : Message : 544.822948 s : Deo mflop/s per rank 2.44975e+06 Grid : Message : 544.822950 s : Deo mflop/s per node 9.79899e+06 Grid : Message : 544.822953 s : #### Dhop calls report Grid : Message : 544.822955 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 544.822957 s : WilsonFermion5D TotalTime /Calls : 4521.57 us Grid : Message : 544.822959 s : WilsonFermion5D CommTime /Calls : 2975.09 us Grid : Message : 544.822961 s : WilsonFermion5D FaceTime /Calls : 560.933 us Grid : Message : 544.822963 s : WilsonFermion5D ComputeTime1/Calls : 5.9897 us Grid : Message : 544.822965 s : WilsonFermion5D ComputeTime2/Calls : 1011.67 us Grid : Message : 544.822988 s : Average mflops/s per call : 1.0607e+11 Grid : Message : 544.822992 s : Average mflops/s per call per rank : 1.65734e+09 Grid : Message : 544.822994 s : Average mflops/s per call per node : 6.62937e+09 Grid : Message : 544.822996 s : Average mflops/s per call (full) : 1.5958e+08 Grid : Message : 544.823002 s : Average mflops/s per call per rank (full): 2.49345e+06 Grid : Message : 544.823006 s : Average mflops/s per call per node (full): 9.97378e+06 Grid : Message : 544.823009 s : WilsonFermion5D Stencil Grid : Message : 544.823010 s : WilsonFermion5D StencilEven Grid : Message : 544.823012 s : WilsonFermion5D StencilOdd Grid : Message : 544.823014 s : WilsonFermion5D Stencil Reporti() Grid : Message : 544.823015 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 544.823017 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 544.895348 s : r_e6.02108 Grid : Message : 544.902277 s : r_o6.02101 Grid : Message : 544.908334 s : res12.0421 Grid : Message : 545.528282 s : norm diff 0 Grid : Message : 546.532874 s : norm diff even 0 Grid : Message : 547.251360 s : norm diff odd 0