tu-c0r2n30 - 0 device=0 binding=--interleave=0,1 tu-c0r1n27 - 0 device=0 binding=--interleave=0,1 tu-c0r2n60 - 0 device=0 binding=--interleave=0,1 tu-c0r1n63 - 0 device=0 binding=--interleave=0,1 tu-c0r1n24 - 0 device=0 binding=--interleave=0,1 tu-c0r1n69 - 0 device=0 binding=--interleave=0,1 tu-c0r2n69 - 0 device=0 binding=--interleave=0,1 tu-c0r1n24 - 1 device=1 binding=--interleave=2,3 tu-c0r2n24 - 0 device=0 binding=--interleave=0,1 tu-c0r2n27 - 0 device=0 binding=--interleave=0,1 tu-c0r2n33 - 0 device=0 binding=--interleave=0,1 tu-c0r2n63 - 0 device=0 binding=--interleave=0,1 tu-c0r2n66 - 0 device=0 binding=--interleave=0,1 tu-c0r1n63 - 1 device=1 binding=--interleave=2,3 tu-c0r1n27 - 1 device=1 binding=--interleave=2,3 tu-c0r2n63 - 1 device=1 binding=--interleave=2,3 tu-c0r2n33 - 1 device=1 binding=--interleave=2,3 tu-c0r1n69 - 1 device=1 binding=--interleave=2,3 tu-c0r2n66 - 1 device=1 binding=--interleave=2,3 tu-c0r2n27 - 1 device=1 binding=--interleave=2,3 tu-c0r2n24 - 1 device=1 binding=--interleave=2,3 tu-c0r2n30 - 1 device=1 binding=--interleave=2,3 tu-c0r2n30 - 2 device=2 binding=--interleave=4,5 tu-c0r2n60 - 2 device=2 binding=--interleave=4,5 tu-c0r1n66 - 0 device=0 binding=--interleave=0,1 tu-c0r2n69 - 1 device=1 binding=--interleave=2,3 tu-c0r2n30 - 3 device=3 binding=--interleave=6,7 tu-c0r2n33 - 2 device=2 binding=--interleave=4,5 tu-c0r2n66 - 2 device=2 binding=--interleave=4,5 tu-c0r1n24 - 2 device=2 binding=--interleave=4,5 tu-c0r2n69 - 3 device=3 binding=--interleave=6,7 tu-c0r2n27 - 2 device=2 binding=--interleave=4,5 tu-c0r2n69 - 2 device=2 binding=--interleave=4,5 tu-c0r1n66 - 1 device=1 binding=--interleave=2,3 tu-c0r1n69 - 2 device=2 binding=--interleave=4,5 tu-c0r1n69 - 3 device=3 binding=--interleave=6,7 tu-c0r1n66 - 2 device=2 binding=--interleave=4,5 tu-c0r2n60 - 1 device=1 binding=--interleave=2,3 tu-c0r2n33 - 3 device=3 binding=--interleave=6,7 tu-c0r1n66 - 3 device=3 binding=--interleave=6,7 tu-c0r1n27 - 2 device=2 binding=--interleave=4,5 tu-c0r2n66 - 3 device=3 binding=--interleave=6,7 tu-c0r1n63 - 3 device=3 binding=--interleave=6,7 tu-c0r2n63 - 2 device=2 binding=--interleave=4,5 tu-c0r2n60 - 3 device=3 binding=--interleave=6,7 tu-c0r2n63 - 3 device=3 binding=--interleave=6,7 tu-c0r2n24 - 3 device=3 binding=--interleave=6,7 tu-c0r1n24 - 3 device=3 binding=--interleave=6,7 tu-c0r1n63 - 2 device=2 binding=--interleave=4,5 tu-c0r2n24 - 2 device=2 binding=--interleave=4,5 tu-c0r2n27 - 3 device=3 binding=--interleave=6,7 tu-c0r1n27 - 3 device=3 binding=--interleave=6,7 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 - 1 device=1 binding=--interleave=2,3 tu-c0r1n60 - 3 device=3 binding=--interleave=6,7 tu-c0r1n60 - 1 device=1 binding=--interleave=2,3 tu-c0r1n30 - 2 device=2 binding=--interleave=4,5 tu-c0r1n30 - 3 device=3 binding=--interleave=6,7 tu-c0r1n33 - 0 device=0 binding=--interleave=0,1 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 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[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: 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 0 device 0 bus id: 0000:03:00.0 AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ AcceleratorCudaInit: ================================================ local rank 1 device 0 bus id: 0000:44:00.0 AcceleratorCudaInit: ================================================ 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 0x14d4a0000000 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 : 1.591037 s : Grid Layout Grid : Message : 1.591041 s : Global lattice size : 64 64 64 256 Grid : Message : 1.591048 s : OpenMP threads : 4 Grid : Message : 1.591051 s : MPI tasks : 2 2 2 8 Grid : Message : 1.631861 s : Making s innermost grids Grid : Message : 1.687484 s : Initialising 4d RNG Grid : Message : 1.776720 s : Intialising parallel RNG with unique string 'The 4D RNG' Grid : Message : 1.776744 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1 Grid : Message : 3.540782 s : Initialising 5d RNG Grid : Message : 4.945093 s : Intialising parallel RNG with unique string 'The 5D RNG' Grid : Message : 4.945125 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a Grid : Message : 38.249960 s : Initialised RNGs Grid : Message : 42.189661 s : Drawing gauge field Grid : Message : 43.869980 s : Random gauge initialised Grid : Message : 43.102201 s : Setting up Cshift based reference Grid : Message : 72.356840 s : ***************************************************************** Grid : Message : 72.357100 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm Grid : Message : 72.357110 s : ***************************************************************** Grid : Message : 72.357120 s : ***************************************************************** Grid : Message : 72.357130 s : * Benchmarking DomainWallFermionR::Dhop Grid : Message : 72.357140 s : * Vectorising space-time by 8 Grid : Message : 72.357150 s : * VComplexF size is 64 B Grid : Message : 72.357160 s : * SINGLE precision Grid : Message : 72.357180 s : * Using Overlapped Comms/Compute Grid : Message : 72.357190 s : * Using GENERIC Nc WilsonKernels Grid : Message : 72.357200 s : ***************************************************************** Grid : Message : 74.693440 s : Called warmup Grid : Message : 352.669006 s : Called Dw 30000 times in 2.78599e+08 us Grid : Message : 352.669053 s : mflop/s = 1.52621e+08 Grid : Message : 352.669055 s : mflop/s per rank = 2.38471e+06 Grid : Message : 352.669057 s : mflop/s per node = 9.53883e+06 Grid : Message : 352.669059 s : RF GiB/s (base 2) = 310123 Grid : Message : 352.669061 s : mem GiB/s (base 2) = 193827 Grid : Message : 352.672594 s : norm diff 1.06407e-13 Grid : Message : 352.719634 s : #### Dhop calls report Grid : Message : 352.719642 s : WilsonFermion5D Number of DhopEO Calls : 60002 Grid : Message : 352.719645 s : WilsonFermion5D TotalTime /Calls : 4647.2 us Grid : Message : 352.719647 s : WilsonFermion5D CommTime /Calls : 3145.58 us Grid : Message : 352.719649 s : WilsonFermion5D FaceTime /Calls : 465.634 us Grid : Message : 352.719651 s : WilsonFermion5D ComputeTime1/Calls : 5.1078 us Grid : Message : 352.719653 s : WilsonFermion5D ComputeTime2/Calls : 1049.57 us Grid : Message : 352.719675 s : Average mflops/s per call : 1.28235e+11 Grid : Message : 352.719680 s : Average mflops/s per call per rank : 2.00368e+09 Grid : Message : 352.719683 s : Average mflops/s per call per node : 8.01471e+09 Grid : Message : 352.719685 s : Average mflops/s per call (full) : 1.55267e+08 Grid : Message : 352.719688 s : Average mflops/s per call per rank (full): 2.42604e+06 Grid : Message : 352.719690 s : Average mflops/s per call per node (full): 9.70416e+06 Grid : Message : 352.719692 s : WilsonFermion5D Stencil Grid : Message : 352.719693 s : WilsonFermion5D StencilEven Grid : Message : 352.719695 s : WilsonFermion5D StencilOdd Grid : Message : 352.719697 s : WilsonFermion5D Stencil Reporti() Grid : Message : 352.719698 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 352.719699 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 407.935241 s : Compare to naive wilson implementation Dag to verify correctness Grid : Message : 407.935264 s : Called DwDag Grid : Message : 407.935265 s : norm dag result 12.0421 Grid : Message : 407.948431 s : norm dag ref 12.0421 Grid : Message : 407.963681 s : norm dag diff 7.21924e-14 Grid : Message : 408.416000 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec Grid : Message : 408.409027 s : src_e0.499998 Grid : Message : 409.712320 s : src_o0.500002 Grid : Message : 409.181353 s : ********************************************************* Grid : Message : 409.181357 s : * Benchmarking DomainWallFermionF::DhopEO Grid : Message : 409.181358 s : * Vectorising space-time by 8 Grid : Message : 409.181359 s : * SINGLE precision Grid : Message : 409.181360 s : * Using Overlapped Comms/Compute Grid : Message : 409.181361 s : * Using GENERIC Nc WilsonKernels Grid : Message : 409.181362 s : ********************************************************* Grid : Message : 544.904212 s : Deo mflop/s = 1.56711e+08 Grid : Message : 544.904240 s : Deo mflop/s per rank 2.44861e+06 Grid : Message : 544.904242 s : Deo mflop/s per node 9.79442e+06 Grid : Message : 544.904245 s : #### Dhop calls report Grid : Message : 544.904247 s : WilsonFermion5D Number of DhopEO Calls : 30001 Grid : Message : 544.904250 s : WilsonFermion5D TotalTime /Calls : 4523.85 us Grid : Message : 544.904252 s : WilsonFermion5D CommTime /Calls : 2972.66 us Grid : Message : 544.904254 s : WilsonFermion5D FaceTime /Calls : 561.771 us Grid : Message : 544.904256 s : WilsonFermion5D ComputeTime1/Calls : 6.26712 us Grid : Message : 544.904258 s : WilsonFermion5D ComputeTime2/Calls : 1016.18 us Grid : Message : 544.904280 s : Average mflops/s per call : 1.07023e+11 Grid : Message : 544.904284 s : Average mflops/s per call per rank : 1.67224e+09 Grid : Message : 544.904286 s : Average mflops/s per call per node : 6.68897e+09 Grid : Message : 544.904288 s : Average mflops/s per call (full) : 1.595e+08 Grid : Message : 544.904294 s : Average mflops/s per call per rank (full): 2.49219e+06 Grid : Message : 544.904298 s : Average mflops/s per call per node (full): 9.96876e+06 Grid : Message : 544.904300 s : WilsonFermion5D Stencil Grid : Message : 544.904301 s : WilsonFermion5D StencilEven Grid : Message : 544.904303 s : WilsonFermion5D StencilOdd Grid : Message : 544.904306 s : WilsonFermion5D Stencil Reporti() Grid : Message : 544.904307 s : WilsonFermion5D StencilEven Reporti() Grid : Message : 544.904309 s : WilsonFermion5D StencilOdd Reporti() Grid : Message : 544.975585 s : r_e6.02108 Grid : Message : 544.984749 s : r_o6.02101 Grid : Message : 544.990859 s : res12.0421 Grid : Message : 545.680044 s : norm diff 0 Grid : Message : 546.449537 s : norm diff even 0 Grid : Message : 546.888971 s : norm diff odd 0