255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r1n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n81 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n78 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n81 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n78 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n78 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n90 - 3 device=3 binding=--interleave=6,7
|
|
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
|
|
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
|
|
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 3 device 0 bus id: 0000:C4:00.0
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 2 device 0 bus id: 0000:84:00.0
|
|
local rank 1 device 0 bus id: 0000:44:00.0
|
|
SharedMemoryMpi: World communicator of size 32
|
|
SharedMemoryMpi: Node communicator of size 4
|
|
0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14eea0000000 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 : 1.366393 s : Grid Layout
|
|
Grid : Message : 1.366397 s : Global lattice size : 64 64 64 128
|
|
Grid : Message : 1.366402 s : OpenMP threads : 4
|
|
Grid : Message : 1.366404 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.407148 s : Making s innermost grids
|
|
Grid : Message : 1.464257 s : Initialising 4d RNG
|
|
Grid : Message : 1.557730 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.557758 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 2.356467 s : Initialising 5d RNG
|
|
Grid : Message : 3.801979 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 3.802012 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 20.483524 s : Initialised RNGs
|
|
Grid : Message : 24.230918 s : Drawing gauge field
|
|
Grid : Message : 25.177490 s : Random gauge initialised
|
|
Grid : Message : 25.295480 s : Setting up Cshift based reference
|
|
Grid : Message : 54.973180 s : *****************************************************************
|
|
Grid : Message : 54.973410 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 54.973430 s : *****************************************************************
|
|
Grid : Message : 54.973440 s : *****************************************************************
|
|
Grid : Message : 54.973490 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 54.973510 s : * Vectorising space-time by 8
|
|
Grid : Message : 54.973530 s : * VComplexF size is 64 B
|
|
Grid : Message : 54.973560 s : * SINGLE precision
|
|
Grid : Message : 54.973580 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 54.973600 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 54.973630 s : *****************************************************************
|
|
Grid : Message : 56.188907 s : Called warmup
|
|
Grid : Message : 338.221994 s : Called Dw 30000 times in 2.82032e+08 us
|
|
Grid : Message : 338.222041 s : mflop/s = 7.53818e+07
|
|
Grid : Message : 338.222043 s : mflop/s per rank = 2.35568e+06
|
|
Grid : Message : 338.222045 s : mflop/s per node = 9.42273e+06
|
|
Grid : Message : 338.222047 s : RF GiB/s (base 2) = 153174
|
|
Grid : Message : 338.222049 s : mem GiB/s (base 2) = 95733.8
|
|
Grid : Message : 338.225548 s : norm diff 1.07359e-13
|
|
Grid : Message : 338.275111 s : #### Dhop calls report
|
|
Grid : Message : 338.275118 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 338.275121 s : WilsonFermion5D TotalTime /Calls : 4704.45 us
|
|
Grid : Message : 338.275123 s : WilsonFermion5D CommTime /Calls : 3197.7 us
|
|
Grid : Message : 338.275125 s : WilsonFermion5D FaceTime /Calls : 471.81 us
|
|
Grid : Message : 338.275127 s : WilsonFermion5D ComputeTime1/Calls : 5.0956 us
|
|
Grid : Message : 338.275129 s : WilsonFermion5D ComputeTime2/Calls : 1048.58 us
|
|
Grid : Message : 338.275196 s : Average mflops/s per call : 6.11343e+10
|
|
Grid : Message : 338.275200 s : Average mflops/s per call per rank : 1.91045e+09
|
|
Grid : Message : 338.275202 s : Average mflops/s per call per node : 7.64179e+09
|
|
Grid : Message : 338.275204 s : Average mflops/s per call (full) : 7.66885e+07
|
|
Grid : Message : 338.275206 s : Average mflops/s per call per rank (full): 2.39652e+06
|
|
Grid : Message : 338.275208 s : Average mflops/s per call per node (full): 9.58606e+06
|
|
Grid : Message : 338.275211 s : WilsonFermion5D Stencil
|
|
Grid : Message : 338.275212 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 338.275213 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 338.275214 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 338.275215 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 338.275216 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 393.586448 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 393.586467 s : Called DwDag
|
|
Grid : Message : 393.586468 s : norm dag result 12.0421
|
|
Grid : Message : 393.600340 s : norm dag ref 12.0421
|
|
Grid : Message : 393.616373 s : norm dag diff 7.28475e-14
|
|
Grid : Message : 393.662063 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 394.592240 s : src_e0.499997
|
|
Grid : Message : 394.431906 s : src_o0.500003
|
|
Grid : Message : 394.530690 s : *********************************************************
|
|
Grid : Message : 394.530693 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 394.530694 s : * Vectorising space-time by 8
|
|
Grid : Message : 394.530695 s : * SINGLE precision
|
|
Grid : Message : 394.530696 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 394.530697 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 394.530698 s : *********************************************************
|
|
Grid : Message : 534.917450 s : Deo mflop/s = 7.61957e+07
|
|
Grid : Message : 534.917770 s : Deo mflop/s per rank 2.38112e+06
|
|
Grid : Message : 534.917790 s : Deo mflop/s per node 9.52446e+06
|
|
Grid : Message : 534.917860 s : #### Dhop calls report
|
|
Grid : Message : 534.917900 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 534.917930 s : WilsonFermion5D TotalTime /Calls : 4651.72 us
|
|
Grid : Message : 534.917970 s : WilsonFermion5D CommTime /Calls : 3091.21 us
|
|
Grid : Message : 534.918000 s : WilsonFermion5D FaceTime /Calls : 583.213 us
|
|
Grid : Message : 534.918030 s : WilsonFermion5D ComputeTime1/Calls : 6.04677 us
|
|
Grid : Message : 534.918070 s : WilsonFermion5D ComputeTime2/Calls : 1003.12 us
|
|
Grid : Message : 534.918280 s : Average mflops/s per call : 5.15468e+10
|
|
Grid : Message : 534.918320 s : Average mflops/s per call per rank : 1.61084e+09
|
|
Grid : Message : 534.918350 s : Average mflops/s per call per node : 6.44335e+09
|
|
Grid : Message : 534.918380 s : Average mflops/s per call (full) : 7.75578e+07
|
|
Grid : Message : 534.918410 s : Average mflops/s per call per rank (full): 2.42368e+06
|
|
Grid : Message : 534.918450 s : Average mflops/s per call per node (full): 9.69473e+06
|
|
Grid : Message : 534.918480 s : WilsonFermion5D Stencil
|
|
Grid : Message : 534.918510 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 534.918520 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 534.918540 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 534.918560 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 534.918590 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 534.162791 s : r_e6.02113
|
|
Grid : Message : 534.171110 s : r_o6.02101
|
|
Grid : Message : 534.177848 s : res12.0421
|
|
Grid : Message : 534.858243 s : norm diff 0
|
|
Grid : Message : 535.620756 s : norm diff even 0
|
|
Grid : Message : 536.317800 s : norm diff odd 0
|