255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r1n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n78 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n78 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n78 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n81 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n90 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n81 - 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: 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
|
|
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 0x150400000000 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 : 1.553137 s : Grid Layout
|
|
Grid : Message : 1.553140 s : Global lattice size : 64 64 64 128
|
|
Grid : Message : 1.553144 s : OpenMP threads : 4
|
|
Grid : Message : 1.553146 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.591415 s : Making s innermost grids
|
|
Grid : Message : 1.643527 s : Initialising 4d RNG
|
|
Grid : Message : 1.733769 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.733793 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 2.687944 s : Initialising 5d RNG
|
|
Grid : Message : 4.932540 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 4.933190 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 21.773430 s : Initialised RNGs
|
|
Grid : Message : 24.775839 s : Drawing gauge field
|
|
Grid : Message : 25.506673 s : Random gauge initialised
|
|
Grid : Message : 25.516620 s : Setting up Cshift based reference
|
|
Grid : Message : 54.420958 s : *****************************************************************
|
|
Grid : Message : 54.420980 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 54.420981 s : *****************************************************************
|
|
Grid : Message : 54.420982 s : *****************************************************************
|
|
Grid : Message : 54.420983 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 54.420984 s : * Vectorising space-time by 8
|
|
Grid : Message : 54.420985 s : * VComplexF size is 64 B
|
|
Grid : Message : 54.420986 s : * SINGLE precision
|
|
Grid : Message : 54.420987 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 54.420988 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 54.420989 s : *****************************************************************
|
|
Grid : Message : 56.418238 s : Called warmup
|
|
Grid : Message : 337.944860 s : Called Dw 30000 times in 2.80676e+08 us
|
|
Grid : Message : 337.945460 s : mflop/s = 7.5746e+07
|
|
Grid : Message : 337.945480 s : mflop/s per rank = 2.36706e+06
|
|
Grid : Message : 337.945500 s : mflop/s per node = 9.46825e+06
|
|
Grid : Message : 337.945520 s : RF GiB/s (base 2) = 153914
|
|
Grid : Message : 337.945540 s : mem GiB/s (base 2) = 96196.3
|
|
Grid : Message : 337.980600 s : norm diff 1.07359e-13
|
|
Grid : Message : 337.146303 s : #### Dhop calls report
|
|
Grid : Message : 337.146310 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 337.146313 s : WilsonFermion5D TotalTime /Calls : 4682.02 us
|
|
Grid : Message : 337.146315 s : WilsonFermion5D CommTime /Calls : 3157.4 us
|
|
Grid : Message : 337.146317 s : WilsonFermion5D FaceTime /Calls : 471.742 us
|
|
Grid : Message : 337.146319 s : WilsonFermion5D ComputeTime1/Calls : 4.66553 us
|
|
Grid : Message : 337.146324 s : WilsonFermion5D ComputeTime2/Calls : 1066.42 us
|
|
Grid : Message : 337.146339 s : Average mflops/s per call : 6.05546e+10
|
|
Grid : Message : 337.146342 s : Average mflops/s per call per rank : 1.89233e+09
|
|
Grid : Message : 337.146344 s : Average mflops/s per call per node : 7.56933e+09
|
|
Grid : Message : 337.146347 s : Average mflops/s per call (full) : 7.70559e+07
|
|
Grid : Message : 337.146349 s : Average mflops/s per call per rank (full): 2.408e+06
|
|
Grid : Message : 337.146352 s : Average mflops/s per call per node (full): 9.63198e+06
|
|
Grid : Message : 337.146354 s : WilsonFermion5D Stencil
|
|
Grid : Message : 337.146355 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 337.146356 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 337.146357 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 337.146358 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 337.146361 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 392.570148 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 392.570167 s : Called DwDag
|
|
Grid : Message : 392.570168 s : norm dag result 12.0421
|
|
Grid : Message : 392.597817 s : norm dag ref 12.0421
|
|
Grid : Message : 392.613608 s : norm dag diff 7.28475e-14
|
|
Grid : Message : 392.655240 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 393.337360 s : src_e0.499997
|
|
Grid : Message : 393.428755 s : src_o0.500003
|
|
Grid : Message : 393.551540 s : *********************************************************
|
|
Grid : Message : 393.551542 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 393.551543 s : * Vectorising space-time by 8
|
|
Grid : Message : 393.551544 s : * SINGLE precision
|
|
Grid : Message : 393.551545 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 393.551546 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 393.551547 s : *********************************************************
|
|
Grid : Message : 531.331972 s : Deo mflop/s = 7.71814e+07
|
|
Grid : Message : 531.331998 s : Deo mflop/s per rank 2.41192e+06
|
|
Grid : Message : 531.332000 s : Deo mflop/s per node 9.64768e+06
|
|
Grid : Message : 531.332003 s : #### Dhop calls report
|
|
Grid : Message : 531.332008 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 531.332011 s : WilsonFermion5D TotalTime /Calls : 4592.41 us
|
|
Grid : Message : 531.332015 s : WilsonFermion5D CommTime /Calls : 3024.25 us
|
|
Grid : Message : 531.332017 s : WilsonFermion5D FaceTime /Calls : 573.717 us
|
|
Grid : Message : 531.332020 s : WilsonFermion5D ComputeTime1/Calls : 5.83554 us
|
|
Grid : Message : 531.332023 s : WilsonFermion5D ComputeTime2/Calls : 1021.88 us
|
|
Grid : Message : 531.332042 s : Average mflops/s per call : 5.06597e+10
|
|
Grid : Message : 531.332046 s : Average mflops/s per call per rank : 1.58312e+09
|
|
Grid : Message : 531.332048 s : Average mflops/s per call per node : 6.33246e+09
|
|
Grid : Message : 531.332050 s : Average mflops/s per call (full) : 7.85594e+07
|
|
Grid : Message : 531.332053 s : Average mflops/s per call per rank (full): 2.45498e+06
|
|
Grid : Message : 531.332055 s : Average mflops/s per call per node (full): 9.81993e+06
|
|
Grid : Message : 531.332057 s : WilsonFermion5D Stencil
|
|
Grid : Message : 531.332059 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 531.332060 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 531.332063 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 531.332064 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 531.332065 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 531.403155 s : r_e6.02113
|
|
Grid : Message : 531.411033 s : r_o6.02101
|
|
Grid : Message : 531.417417 s : res12.0421
|
|
Grid : Message : 532.503110 s : norm diff 0
|
|
Grid : Message : 532.830118 s : norm diff even 0
|
|
Grid : Message : 533.297755 s : norm diff odd 0
|