255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r2n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n78 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n78 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n90 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n78 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n81 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n81 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n84 - 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
|
|
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[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
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
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 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 32
|
|
SharedMemoryMpi: Node communicator of size 4
|
|
0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14c120000000 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 : 1.340523 s : Grid Layout
|
|
Grid : Message : 1.340526 s : Global lattice size : 64 64 64 128
|
|
Grid : Message : 1.340532 s : OpenMP threads : 4
|
|
Grid : Message : 1.340534 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.377020 s : Making s innermost grids
|
|
Grid : Message : 1.423255 s : Initialising 4d RNG
|
|
Grid : Message : 1.516862 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.516891 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 2.453396 s : Initialising 5d RNG
|
|
Grid : Message : 3.913055 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 3.913090 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 20.601953 s : Initialised RNGs
|
|
Grid : Message : 24.611804 s : Drawing gauge field
|
|
Grid : Message : 25.443310 s : Random gauge initialised
|
|
Grid : Message : 25.459673 s : Setting up Cshift based reference
|
|
Grid : Message : 54.429080 s : *****************************************************************
|
|
Grid : Message : 54.429107 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 54.429110 s : *****************************************************************
|
|
Grid : Message : 54.429117 s : *****************************************************************
|
|
Grid : Message : 54.429119 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 54.429121 s : * Vectorising space-time by 8
|
|
Grid : Message : 54.429123 s : * VComplexF size is 64 B
|
|
Grid : Message : 54.429125 s : * SINGLE precision
|
|
Grid : Message : 54.429127 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 54.429128 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 54.429129 s : *****************************************************************
|
|
Grid : Message : 56.497413 s : Called warmup
|
|
Grid : Message : 339.501650 s : Called Dw 30000 times in 2.82552e+08 us
|
|
Grid : Message : 339.502430 s : mflop/s = 7.5243e+07
|
|
Grid : Message : 339.502450 s : mflop/s per rank = 2.35134e+06
|
|
Grid : Message : 339.502470 s : mflop/s per node = 9.40538e+06
|
|
Grid : Message : 339.502490 s : RF GiB/s (base 2) = 152892
|
|
Grid : Message : 339.502510 s : mem GiB/s (base 2) = 95557.6
|
|
Grid : Message : 339.537540 s : norm diff 1.07359e-13
|
|
Grid : Message : 339.103222 s : #### Dhop calls report
|
|
Grid : Message : 339.103229 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 339.103233 s : WilsonFermion5D TotalTime /Calls : 4713.47 us
|
|
Grid : Message : 339.103235 s : WilsonFermion5D CommTime /Calls : 3231.75 us
|
|
Grid : Message : 339.103237 s : WilsonFermion5D FaceTime /Calls : 480.174 us
|
|
Grid : Message : 339.103239 s : WilsonFermion5D ComputeTime1/Calls : 5.1041 us
|
|
Grid : Message : 339.103241 s : WilsonFermion5D ComputeTime2/Calls : 1015.05 us
|
|
Grid : Message : 339.103880 s : Average mflops/s per call : 6.26498e+10
|
|
Grid : Message : 339.103883 s : Average mflops/s per call per rank : 1.9578e+09
|
|
Grid : Message : 339.103885 s : Average mflops/s per call per node : 7.83122e+09
|
|
Grid : Message : 339.103887 s : Average mflops/s per call (full) : 7.65417e+07
|
|
Grid : Message : 339.103889 s : Average mflops/s per call per rank (full): 2.39193e+06
|
|
Grid : Message : 339.103891 s : Average mflops/s per call per node (full): 9.56771e+06
|
|
Grid : Message : 339.103893 s : WilsonFermion5D Stencil
|
|
Grid : Message : 339.103894 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 339.103895 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 339.103898 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 339.103899 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 339.103901 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 394.464941 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 394.464969 s : Called DwDag
|
|
Grid : Message : 394.464970 s : norm dag result 12.0421
|
|
Grid : Message : 394.478684 s : norm dag ref 12.0421
|
|
Grid : Message : 394.494808 s : norm dag diff 7.28475e-14
|
|
Grid : Message : 394.536229 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 394.922983 s : src_e0.499997
|
|
Grid : Message : 395.309310 s : src_o0.500003
|
|
Grid : Message : 395.434448 s : *********************************************************
|
|
Grid : Message : 395.434452 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 395.434453 s : * Vectorising space-time by 8
|
|
Grid : Message : 395.434454 s : * SINGLE precision
|
|
Grid : Message : 395.434455 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 395.434456 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 395.434457 s : *********************************************************
|
|
Grid : Message : 535.133103 s : Deo mflop/s = 7.61307e+07
|
|
Grid : Message : 535.133139 s : Deo mflop/s per rank 2.37909e+06
|
|
Grid : Message : 535.133142 s : Deo mflop/s per node 9.51634e+06
|
|
Grid : Message : 535.133145 s : #### Dhop calls report
|
|
Grid : Message : 535.133147 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 535.133149 s : WilsonFermion5D TotalTime /Calls : 4656.35 us
|
|
Grid : Message : 535.133151 s : WilsonFermion5D CommTime /Calls : 3088.67 us
|
|
Grid : Message : 535.133153 s : WilsonFermion5D FaceTime /Calls : 594.975 us
|
|
Grid : Message : 535.133155 s : WilsonFermion5D ComputeTime1/Calls : 6.24439 us
|
|
Grid : Message : 535.133157 s : WilsonFermion5D ComputeTime2/Calls : 997.716 us
|
|
Grid : Message : 535.133176 s : Average mflops/s per call : 5.26083e+10
|
|
Grid : Message : 535.133179 s : Average mflops/s per call per rank : 1.64401e+09
|
|
Grid : Message : 535.133181 s : Average mflops/s per call per node : 6.57603e+09
|
|
Grid : Message : 535.133183 s : Average mflops/s per call (full) : 7.74807e+07
|
|
Grid : Message : 535.133185 s : Average mflops/s per call per rank (full): 2.42127e+06
|
|
Grid : Message : 535.133187 s : Average mflops/s per call per node (full): 9.68508e+06
|
|
Grid : Message : 535.133189 s : WilsonFermion5D Stencil
|
|
Grid : Message : 535.133190 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 535.133192 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 535.133193 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 535.133194 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 535.133195 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 535.206775 s : r_e6.02113
|
|
Grid : Message : 535.214700 s : r_o6.02101
|
|
Grid : Message : 535.221223 s : res12.0421
|
|
Grid : Message : 535.897013 s : norm diff 0
|
|
Grid : Message : 536.685521 s : norm diff even 0
|
|
Grid : Message : 537.117656 s : norm diff odd 0
|