255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r2n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n90 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n78 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n78 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n78 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n81 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n81 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r2n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r2n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r2n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r2n84 - 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: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
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 2 device 0 bus id: 0000:84:00.0
|
|
local rank 3 device 0 bus id: 0000:C4:00.0
|
|
SharedMemoryMpi: World communicator of size 32
|
|
SharedMemoryMpi: Node communicator of size 4
|
|
0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14bf00000000 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 : 1.525811 s : Grid Layout
|
|
Grid : Message : 1.525815 s : Global lattice size : 64 64 64 128
|
|
Grid : Message : 1.525821 s : OpenMP threads : 4
|
|
Grid : Message : 1.525824 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.565177 s : Making s innermost grids
|
|
Grid : Message : 1.620618 s : Initialising 4d RNG
|
|
Grid : Message : 1.715588 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.715614 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 2.812679 s : Initialising 5d RNG
|
|
Grid : Message : 4.218765 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 4.218809 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 20.946370 s : Initialised RNGs
|
|
Grid : Message : 25.908590 s : Drawing gauge field
|
|
Grid : Message : 25.673282 s : Random gauge initialised
|
|
Grid : Message : 25.684592 s : Setting up Cshift based reference
|
|
Grid : Message : 54.633199 s : *****************************************************************
|
|
Grid : Message : 54.633226 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 54.633228 s : *****************************************************************
|
|
Grid : Message : 54.633229 s : *****************************************************************
|
|
Grid : Message : 54.633230 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 54.633231 s : * Vectorising space-time by 8
|
|
Grid : Message : 54.633232 s : * VComplexF size is 64 B
|
|
Grid : Message : 54.633233 s : * SINGLE precision
|
|
Grid : Message : 54.633235 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 54.633236 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 54.633237 s : *****************************************************************
|
|
Grid : Message : 56.687774 s : Called warmup
|
|
Grid : Message : 334.924814 s : Called Dw 30000 times in 2.78236e+08 us
|
|
Grid : Message : 334.924867 s : mflop/s = 7.64102e+07
|
|
Grid : Message : 334.924869 s : mflop/s per rank = 2.38782e+06
|
|
Grid : Message : 334.924871 s : mflop/s per node = 9.55127e+06
|
|
Grid : Message : 334.924873 s : RF GiB/s (base 2) = 155264
|
|
Grid : Message : 334.924875 s : mem GiB/s (base 2) = 97039.8
|
|
Grid : Message : 334.928437 s : norm diff 1.07359e-13
|
|
Grid : Message : 334.973847 s : #### Dhop calls report
|
|
Grid : Message : 334.973853 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 334.973856 s : WilsonFermion5D TotalTime /Calls : 4641.74 us
|
|
Grid : Message : 334.973858 s : WilsonFermion5D CommTime /Calls : 3187.86 us
|
|
Grid : Message : 334.973860 s : WilsonFermion5D FaceTime /Calls : 475.078 us
|
|
Grid : Message : 334.973862 s : WilsonFermion5D ComputeTime1/Calls : 4.70608 us
|
|
Grid : Message : 334.973864 s : WilsonFermion5D ComputeTime2/Calls : 992.064 us
|
|
Grid : Message : 334.973939 s : Average mflops/s per call : 6.18754e+10
|
|
Grid : Message : 334.973942 s : Average mflops/s per call per rank : 1.93361e+09
|
|
Grid : Message : 334.973944 s : Average mflops/s per call per node : 7.73443e+09
|
|
Grid : Message : 334.973946 s : Average mflops/s per call (full) : 7.77246e+07
|
|
Grid : Message : 334.973951 s : Average mflops/s per call per rank (full): 2.42889e+06
|
|
Grid : Message : 334.973954 s : Average mflops/s per call per node (full): 9.71558e+06
|
|
Grid : Message : 334.973957 s : WilsonFermion5D Stencil
|
|
Grid : Message : 334.973959 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 334.973961 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 334.973963 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 334.973966 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 334.973969 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 390.277780 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 390.277810 s : Called DwDag
|
|
Grid : Message : 390.277811 s : norm dag result 12.0421
|
|
Grid : Message : 390.289524 s : norm dag ref 12.0421
|
|
Grid : Message : 390.304678 s : norm dag diff 7.28475e-14
|
|
Grid : Message : 390.343470 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 390.740270 s : src_e0.499997
|
|
Grid : Message : 391.134645 s : src_o0.500003
|
|
Grid : Message : 391.231945 s : *********************************************************
|
|
Grid : Message : 391.231949 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 391.231950 s : * Vectorising space-time by 8
|
|
Grid : Message : 391.231951 s : * SINGLE precision
|
|
Grid : Message : 391.231952 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 391.231953 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 391.231954 s : *********************************************************
|
|
Grid : Message : 526.406274 s : Deo mflop/s = 7.86675e+07
|
|
Grid : Message : 526.406307 s : Deo mflop/s per rank 2.45836e+06
|
|
Grid : Message : 526.406309 s : Deo mflop/s per node 9.83344e+06
|
|
Grid : Message : 526.406311 s : #### Dhop calls report
|
|
Grid : Message : 526.406312 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 526.406314 s : WilsonFermion5D TotalTime /Calls : 4505.52 us
|
|
Grid : Message : 526.406316 s : WilsonFermion5D CommTime /Calls : 2992.05 us
|
|
Grid : Message : 526.406318 s : WilsonFermion5D FaceTime /Calls : 565.233 us
|
|
Grid : Message : 526.406320 s : WilsonFermion5D ComputeTime1/Calls : 5.99477 us
|
|
Grid : Message : 526.406322 s : WilsonFermion5D ComputeTime2/Calls : 973.471 us
|
|
Grid : Message : 526.406345 s : Average mflops/s per call : 5.27856e+10
|
|
Grid : Message : 526.406348 s : Average mflops/s per call per rank : 1.64955e+09
|
|
Grid : Message : 526.406350 s : Average mflops/s per call per node : 6.5982e+09
|
|
Grid : Message : 526.406352 s : Average mflops/s per call (full) : 8.00744e+07
|
|
Grid : Message : 526.406355 s : Average mflops/s per call per rank (full): 2.50233e+06
|
|
Grid : Message : 526.406358 s : Average mflops/s per call per node (full): 1.00093e+07
|
|
Grid : Message : 526.406361 s : WilsonFermion5D Stencil
|
|
Grid : Message : 526.406364 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 526.406365 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 526.406367 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 526.406369 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 526.406372 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 526.478124 s : r_e6.02113
|
|
Grid : Message : 526.484671 s : r_o6.02101
|
|
Grid : Message : 526.490617 s : res12.0421
|
|
Grid : Message : 527.120240 s : norm diff 0
|
|
Grid : Message : 527.925344 s : norm diff even 0
|
|
Grid : Message : 528.408314 s : norm diff odd 0
|