255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r1n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n90 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n81 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n81 - 3 device=3 binding=--interleave=6,7
|
|
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-c0r1n78 - 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: 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[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
|
|
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 0x14ffa0000000 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 : 1.565327 s : Grid Layout
|
|
Grid : Message : 1.565331 s : Global lattice size : 48 48 48 48
|
|
Grid : Message : 1.565336 s : OpenMP threads : 4
|
|
Grid : Message : 1.565338 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.576732 s : Making s innermost grids
|
|
Grid : Message : 1.591292 s : Initialising 4d RNG
|
|
Grid : Message : 1.607386 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.607406 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 1.733296 s : Initialising 5d RNG
|
|
Grid : Message : 1.967786 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 1.967813 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 4.633889 s : Initialised RNGs
|
|
Grid : Message : 5.699185 s : Drawing gauge field
|
|
Grid : Message : 5.800869 s : Random gauge initialised
|
|
Grid : Message : 5.804955 s : Setting up Cshift based reference
|
|
Grid : Message : 10.808527 s : *****************************************************************
|
|
Grid : Message : 10.808549 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 10.808551 s : *****************************************************************
|
|
Grid : Message : 10.808553 s : *****************************************************************
|
|
Grid : Message : 10.808554 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 10.808562 s : * Vectorising space-time by 8
|
|
Grid : Message : 10.808564 s : * VComplexF size is 64 B
|
|
Grid : Message : 10.808566 s : * SINGLE precision
|
|
Grid : Message : 10.808568 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 10.808570 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 10.808572 s : *****************************************************************
|
|
Grid : Message : 11.365381 s : Called warmup
|
|
Grid : Message : 97.739052 s : Called Dw 30000 times in 8.63735e+07 us
|
|
Grid : Message : 97.739106 s : mflop/s = 3.89403e+07
|
|
Grid : Message : 97.739108 s : mflop/s per rank = 1.21688e+06
|
|
Grid : Message : 97.739110 s : mflop/s per node = 4.86754e+06
|
|
Grid : Message : 97.739112 s : RF GiB/s (base 2) = 79125.8
|
|
Grid : Message : 97.739114 s : mem GiB/s (base 2) = 49453.6
|
|
Grid : Message : 97.739684 s : norm diff 1.05759e-13
|
|
Grid : Message : 97.749608 s : #### Dhop calls report
|
|
Grid : Message : 97.749616 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 97.749620 s : WilsonFermion5D TotalTime /Calls : 1440.85 us
|
|
Grid : Message : 97.749622 s : WilsonFermion5D CommTime /Calls : 1003.73 us
|
|
Grid : Message : 97.749624 s : WilsonFermion5D FaceTime /Calls : 215.311 us
|
|
Grid : Message : 97.749626 s : WilsonFermion5D ComputeTime1/Calls : 3.08775 us
|
|
Grid : Message : 97.749628 s : WilsonFermion5D ComputeTime2/Calls : 234.501 us
|
|
Grid : Message : 97.749646 s : Average mflops/s per call : 1.78099e+10
|
|
Grid : Message : 97.749650 s : Average mflops/s per call per rank : 5.5656e+08
|
|
Grid : Message : 97.749652 s : Average mflops/s per call per node : 2.22624e+09
|
|
Grid : Message : 97.749656 s : Average mflops/s per call (full) : 3.96128e+07
|
|
Grid : Message : 97.749659 s : Average mflops/s per call per rank (full): 1.2379e+06
|
|
Grid : Message : 97.749661 s : Average mflops/s per call per node (full): 4.9516e+06
|
|
Grid : Message : 97.749663 s : WilsonFermion5D Stencil
|
|
Grid : Message : 97.749665 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 97.749668 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 97.749670 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 97.749672 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 97.749675 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 106.415478 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 106.415502 s : Called DwDag
|
|
Grid : Message : 106.415503 s : norm dag result 12.0422
|
|
Grid : Message : 106.429244 s : norm dag ref 12.0422
|
|
Grid : Message : 106.432306 s : norm dag diff 7.13141e-14
|
|
Grid : Message : 106.447571 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 106.514419 s : src_e0.499992
|
|
Grid : Message : 106.579087 s : src_o0.500008
|
|
Grid : Message : 106.595293 s : *********************************************************
|
|
Grid : Message : 106.595296 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 106.595297 s : * Vectorising space-time by 8
|
|
Grid : Message : 106.595298 s : * SINGLE precision
|
|
Grid : Message : 106.595299 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 106.595300 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 106.595301 s : *********************************************************
|
|
Grid : Message : 153.296330 s : Deo mflop/s = 3.62241e+07
|
|
Grid : Message : 153.296850 s : Deo mflop/s per rank 1.132e+06
|
|
Grid : Message : 153.296870 s : Deo mflop/s per node 4.52801e+06
|
|
Grid : Message : 153.296900 s : #### Dhop calls report
|
|
Grid : Message : 153.296920 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 153.296940 s : WilsonFermion5D TotalTime /Calls : 1547.63 us
|
|
Grid : Message : 153.296960 s : WilsonFermion5D CommTime /Calls : 1046.74 us
|
|
Grid : Message : 153.296980 s : WilsonFermion5D FaceTime /Calls : 286.366 us
|
|
Grid : Message : 153.297020 s : WilsonFermion5D ComputeTime1/Calls : 4.8817 us
|
|
Grid : Message : 153.297040 s : WilsonFermion5D ComputeTime2/Calls : 238.437 us
|
|
Grid : Message : 153.297230 s : Average mflops/s per call : 1.02065e+10
|
|
Grid : Message : 153.297270 s : Average mflops/s per call per rank : 3.18952e+08
|
|
Grid : Message : 153.297290 s : Average mflops/s per call per node : 1.27581e+09
|
|
Grid : Message : 153.297320 s : Average mflops/s per call (full) : 3.68796e+07
|
|
Grid : Message : 153.297340 s : Average mflops/s per call per rank (full): 1.15249e+06
|
|
Grid : Message : 153.297360 s : Average mflops/s per call per node (full): 4.60995e+06
|
|
Grid : Message : 153.297400 s : WilsonFermion5D Stencil
|
|
Grid : Message : 153.297410 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 153.297420 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 153.297430 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 153.297460 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 153.297490 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 153.487210 s : r_e6.02129
|
|
Grid : Message : 153.503240 s : r_o6.02097
|
|
Grid : Message : 153.516860 s : res12.0423
|
|
Grid : Message : 153.160184 s : norm diff 0
|
|
Grid : Message : 153.295561 s : norm diff even 0
|
|
Grid : Message : 153.362804 s : norm diff odd 0
|