255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
tu-c0r1n72 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n72 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n72 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n72 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n93 - 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-c0r1n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n78 - 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-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-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: 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
|
|
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
|
|
local rank 3 device 0 bus id: 0000:C4:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
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: ================================================
|
|
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 0x153620000000 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 : 1.586387 s : Grid Layout
|
|
Grid : Message : 1.586391 s : Global lattice size : 64 64 64 128
|
|
Grid : Message : 1.586395 s : OpenMP threads : 4
|
|
Grid : Message : 1.586397 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.623450 s : Making s innermost grids
|
|
Grid : Message : 1.669091 s : Initialising 4d RNG
|
|
Grid : Message : 1.764584 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.764609 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 2.809637 s : Initialising 5d RNG
|
|
Grid : Message : 4.244322 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 4.244348 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 20.933733 s : Initialised RNGs
|
|
Grid : Message : 24.984408 s : Drawing gauge field
|
|
Grid : Message : 25.764404 s : Random gauge initialised
|
|
Grid : Message : 25.776965 s : Setting up Cshift based reference
|
|
Grid : Message : 54.920325 s : *****************************************************************
|
|
Grid : Message : 54.920345 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 54.920346 s : *****************************************************************
|
|
Grid : Message : 54.920347 s : *****************************************************************
|
|
Grid : Message : 54.920348 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 54.920349 s : * Vectorising space-time by 8
|
|
Grid : Message : 54.920350 s : * VComplexF size is 64 B
|
|
Grid : Message : 54.920351 s : * SINGLE precision
|
|
Grid : Message : 54.920353 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 54.920354 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 54.920355 s : *****************************************************************
|
|
Grid : Message : 56.979810 s : Called warmup
|
|
Grid : Message : 344.808695 s : Called Dw 30000 times in 2.87828e+08 us
|
|
Grid : Message : 344.808743 s : mflop/s = 7.38638e+07
|
|
Grid : Message : 344.808745 s : mflop/s per rank = 2.30824e+06
|
|
Grid : Message : 344.808747 s : mflop/s per node = 9.23297e+06
|
|
Grid : Message : 344.808749 s : RF GiB/s (base 2) = 150089
|
|
Grid : Message : 344.808751 s : mem GiB/s (base 2) = 93805.9
|
|
Grid : Message : 344.812244 s : norm diff 1.07359e-13
|
|
Grid : Message : 344.863370 s : #### Dhop calls report
|
|
Grid : Message : 344.863377 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 344.863380 s : WilsonFermion5D TotalTime /Calls : 4801.08 us
|
|
Grid : Message : 344.863382 s : WilsonFermion5D CommTime /Calls : 3288.96 us
|
|
Grid : Message : 344.863384 s : WilsonFermion5D FaceTime /Calls : 481.243 us
|
|
Grid : Message : 344.863386 s : WilsonFermion5D ComputeTime1/Calls : 4.66106 us
|
|
Grid : Message : 344.863388 s : WilsonFermion5D ComputeTime2/Calls : 1044.48 us
|
|
Grid : Message : 344.863413 s : Average mflops/s per call : 6.24625e+10
|
|
Grid : Message : 344.863417 s : Average mflops/s per call per rank : 1.95195e+09
|
|
Grid : Message : 344.863419 s : Average mflops/s per call per node : 7.80781e+09
|
|
Grid : Message : 344.863421 s : Average mflops/s per call (full) : 7.5145e+07
|
|
Grid : Message : 344.863426 s : Average mflops/s per call per rank (full): 2.34828e+06
|
|
Grid : Message : 344.863428 s : Average mflops/s per call per node (full): 9.39312e+06
|
|
Grid : Message : 344.863431 s : WilsonFermion5D Stencil
|
|
Grid : Message : 344.863432 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 344.863433 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 344.863435 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 344.863436 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 344.863437 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 399.969847 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 399.969867 s : Called DwDag
|
|
Grid : Message : 399.969868 s : norm dag result 12.0421
|
|
Grid : Message : 399.992452 s : norm dag ref 12.0421
|
|
Grid : Message : 400.913200 s : norm dag diff 7.28475e-14
|
|
Grid : Message : 400.527470 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 400.450056 s : src_e0.499997
|
|
Grid : Message : 400.898607 s : src_o0.500003
|
|
Grid : Message : 401.789000 s : *********************************************************
|
|
Grid : Message : 401.789500 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 401.789700 s : * Vectorising space-time by 8
|
|
Grid : Message : 401.790200 s : * SINGLE precision
|
|
Grid : Message : 401.790400 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 401.790700 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 401.790900 s : *********************************************************
|
|
Grid : Message : 546.400468 s : Deo mflop/s = 7.31426e+07
|
|
Grid : Message : 546.400499 s : Deo mflop/s per rank 2.28571e+06
|
|
Grid : Message : 546.400501 s : Deo mflop/s per node 9.14282e+06
|
|
Grid : Message : 546.400503 s : #### Dhop calls report
|
|
Grid : Message : 546.400505 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 546.400507 s : WilsonFermion5D TotalTime /Calls : 4846.12 us
|
|
Grid : Message : 546.400509 s : WilsonFermion5D CommTime /Calls : 3261.72 us
|
|
Grid : Message : 546.400511 s : WilsonFermion5D FaceTime /Calls : 613.301 us
|
|
Grid : Message : 546.400513 s : WilsonFermion5D ComputeTime1/Calls : 5.89694 us
|
|
Grid : Message : 546.400515 s : WilsonFermion5D ComputeTime2/Calls : 996.607 us
|
|
Grid : Message : 546.400534 s : Average mflops/s per call : 5.12518e+10
|
|
Grid : Message : 546.400538 s : Average mflops/s per call per rank : 1.60162e+09
|
|
Grid : Message : 546.400540 s : Average mflops/s per call per node : 6.40647e+09
|
|
Grid : Message : 546.400542 s : Average mflops/s per call (full) : 7.44467e+07
|
|
Grid : Message : 546.400544 s : Average mflops/s per call per rank (full): 2.32646e+06
|
|
Grid : Message : 546.400546 s : Average mflops/s per call per node (full): 9.30583e+06
|
|
Grid : Message : 546.400548 s : WilsonFermion5D Stencil
|
|
Grid : Message : 546.400549 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 546.400550 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 546.400551 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 546.400552 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 546.400553 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 546.474888 s : r_e6.02113
|
|
Grid : Message : 546.482875 s : r_o6.02101
|
|
Grid : Message : 546.489695 s : res12.0421
|
|
Grid : Message : 547.146183 s : norm diff 0
|
|
Grid : Message : 547.931015 s : norm diff even 0
|
|
Grid : Message : 548.405222 s : norm diff odd 0
|