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-c0r1n84 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n84 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n84 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n84 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n75 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n93 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n75 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n93 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n93 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n93 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n87 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n87 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n87 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n90 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n90 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n90 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n90 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n78 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n78 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n78 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n78 - 3 device=3 binding=--interleave=6,7
|
|
tu-c0r1n81 - 1 device=1 binding=--interleave=2,3
|
|
tu-c0r1n81 - 0 device=0 binding=--interleave=0,1
|
|
tu-c0r1n81 - 2 device=2 binding=--interleave=4,5
|
|
tu-c0r1n81 - 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: 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
|
|
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 3 device 0 bus id: 0000:C4:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
local rank 0 device 0 bus id: 0000:03:00.0
|
|
AcceleratorCudaInit: ================================================
|
|
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
|
|
SharedMemoryMpi: World communicator of size 32
|
|
SharedMemoryMpi: Node communicator of size 4
|
|
0SharedMemoryMpi: SharedMemoryMPI.cc acceleratorAllocDevice 2147483648bytes at 0x14ea40000000 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 : 1.295954 s : Grid Layout
|
|
Grid : Message : 1.295959 s : Global lattice size : 64 64 64 128
|
|
Grid : Message : 1.295967 s : OpenMP threads : 4
|
|
Grid : Message : 1.295971 s : MPI tasks : 2 2 2 4
|
|
Grid : Message : 1.333442 s : Making s innermost grids
|
|
Grid : Message : 1.416916 s : Initialising 4d RNG
|
|
Grid : Message : 1.509007 s : Intialising parallel RNG with unique string 'The 4D RNG'
|
|
Grid : Message : 1.509035 s : Seed SHA256: 49db4542db694e3b1a74bf2592a8c1b83bfebbe18401693c2609a4c3af1
|
|
Grid : Message : 2.308164 s : Initialising 5d RNG
|
|
Grid : Message : 3.743802 s : Intialising parallel RNG with unique string 'The 5D RNG'
|
|
Grid : Message : 3.743837 s : Seed SHA256: b6316f2fac44ce14111f93e0296389330b077bfd0a7b359f781c58589f8a
|
|
Grid : Message : 20.420436 s : Initialised RNGs
|
|
Grid : Message : 24.121170 s : Drawing gauge field
|
|
Grid : Message : 24.649839 s : Random gauge initialised
|
|
Grid : Message : 24.662558 s : Setting up Cshift based reference
|
|
Grid : Message : 54.205230 s : *****************************************************************
|
|
Grid : Message : 54.205252 s : * Kernel options --dslash-generic, --dslash-unroll, --dslash-asm
|
|
Grid : Message : 54.205253 s : *****************************************************************
|
|
Grid : Message : 54.205254 s : *****************************************************************
|
|
Grid : Message : 54.205255 s : * Benchmarking DomainWallFermionR::Dhop
|
|
Grid : Message : 54.205256 s : * Vectorising space-time by 8
|
|
Grid : Message : 54.205257 s : * VComplexF size is 64 B
|
|
Grid : Message : 54.205258 s : * SINGLE precision
|
|
Grid : Message : 54.205260 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 54.205261 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 54.205262 s : *****************************************************************
|
|
Grid : Message : 56.295984 s : Called warmup
|
|
Grid : Message : 383.373081 s : Called Dw 30000 times in 3.27077e+08 us
|
|
Grid : Message : 383.373145 s : mflop/s = 6.50003e+07
|
|
Grid : Message : 383.373147 s : mflop/s per rank = 2.03126e+06
|
|
Grid : Message : 383.373149 s : mflop/s per node = 8.12504e+06
|
|
Grid : Message : 383.373151 s : RF GiB/s (base 2) = 132079
|
|
Grid : Message : 383.373153 s : mem GiB/s (base 2) = 82549.5
|
|
Grid : Message : 383.376688 s : norm diff 1.07359e-13
|
|
Grid : Message : 383.429635 s : #### Dhop calls report
|
|
Grid : Message : 383.429643 s : WilsonFermion5D Number of DhopEO Calls : 60002
|
|
Grid : Message : 383.429647 s : WilsonFermion5D TotalTime /Calls : 5455.14 us
|
|
Grid : Message : 383.429649 s : WilsonFermion5D CommTime /Calls : 3893.73 us
|
|
Grid : Message : 383.429651 s : WilsonFermion5D FaceTime /Calls : 596.343 us
|
|
Grid : Message : 383.429653 s : WilsonFermion5D ComputeTime1/Calls : 5.03388 us
|
|
Grid : Message : 383.429655 s : WilsonFermion5D ComputeTime2/Calls : 979.741 us
|
|
Grid : Message : 383.429683 s : Average mflops/s per call : 6.20016e+10
|
|
Grid : Message : 383.429688 s : Average mflops/s per call per rank : 1.93755e+09
|
|
Grid : Message : 383.429691 s : Average mflops/s per call per node : 7.7502e+09
|
|
Grid : Message : 383.429695 s : Average mflops/s per call (full) : 6.61353e+07
|
|
Grid : Message : 383.429699 s : Average mflops/s per call per rank (full): 2.06673e+06
|
|
Grid : Message : 383.429702 s : Average mflops/s per call per node (full): 8.26691e+06
|
|
Grid : Message : 383.429706 s : WilsonFermion5D Stencil
|
|
Grid : Message : 383.429708 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 383.429710 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 383.429713 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 383.429715 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 383.429717 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 439.293531 s : Compare to naive wilson implementation Dag to verify correctness
|
|
Grid : Message : 439.293554 s : Called DwDag
|
|
Grid : Message : 439.293555 s : norm dag result 12.0421
|
|
Grid : Message : 439.339776 s : norm dag ref 12.0421
|
|
Grid : Message : 439.358145 s : norm dag diff 7.28475e-14
|
|
Grid : Message : 439.412433 s : Calling Deo and Doe and //assert Deo+Doe == Dunprec
|
|
Grid : Message : 439.798246 s : src_e0.499997
|
|
Grid : Message : 440.170182 s : src_o0.500003
|
|
Grid : Message : 440.278522 s : *********************************************************
|
|
Grid : Message : 440.278525 s : * Benchmarking DomainWallFermionF::DhopEO
|
|
Grid : Message : 440.278526 s : * Vectorising space-time by 8
|
|
Grid : Message : 440.278527 s : * SINGLE precision
|
|
Grid : Message : 440.278528 s : * Using Overlapped Comms/Compute
|
|
Grid : Message : 440.278529 s : * Using GENERIC Nc WilsonKernels
|
|
Grid : Message : 440.278530 s : *********************************************************
|
|
Grid : Message : 612.700639 s : Deo mflop/s = 6.16717e+07
|
|
Grid : Message : 612.700671 s : Deo mflop/s per rank 1.92724e+06
|
|
Grid : Message : 612.700673 s : Deo mflop/s per node 7.70896e+06
|
|
Grid : Message : 612.700676 s : #### Dhop calls report
|
|
Grid : Message : 612.700678 s : WilsonFermion5D Number of DhopEO Calls : 30001
|
|
Grid : Message : 612.700680 s : WilsonFermion5D TotalTime /Calls : 5747.06 us
|
|
Grid : Message : 612.700682 s : WilsonFermion5D CommTime /Calls : 4013.18 us
|
|
Grid : Message : 612.700684 s : WilsonFermion5D FaceTime /Calls : 811.504 us
|
|
Grid : Message : 612.700686 s : WilsonFermion5D ComputeTime1/Calls : 6.04023 us
|
|
Grid : Message : 612.700688 s : WilsonFermion5D ComputeTime2/Calls : 950.362 us
|
|
Grid : Message : 612.700708 s : Average mflops/s per call : 5.10171e+10
|
|
Grid : Message : 612.700712 s : Average mflops/s per call per rank : 1.59429e+09
|
|
Grid : Message : 612.700714 s : Average mflops/s per call per node : 6.37714e+09
|
|
Grid : Message : 612.700717 s : Average mflops/s per call (full) : 6.2776e+07
|
|
Grid : Message : 612.700720 s : Average mflops/s per call per rank (full): 1.96175e+06
|
|
Grid : Message : 612.700724 s : Average mflops/s per call per node (full): 7.847e+06
|
|
Grid : Message : 612.700727 s : WilsonFermion5D Stencil
|
|
Grid : Message : 612.700730 s : WilsonFermion5D StencilEven
|
|
Grid : Message : 612.700732 s : WilsonFermion5D StencilOdd
|
|
Grid : Message : 612.700733 s : WilsonFermion5D Stencil Reporti()
|
|
Grid : Message : 612.700734 s : WilsonFermion5D StencilEven Reporti()
|
|
Grid : Message : 612.700736 s : WilsonFermion5D StencilOdd Reporti()
|
|
Grid : Message : 612.777627 s : r_e6.02113
|
|
Grid : Message : 612.786837 s : r_o6.02101
|
|
Grid : Message : 612.794496 s : res12.0421
|
|
Grid : Message : 613.490443 s : norm diff 0
|
|
Grid : Message : 614.221091 s : norm diff even 0
|
|
Grid : Message : 614.615303 s : norm diff odd 0
|