From a8eda8f6da2c33fb06ef95db503fdd7780653ffc Mon Sep 17 00:00:00 2001 From: Peter Boyle Date: Tue, 5 Oct 2021 21:22:10 -0400 Subject: [PATCH] Summit scripts --- systems/Summit/dwf16.lsf | 14 +++++++------- systems/Summit/dwf4.lsf | 10 +++++----- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/systems/Summit/dwf16.lsf b/systems/Summit/dwf16.lsf index 16f4b82d..ef8c21a5 100644 --- a/systems/Summit/dwf16.lsf +++ b/systems/Summit/dwf16.lsf @@ -1,7 +1,7 @@ #!/bin/bash #BSUB -P LGT104 #BSUB -W 2:00 -#BSUB -nnodes 4 +#BSUB -nnodes 16 #BSUB -J DWF export OMP_NUM_THREADS=6 @@ -9,14 +9,14 @@ export PAMI_IBV_ADAPTER_AFFINITY=1 export PAMI_ENABLE_STRIPING=1 export OPT="--comms-concurrent --comms-overlap " -APP="./benchmarks/Benchmark_comms_host_device --mpi 2.2.2.3 " -jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP +APP="./benchmarks/Benchmark_comms_host_device --mpi 4.4.4.3 " +jsrun --nrs 16 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP > comms.16node.log -APP="./benchmarks/Benchmark_dwf_fp32 --grid 48.48.48.72 --mpi 2.2.2.3 --shm 1024 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " -jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP +APP="./benchmarks/Benchmark_dwf_fp32 --grid 96.96.96.72 --mpi 4.4.4.3 --shm 2048 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " +jsrun --nrs 16 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP > dwf.16node.24.log -APP="./benchmarks/Benchmark_dwf_fp32 --grid 64.64.64.96 --mpi 2.2.2.3 --shm 1024 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " -jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP +APP="./benchmarks/Benchmark_dwf_fp32 --grid 128.128.128.96 --mpi 4.4.4.3 --shm 2048 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " +jsrun --nrs 16 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP > dwf.16node.32.log diff --git a/systems/Summit/dwf4.lsf b/systems/Summit/dwf4.lsf index fcd80bcb..7d940338 100644 --- a/systems/Summit/dwf4.lsf +++ b/systems/Summit/dwf4.lsf @@ -10,13 +10,13 @@ export PAMI_ENABLE_STRIPING=1 export OPT="--comms-concurrent --comms-overlap " #export GRID_ALLOC_NCACHE_LARGE=1 export APP="./benchmarks/Benchmark_comms_host_device --mpi 2.2.2.3 " -jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP +jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP > comms.4node -APP="./benchmarks/Benchmark_dwf_fp32 --grid 48.48.48.72 --mpi 2.2.2.3 --shm 1024 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " -jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP +APP="./benchmarks/Benchmark_dwf_fp32 --grid 48.48.48.72 --mpi 2.2.2.3 --shm 2048 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " +jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP > dwf.24.4node -APP="./benchmarks/Benchmark_dwf_fp32 --grid 64.64.64.96 --mpi 2.2.2.3 --shm 1024 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " -jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP +APP="./benchmarks/Benchmark_dwf_fp32 --grid 64.64.64.96 --mpi 2.2.2.3 --shm 2048 --shm-force-mpi 1 --device-mem 8000 --shm-force-mpi 1 $OPT " +jsrun --nrs 4 -a6 -g6 -c42 -dpacked -b packed:7 --latency_priority gpu-cpu --smpiargs=-gpu $APP > dwf.32.4node