portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2024-11-09 23:45:36 +00:00
Code Releases Activity

Summit set up

Browse Source
This commit is contained in:
Peter Boyle 2021-10-05 14:56:17 -04:00
parent 8ed0b57b09
commit 2f4e85e5d6
4 changed files with 72 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
systems/Summit/config-command Normal file
View File

@ -0,0 +1,14 @@
../../configure --enable-comms=mpi \
--enable-simd=GPU \
--enable-gen-simd-width=32 \
--enable-unified=no \
--enable-shm=nvlink \
--disable-gparity \
--enable-setdevice \
--disable-fermion-reps \
--enable-accelerator=cuda \
--prefix /ccs/home/paboyle/prefix \
CXX=nvcc \
LDFLAGS=-L/ccs/home/paboyle/prefix/lib/ \
CXXFLAGS="-ccbin mpicxx -gencode arch=compute_70,code=sm_70 -I/ccs/home/paboyle/prefix/include/ -std=c++14"

25
systems/Summit/dwf16.lsf Normal file
View File

@ -0,0 +1,25 @@
#!/bin/bash
#BSUB -P LGT104
#BSUB -W 2:00
#BSUB -nnodes 4
#BSUB -J DWF
export OMP_NUM_THREADS=6
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_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 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

25
systems/Summit/dwf4.lsf Normal file
View File

@ -0,0 +1,25 @@
#!/bin/bash
#BSUB -P LGT104
#BSUB -W 2:00
#BSUB -nnodes 4
#BSUB -J DWF
export OMP_NUM_THREADS=6
export PAMI_IBV_ADAPTER_AFFINITY=1
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
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 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

8
systems/Summit/sourceme-cuda10.sh Normal file
View File

@ -0,0 +1,8 @@
export UCX_GDR_COPY_RCACHE=no
export UCX_MEMTYPE_CACHE=n
export UCX_RNDV_SCHEME=put_zcopy
module load gcc/7.5.0
module load cuda/10.2.89
#cuda/11.4.0
export LD_LIBRARY_PATH=/ccs/home/paboyle/prefix/lib/:$LD_LIBRARY_PATH