StarPU MORSE Nightly Tests

• dgemm, sgemm and spotrf miriel benchmarks are run on OPA miriel nodes.
• other spotrf benchmarks are run on sirocco nodes from 2017, december 15th (sequential benchmarks used to be run on mirage nodes).

Execution on queue routage with 4 node(s) (-C "haswell&sirocco") of the following script:

printenv | grep SLURM 
printenv | grep STARPU_ 
module list 
ulimit -c 0 
export STARPU_WORKER_STATS=1 
export STARPU_CALIBRATE=2 
export STARPU_LIMIT_CPU_MEM=120000 
export STARPU_LIMIT_MIN_SUBMITTED_TASKS=15000 
export STARPU_LIMIT_MAX_SUBMITTED_TASKS=16000 
export p=$(perl -e 'print int(sqrt('$SLURM_NNODES')), "n"') 
export nbgpus=4 
procs=$(echo $SLURM_JOB_CPUS_PER_NODE | awk -F'(' '{print $1}') 
export nbthreads=$(($procs - 2 -$nbgpus)) 
export niter=${NITER:-10} 
mpiexec -np $SLURM_NNODES --map-by node hostname 
mpiexec --mca btl self,openib -np $SLURM_NNODES --map-by node -- $PWD/testing/chameleon_stesting --op \ 
   potrf --check --niter $niter --ib 96 --nb 1440 --n 144000:144000:14400 --P $p --threads $nbthreads --gpus \ 
   $nbgpus 

See also the test archives: 2020 2021 2022 2023 .

Execution on queue routage with 4 node(s) (-C "haswell&sirocco") of the following script:

printenv | grep SLURM 
printenv | grep STARPU_ 
module list 
ulimit -c 0 
export STARPU_WORKER_STATS=1 
export STARPU_CALIBRATE=2 
export STARPU_LIMIT_CPU_MEM=120000 
export STARPU_LIMIT_MIN_SUBMITTED_TASKS=15000 
export STARPU_LIMIT_MAX_SUBMITTED_TASKS=16000 
export p=$(perl -e 'print int(sqrt('$SLURM_NNODES')), "n"') 
export nbgpus=4 
procs=$(echo $SLURM_JOB_CPUS_PER_NODE | awk -F'(' '{print $1}') 
export nbthreads=$(($procs - 2 -$nbgpus)) 
export niter=${NITER:-30} 
type mpiexec 
mpiexec -DPATH=${PATH} -DLD_LIBRARY_PATH=${LD_LIBRARY_PATH} -np $SLURM_NNODES hostname 
mpiexec -DPATH=${PATH} -DLD_LIBRARY_PATH=${LD_LIBRARY_PATH} -np $SLURM_NNODES $PWD/testing/chameleon_stesting \ 
   --op potrf --check --niter $niter --ib 96 --nb 1440 --n 144000:144000:14400 --P $p --threads $nbthreads \ 
   --gpus $nbgpus 

See also the test archives: 2019 2020 2021 2022 2023 .

Execution on queue routage with 4 node(s) (-C "haswell&sirocco") of the following script:

printenv | grep SLURM 
printenv | grep STARPU_ 
module list 
ulimit -c 0 
export STARPU_WORKER_STATS=1 
export STARPU_CALIBRATE=2 
export STARPU_LIMIT_CPU_MEM=120000 
export STARPU_LIMIT_MIN_SUBMITTED_TASKS=15000 
export STARPU_LIMIT_MAX_SUBMITTED_TASKS=16000 
export p=$(perl -e 'print int(sqrt('$SLURM_NNODES')), "n"') 
export nbgpus=4 
procs=$(echo $SLURM_JOB_CPUS_PER_NODE | awk -F'(' '{print $1}') 
export nbthreads=$(($procs - 2 -$nbgpus)) 
export niter=${NITER:-30} 
type mpiexec 
mpiexec -DPATH=${PATH} -DLD_LIBRARY_PATH=${LD_LIBRARY_PATH} -np $SLURM_NNODES hostname 
mpiexec -DPATH=${PATH} -DLD_LIBRARY_PATH=${LD_LIBRARY_PATH} -np $SLURM_NNODES $PWD/testing/chameleon_stesting \ 
   --op potrf --check --niter $niter --ib 96 --nb 1440 --n 144000:144000:14400 --P $p --threads $nbthreads \ 
   --gpus $nbgpus 

See also the test archives: 2019 2020 2021 2022 2023 .

Execution on queue routage with 1 node(s) (-C "haswell&sirocco") of the following script:

printenv | grep SLURM 
printenv | grep STARPU_ 
module list 
ulimit -c 0 
export STARPU_HOME="$prefix_dir/../morse/master/simucore/perfmodels/" 
export STARPU_HOSTNAME=sirocco 
export STARPU_CALIBRATE=0 
export STARPU_WORKER_STATS=1 
export STARPU_LIMIT_CPU_MEM=120000 
export STARPU_LIMIT_MIN_SUBMITTED_TASKS=15000 
export STARPU_LIMIT_MAX_SUBMITTED_TASKS=16000 
export STARPU_MALLOC_SIMULATION_FOLD=2 
SLURM_JOB_NUM_NODES=4 
SLURM_CPUS_ON_NODE=24 
p=$(perl -e 'print int(sqrt('$SLURM_JOB_NUM_NODES')), "n"') 
nbgpus=4 
procs=$(echo $SLURM_JOB_CPUS_PER_NODE | awk -F'(' '{print $1}') 
export nbthreads=$(($procs - 1 -$nbgpus)) 
time $rootdir/starpu.inst/bin/starpu_smpirun -np $SLURM_JOB_NUM_NODES -platform $HOME/.starpu/cluster.xml \ 
   -hostfile $HOME/.starpu/hostfile --cfg=surf/precision:0.000010 --cfg=maxmin/precision:0.000010 --cfg=network/model:IB \ 
   --cfg=smpi/test:0.000010 ./testing/chameleon_stesting --op potrf --ib 96 --nb 1440 --n 144000:144000:14400 \ 
   --P $p --gpus $nbgpus 

See also the test archives: 2020 2021 2022 2023 2024 .

• results_master_HEAD_spotrf_mpi.dat
• results_master_HEAD_spotrf_mpi_nmad.dat
• results_master_HEAD_spotrf_mpi_mad_mpi.dat
• results_master_HEAD_spotrf_mpi_sim.dat