Hello everyone!
I was trying to submit a similar job to run a large parametric simulation on 100 cores with the launcher module.
I haven’t succeeded in launching it correctly. Is there a max number of processes a user can launch? Am I understanding not the node architecture correctly?
This is one of the attempts. The LAUNCHER_JOB_FILE has 100 lines.
I was also considering starting a separate thread for the launcher module if anyone is also using it.
# !/bin/bash
# Simple SLURM script for submitting multiple serial
# jobs (e.g. parametric studies) using a script wrapper
# to launch the jobs.
#
# To use, build the launcher executable and your
# serial application(s) and place them in your WORKDIR
# directory. Then, edit the LAUNCHER_JOB_FILE to specify
# each executable per process.
#-------------------------------------------------------
#
# <------ Setup Parameters ------>
#
#SBATCH -J launcher
#SBATCH -N 7
#SBATCH -n 16
#SBATCH -p normal
#SBATCH -o Parametric.%j.out
#SBATCH -e Parametric.%j.err
#SBATCH -t 48:00:00
#------------------------------------------------------
module load launcher
export LAUNCHER_SCHED=interleaved
export LAUNCHER_WORKDIR=~/monte
export LAUNCHER_JOB_FILE=script/montecmd1
$LAUNCHER_DIR/paramrun