03-submit-param-sweep.slurm

#!/bin/bash
#SBATCH --ntasks 3
#SBATCH --output submit.out
#SBATCH --dependency singleton
#SBATCH --job-name example-03-parameter-sweep
# Kill job after 1 minute to show resuming feature.
#SBATCH --time 1:00

parallel_opts=$(~/parallel-slurm/parallel_opts.sh)
module load parallel

# Alias our model running program.
model="python model.py"

# Read the number of simulations to run.
n_sim=$( $model --sim )
n_remaining=$( $model --remaining )

# Check if all simulations are completed.
echo "Started SLURM job $SLURM_JOB_ID"
if [[ n_remaining -eq 0 ]]
then
    echo "Nothing to run; all $n_sim simulations complete."
    
    echo "Completed SLURM job $SLURM_JOB_ID in $(sacct -nXj $SLURM_JOB_ID -o elapsed)"
    exit 0
fi

# Run an interruption prone program.
seq $n_sim > param_index
echo "Running $n_remaining of total $n_sim simulations."
# It's okay to use
parallel $parallel_opts \
	 --joblog joblog \
	 --resume \
	 --retries 3 \
	 --line-buffer \
	 $model \
	 :::: param_index
echo "Completed SLURM job $SLURM_JOB_ID in $(sacct -nXj $SLURM_JOB_ID -o elapsed)"