slurm.tmpl

#!/bin/bash
## Job Resource Interface Definition
##
## ntasks [integer(1)]:       Number of required tasks,
##                            Set larger than 1 if you want to further parallelize
##                            with MPI within your job.
## ncpus [integer(1)]:        Number of required cpus per task,
##                            Set larger than 1 if you want to further parallelize
##                            with multicore/parallel within each task.
## walltime [integer(1)]:     Walltime for this job, in seconds.
##                            Must be at least 60 seconds for Slurm to work properly.
## memory   [integer(1)]:     Memory in megabytes for each cpu.
##                            Must be at least 100 (when I tried lower values my
##                            jobs did not start at all).
##
## Default resources can be set in your .batchtools.conf.R by defining the variable
## 'default.resources' as a named list.

<%
# relative paths are not handled well by Slurm
log.file = fs::path_expand(log.file)
-%>

#SBATCH --job-name=<%= job.name %>
#SBATCH --output=<%= log.file %>
#SBATCH --error=<%= log.file %>
#SBATCH --time=<%= ceiling(resources$walltime / 60) %>
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=<%= resources$ncpus %>
#SBATCH --mem-per-cpu=<%= resources$memory %>
#SBATCH --account=eap-larsko
#SBATCH --partition=<%= resources$partition %>
#SBATCH -A mallet
<% if (!is.null(resources$gres)) sprintf("#SBATCH --gres=%s", resources$gres) else "" %>

<%= if (array.jobs) sprintf("#SBATCH --array=1-%i", nrow(jobs)) else "" %>

## Initialize work environment like
## source /etc/profile
## module add ...
# source /home/mbecke16/mlr-benchmark/modules_medbo

## Export value of DEBUGME environemnt var to slave
export DEBUGME=<%= Sys.getenv("DEBUGME") %>

<%= sprintf("export OMP_NUM_THREADS=%i", resources$omp.threads) -%>
<%= sprintf("export OPENBLAS_NUM_THREADS=%i", resources$blas.threads) -%>
<%= sprintf("export MKL_NUM_THREADS=%i", resources$blas.threads) -%>

module load miniconda3/24.3.0
nvidia-smi
conda activate mlr3torch


## Run R:
## we merge R output with stdout from SLURM, which gets then logged via --output option
Rscript -e 'batchtools::doJobCollection("<%= uri %>")'