Update slurm.md

config/hpc/slurm.md

@@ -22,9 +22,32 @@ breadcrumbs:
     - Show job details: `scontrol show jobid -dd <jobid>`
 - Job handling:
     - Create a job (overview): Make a Slurm script, make it executable and submit it.
-    - Submit interactive/blocking job: `srun [--pty bash] <...>`
-    - Submit batch/non-blocking job: `sbatch <...>`
+    - Using GPUs: See example Slurm-file, using `--gres=gpu[:<type>]:<n>`.
+    - Submit batch/non-blocking job: `sbatch <slurm-file>`
+    - Start interactive/blocking job: `srun <job options> [--pty] <bash|app>`
     - Cancel specific job: `scancel <jobid>`
-    - Cancel multiple jobs: `scancel [-t <state>] [-u <user>]`
+    - Cancel set of jobs: `scancel [-t <state>] [-u <user>]`
+
+## Example Slurm-File
+
+```sh
+#!/bin/sh
+
+#SBATCH --partition=<partition>
+#SBATCH --time=03:00:00
+#SBATCH --nodes=2
+# #SBATCH --nodelist=compute-2-0-[17-18],compute-5-0-[20-21]
+#SBATCH --ntasks-per-node=2
+# #SBATCH --exclusive
+# #SBATCH --mem=64G
+#SBATCH --gres=gpu:V100:2
+#SBATCH --job-name="xxx"
+#SBATCH --output=log.txt
+## SBATCH --mail-user=user@example.net
+# #SBATCH --mail-type=ALL
+
+# Run some program on all processors using mpirun
+mpirun uname -a
+```
 
 {% include footer.md %}