...
| Code Block |
|---|
# a very big sleep job that needs 16 x CPUs, 2 x GPGPUs, 64GB memory, 10G disk space qsub -b y -N generic_gpgpu -pe smp 16 -l ngpus=2,mem=65G,jobfs=10G sleep 1m # a smaller sleep job that requires the specific A2 GPGPU... qsub -b y -N t1000_gpgpu -pe smp 8 -l ngpus=2,gpgpu_model=A2,mem=16G,jobfs=10G sleep 1m # a big job runs on multiple H100 nodes inside the same physical rack/cabinet F (rack awareness) qsub -b y -N h100_gpgpu -pe mpi 256 -l ngpus=2,gpgpu_model=H100,rack=f,mem=128G,jobfs=100G sleep 1m |
Submission Script
...
| Code Block |
|---|
#!/bin/bash
#
# It prints the actual path of the job scratch directory.
#$ -pe smp 8
#$ -j y
#$ -e logs/$JOB_ID_$JOB_NAME.out
#$ -o logs/$JOB_ID_$JOB_NAME.out
#$ -cwd
#$ -N dd_smp
#$ -l mem=1G,jobfs=110G,tmpfree=150G,walltime=00:30:00
#
echo "$HOST $tmp_requested $TMPDIR"
# about 107GB
dd if=/dev/zero of=$TMPDIR/dd.test bs=512M count=200 |