...
| Code Block |
|---|
#!/bin/bash #SBATCH -N 1 #SBATCH -t 2:00:00 #SBATCH --ntasks-per-node=12 #SBATCH --cpus-per-task=32 #SBTACH --gpus-per-task=1 #SBATCH --gres=gpu:a100:2 #SBATCH -p gpu #alternatively for testing in small/short jobs, see https://upb-pc2.atlassian.net/wiki/spaces/PC2DOK/pages/1902952/Running+Compute+Jobs#Using-GPUs-for-Development-and-Testing-Purposes ##SBATCH -p dgx ##SBATCH -q devel export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK export OMP_PLACES=cores export OMP_PROC_BIND=true export TF_INTER_OP_PARALLELISM_THREADS=2 export TF_INTRA_OP_PARALLELISM_THREADS=`echo "$OMP_NUM_THREADS-$TF_INTER_OP_PARALLELISM_THREADS" | bc` module reset module load toolchain/foss/2022a module load lang/Python/3.10.4-GCCcore-11.3.0 module load system/CUDA/12.6.0 source /pc2/groups/[project name]/venv_deepmd_horovod/bin/activate srun horovodrun -np 2 dp train input.json |