#!/bin/bash
#SBATCH -t 02:00:00
#SBATCH -p gpu
#SBATCH -N 2
#SBATCH -n 4
#SBATCH --gpus-per-node=gtx1080:2
export OMP_NUM_THREADS=4

module load singularity
module load gcc/9.2.0
module load cuda10.1/toolkit/10.1.105
module load openmpi/gcc/64/4.0.3_cuda-10.1

mpirun --mca btl vader,self,tcp -mca mca_btl_openib 1 -mca orte_base_help_aggregate 0 singularity exec --nv Pytorch_DL_HPC.sif python -u DistributedLearning_MPI.py