GPU+MPI+OpenMP
#!/bin/bash
#SBATCH -J job_name # name of the job
#SBATCH -p standard-low # name of the partition: available options "standard,standard-low,gpu,gpu-low,hm"
#SBATCH -N 1 # no of Nodes
#SBATCH -n 4 # no of processes or tasks
#SBATCH --gres=gpu:1 # request gpu card: it should be either 1 or 2
#SBATCH --cpus-per-task=4 # no of threads per process or task
#SBATCH -t 01:00:00 # walltime in HH:MM:SS, max value 72:00:00
#list of modules you want to use, for example
#module load apps/lammps/12.12.2018/cuda9.2/gpu
#name of the executable
exe=name_executable
export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
#run the application
mpirun -bootstrap slurm -n $SLURM_NTASKS $exe #specify the application command-line options, if any, after $exe