Page Comparison

#!/bin/bash --login

#SBATCH --account=project-gpu
#SBATCH --partition=gpu
#SBATCH --nodes=1              #1 nodes in this example
#SBATCH --gpus-per-node=1gres=gpu:1           #1 GPUsGPU per node (1 "allocation packs-pack" in total for the job)
#SBATCH --time=00:05:00

#----
#Loading needed modules (adapt this for your own purposes):
module load PrgEnv-cray
module load rocm craype-accel-amd-gfx90a
module list

#----
#MPI & OpenMP settings
export OMP_NUM_THREADS=1 #This controls the real number of threads per task

#----
#Execution
srun -N 1 -n 1 -c 8 --gpus-per-node=gres=gpu:1 ./program

#!/bin/bash --login

#SBATCH --account=project-gpu
#SBATCH --partition=gpu
#SBATCH --nodes=1              #1 nodes in this example
#SBATCH --exclusive            #All resources of the node are exclusive to this job
#                              #8 GPUs per node (8 "allocation -packs" in total for the job)
#SBATCH --time=00:05:00

#----
#Loading needed modules (adapt this for your own purposes):
module load PrgEnv-cray
module load rocm craype-accel-amd-gfx90a
module list

#----
#MPI & OpenMP settings
export OMP_NUM_THREADS=1           #This controls the real CPU-cores per task for the executable

#----
#Execution
srun -N 1 -n 1 -c 64128 --gpus-per-node=gres=gpu:8 --gpus-per-task=8 ./program

#!/bin/bash --login

#SBATCH --account=project-gpu
#SBATCH --partition=gpu
#SBATCH --nodes=1              #1 nodes in this example
#SBATCH --exclusive            #All resources of the node are exclusive to this job
#                              #8 GPUs per node (8 "allocation packs" in total for the job)
#SBATCH --time=00:05:00

#----
#Loading needed modules (adapt this for your own purposes):
module load PrgEnv-cray
module load rocm craype-accel-amd-gfx90a
module list

#----
#MPI & OpenMP settings
export MPICH_GPU_SUPPORT_ENABLED=1 #This allows for GPU-aware MPI communication among GPUs
export OMP_NUM_THREADS=1           #This controls the real number of threads per task

#----
#Execution
srun -N 1 -n 8 -c 8 --gpus-per-node=gres=gpu:8 --gpus-per-task=1 --gpu-bind=closest ./program

The use of --gpu-bind=closest may not work for all codes. For those codes, "manual" binding may be the only reliable method if they relying OpenMP or OpenACC pragma's for moving data from/to host to/from GPU and attempting to use GPU-to-GPU enabled MPI communication.