Using ExaGRyPE on clusters is straightforward in principle, the correct configure command will allow you run the code in parallel automatically.

However, the module you need to load is usually different in name as the convention is not unified. We kindly encourage users to contribute to this page by sharing their setups if they have successfully run ExaGRyPE on their clusters.

Compiling on COSMA

the suggest loading module and setup (before compiling the Peano kernel) when you use COSMA or DINE are

module purge
module load cosma
module load intel_comp/2025.2.1 compiler-rt tbb umf compiler mpi
module load intel_mpi
export FLAVOUR_NOCONFLICT=1
module load gnu_comp/13.1.0
export I_MPI_CC=icx
export I_MPI_CXX=icpx

Compiling on Hamilton

the suggest loading module when you use Hamilton are

module purge
module load intel/2024.2
module load compiler-rt tbb compiler mpi 
module load python/3.10.8
export I_MPI_CXX=icpx

SLURM script

The following script gives an exmaple for submitting ExaGRyPE job to the cluster via SLURM system.

#!/bin/bash -l
 
#SBATCH -o %A.out
#SBATCH -e %A.err
#SBATCH -p cosma7
#SBATCH -A prj00
#SBATCH -t 24:00:00
#SBATCH --ntasks-per-node=1
#SBATCH --nodes=2
#SBATCH -J ExaGRyPE
#SBATCH --exclusive
#SBATCH --no-requeue
 
echo "My SLURM_ARRAY_TASK_ID: " $SLURM_ARRAY_TASK_ID
 
module purge
module load intel_comp/2024.2.0
module load compiler-rt tbb compiler mpi 
export FLAVOUR_NOCONFLICT=1
module load python
 
export UCX_TLS=ud,sm,self
 
export OMP_NUM_THREADS=28
 
mpirun ./peano4_sbh --timeout 18000