Gkeyll Job Scripts

From UFRC
Revision as of 14:25, 3 June 2024 by Perera (talk | contribs) (Created page with "#!/bin/bash #SBATCH --time= # walltime, #SBATCH --ntasks= # number of mpi processes #SBATCH --cpus-per-task= # Number of OpenMP threads for each...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search
  1. !/bin/bash
  2. SBATCH --time= # walltime,
  3. SBATCH --ntasks= # number of mpi processes
  4. SBATCH --cpus-per-task= # Number of OpenMP threads for each MPI process/rank
  5. SBATCH --nodes= # Number of nodes
  6. SBATCH --ntasks-per-node= # How many tasks on each node
  7. SBATCH --ntasks-per-socket= # How many tasks on each CPU or socket
  8. SBATCH --mem-per-cpu=100mb # Memory per core
  1. load modules

module load openmpi/4.1.5 module load openblas/0.3.24 module load superlu_dist/6.0.1 module load metis/5.2.

  1. run the program

srun --mpi=pmix_v3 gkyl innput.lua >& output.log

  • Note: The user must decide the number of tasks and how they are distributed. This depends on

on the availability of resources and the extent of the parallelization of the software. Also user must specify the the account ($SBATCH --account) and the Quality of Service (QOS) (#SBATCH --qos) must be specified.