Difference between revisions of "Parallel job submission"

Revision as of 14:37, 12 May 2021

Shared memory job (OpenMP)

• Runs on a single compute node
• Can use up to 24 processors
• Number of processors must be defined in $OMP_NUM_THREADS

export OMP_NUM_THREADS=8
bsub -n 8 ./program

Distributed memory job (MPI)

• Runs on multiple compute nodes
• Can use tens or even hundreds of processors
• Program must be launched using mpirun

module load compiler
module load mpi_library
bsub -n 240 mpirun ./program

Example

$ export OMP_NUM_THREADS=8
$ bsub -n 8 ./hello_omp
Generic job.
Job <8147290> is submitted to queue <normal.4h>.

$ unset OMP_NUM_THREADS
$ bsub -n 240 mpirun ./hello_mpi
MPI job.
Your environment is not configured for MPI.
Please load the module(s) needed by your job before executing 'bsub'.
Request aborted by esub. Job not submitted.

$ module load intel open_mpi
$ bsub -n 240 mpirun ./hello_mpi
MPI job.
Job <8147303> is submitted to queue <normal.4h>.