Parallel job submission with SLURM

< Submit a job

Home

Submit a GPU job >

Shared memory job (OpenMP)

In shared-memory parallel computing, multiple processors (or "threads") perform tasks independently but share a common global memory. If a processor modified an array in the memory, all other processors can see this update as well A serial code can be parallelized by marking code sections, which should be run in parallel, with openMP directives. An openMP code can run on a single compute node and use up to maximum number of processors in that compute node, e.g., 128 or 192 processors. To compile an openMP code: $ module load stack/2024-06 $ gcc -o hello_omp -fopenmp hello_omp.c To run an openMP code, define number of processors(threads) in $OMP_NUM_THREADS and force the program to run on a single node (-c), where all of the cores share their memory: $ export OMP_NUM_THREADS=8 $ sbatch -c 8 --wrap="./hello_omp"

Distributed memory job (MPI)

In distributed-memory parallel computing, multiple processors (or "cores") perform tasks independently while each processor possesses its own private memory resource. If a processor modify an array in its memory, this processor has to communicate to other processors so that the others see this update. Cores should be requested with the sbatch option -n (--ntasks) Massage Passing Interface (MPI) library implements distributed memory parallel computing which can be programmed in C, C++ and Fortran An MPI program can run on a single compute node as well as on multiple compute nodes To compile an MPI code, use MPI wrappers, e.g., mpicc for C code, mpif90 for Fortran code $ module load stack/2024-06 gcc/12.2.0 openmpi/4.1.6 $ mpicc -o mpi_hello_world mpi_hello_world.c To run an MPI program, launch the program with "mpirun" $ module load stack/2024-06 gcc/12.2.0 openmpi/4.1.6 $ sbatch -n 240 --wrap="srun ./mpi_hello_world"

Examples

• C/C++

Further readings

• Parallel computing
• Four-day course in parallel programming with MPI/OpenMP at ETH

Helper

• SLURM Submission Line Advisor

< Submit a job

Home

Submit a GPU job >