Difference between revisions of "Parallel job submission"

< Submit a job

Home

Submit a GPU job >

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., 24, 36, or 128 processors.
• To compile an openMP code:

$ module load gcc/6.3.0
$ gcc -o hello_omp -fopenmp hello_omp.c

• To run an openMP code, first define number of processors(threads) in $OMP_NUM_THREADS

$ export OMP_NUM_THREADS=8
$ bsub -n 8 ./hello_omp

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.

• 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 gcc/6.3.0 openmpi/4.0.2
$ mpicc -o mpi_hello_world mpi_hello_world.c

• To run an MPI program, launch the program with "mpirun"

$ module load gcc/6.3.0 openmpi/4.0.2
$ bsub -n 240 mpirun ./mpi_hello_world

< Submit a job

Home

Submit a GPU job >