A hybrid job uses both OpenMP and MPI for parallelization. This requires the number of tasks and CPUs per task to be set up correctly. Here is an example of such a job. We will use Intel MPI in this example, but this also works using OpenMPI.
Code
#include <mpi.h>
#include <stdio.h>
int main(int argc, char** argv) {
// Initialize the MPI environment
MPI_Init(NULL, NULL);
// Get the number of processes
int world_size;
MPI_Comm_size(MPI_COMM_WORLD, &world_size);
// Get the rank of the process
int world_rank;
MPI_Comm_rank(MPI_COMM_WORLD, &world_rank);
// Get the name of the processor
char processor_name[MPI_MAX_PROCESSOR_NAME];
int name_len;
MPI_Get_processor_name(processor_name, &name_len);
int nthreads, tid;
/* Fork a team of threads giving them their own copies of variables */
#pragma omp parallel private(nthreads, tid)
{
/* Obtain thread number */
tid = omp_get_thread_num();
printf("Hello World from thread = %d, processor %s, rank %d out of %d processors\n", tid, processor_name, world_rank, world_size);
/* Only master thread does this */
if (tid == 0)
{
nthreads = omp_get_num_threads();
printf("Number of threads = %d\n", nthreads);
}
} /* All threads join master thread and disband */
// Finalize the MPI environment.
MPI_Finalize();
}
Compilation
This can be compiles with both the Intel or the GNU compiler.
module load intel
module load impi
mpiicc -qopenmp -Wl,-rpath,$LD_RUN_PATH -o hybrid_hello_world.bin hybrid_hello_world.c
module load gcc
module load impi
mpigcc -fopenmp -Wl,-rpath,$LD_RUN_PATH -o hybrid_hello_world.bin hybrid_hello_world.c
Batch Job
#!/bin/bash
#SBATCH --time=00:10:00
#SBATCH --nodes=2
#SBATCH --tasks-per-node=4
#SBATCH --cpus-per-task=10
#SBATCH --partition=standard96:test
module load impi
export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
srun ./hybrid_hello_world.bin
Related articles
-
Seite:
-
Seite:
-
Seite:
-
Seite:
-
Seite: