Difference between revisions of "Programming/OpenMPI"
m |
m |
||
| Line 72: | Line 72: | ||
=== Batch Submission === | === Batch Submission === | ||
| − | <pre style="background-color: # | + | <pre style="background-color: #f5f5dc; color: black; font-family: monospace, sans-serif;"> |
| + | |||
#!/bin/bash | #!/bin/bash | ||
#SBATCH -J MPI-testXX | #SBATCH -J MPI-testXX | ||
#SBATCH -N 10 | #SBATCH -N 10 | ||
#SBATCH --ntasks-per-node 28 | #SBATCH --ntasks-per-node 28 | ||
| − | |||
#SBATCH -o %N.%j.%a.out | #SBATCH -o %N.%j.%a.out | ||
#SBATCH -e %N.%j.%a.err | #SBATCH -e %N.%j.%a.err | ||
| Line 86: | Line 86: | ||
module purge | module purge | ||
| − | module | + | module add gcc/4.9.3 |
| − | module | + | module add openmpi/gcc/1.10.2 |
export I_MPI_DEBUG=5 | export I_MPI_DEBUG=5 | ||
Revision as of 15:05, 7 February 2017
Contents
Programming Details
MPI defines not only point-to-point communication (e.g., send and receive), it also defines other communication patterns, such as collective communication. Collective operations are where multiple processes are involved in a single communication action. Reliable broadcast, for example, is where one process has a message at the beginning of the operation, and at the end of the operation, all processes in a group have the message.
Message-passing performance and resource utilization are the king and queen of high-performance computing. Open MPI was specifically designed in such a way that it could operate at the very bleeding edge of high performance: incredibly low latencies for sending short messages, extremely high short message injection rates on supported networks, fast ramp-ups to maximum bandwidth for large messages, etc.
The Open MPI code has 3 major code modules:
- OMPI - MPI code
- ORTE - the Open Run-Time Environment
- OPAL - the Open Portable Access Layer
Program Example
#include <mpi.h>
#include <stdio.h>
int main(int argc, char** argv)
{
int rank;
int buf;
MPI_Status status;
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
if(rank == 0)
{
buf = 777;
MPI_Bcast(&buf, 1, MPI_INT, 0, MPI_COMM_WORLD);
}
else
{
MPI_Recv(&buf, 1, MPI_INT, 0, 0, MPI_COMM_WORLD, &status);
printf("rank %d receiving received %d\n", rank, buf);
}
MPI_Finalize();
return 0;
}
Modules Available
The following modules are available for OpenMPI:
- module load gcc/4.9.3 (GNU compiler)
- module load intel/compiler/64/2016.2.181 (Intel compiler)
- module load openmpi/gcc/1.10.2
- module load openmpi/gcc/1.10.5
- module load openmpi/intel/1.10.2
- module load openmpi/intel/1.8.8
- module load openmpi/intel/2.0.1
Compilation
[username@login01 ~]$ module load gcc/4.9.3 [username@login01 ~]$ gcc -o testMPI testMPI.c
Usage Examples
Batch Submission
#!/bin/bash #SBATCH -J MPI-testXX #SBATCH -N 10 #SBATCH --ntasks-per-node 28 #SBATCH -o %N.%j.%a.out #SBATCH -e %N.%j.%a.err #SBATCH -p compute #SBATCH --exclusive echo $SLURM_JOB_NODELIST module purge module add gcc/4.9.3 module add openmpi/gcc/1.10.2 export I_MPI_DEBUG=5 export I_MPI_FABRICS=shm:tmi export I_MPI_FALLBACK=no mpirun -mca pml cm -mca mtl psm2 /home/user/CODE_SAMPLES/OPENMPI/scatteravg 100
[username@login01 ~]$ sbatch MPI-demo.job Submitted batch job 289523