首先,程序编写与mpi单独要有区别,MPI_Init()要改为MPI_Init_thread(),还需要判断一下环境是否满足需求。
其次,程序不能使用默认openmp 的线程数,因为,torque不能用qsub脚本设置计算节点的环境变量。而openmp默认线程数是由OMP_NUM_THREADS环境变量设置的。为了更好的适用性和可移植,把线程数用参数传入,使用omp_set_num_threads()动态设置。
测试代码:
#include <stdio.h>
#include <omp.h>
#include <mpi.h>
#include <stdlib.h>
int rank, size;
int main (int argc, char* argv[])
{
int provided;
MPI_Init_thread (&argc, &argv, MPI_THREAD_FUNNELED, &provided);
if (MPI_THREAD_FUNNELED != provided)
{
printf ("%d != required %d", MPI_THREAD_FUNNELED, provided);
return 0;
}
MPI_Comm_rank (MPI_COMM_WORLD, &rank);
MPI_Comm_size (MPI_COMM_WORLD, &size);
char name[MPI_MAX_PROCESSOR_NAME];
int length;
MPI_Get_processor_name (name, &length);
int omp_num_threads = 1;
if (argc > 1)
{
omp_num_threads = atoi (argv[1]);
}
printf ("%s \n", name);
omp_set_num_threads (omp_num_threads);
#pragma omp parallel
{
printf ("%d omp thread from %d mpi process\n", omp_get_thread_num(), rank);
}
MPI_Finalize();
return 0;
}
提交脚本:
#!/bin/sh -f
#PBS -N hybrid
#PBS -l nodes=2:ppn=2
#PBS -l walltime=00:05:00
#PBS -l mem=1024mb
#PBS -o moe.txt
#PBS -e mee.txt
#PBS -q default
cd $PBS_O_WORKDIR
MVA='/usr/mpi/intel/mvapich-1.2.0/bin/mpirun '
eval $MVA -n 2 ./hybrid 2
基本框架就是这个样子滴,在本机上,最简单的还是设置OMP_NUM_THREADS环境变量。