[mpich-discuss] Poor MPICH Performance on Windows Vista vs. XP

Rahul Mukerjee r.mukerjee at gmail.com
Thu Oct 29 12:17:01 CDT 2009


Hi,

I am using MPICH2 version 1.0.8p1. I am using a simple C code to
measure the time taken for 100 MPI_BARRIER calls in Windows Vista vs.
XP. Here is the code:

#include "mpi.h"
#include <stdio.h>
#include <stdlib.h>
int main(int argc, char **argv)
{
    int cpuid, ncpu;
    int i, count;
    double t1, t2, sum;
    count = 100;
    sum = 0.0;
    MPI_Init(&argc, &argv);
    MPI_Comm_size(MPI_COMM_WORLD, &ncpu);
    MPI_Comm_rank(MPI_COMM_WORLD, &cpuid);
    printf("NCPU:%d, CPUID:%d\n", ncpu, cpuid);
    fflush(stdout);
    printf("start barrier\n"); fflush(stdout);
    for (i=0; i<count; i++)
	{
		t1 = MPI_Wtime();
		MPI_Barrier(MPI_COMM_WORLD);
		t2 = MPI_Wtime();
		if (cpuid == 0) sum = sum + (t2 - t1);
	}
	printf("end barrier\n"); fflush(stdout);
	if (cpuid == 0) printf("Time = %lf\n", sum);
	MPI_Finalize();
    return 0;
}

The results are:

Windows XP:
3 hosts: Time = 0.034093 secs
4 hosts: Time = 0.041328 secs

Windows Vista:
3 hosts: Time = 0.347072 secs (Slow, but still bearable)
4 hosts: Time = 11.820926 secs (WTF???)

Someone had posted earlier about poor MPICH performance with HPC
Server 2008 / Vista. This is in continuation of that, in a way. Any
help would be greatly appreciated. Thank you.

Sincerely,

Rahul Mukerjee.


More information about the mpich-discuss mailing list