CPI 的 loop 只會跑一次

#include "mpi.h"
#include <stdio.h>
#include <math.h>

double f( double );
double f( double a )
{
    return (4.0 / (1.0 + a*a));
}

int main( int argc, char *argv[])
{
    int done = 0, n, myid, numprocs, i, count=0;
    double PI25DT = 3.141592653589793238462643;
    double mypi, pi, h, sum, x;
    double startwtime = 0.0, endwtime;
    int  namelen;
    char processor_name[MPI_MAX_PROCESSOR_NAME];

    MPI_Init(&argc,&argv);
    MPI_Comm_size(MPI_COMM_WORLD,&numprocs);
    MPI_Comm_rank(MPI_COMM_WORLD,&myid);
    MPI_Get_processor_name(processor_name,&namelen);

    fprintf(stderr,"Process %d on %s\n",
	    myid, processor_name);

    n = 0;
    while (!done)
    {

/* 註 1: 我在這邊開始計算 loop 執行的次數 */
        count++;

        if (myid == 0)
        {
/*
            printf("Enter the number of intervals: (0 quits) ");
            scanf("%d",&n);
*/
	    if (n==0) n=100; else n=0;

	    startwtime = MPI_Wtime();
        }
        MPI_Bcast(&n, 1, MPI_INT, 0, MPI_COMM_WORLD);
        if (n == 0)
            done = 1;
        else
        {
            h   = 1.0 / (double) n;
            sum = 0.0;
            for (i = myid + 1; i <= n; i += numprocs)
            {
                x = h * ((double)i - 0.5);
                sum += f(x);
            }
            mypi = h * sum;

            MPI_Reduce(&mypi, &pi, 1, MPI_DOUBLE, MPI_SUM, 0, MPI_COMM_WORLD);

/* 註 2: 在這邊我把每個 node 所執行的 loop 次數印出 */
            if (myid == 0)
	    {
                printf("pi is approximately %.16f, Error is %.16f\n",
                       pi, fabs(pi - PI25DT));
		endwtime = MPI_Wtime();
		printf("wall clock time = %f\n",
		       endwtime-startwtime);	       
		printf("Node 0 loop runs  %d  times\n", count);
	    } else
	    {
	        printf("Node not 0 loop runs  %d  times\n", count);
	    }

        }
    }
    MPI_Finalize();
    return 0;
}

結果

就算去掉 while loop 也能執行。

MPICH Performance Report

Machine Specification

Node	8 nodes (1 server , 7 client provide disks)
CPU	Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
Memory	2GB DDR2 667 (each node)

CPI.c

Description

這是一個 mpich 內附用來算 pi 的程式。

Performance

以下為使用 1～10 顆的 CPU 測試 100 次的結果

PI	3.14159265358979323846
Our result	3.14159265358979267191
error	0.00000000000000056655

cpus	平均數
1	0.3792575
2	0.1898436
3	0.1280467
4	0.1004294
5	0.0812890
6	0.0696091
7	0.0672654
8	0.0662498
9	0.0625782
10	0.0587502