= CPI 的 loop 只會跑一次 =
{{{
#include "mpi.h"
#include <stdio.h>
#include <math.h>
#include <stdlib.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=0, 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)
    {
        count++;
        printf("Node %d : loop runs  %d  times\n", myid, 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();
        }
	printf("Node %d :  n = %d before MPI_Bcast\n", myid, n);
        MPI_Bcast(&n, 1, MPI_INT, 0, MPI_COMM_WORLD);
	printf("Node %d :  n = %d before MPI_Bcast\n", myid, n);
        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);

            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);	       
	    }
        }
    }
    MPI_Finalize();

    return 0;
}
}}}
== 結果 ==
去掉 while loop 也能執行，是因為 while loop 的目的為展現出，每個 Node 在第二次進入 while loop 時，Node 0 會將 n = 0 藉由 MPI_Bcast 廣播出去。由下圖可發現，每個 Node 只會執行二次，因為在 MPI_Bcast 中，每個 Node 皆會被 lock 住，直到 Node 0 將 n = 0 送到其它的 Node ，每個 Node 才會接著往下做，不過 lock 的機制，似乎與「群」有關，有些 function 如 sprintf，本身就是一個群，所以可以看見前面所有的 Node 會全部將結果顯示在螢幕上才繼續做下一「群」的程式，而我們也可以發現，在下一「群」的程式中，也是將這「群」的程式執行完後才將結果顯示出。 
[[Image(cpi_02.png)]]


= 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
}}}

[[Image(cpi_01.png)]]