cpi.c

MPI的工具 MPI_tuning_ClusterTools Record_Custom_Performance_Counter

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

int application_class;
int counter_class;

double f( double );
double f( double a )
{
double result;

    {
        static int scl = VT_NOSCL;
        static int f_state = 0;
        if( scl == VT_NOSCL ) {
          VT_scldef( __FILE__, __LINE__, &scl );
          VT_funcdef( "f", application_class, &f_state );
        }
        VT_enter( f_state, scl );
    }
    result = 4.0 / (1.0 + a*a);
    {
        static int counter_handle = 0;
        const double boundaries[2];
        if (counter_handle == 0) {
          VT_countdef("f_result", counter_class, VT_COUNT_FLOAT|VT_COUNT_ABSVAL|
                      VT_COUNT_VALID_AFTER, VT_GROUP_PROCESS, boundaries, "#", &counter_handle);
        }
        VT_countval( 1, &counter_handle, &result );
    }
    {
        VT_leave( VT_NOSCL );
    }
    return (result);
}

int main( int argc, char *argv[])
{
    int done = 0, n, myid, numprocs, i;
    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);
    {
        VT_classdef( "Application" , &application_class );
        VT_classdef( "Custom_counter", &counter_class );
    }
    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)
    {
        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);

            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;
}