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

double PI25DT = 3.141592653589793238462643;
long n = 10000;

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

int main(int argc, char *argv[])
{
    int myid, np, i;    
    double mypi, pi, h, sum, x;
    double startwtime, endwtime;
    int  namelen;
    char processor_name[MPI_MAX_PROCESSOR_NAME];

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

    // printf("Process %d on %s\n", myid, processor_name);

    if (myid == 0) startwtime = MPI_Wtime(); 
        
	h = 1.0/n;
    sum = 0.0;
    for (i=myid; i<n; i+=np)
    {
        x = h*(i+0.5);
        sum += f(x);
    }
    mypi = h*sum;
    printf("Process %d: mypi=%.16f\n", myid, mypi);
	MPI_Barrier(MPI_COMM_WORLD);

    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;
}