MPI parallel Programming - c

Question

I have three user-defined functions in a Monte Carlo simulator program. In main() they are being called using the appropriate parameters.
It is a serial program.
How do I convert it into the Parallel program?
The steps I have done so far for the serial program to make it as an MPI Parallel Program
are:
#include <conio.h>
#include <stdio.h>
#include "mpi.h"
//Global Varibles Declared
#define a=4;
#define b=2;
#define c=4;
#define d=6;
function1(Parameter4, Parameter))
{
// body of function
}
function2( parameter 1, parameter2)
{
//body of function
}
int main(int argc, char *argv[])
{
// Local Variables defined
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
function1(a, b);
function2(c, d);
MPI_Finalize ();
}
Now my questions are
Where do I specify
Number of processor(like running it with 2, 4, 6 , 8 processors)
Send and Recv Methods
How do I see the graphs of output using different number of processor.
Could any try to help me please as I am new to this language and don't know lot about it.

Answer 1

MPI is a communications protocol. We can't help you without know what platform/library you are working with. If you know what library you are working with, odds are good that there is a sample on the web somewhere showing how to implement Monte Carlo simulations with it.

Answer 2

First of all, your sample code is not valid C code. The #define lines should look like:
#define a 4
The number of processors is typically specified when running the program, which is usually done via
mpiexec -np PROCS MPIPROG
or the like, where PROCS is the number of MPI tasks to start and MPIPROG is the name of the compiled MPI executable. There is also a possibility to spawn MPI tasks from within MPI, but this doesn't work everywhere, so I would not recommend it. The advantage of specifying the number of tasks at runtime is that you can choose how many tasks to use depending on the platform you are working on.
Send and Recv can be used anywhere in the code, after MPI_Init has been called, and before MPI_Finalize has been called. As an example, to send an integer from task 0 to task 1, you would use something like
int number;
if (rank == 0) {
/* compute the number on proc 0 */
number = some_complex_function();
/* send the number to proc 1 */
MPI_Send(&number, 1, MPI_INT, 1, 42, MPI_COMM_WORLD);
} else if (rank == 1) {
/* receive the number from proc 0 */
MPI_Recv(&number, 1, MPI_INT, 0, 42, MPI_COMM_WORLD, 0);
}
// now both procs can do something with the number
Note that in this case, Task 1 will have to wait until the number is received from task 0, so in a real application you might want to give task 1 some work to do while task 0 computes "some_complex_function".