How to send and receive variables in mpi C++

Question

0.00/5 (No votes)

See more:

I am a beginner in MPI programing and I am trying to do a matrix-vector multiplication (Ax=b).
I divided A matrix into two matrix A1 and A2.
I need to calculate Ax=b such a way that the process number 1 does the A1 * x multiplication and gives C1 and process number 2 does the A2 * x multiplication and gives C2 and at the end the sum of C1 and C2 will be wrapped up in C. when I run the code through cmd it stops working and I don't know what is the problem. I would be really grateful if you could help me to find out what is the problem in code, here is my code,

What I have tried:

#define _CRT_SECURE_NO_WARNINGS
#include<iostream>
#include<fstream>
#include<vector>
#include<iterator>
#include<sstream>
#include<string>
#include<cstdlib>
#include<cmath>
#include<stdio.h>
#include<conio.h>
#include<algorithm>
#include<ctime> 
#include<iomanip>
#include<mpi.h>
#include<time.h>
#include<assert.h>

using namespace std;

void Initialise(int **res, int rows, int cols);
void Multiply(int **res, int **A, int **B, int aRows, int aCols, int bRows, int bCols);
void timestamp();




//**********************************************************
/*              |3  2  5|
    matrix A=   |4  3  1|
                |2  4  2|

   matrix A is divided into two matrix A1,A2

                |1  2  3|
    matrix A1=  |3  2  1|
                |1  2  0|

                |2  0  2|
    matrix A2=  |1  1  0|
                |1  2  2|


                | 2 |
    vector x=   | 1 |
                | 3 |


                | 23 |
    C   =       | 14 |
                | 14 |

//*********************************************************
*/


    int main(int argc,char **argv)

     {



    int  id, p;

    MPI_Status status;


// p -> no. of processes

// id -> process id

    MPI_Init(&argc, &argv);
    MPI_Comm_rank(MPI_COMM_WORLD, &id);

    MPI_Comm_size(MPI_COMM_WORLD, &p);
    cout << p << endl;
    char processor_name[MPI_MAX_PROCESSOR_NAME];
    int name_len;
    MPI_Get_processor_name(processor_name, &name_len);


    if (id == 0)// master
    {
        wtime = MPI_Wtime();


        int aRows = 3;
        int aCols = 3;
        int bRows = 3;
        int bCols = 1;

        int** A = new int*[aRows];
        for (int i = 0; i < aRows; i++)
        {
            A[i] = new int[aCols];
        }
        int** A1 = new int*[aRows];
        for (int i = 0; i < aRows; i++)
        {
            A1[i] = new int[aCols];
        }
        int** A2 = new int*[aRows];
        for (int i = 0; i < aRows; i++)
        {
            A2[i] = new int[aCols];
        }

        int** B = new int*[bRows];
        for (int i = 0; i < bRows; i++)
        {
            B[i] = new int[bCols];
        }

        //***************************************
        A[0][0] = 3;
        A[0][1] = 2;
        A[0][2] = 5;
        A[1][0] = 4;
        A[1][1] = 3;
        A[1][2] = 1;
        A[2][0] = 2;
        A[2][1] = 4;
        A[2][2] = 2;
        B[0][0] = 2;
        B[1][0] = 1;
        B[2][0] = 3;
        //**************************************
        A1[0][0] = 1;
        A1[0][1] = 2;
        A1[0][2] = 3;
        A1[1][0] = 3;
        A1[1][1] = 2;
        A1[1][2] = 1;
        A1[2][0] = 1;
        A1[2][1] = 2;
        A1[2][2] = 0;
        //**************************************
        A2[0][0] = 2;
        A2[0][1] = 0;
        A2[0][2] = 2;
        A2[1][0] = 1;
        A2[1][1] = 1;
        A2[1][2] = 0;
        A2[2][0] = 1;
        A2[2][1] = 2;
        A2[2][2] = 2;
        //*************************************
        B[0][0] = 2;
        B[1][0] = 1;
        B[2][0] = 3;
        //*************************************
        int** C;
        C = new int*[aRows];
        for (int i = 0; i < aRows; i++)
        {
            C[i] = new int[bCols];
        }
        //************************************
        int** C1;
        C1 = new int*[aRows];
        for (int i = 0; i < aRows; i++)
        {
            C1[i] = new int[bCols];
        }
        //************************************
        int** C2;
        C2 = new int*[aRows];
        for (int i = 0; i < aRows; i++)
        {
            C2[i] = new int[bCols];
        }
        //***********************************
        Multiply(C, A, B, aRows, aCols, bRows, bCols);

        for (int i = 0; i < aRows; i++)
        {
            for (int j = 0; j < bCols; j++)
            {
                std::cout << C[i][j] << ' ';
            }
            std::cout << '\n';
        }

        MPI_Send(&aRows, 1, MPI_INT, 1, 1, MPI_COMM_WORLD);
        MPI_Send(&aCols, 1, MPI_INT, 1, 2, MPI_COMM_WORLD);
        MPI_Send(&bRows, 1, MPI_INT, 1, 3, MPI_COMM_WORLD);
        MPI_Send(&bCols, 1, MPI_INT, 1, 4, MPI_COMM_WORLD);

        MPI_Send(&aRows, 1, MPI_INT, 2, 5, MPI_COMM_WORLD);
        MPI_Send(&aCols, 1, MPI_INT, 2, 6, MPI_COMM_WORLD);
        MPI_Send(&bRows, 1, MPI_INT, 2, 7, MPI_COMM_WORLD);
        MPI_Send(&bCols, 1, MPI_INT, 2, 8, MPI_COMM_WORLD);

        MPI_Send(&A1, aRows*aCols, MPI_INT, 1, 9, MPI_COMM_WORLD);
        MPI_Send(&B , bRows*bCols, MPI_INT, 1, 10, MPI_COMM_WORLD);

        MPI_Send(&A2, aRows*aCols, MPI_INT, 2, 11, MPI_COMM_WORLD);
        MPI_Send(&B, bRows*bCols, MPI_INT, 2, 12, MPI_COMM_WORLD);

    }


      for (id=1;id<3;id++)
        {
        if (id == 1)
        {

            int aRows, aCols, bRows, bCols;

            MPI_Recv(&aRows, 1, MPI_INT, 0, 1, MPI_COMM_WORLD, &status);
            printf("receive data:%d", aRows);
            MPI_Recv(&aCols, 1, MPI_INT, 0, 2, MPI_COMM_WORLD, &status);
            printf("receive data:%d", aCols);
            MPI_Recv(&bRows, 1, MPI_INT, 0, 3, MPI_COMM_WORLD, &status);
            printf("receive data:%d", bRows);
            MPI_Recv(&bCols, 1, MPI_INT, 0, 4, MPI_COMM_WORLD, &status);
            printf("receive data:%d", bCols);

            //int s = status.MPI_SOURCE;
            //int t = status.MPI_TAG;

    
            int** A1 = new int*[aRows];
            for (int i = 0; i < aRows; i++)
            {
                A1[i] = new int[aCols];
            }

            int** B = new int*[bRows];
            for (int i = 0; i < bRows; i++)
            {
                B[i] = new int[bCols];
            }

            int** C1 = new int*[bRows];
            for (int i = 0; i < bRows; i++)
            {
                C1[i] = new int[bCols];
            }

            //***********************************************************

            MPI_Recv(&A1, aRows*aCols, MPI_INT, 0, 9, MPI_COMM_WORLD, &status);
            printf("receive data:%d", A1);
            MPI_Recv(&B , aRows*aCols, MPI_INT, 0, 10, MPI_COMM_WORLD, &status);
            printf("receive data:%d", B);

            Multiply(C1, A1, B, aRows, aCols, bRows, bCols);

            for (int i = 0; i < aRows; i++)
            {
                for (int j = 0; j < bCols; j++)
                {
                    cout << C1[i][j] << endl;

                }
            }
        }



        else
        {
            int aRows, aCols, bRows, bCols;

            MPI_Recv(&aRows, 1, MPI_INT, 0, 5, MPI_COMM_WORLD, &status);
            MPI_Recv(&aCols, 1, MPI_INT, 0, 6, MPI_COMM_WORLD, &status);
            MPI_Recv(&bRows, 1, MPI_INT, 0, 7, MPI_COMM_WORLD, &status);
            MPI_Recv(&bCols, 1, MPI_INT, 0, 8, MPI_COMM_WORLD, &status);


            int** A2 = new int*[aRows];
            for (int i = 0; i < aRows; i++)
            {
                A2[i] = new int[aCols];
            }

            int** B = new int*[bRows];
            for (int i = 0; i < bRows; i++)
            {
                B[i] = new int[bCols];
            }

            int** C2 = new int*[bRows];
            for (int i = 0; i < bRows; i++)
            {
                C2[i] = new int[bCols];
            }

            MPI_Recv(&A2, aRows*aCols, MPI_INT, 0, 11, MPI_COMM_WORLD, &status);
            printf("receive data:%d", A2);
            MPI_Recv(&B , aRows*aCols, MPI_INT, 0, 12, MPI_COMM_WORLD, &status);
            printf("receive data:%d", B);

            //**************************************************************
            MPI_Status status;
            Multiply(C2, A2, B, aRows, aCols, bRows, bCols);
            for (int i = 0; i < aRows; i++)
            {
                for (int j = 0; j < bCols; j++)
                {
                    cout << C2[i][j] << endl;
                }

            }
        }
        //MPI_Recv(&(C1[0][0]), aRows*bCols, MPI_INT, 0, tag, MPI_COMM_WORLD,&status);
    }

    MPI_Finalize();
    return 0;
}

void Multiply(int **res, int **A, int **B, int aRows, int aCols, int bRows, int bCols)
{
    if (aCols != bRows)
        return;

    for (int i = 0; i < aRows; i++)
    {
        for (int j = 0; j < bCols; j++)
        {
            res[i][j] = 0;
            for (int k = 0; k < aCols; k++)
            {
                res[i][j] += A[i][k] * B[k][j];
            }
        }
    }
}

void Initialise(int **res, int rows, int cols)
{
    for (int i = 0; i < rows; i++)
    {
        for (int j = 0; j < cols; j++)
        {
            res[i][j] = 0;
        }
    }
}

Posted 3-May-21 0:15am

Member 15181211

Updated 3-May-21 1:35am

Add a Solution

Comments

merano99 3-May-21 19:05pm

Does not compile with Visual-Studio

1. xxx.cpp(87): error C2065: "wtime": not declared
2. xxx.cpp(247): warning C4477: "printf": ... Typ "int **" (several warnings)

Are you really shure you want a loop with id?

Member 15181211 3-May-21 19:31pm

Yes about wtime you're right.
My problem is I don't know how to implement master and slave process along the code. Actually I am very beginner in MPI and I don't know whether I need for loop in this case or not. I have 32 logica processes in my PC and I just need to use few of them,let's say 3 of them. Could you please help me with these issues by showing on this code. Thanks

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

KarstenK · Answer 1 · 2021-05-03T01:35:00

You need to use the debugger. Visit some C++ Debugger tutorial to kickstart your efforts.

Your code looks quiet good, so my best guess is that problem is some out of bounds memory access or misuse of the mpi functions. The cause is mostly a flaw in memory access arithmetics like to small memory or too far loops. So step with debugger til the error occurs.
Have in mind that the error cause maybe in the preconditions or if you have bad luck it is somewhere before. Try to use than memory view.