MPI_Gatherv不等的2D数组

Question

我希望example使用MPI_Scatterv和MPI_Gatherv将此Jonathan Dursi扩展为不等的2D数组。基本上，我有4个本地进程，每个进程都有一个不同大小的数组：

流程= 0

|00000| 
|00000| 
|00000|

流程= 1

|1111| 
|1111| 
|1111|

流程= 2

|22222|
|22222|

流程= 3

|33333| 
|33333|

我将他们收集到主流程中，我希望得到：

Master = 0

|000001111|
|000001111|
|000001111|
|222223333|
|222223333|

但是，以下是我从代码中获得的内容。

掌握流程

|000001111|
|100000111|
|110000011|
|222223333|
|322222333|

我认为我的MPI_Type_vector出了问题。任何解决此问题的建议。

以下是我的代码：

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

int main(int argc, char **argv)
{
    int rank, size;        // rank of current process and no. of processes
    int domain_x, domain_y;
    int global_x, global_y;
    int topx = 2, topy = 2;

    MPI_Init(&argc, &argv);
    MPI_Comm_size(MPI_COMM_WORLD, &size);
    MPI_Comm_rank(MPI_COMM_WORLD, &rank);

    if (rank == 0)
    {
        domain_x = 5;
        domain_y = 3;
    }

    if (rank == 1)
    {
        domain_x = 4;
        domain_y = 3;
    }

    if (rank == 2)
    {
        domain_x = 5;
        domain_y = 2;
    }

    if (rank == 3)
    {
        domain_x = 4;
        domain_y = 2;
    }

    global_x = 9;
    global_y = 5;

    int *glob_data = new int[global_x*global_y];

    // Initialize local data   
    int *local_data = new int[domain_x*domain_y]; 
    for (int i = 0; i < domain_x; ++i)
    {
        for (int j = 0; j < domain_y; ++j)
        {
            local_data[j*domain_x+i] = rank;
        }
    }

    for (int p=0; p<size; p++) {
        if (p == rank) {
            printf("rank = %d\n", rank);
            for (int j=0; j<domain_y; j++) {
                for (int i=0; i<domain_x; i++) {
                    printf("%3d ",(int)local_data[j*domain_x+i]);
                }
                printf("\n");
            }
            printf("\n");
        }
        MPI_Barrier(MPI_COMM_WORLD);
    }


    MPI_Datatype blocktype, blocktype2;
    MPI_Type_vector(domain_y, domain_x, topx*domain_x, MPI_INT, &blocktype2);
    MPI_Type_create_resized(blocktype2, 0, sizeof(int), &blocktype);
    MPI_Type_commit(&blocktype);

    int *displs = new int[topx*topy];
    int *counts = new int[topx*topy];
    for (int j=0; j<topy; j++) {
        for (int i=0; i<topx; i++) {
            displs[j*topx+i] = j*global_x*domain_y + i*domain_x;
            counts [j*topx+i] = 1;
        }
    }

    MPI_Gatherv(local_data, domain_x*domain_y, MPI_INT, glob_data, counts, displs, blocktype, 0, MPI_COMM_WORLD);

    if (rank == 0)
    {
        printf("Master process = %d\n", rank);
        for (int j=0; j<global_y; j++) {
            for (int i=0; i<global_x; i++) {
                printf("%d  ", glob_data[j*global_x+i]);
            }
            printf("\n");
        }
    }

    MPI_Type_free(&blocktype);
    MPI_Type_free(&blocktype2);
    MPI_Finalize();

    return 0;
}