Question

我编写了一个程序来通过MPI查找数组元素的总和。 root和worker都会找到一部分的总和，而worker会在最后将部分总和发送给root。当我尝试使用静态大小的数组时，没有任何问题。但如果我使用calloc，它会给出分段错误。源代码如下：

#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
#define tag1 1 /* send from root to workers */
#define tag2 2 /* send from workers to root */
#define root 0
#define n_data 12

int main(int argc, char *argv[]) 
{ 
    int total_sum, partial_sum;
    int my_id, i, n_procs, n_portion;

    MPI_Init(&argc, &argv);
    MPI_Status status;
    MPI_Comm_rank(MPI_COMM_WORLD, &my_id);
    MPI_Comm_size(MPI_COMM_WORLD, &n_procs);
    n_portion=n_data/n_procs;

    int *array = (int *)calloc(n_data, sizeof(int));
    int *local  = (int *)calloc(n_portion, sizeof(int));

    if(my_id == root) { 

        /* initialize array */
        for(i = 0; i < n_data; i++) 
            array[i]=i;

        /* send a portion of the array to each worker */
        for(i= 1; i < n_procs; i++) 
            MPI_Send( &array[i*n_portion], n_portion, MPI_INT,i, tag1, MPI_COMM_WORLD); 

        /* calculate the sum of my portion */
        for(i = 0; i < n_portion; i++)
            total_sum += array[i];

        /* collect the partial sums from workers */
        for(i= 1; i < n_procs; i++) {
            MPI_Recv( &partial_sum, 1, MPI_INT, MPI_ANY_SOURCE,tag2, MPI_COMM_WORLD, &status);
            total_sum += partial_sum; 
        }

        printf("The total sum is: %d\n", total_sum);
    }
    else { /* I am a worker, receive data from root */

        MPI_Recv( &local, n_portion, MPI_INT, root, tag1, MPI_COMM_WORLD, &status);

        /* Calculate the sum of my portion of the array */
        partial_sum = 0;
        for(i = 0; i < n_portion; i++)
            partial_sum += local[i];

        /* send my partial sum to the root */
        MPI_Send( &partial_sum, 1, MPI_INT, root, tag2, MPI_COMM_WORLD);
    }

    MPI_Finalize(); 
    return 0;
}

我犯的错误是：

-bash-4.1$ mpirun -np 3 distApprox
--------------------------------------------------------------------------
mpirun noticed that process rank 2 with PID 110834 on node levrek1 exited on signal 11 (Segmentation fault).
--------------------------------------------------------------------------

感谢您的帮助。

Answer 1

我说问题出在工人方面的MPI_Recv上。你应该使用＆＃39; local＆＃39;而不是＆＃39;＆amp; local＆＃39;作为缓冲区。 MPI期望接收缓冲区的初始地址＆＃34; (see MPI standard)，在动态数组的情况下，它本身就是数组变量。

MPI_Recv( local, n_portion, MPI_INT, root, tag1, MPI_COMM_WORLD, &status);

您可能还想初始化＆＃39; total_sum＆＃39;在root上为0然后你的代码应该运行。

编辑：刚看到Martin Zabel已经在评论中指出了这一点

MPI calloc导致分段错误

1 个答案: