Ошибка сегментации после разброса

     /**
     * BLOCK_LOW
     * Returns the offset of a local array
     * with regards to block decomposition
     * of a global array.
     *
     * @param  (int) process rank
     * @param  (int) total number of processes
     * @param  (int) size of global array
     * @return (int) offset of local array in global array
     */
    #define BLOCK_LOW(id, p, n) ((id)*(n)/(p))

    /**
     * BLOCK_HIGH
     * Returns the index immediately after the
     * end of a local array with regards to
     * block decomposition of a global array.
     *
     * @param  (int) process rank
     * @param  (int) total number of processes
     * @param  (int) size of global array
     * @return (int) offset after end of local array
     */
    #define BLOCK_HIGH(id, p, n) (BLOCK_LOW((id)+1, (p), (n)))

    /**
     * BLOCK_SIZE
     * Returns the size of a local array
     * with regards to block decomposition
     * of a global array.
     *
     * @param  (int) process rank
     * @param  (int) total number of processes
     * @param  (int) size of global array
     * @return (int) size of local array
     */
    #define BLOCK_SIZE(id, p, n) ((BLOCK_HIGH((id), (p), (n))) - (BLOCK_LOW((id), (p), (n))))

    /**
     * BLOCK_OWNER
     * Returns the rank of the process that
     * handles a certain local array with
     * regards to block decomposition of a
     * global array.
     *
     * @param  (int) index in global array
     * @param  (int) total number of processes
     * @param  (int) size of global array
     * @return (int) rank of process that handles index
     */
    #define BLOCK_OWNER(i, p, n) (((p)*((i)+1)-1)/(n))



    /*Matricefilenames:
      small matrix A.bin of dimension 100 × 50
      small matrix B.bin of dimension 50 × 100
      large matrix A.bin of dimension 1000 × 500
      large matrix B.bin of dimension 500 × 1000

    An MPI program should be implemented such that it can
    • accept two file names at run-time,
    • let process 0 read the A and B matrices from the two data files,
    • let process 0 distribute the pieces of A and B to all the other processes,
    • involve all the processes to carry out the the chosen parallel algorithm
    for matrix multiplication C = A * B ,
    • let process 0 gather, from all the other processes, the different pieces
    of C ,
    • let process 0 write out the entire C matrix to a data file.
    */


    #include <stdio.h>
    #include <stdlib.h>
    #include <mpi.h>
    #include "mpi-utils.c"
    void read_matrix_binaryformat (char*, double***, int*, int*);
    void write_matrix_binaryformat (char*, double**, int, int);
    void create_matrix (double***,int,int);
    void matrix_multiplication (double ***, double ***, double ***,int,int, int);

    int main(int argc, char *argv[]) {
        int id,p; // Process rank and total amount of processes
        int rowsA, colsA, rowsB, colsB; // Matrix dimensions
        double **A; // Matrix A
        double **B; // Matrix B
        double **C; // Result matrix C : AB
        int local_rows; // Local row dimension of the matrix A
        double **local_A; // The local A matrix
        double **local_C;  // The local C matrix

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

        if(argc != 3) {
            if(id == 0) {
                printf("Usage:\n>> %s matrix_A matrix_B\n",argv[0]);
            }       
            MPI_Finalize();
            exit(1);
        }

        if (id == 0) {
            read_matrix_binaryformat (argv[1], &A, &rowsA, &colsA);
            read_matrix_binaryformat (argv[2], &B, &rowsB, &colsB);
        }

        if (p == 1) {
            create_matrix(&C,rowsA,colsB);
            matrix_multiplication (&A,&B,&C,rowsA,colsB,colsA);

            char* filename = "matrix_C.bin";
            write_matrix_binaryformat (filename, C, rowsA, colsB);
            free(A);
            free(B);
            free(C);
            MPI_Finalize();
            return 0;
        }


        // For this assignment we have chosen to bcast the whole matrix B:
        MPI_Bcast (&B, 1, MPI_DOUBLE, 0, MPI_COMM_WORLD); 
        MPI_Bcast (&colsA, 1, MPI_INT, 0, MPI_COMM_WORLD);
        MPI_Bcast (&colsB, 1, MPI_INT, 0, MPI_COMM_WORLD);
        MPI_Bcast (&rowsA, 1, MPI_INT, 0, MPI_COMM_WORLD);
        MPI_Bcast (&rowsB, 1, MPI_INT, 0, MPI_COMM_WORLD);

        local_rows = BLOCK_SIZE(id, p, rowsA);


        /*    SCATTER VALUES    */

        int *proc_elements = (int*)malloc(p*sizeof(int)); // amount of elements for each processor
        int *displace = (int*)malloc(p*sizeof(int)); // displacement of elements for each processor
        int i;
        for (i = 0; i<p; i++) {
            proc_elements[i] = BLOCK_SIZE(i, p, rowsA)*colsA;
            displace[i] = BLOCK_LOW(i, p, rowsA)*colsA;
        }

        create_matrix(&local_A,local_rows,colsA);

        MPI_Scatterv(&A[0],&proc_elements[0],&displace[0],MPI_DOUBLE,&local_A[0],
                     local_rows*colsA,MPI_DOUBLE,0,MPI_COMM_WORLD);

        /*    END  SCATTER  VALUES  */  

        create_matrix (&local_C,local_rows,colsB);
        matrix_multiplication (&local_A,&B,&local_C,local_rows,colsB,colsA);

        /*    GATHER VALUES    */

        MPI_Gatherv(&local_C[0], rowsA*colsB, MPI_DOUBLE,&C[0],
              &proc_elements[0],&displace[0],MPI_DOUBLE,0, MPI_COMM_WORLD);

        /*    END  GATHER VALUES  */

        char* filename = "matrix_C.bin";
        write_matrix_binaryformat (filename, C, rowsA, colsB);  

        free (proc_elements);
        free (displace);    
        free (local_A);
        free (local_C);
        free (A);
        free (B);
        free (C);   
        MPI_Finalize ();
        return 0;
    }

    void create_matrix (double ***C,int rows,int cols) {
        *C = (double**)malloc(rows*sizeof(double*));
        (*C)[0] = (double*)malloc(rows*cols*sizeof(double));
        int i;
        for (i=1; i<rows; i++)
            (*C)[i] = (*C)[i-1] + cols;
    }

    void matrix_multiplication (double ***A, double ***B, double ***C, int rowsC,int colsC,int colsA) {
        double sum;
        int i,j,k;
        for (i = 0; i < rowsC; i++) {
            for (j = 0; j < colsC; j++) {
                sum = 0.0;
                for (k = 0; k < colsA; k++) {
                    sum = sum + (*A)[i][k]*(*B)[k][j];
                }
                (*C)[i][j] = sum;
            }
        }
    }

    /* Reads a 2D array from a binary file*/ 
    void read_matrix_binaryformat (char* filename, double*** matrix, int* num_rows, int* num_cols) {
        int i;
        FILE* fp = fopen (filename,"rb");
        fread (num_rows, sizeof(int), 1, fp);
        fread (num_cols, sizeof(int), 1, fp);
        /* storage allocation of the matrix */
        *matrix = (double**)malloc((*num_rows)*sizeof(double*));
        (*matrix)[0] = (double*)malloc((*num_rows)*(*num_cols)*sizeof(double));
        for (i=1; i<(*num_rows); i++)
            (*matrix)[i] = (*matrix)[i-1]+(*num_cols);
        /* read in the entire matrix */
        fread ((*matrix)[0], sizeof(double), (*num_rows)*(*num_cols), fp);
        fclose (fp);
    }

    /* Writes a 2D array in a binary file */
    void write_matrix_binaryformat (char* filename, double** matrix, int num_rows, int num_cols) {
      FILE *fp = fopen (filename,"wb");
      fwrite (&num_rows, sizeof(int), 1, fp);
      fwrite (&num_cols, sizeof(int), 1, fp);
      fwrite (matrix[0], sizeof(double), num_rows*num_cols, fp);
      fclose (fp);
    }

Моя задача состоит в том, чтобы выполнить параллельное матричное умножение матриц A и B и собрать результаты в матрице C.

Я делаю это, разделяя матрицу A на части по строкам, и каждый процесс будет использовать свою часть, чтобы умножить матрицу B, и получить свою часть от умножения. Затем я соберу все части процессов и сложу их в матрицу C.

Я уже публиковал аналогичный вопрос, но этот код улучшен, и я продвинулся вперед, но после вызова scatterv я все еще получаю ошибку сегментации.