C++ openMP 并行矩阵乘法

Question

我的 openMP 代码有什么问题？它总是只需要 1 个线程，并且与非并行版本的工作时间相同

template <typename T>
Matrix<T>* Matrix<T>::OMPMultiplication(Matrix<T>* A, Matrix<T>* B){ 

    if(A->ySize != B->xSize)
      throw;

    Matrix<T>* C = new Matrix<T>(A->xSize, B->ySize);

    sizeType i, j, k;
    T element;

    #pragma omp parallel for private(i, j)
    {
      #pragma omp for private(i, j)
      for( i = 0; i < A->xSize; i++ )
          cout<<"There are "<<omp_get_num_threads()<<" threads"<<endl;

          for(j = 0; j < B->ySize; j++){

              C->matrix[i][j] = 0;
              for(k = 0; k < A->ySize; k++){
                  C->matrix[i][j] += A->matrix[i][k] * B->matrix[k][j]; 
              }   

      }   
    }   
    return C;
}

Answer 1

首先，您在i 循环中缺少一些{}，并且变量k 需要对i 循环的每次迭代都是私有的。但是，我认为您还混淆了 parallel 和 for 杂注的组合方式。要成功并行化 for 循环，您需要将其放入 parallel pragma 中，然后放入 for pragma 中。为此，您可以将代码更改为

#pragma omp parallel private(i, j, k)
{
    #pragma omp for
    for( i = 0; i < A->xSize; i++ ) {
        cout<<"There are "<<omp_get_num_threads()<<" threads"<<endl;

        for(j = 0; j < B->ySize; j++) {

            C->matrix[i][j] = 0;
            for(k = 0; k < A->ySize; k++){
                C->matrix[i][j] += A->matrix[i][k] * B->matrix[k][j]; 
            }   

        }
    }
}

或使用组合的parallel for 表示法

#pragma omp parallel for private(i, j, k)
for( i = 0; i < A->xSize; i++ ) {
    ...
}

另外，请确保您告诉 OpenMP 在此处使用超过 1 个线程。这可以通过omp_set_num_threads(<number of threads here>) 和设置环境变量（如OMP_NUM_THREADS）来完成。

希望你能并行化。 :)

Answer 2

使用此代码，我的 4 个内核得到了稍微快一点的结果：

    omp_set_num_threads(4);
    #pragma omp parallel for
    for (i = 0; i < n; i++) {
        for (j = 0; j < n; j++) {
            c[i] += b[j] * a[j][i];
        }
    }

完整程序

#include <stdio.h>
#include <time.h>
#include <omp.h>
#include <stdlib.h>


int main() {
    int i, j, n, a[719][719], b[719], c[719];

    clock_t start = clock();

    n = 100; //Max 719

    printf("Matrix A\n");

    for (i = 0; i < n; ++i) {
        for (j = 0; j < n; ++j) {
            a[i][j] = 10;
            printf("%d ", a[i][j]);
        }
        printf("\n");
    }

    printf("\nMatrix B\n");

#pragma omp parallel private(i) shared(b)
    {
#pragma omp for
        for (i = 0; i < n; ++i) {
            b[i] = 5;
            printf("%d\n", b[i]);
        }
    }

    printf("\nA * B\n");

#pragma omp parallel private(i) shared(c)
    {
#pragma omp for
        for (i = 0; i < n; ++i) {
            c[i] = 0;
        }
    }

#pragma omp parallel private(i,j) shared(n,a,b,c)
    {
#pragma omp for schedule(dynamic)
        for (i = 0; i < n; ++i) {
            for (j = 0; j < n; ++j) {
                c[i] += b[j] * a[j][i];
            }
        }
    }


#pragma omp parallel private(i) shared(c)
    {
#pragma omp for
        for (i = 0; i < n; ++i) {
            printf("%d\n", c[i]);
        }
    }

    clock_t stop = clock();
    double elapsed = (double) (stop - start) / CLOCKS_PER_SEC;
    printf("\nTime elapsed: %.5f\n", elapsed);
    start = clock();
    printf("Matrix A\n");

    for (i = 0; i < n; ++i) {
        for (j = 0; j < n; ++j) {
            a[i][j] = 10;
            printf("%d ", a[i][j]);
        }
        printf("\n");
    }

    printf("\nMatrix B\n");

#pragma omp parallel private(i) shared(b)
    {
#pragma omp for
        for (i = 0; i < n; ++i) {
            b[i] = 5;
            printf("%d\n", b[i]);
        }
    }
    printf("\nA * B\n");
    omp_set_num_threads(4);
#pragma omp parallel for
    for (i = 0; i < n; i++) {
        for (j = 0; j < n; j++) {
            c[i] += b[j] * a[j][i];
        }
    }
    stop = clock();
    elapsed = (double) (stop - start) / CLOCKS_PER_SEC;
    printf("\nTime elapsed: %.5f\n", elapsed);
    return 0;
}

第一种方法

经过的时间：0.03442

第二种方法

经过的时间：0.02630