Question

您能否建议我如何使openacc更加平行。我正在使用插入排序进行mergesort。我应该使用“循环”或“for”来使用循环。对于插入排序，它应该是内核或并行。

#include <stdlib.h>
#include<stdio.h>
#include <time.h>
#include <openacc.h>
#define THR 1000

//Insertion sort
void isort (int *a, int left, int mid, int right) {

int i,j;
# pragma acc kernels
{
# pragma acc parallel loop num_gangs (1024)
for ( i = mid; i <= right; i++) {
    for ( j = i - 1; j >= 0; j--) {
        if (a[i] < a [j]) {
            int temp = a[j];
            a[j] = a[i];
            a[i] = temp;
            i--;
        }
    }
}
}
}
void merge(int a[], int left, int right,int left_half[], int right_half[])
{
int i, j, k;
int mid = (left + right + 1) / 2;

i = j = 0;
k = left;

while (i < mid - left && j <= right - mid) {
    if (left_half[i] < right_half[j]) {
        a[k] = left_half[i];
        ++i;
    } else {
        a[k] = right_half[j];
        ++j;
    }

    ++k;
   }

  // Copying any leftover elements
  #pragma acc data copy(a, right_half)
  while (j <= right - mid) {
        a[k++] = right_half[j++];//copy remaining elements of the first half

    }
   #pragma acc data copy(a, left_half)
   while (i < mid - left) {
        a[k++] = left_half[i++]; //copy remaining elements of the second list
    }
   }

  void mergeSort(int a[], int left, int right)
{
if (left < right) {
    int mid = (left + right + 1) / 2;
    int left_half[mid - left];
    int right_half[right - mid + 1];
    int i;
   # pragma acc kernels
   {
    // Copying elements
    # pragma acc parallel loop shared (left_half, a)
    for (i = left; i < mid; ++i) {
        left_half[i - left] = a[i];
    }

    // Copying elements
    # pragma acc parallel loop shared (right_half, a)
    for (i = mid; i <= right; ++i) {
        right_half[i - mid] = a[i];
    }
  }
    // Recursive call
    mergeSort(left_half, 0, mid - left - 1);
    mergeSort(right_half, 0, right - mid);
    // Merge the two partitions
    if ((right - left) > THR){
        merge(a, left, right, left_half, right_half);
    } else {
        isort(a, left,mid, right);
    }
}
}


  int main()
   {
int i, n, *a,c;

printf("Enter the number of elements\n");
scanf("%d",&n);      
a = (int *)acc_malloc(sizeof(int) * n);  
srand(time(0));
for(i=0;i<n;i++){
   a[i]=rand()%1000;
}
printf("\nThe unsorted a is:");
printf("\n");
for(i=0;i<n;i++)
    printf("%d  ",a[i]);;

    mergeSort(a, 0, n-1);
printf("\nSorted a:");
printf("\n");
for(i=0;i<n;i++)
    printf("%d  ",a[i]);
printf("\n");
 }

Answer 1

我不知道openacc的语法。 从openmp语法开始，如果你有更大的数组循环，你甚至可以并行运行for循环的每个循环，而for循环都是并行的。请查看此link1，link2。我不知道你是否通过写# pragma acc parallel loop above for loops来表达同样的意思，或者如果你在openacc中有这样的东西，你可以添加它。

你可以同时运行两个mergesorts，就像这样。

# pragma acc kernels
   {
     # pragma acc parallel{mergeSort(left_half, 0, mid - left - 1);}
     # pragma acc parallel{mergeSort(right_half, 0, right - mid);}
   }

Openacc：如何使插入排序更加平行

1 个答案: