C++ OMP并行嵌套循环

我正在try 使用C中的OMP将两个n乘以n的矩阵相乘. 但我的代码只计算对角线元素.以下是代码:

我的代码

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

int main(void){

  int N, element, tid;
  int i, j;
  scanf("%d", &N); // matrix dimension
  
  int A[N][N]; // matrix A
  int B[N][N]; // matrix B
  int C[N][N]; // matrix C := AB
  
  // declare elements matrix A
  for(i = 0; i < N; i++){
    for(j = 0; j < N; j++){
      scanf("%d", &element);
      A[i][j] = element;
    }
  }

  // declare elements matrix B
  for(i = 0; i < N; i++){
    for(j = 0; j < N; j++){
      scanf("%d", &element);
      B[i][j] = element;
    }
  }
  
  omp_set_num_threads(N); // set the number of threads

  #pragma omp parallel default(none) shared(A, B, C, N) private(i, j, tid) 
  { 
    tid = omp_get_thread_num(); // returns the number of the currently executing thread within the team
    #pragma omp for 
    for (i = 0; i < N; i++){
      C[tid][i] = 0;
      for (j = 0; j < N; j++){
        //tid = i*n + j;
        C[tid][i] += A[tid][j]*B[j][i];
      }
    }
  }

  // print matrix C 
  for(i = 0; i < N; i++){
    for(j = 0; j < N; j++){
      printf("%d ", C[i][j]);
    }
    printf("\n");
  }

  return(0);
}\

这是我用N=2和矩阵A={{1，2}，{3，4}}B={{1，2}，{3，4}得到的结果

C={{7，随机数}，{随机数，22}}