在CUDA中的块之间分配线程

Question

I'm working on a project in CUDA. The first time I used only one block with Dim 8*8 as my matrix. And then I calculated the index as follows:

int idx = blockIdx.x * blockDim.x + threadIdx.x;  
int idy = blockIdx.y * blockDim.y + threadIdx.y;  

And it gave me a correct answer. After that I want to distribute the threads between blocks to measure the performance. I make the grid dim to be (2,1) and the block dim to be (4,8).

When I debug the code by hand, it seems to give me the correct index without changing the formula mentioned above. But when I run the program, the screen hangs and the results are all zero.

What did I do wrong, and how can I fix this?

This is the kernel function

__global__ void cover_fault(int *a,int *b, int *c, int *d, int *mulFV1, int *mulFV2,     int *checkDalU1, int *checkDalU2, int N)  

 {  
//Fig.2
__shared__ int f[9][9];
__shared__ int compV1[9],compV2[9];
int dalU1[9] , dalU2[9];
int Ra=2 , Ca=2;
for (int i = 0 ; i < N ; i++)
  for (int j = 0 ; j < N ; j++)
         f[i][j]=0;

f[3][0] = 1;
f[0][2] = 1;
f[0][6] = 1;
f[3][7] = 1;
f[2][4] = 1;
f[6][4] = 1;
f[7][1] = 1; 

int t =0 ,A = 1,B = 1 , UTP = 5 , LTP = -5 , U_max = 40 , U_min = -160;
bool flag = true;
int sumV1, sumV2;
int checkZero1 , checkZero2;


int idx = blockIdx.x * blockDim.x + threadIdx.x;  
int idy = blockIdx.y * blockDim.y + threadIdx.y;  

while ( flag == true)
{
    if ( c[idy] == 0 )
            compV1[idy] = 1;

       else if ( c[idy]==1)
                compV1[idy] = 0 ;

       if ( d[idy] == 0 )
            compV2[idy] = 1;

       else if ( d[idy]==1 )
                  compV2[idy] = 0 ;


   sumV1 = reduce ( c, N );
   sumV2 = reduce ( d, N );


   if (idx<N && idy <N)    
    {        
     if(idx==0)                  
          mulFV1[idy]=0;     
     if(idy==0)      
          mulFV2[idx]=0;               

     __syncthreads();     

     atomicAdd(&(mulFV1[idy]),f[idy][idx]*compV2[idx]);     
     atomicAdd(&(mulFV2[idx]),f[idy][idx]*compV1[idy]);   

      } 


    dalU1[idy] = ( -1*A*( sumV1 - Ra )) + (B * mulFV1[idy] * compV1[idy]) ;
    dalU2[idy] = ( -1*A*( sumV2 - Ca )) + (B * mulFV2[idy] * compV2[idy]) ;


    a[idy] = a[idy] + dalU1[idy];
    b[idy] = b[idy] + dalU2[idy];


       if ( a[idy] > U_max )
               a[idy] = U_max;
       else
           if (a[idy] < U_min )
                a[idy] = U_min;

       if ( b[idy] > U_max )
                 b[idy] = U_max;
       else
           if (b[idy] < U_min )
                b[idy] = U_min;


      if (dalU1[idy]==0)
           checkDalU1[idy]=0;
         else
            checkDalU1[idy]=1;

      if (dalU2[idy]==0)
           checkDalU2[idy]=0;
            else
               checkDalU2[idy]=1;

       __syncthreads();     
      checkZero1 = reduce(checkDalU1,N);
      checkZero2 = reduce(checkDalU2,N);

      if ( checkZero1==0 && checkZero2==0)
               flag = false;


      else
      {

       if ( a[idy] > UTP )
              c[idy] = 1;
           else
               if ( a[idy] < LTP )
                      c[idy] = 0 ;

            if ( b[idy] > UTP )
                   d[idy] = 1;
           else
               if ( b[idy] < LTP )
                      d[idy] = 0 ;  

      t++;

      }//end else 
      sumV1=0;
      sumV2=0;
      mulFV1[idy]=0;
      mulFV2[idy]=0;
      } //end while

}//end function

Answer 1

In your index computation, idx will give you the column index and idy the row index. Are you accessing your matrix as M[idy][idx] ?

The cuda threads are organized according to the orthogonal system: X is horizontal and Y is vertical. So if you say the point M[0][1] in the actual matrix it's M[1][0].