2021-04-07

__global void MatAdd(float A[N][N], float B[N][N], float C[N][N])  
{  
    int i = blockIdx.x ∗ blockDim.x + threadIdx.x;  
    int j = blockIdx.y ∗ blockDim.y + threadIdx.y;  
    if (i < N && j < N)  
        C[i ][ j ] = A[i][ j ] + B[i][ j ];  
}  
int main()  
{  
    ...  
    // Kernel invocation  
    dim3 threadsPerBlock(16, 16);  
    dim3 numBlocks(N / threadsPerBlock.x, N / threadsPerBlock.y);  
    MatAdd<<<numBlocks, threadsPerBlock>>>(A, B, C);  
    ...  
}