How to do Matrix Addition with CUDA C

Question

I am writing a simpled code about the addition of the elements of 2 matrices A and B; the code is quite simple and it is inspired on the example given in chapter 2 of the CUDA C Programming Guide.

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

#define N 2

__global__ void MatAdd(int A[][N], int B[][N], int C[][N]){
           int i = threadIdx.x;
           int j = threadIdx.y;

           C[i][j] = A[i][j] + B[i][j];
       }


int main(){

int A[N][N] = {{1,2},{3,4}};
int B[N][N] = {{5,6},{7,8}};
int C[N][N] = {{0,0},{0,0}};    

int (*pA)[N], (*pB)[N], (*pC)[N];

cudaMalloc((void**)&pA, (N*N)*sizeof(int));
cudaMalloc((void**)&pB, (N*N)*sizeof(int));
cudaMalloc((void**)&pC, (N*N)*sizeof(int));

cudaMemcpy(pA, A, (N*N)*sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(pB, B, (N*N)*sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(pC, C, (N*N)*sizeof(int), cudaMemcpyHostToDevice);

int numBlocks = 1;
dim3 threadsPerBlock(N,N);
MatAdd<<<numBlocks,threadsPerBlock>>>(A,B,C);

cudaMemcpy(C, pC, (N*N)*sizeof(int), cudaMemcpyDeviceToHost);

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

cudaFree(pA); 
cudaFree(pB); 
cudaFree(pC);

printf("\n");

return 0;
}

when i run it i keep getting the initial matrix C = [0 0 ; 0 0] instead of the addition of the elements(i,j) of the 2 matrices A and B; i have previously done another example about the addition of the elements of two arrays and it seems to work fine; however this time i don't know why it does not work.

I believe there's something wrong with the cudaMalloc command by i don't really know what else could it be.

Any ideas?

Answer 1

MatAdd<<<numBlocks,threadsPerBlock>>>(pA,pB,pC); instead of MatAdd<<<numBlocks,threadsPerBlock>>>(A,B,C); solves the problem.

The reason is that A,B and C are allocated on the CPU, while pA,pB and pC are allocated of the GPU, using CudaMalloc(). Once pA,pB and pC are allocated, the values are sent from the CPU to GPU by cudaMemcpy(pA, A, (N*N)*sizeof(int), cudaMemcpyHostToDevice);

Then, the addition is performed on the GPU, that is with pA,pB and pC. To use printf, the result pC is sent from the GPU to the CPU via cudaMemcpy(C, pC, (N*N)*sizeof(int), cudaMemcpyDeviceToHost);

Think as if the CPU cannot see pA and the GPU cannot see A.