cuda matrix addition example

gistfile1.c

// Kernel definition
__global__ void MatAdd(float A[N][N], float B[N][N], float C[N][N]) {
    int i = threadIdx.x;
    int j = threadIdx.y;
    C[i][j] = A[i][j] + B[i][j];
}

int main() {
    // Kernel invocation with one block of N * N * 1 threads
    int numBlocks = 1;
    dim3 threadsPerBlock(N, N);
    MatAdd<<<numBlocks, threadsPerBlock>>>(A, B, C);
}