#include <cstdio>
const int N = 20;

// Here blockIdx.x identifies the current block.
__global__ void add( int *a, int *b, int *c ) 
{
    int i = blockIdx.x;
    c[i] = a[i] + b[i];
}

int main() 
{ 
    int *a, *b, *c; 
    int *d_a, *d_b, *d_c; 
    int i;

    a = new int[N];  
    b = new int[N];
    c = new int[N];
    for (int i = 0; i < N; i++) {
        a[i] = 1;
        b[i] = 2;
    }

    int size = sizeof(int) * N;
    cudaMalloc((void**) &d_a, size); 
    cudaMemcpy(d_a, a, size,   cudaMemcpyHostToDevice);

    cudaMalloc((void**) &d_b, size); 
    cudaMemcpy(d_b, b, size,   cudaMemcpyHostToDevice);

    cudaMalloc((void**) &d_c, size); 
    cudaMemcpy(d_c, c, size, cudaMemcpyHostToDevice);

    add<<<N,1>>>(d_a, d_b, d_c); 

    cudaMemcpy(c, d_c, size, cudaMemcpyDeviceToHost);
    for (i=0; i < N; i++)
        printf("%d ", c[i]);
    printf("\n");

    cudaFree(d_a); 
    cudaFree(d_b);
    cudaFree(d_c);
    delete[] a; 
    delete[] b;
    delete[] c;
    return 0;
}