#include <stdio.h>
#define N 512


__global__ void add(int *a, int *b, int *c) {
		c[blockIdx.x] = a[blockIdx.x] + b[blockIdx.x];
	}



int main(void) {
		int *a, *b, *c;            // host copies of a, b, c
		int *d_a, *d_b, *d_c;      // device copies of a, b, c
		int size = N * sizeof(int);
		int i;
		
		// Allocate space for device copies of a, b, c
		cudaMalloc((void **)&d_a, size);
		cudaMalloc((void **)&d_b, size);
		cudaMalloc((void **)&d_c, size);

		// Setup input values
		a = (int *) malloc(size);
      b = (int *) malloc(size);
		c = (int *) malloc(size);

		for (i = 0; i < N; i ++){
			a[i] = i % 7;
			b[i] = i % 13;
		}

		// Copy inputs to device
		cudaMemcpy(d_a, &a, size, cudaMemcpyHostToDevice);
		cudaMemcpy(d_b, &b, size, cudaMemcpyHostToDevice);

		// Launch add() kernel on GPU
		add<<<N,1>>>(d_a, d_b, d_c);

		// Copy result back to host
		cudaMemcpy(&c, d_c, size, cudaMemcpyDeviceToHost);


		// check first 10 elements
		for (i= 0; i < 10; i++) printf(" c[%d]=%d\n",i,c[i]);

		// Cleanup
		cudaFree(d_a); cudaFree(d_b); cudaFree(d_c);
		free(a); free(b); free(c);
		return 0;
	}