#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.h>
#define SIZE (1024*1024)

__global__ void addKernel(int *c,int *a, int *b ,int n)
{
    int i = threadIdx.x;
	printf("1");
	if (i < n)
		(c[i] = a[i] + b[i]);

}

int main()
{
	int *a, *b, *c;
	cudaMallocManaged(&a, SIZE * sizeof(int));
	cudaMallocManaged(&b, SIZE * sizeof(int));
	cudaMallocManaged(&c, SIZE * sizeof(int));
	for (int i = 0; i < SIZE; i++) {
		a[i] = i;
		b[i] = i;
		c[i] = 0;
	}

	addKernel <<< 1, SIZE >>> (a, b, c, SIZE);
	cudaDeviceSynchronize();

	for (int i = 0; i < 20; i++) {
		printf("c[%d] = %d\n", i, c[i]);
	}
	cudaFree(a);
	cudaFree(b);
	cudaFree(c);
    return 0;
}