__global__ void vecAdd(int *A,int *B,int *C, int n)
{
	int sum = 0;
	for (int j =0; j<n/1000; j++) {
		int i = blockIdx.x * blockDim.x + threadIdx.x+j*1000;
		sum = sum + A[i];
		__syncthreads();
		C[i]=sum;
		sum = 0;
	}
	//__syncthreads();

	// do average?
}