#include <iostream>
#include <cuda_runtime.h>

__global__ void add(int *a, int *b, int *c, int n) {
int i = threadIdx.x + blockIdx.x * blockDim.x;
if (i < n) c[i] = a[i] + b[i];
}

int main() {
const int N = 1000;
int *h_a = new int[N], *h_b = new int[N], *h_c = new int[N];
for (int i = 0; i < N; ++i) { h_a[i] = i; h_b[i] = 2 * i; }

int *d_a, *d_b, *d_c;
cudaMalloc(&d_a, N * sizeof(int));
cudaMalloc(&d_b, N * sizeof(int));
cudaMalloc(&d_c, N * sizeof(int));

cudaMemcpy(d_a, h_a, N * sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(d_b, h_b, N * sizeof(int), cudaMemcpyHostToDevice);

add<<<(N + 255) / 256, 256>>>(d_a, d_b, d_c, N);

cudaMemcpy(h_c, d_c, N * sizeof(int), cudaMemcpyDeviceToHost);

std::cout << "Result: " << h_c[0] << ", " << h_c[N-1] << std::endl;

cudaFree(d_a); cudaFree(d_b); cudaFree(d_c);
delete[] h_a; delete[] h_b; delete[] h_c;
return 0;
}