#include <stdio.h>
#define N 16
// 1. Define the kernel
__global__ void add(int *a, int *b, int *c) {
  int tid = blockIdx.x; // handle the data at this index
  if (tid < N)
	c[tid] = a[tid] + b[tid];
}

// 2. Declare the main method
int main(void) {
  int a[N], b[N], c[N];
  int *dev_a, *dev_b, *dev_c;
  // 3. allocate the memory on the GPU
  cudaMalloc((void **)&dev_a, N * sizeof(int));
  cudaMalloc((void **)&dev_b, N * sizeof(int));
  cudaMalloc((void **)&dev_c, N * sizeof(int));
  // 4. fill the arrays 'a' and 'b' on the CPU
  for (int i = 0; i < N; i++) {
    a[i] = -i;
    b[i] = i * i;
  }
  // 5. copy the arrays 'a' and 'b' to the GPU
  cudaMemcpy(dev_a, a, N * sizeof(int), cudaMemcpyHostToDevice);
  cudaMemcpy(dev_b, b, N * sizeof(int), cudaMemcpyHostToDevice);
  // 6. launch the kernel on the GPU
  add<<<N, 1>>>(dev_a, dev_b, dev_c);
  // 7. copy the array 'c' back from the GPU to the CPU
  cudaMemcpy(c, dev_c, N * sizeof(int), cudaMemcpyDeviceToHost);
  // 8. the results through the CPU
  for (int i = 0; i < N; i++) {
    printf("%d + %d = %d\n", a[i], b[i], c[i]);
  }
  // 9. free the memory allocated on the GPU
  cudaFree(dev_a);
  cudaFree(dev_b);
  cudaFree(dev_c);
  return 0;
}