#include <stdio.h>
#include <stdlib.h>

__global__ void add(int *a, int *b, int *c) {
  *c = *a + *b;
}

int main(int argc, char** argv) {

  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 = sizeof(int);

  // Allocate space for device copies of a, b, c
  fprintf(stdout, "... allocating memory ...\n");
  cudaMalloc((void **)&d_a, size);
  cudaMalloc((void **)&d_b, size);
  cudaMalloc((void **)&d_c, size);

  // Setup input values
  a = 2;
  b = 7;

  // Copy inputs to device
  fprintf(stdout, "... copy from host to the GPU ...\n");
  cudaMemcpy(d_a, &a, size, cudaMemcpyHostToDevice);
  cudaMemcpy(d_b, &b, size, cudaMemcpyHostToDevice);

  // Launch add() kernel on GPU
  fprintf(stdout, "... launch the kernel ...\n");
  add<<<1,1>>>(d_a, d_b, d_c);
  cudaDeviceSynchronize();
 
  // Copy result back to host
  fprintf(stdout, "... copy data from GPU to host ...\n");
  cudaMemcpy(&c, d_c, size, cudaMemcpyDeviceToHost);
  cudaDeviceSynchronize();

  // Cleanup
  fprintf(stdout, "... clean up ...\n");
  cudaFree(d_a); cudaFree(d_b); cudaFree(d_c);

  // print the result
  //
  fprintf(stdout, "sum = %d\n", c);

 return 0;
}