please share Cuda sample

__global__ void Addition(int *a,int *b,int *c)
{

   *c = *a + *b;
}
int main()
{
  int a,b,c;
  int *dev_a,*dev_b,*dev_c;
  int size = sizeof(int);



  cudaMalloc((void**)&dev_a, size);
  cudaMalloc((void**)&dev_b, size);
  cudaMalloc((void**)&dev_c, size);

  a=12,b=4;

  cudaMemcpy(dev_a, &a,sizeof(int), cudaMemcpyHostToDevice);
  cudaMemcpy(dev_b, &b,sizeof(int), cudaMemcpyHostToDevice);

  Addition<<< 1,1 >>>(dev_a,dev_b,dev_c);
  cudaMemcpy(&c, dev_c,size, cudaMemcpyDeviceToHost);
   //printf("%d + %d is %d\n",a,b,c);

   cudaFree(&dev_a);
   cudaFree(&dev_b);
   cudaFree(&dev_c);

   printf("%d\n", c);
   getch();
   return 0;


}

__global__ void Addition(int *a,int *b,int *c)
{

   *c = *a + *b;
}
int main()
{
  int a,b,c;
  int *dev_a,*dev_b,*dev_c;
  int size = sizeof(int);



  cudaMalloc((void**)&dev_a, size);
  cudaMalloc((void**)&dev_b, size);
  cudaMalloc((void**)&dev_c, size);

  a=12,b=4;

  cudaMemcpy(dev_a, &a,sizeof(int), cudaMemcpyHostToDevice);
  cudaMemcpy(dev_b, &b,sizeof(int), cudaMemcpyHostToDevice);

  Addition<<< 1,1 >>>(dev_a,dev_b,dev_c);
  cudaMemcpy(&c, dev_c,size, cudaMemcpyDeviceToHost);
   //printf("%d + %d is %d\n",a,b,c);

   cudaFree(&dev_a);
   cudaFree(&dev_b);
   cudaFree(&dev_c);

   printf("%d\n", c);
   getch();
   return 0;


}

#include <stdio.h>
#include <conio.h>
#include <cuda.h>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>