#include <stdio.h>

 __global__ void saxpy(int n, float a, float *x, float *y)

 //__global__关键字，表示是将要在GPU里并行运行的核函数

 {

   int i = blockIdx.x*blockDim.x + threadIdx.x;

   if (i < n)

     y[i] = a*x[i] + y[i];

 }

 int main()

 {

   int N = ;

   float *x, *y, *d_x, *d_y;             //都是指针，指向数组所在的内存/显存空间

   x = (float*)malloc(N*sizeof(float));  //在内存中为x,y分配空间

   y = (float*)malloc(N*sizeof(float));

   cudaMalloc(&d_x, N*sizeof(float));    //在显存中为d_x,d_y分配空间

   cudaMalloc(&d_y, N*sizeof(float));

   for (int i = ; i < N; i++)

   {

     x[i] = (float)i;

     y[i] = 2.0f;

   }

   cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);

   cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);

   //将内存中x,y指向的数组空间拷贝到显存中d_x,d_y指向的数组空间

   saxpy<<<,N>>>(N, 10.0f, d_x, d_y);

   //1个block，每个block里N个thread

   cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);

   //将显存中计算好的d_y指向的数组空间拷贝到内存中y指向的数组空间

   for (int i = ; i < N; i++)

     printf("%d  %.3f\n",i,y[i]);

   getchar();

 }

 /*  kernel.cu   */

 //cuda系函数必须放在cu文件里

 #include "cuda_runtime.h"

 #include "device_launch_parameters.h"

 #include <stdio.h>

 __global__ void addKernel(int *c, const int *a, const int *b)

 {

     int i = threadIdx.x;

     c[i] = a[i] + b[i];

 }

 //cpp中不能直接调用核函数，所以在cu文件中还得写一个接口，负责分配内存等

 void addWithCuda(int *c, const int *a, const int *b, unsigned int size)

 {

     int *dev_a = ;

     int *dev_b = ;

     int *dev_c = ;

     // Choose which GPU to run on, change this on a multi-GPU system.

     cudaSetDevice();

     // Allocate GPU buffers for three vectors (two input, one output)    .

     cudaMalloc((void**)&dev_c, size * sizeof(int));

     cudaMalloc((void**)&dev_a, size * sizeof(int));

     cudaMalloc((void**)&dev_b, size * sizeof(int));

     // Copy input vectors from host memory to GPU buffers.

     cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);

     cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);

     // Launch a kernel on the GPU with one thread for each element.

     addKernel<<<, size>>>(dev_c, dev_a, dev_b);

     // Copy output vector from GPU buffer to host memory.

     cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);

     cudaFree(dev_c);

     cudaFree(dev_a);

     cudaFree(dev_b);

     cudaDeviceReset();

 }

 //-------------------------------------------------------------------------------

 /* Source.cpp  */

 #include"cstdio"

 #include"cstring"

 extern void addWithCuda(int *c, const int *a, const int *b, unsigned int size);

 //.cpp是由C编译器来编译的。C编译器里不允许#include一个cu文件（不资词）

 //若要引用cu里的函数，在main.cpp里外部extern声明一下，让VS转为NVCC编译器处理。

 int main()

 {

     const int arraySize = ;

     const int a[arraySize] = { , , , ,  };

     const int b[arraySize] = { , , , ,  };

     int c[arraySize] = {  };

     addWithCuda(c, a, b, arraySize);

     printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",

         c[], c[], c[], c[], c[]);

     getchar();

     return ;

 }