cuda学习第一步：样例程序

注:以下全部都是各个渠道查询得到
安装了vs2015和cuda的包以后就可以创建第一个cuda程序了
以下对这个第一个程序进行分析

//要使用  runtime API  的时候，需要  include cuda_runtime.h。
#include "cuda_runtime.h"
//查看device性能参数
#include "device_launch_parameters.h"

#include 
//函数声明
//这个我暂且把他叫链接cpu和gpu的一个小过道函数吧
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);
//调用gpu执行此函数
__global__ void addKernel(int *c, const int *a, const int *b)
{
    int i = threadIdx.x;
    c[i] = a[i] + b[i];
}

int main()
{
    const int arraySize = 6;
    const int a[arraySize] = { 1, 2, 3, 4, 5, 6 };
    const int b[arraySize] = { 10, 20, 30, 40, 50, 60 };
    int c[arraySize] = { 0 };

    // 通过过道函数去调用gpu执行加法工作
    cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);
    //出错判断
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addWithCuda failed!");
        return 1;
    }
//显示结果
    printf("{1,2,3,4,5,6} + {10,20,30,40,50,60} = {%d,%d,%d,%d,%d,  %d}\n",
        c[0], c[1], c[2], c[3], c[4], c[5]);

    // cudaDeviceReset must be called before exiting in order for profiling and
    // tracing tools such as Nsight and Visual Profiler to show complete traces.
    //cudaDeviceReset重置当前线程所关联过的当前设备的所有资源
如在调用cuda的过程中出现中途错误，需要提前退出程序，可以调用这个cudaDeviceReset来清空之前所关联过得所有资源。
    cudaStatus = cudaDeviceReset();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceReset failed!");
        return 1;
    }
    //用来观察结果
    getchar();
    return 0;
}

// Helper function for using CUDA to add vectors in parallel.
//辅助函数使用CUDA来并行地添加向量。
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size)
{
    int *dev_a = 0;
    int *dev_b = 0;
    int *dev_c = 0;
    cudaError_t cudaStatus;

    // Choose which GPU to run on, change this on a multi-GPU system.
    //使用了cudaSetDevice(0)这个操作，0表示能搜索到的第一个设备号,如果是多gpu可以改动这个0
    cudaStatus = cudaSetDevice(0);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");
        goto Error;
    }

    // Allocate GPU buffers for three vectors (two input, one output)    .
    //分配内存
    cudaStatus = cudaMalloc((void**)&dev_c, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    // Copy input vectors from host memory to GPU buffers.
    //复制数据a[]和b[]
    cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

    cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

    // Launch a kernel on the GPU with one thread for each element.
    //选择1个内核启动size个线程
    addKernel<<<1, size>>>(dev_c, dev_a, dev_b);

    // Check for any errors launching the kernel
    cudaStatus = cudaGetLastError();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));
        goto Error;
    }

    // cudaDeviceSynchronize waits for the kernel to finish, and returns
    // any errors encountered during the launch.
    cudaStatus = cudaDeviceSynchronize();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
        goto Error;
    }

    // Copy output vector from GPU buffer to host memory.
    cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

Error:
    cudaFree(dev_c);
    cudaFree(dev_a);
    cudaFree(dev_b);

    return cudaStatus;
}