CUDA 第一个程序

环境配置：

CUDA从官网下载，但是国内时常会下到只有几KB的安装包其实是抽风了，network也时常出错，感觉最稳妥的还是看运气下local的

下好之后在cmd下输入nvcc --version就可以看到是否安装成功了，也要保证CUDA_PATH的路径是对的

接下来是在VS中新建工程，为了通用性考虑建立一个空的项目

然后是项目属性：

Include Directories:$(CUDA_PATH)\include

Libarary Directories:$(CUDA_PATH)\lib\Win32 (Win32 或是 x64)

Linker:Additional Dependencies:
cuda.lib
cudadevrt.lib
cudart.lib
cudart_static.lib
nvcuvid.lib //这项有可能导致编译错误？
OpenCL.lib

右键项目：

添加.cu文件一定要从这里添加，将cpp改后缀可能会出现一些奇怪的问题

右键.cu 属性：

 

接下来是代码了。

首先要注意的一点是.cu和.cpp是用的不同的编译器，也就是说CUDA的__global__函数和出现的<<<1,size>>>等c++编译器识别不了的关键字必须放在.cu文件里。

而且c++文件包括".h",".cpp"都不能直接引用.cu文件！，编译无法通过，可能会报一个无法识别"<"的错误。

解决方法是在.cu的helper function也就是入口函数前加 extern "C"

并在cpp里extern "C" 这个函数 注意不能include .cu文件

完整文件结构可以如下：

CUDAHelloWorld.cu：

#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];
}

// Helper function for using CUDA to add vectors in parallel.
extern "C"
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.
    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)    .
    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.
    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.
    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;
}

CUDAHelloWorldEntry.h:

#pragma once
#include <iostream>
#include <stdio.h>
#include <stdlib.h>
#include "cuda_runtime.h"  
#include "device_launch_parameters.h"  

class CUDAWrapper
{
public:
	int CUDAHelloWorld();
};

CUDAHelloWorldEntry.cpp:

#include "CUDAHelloWorldEntry.h"

extern "C"
cudaError_t addWithCuda(int* c, const int* a, const int* b, unsigned int size);

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

    // Add vectors in parallel.
    cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addWithCuda failed!");
        return 1;
    }

    printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",
        c[0], c[1], c[2], c[3], c[4]);

    // cudaDeviceReset must be called before exiting in order for profiling and
    // tracing tools such as Nsight and Visual Profiler to show complete traces.
    cudaStatus = cudaDeviceReset();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceReset failed!");
        return 1;
    }

    system("pause");
    return 0;
}

最后只要在需要的地方例如main函数调用

CUDAWrapper cw;
cw.CUDAHelloWorld();

就可以运行第一个CUDA程序了。