C++ 与 Cuda 混合编程的CMakeList 写法 与例子

前言

一般的情况下，C与Cuda混合编程，可能通过 VS的UI方式，创建工程。但是，这种情况下效率不高，并且不能跨平台。因此，高级的方式，是使用CMakeList的方式，创建工程。 Windows情况下，可以CMakeList 成VisualStudio 编译器。

---

CMakeList的模板

通常，可用的一个模板，整理如下：

CMakeList 文件

# required cmake version
cmake_minimum_required(VERSION 3.4)

project(test_cuda)

# packages
find_package(CUDA)

# nvcc flags
set(CUDA_NVCC_FLAGS -gencode arch=compute_20,code=sm_20;-G;-g)

file(GLOB_RECURSE CURRENT_HEADERS  *.h *.hpp *.cuh)
file(GLOB CURRENT_SOURCES  *.cpp *.cu)

source_group("Include" FILES ${CURRENT_HEADERS}) 
source_group("Source" FILES ${CURRENT_SOURCES}) 

set(CMAKE_NVCC_FLAGS "CMAKE_NVCC_FLAGS -std=c++11")

CUDA_ADD_EXECUTABLE(test_cuda ${CURRENT_HEADERS} ${CURRENT_SOURCES})

特殊的地方:

• find_package(CUDA) 寻找cuda的库
• CUDA_ADD_EXECUTABLE(test_cuda ${CURRENT_HEADERS} ${CURRENT_SOURCES}) 生成可执行程序

---

测试的代码：

测试代码，分为 kernel.cu 的cuda 文件，以及C的主函数。

kernel.cu 文件

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include 

__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;
}

main.cpp 文件：

#include 
#include "cuda_runtime.h"
#include "device_launch_parameters.h"

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

int main()
{
	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]);
	printf("cuda工程中调用cpp成功！\n");
 
	// 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;
	}
	getchar(); //here we want the console to hold for a while
	return 0;
}

---

测试结果：

{1,2,3,4,5} + {10,20,30,40,50} = {11,22,33,44,55}
cuda工程中调用cpp成功！

测试的例子，是直接从其它的网站上拿过来的。比较能够说明 cMakeLists.txt 作用。

---

引用：

c++ 和cuda混合编程 VS2015 C++ 调用 cuda