VS上運行CUDA，並在NVDIA顯卡安裝的CUDA中運行OpenCL

1. 首先安裝NVIADIA的最新顯卡驅動

到NVIADIA的官網下載

http://www.nvidia.cn/page/home.html

2. 安裝CUDA 

到CUDA的官網下載

https://developer.nvidia.com/cuda-zone

3. 配置VS的CUDA環境

（1）安裝好後在環境變量中會自動加上CUDA的路徑，不需要自己手動配置

（2）進入VS項目右鍵，屬性->C/C++->常規->附加包含目錄，添加如下路徑

$(CUDA_PATH)代表環境變量的值

（3）進入VS項目右鍵，屬性->鏈接器->添加庫目錄，添加如下：

（4）直接新建CUDA項目測試效果，如果可以則運行成功

（5）如果失敗發生衝突，可以在：屬性->鏈接器->輸入->忽略待定庫，添加LIBCMT

（6）如果在VS2008中添加cuda文件時，選擇第三個匹配的自定義生成規則，然後在編譯cu文件即可

4.配置VS的OpenCL環境

（1）在完成佈置3的條件下，增加：屬性->鏈接器->輸入->添加依賴項，添加如下OpenCL.lib即可

（2）測試OpenCL的demo

核函數文件：HelloWorld.cl

__kernel void hello_kernel(__global const float *a,
    __global const float *b,
    __global float *result)
{
    int gid = get_global_id(0);

    result[gid] = a[gid] + b[gid];
}

main.cpp文件：main.cpp

#include <iostream>
#include <fstream>
#include <sstream>
#include <time.h>

using namespace std;
#ifdef __APPLE__
#include <OpenCL/cl.h>
#else
#include <CL/cl.h>
#endif

const int ARRAY_SIZE = 1000;


//  選擇平臺並創建上下文
cl_context CreateContext()
{
	cl_int errNum;
	cl_uint numPlatforms;
	cl_platform_id firstPlatformId;
	cl_context context = NULL;

	//選擇第一個可用的平臺
	errNum = clGetPlatformIDs(1, &firstPlatformId, &numPlatforms);
	if (errNum != CL_SUCCESS || numPlatforms <= 0)
	{
		std::cerr << "Failed to find any OpenCL platforms." << std::endl;
		return NULL;
	}

	// 創建一個opencl上下文，成功則使用GUP上下文，否則使用cpu
	cl_context_properties contextProperties[] =
	{
		CL_CONTEXT_PLATFORM,
		(cl_context_properties)firstPlatformId,
		0
	};
	context = clCreateContextFromType(contextProperties, CL_DEVICE_TYPE_GPU,
		NULL, NULL, &errNum);
	if (errNum != CL_SUCCESS)
	{
		std::cout << "Could not create GPU context, trying CPU..." << std::endl;
		context = clCreateContextFromType(contextProperties, CL_DEVICE_TYPE_CPU,
			NULL, NULL, &errNum);
		if (errNum != CL_SUCCESS)
		{
			std::cerr << "Failed to create an OpenCL GPU or CPU context." << std::endl;
			return NULL;
		}
	}

	return context;
}


//選擇第一個可用的設備並創建一個命令隊列
cl_command_queue CreateCommandQueue(cl_context context, cl_device_id *device)
{
	cl_int errNum;
	cl_device_id *devices;
	cl_command_queue commandQueue = NULL;
	size_t deviceBufferSize = -1;

	//這個clGetContextInfo獲得設備緩衝區的大小
	errNum = clGetContextInfo(context, CL_CONTEXT_DEVICES, 0, NULL, &deviceBufferSize);
	if (errNum != CL_SUCCESS)
	{
		std::cerr << "Failed call to clGetContextInfo(...,GL_CONTEXT_DEVICES,...)";
		return NULL;
	}

	if (deviceBufferSize <= 0)
	{
		std::cerr << "No devices available.";
		return NULL;
	}

	//爲設備緩衝區分配內存，這個clGetContextInfo用來獲得上下文中所有可用的設備
	devices = new cl_device_id[deviceBufferSize / sizeof(cl_device_id)];
	errNum = clGetContextInfo(context, CL_CONTEXT_DEVICES, deviceBufferSize, devices, NULL);
	if (errNum != CL_SUCCESS)
	{
		delete[] devices;
		std::cerr << "Failed to get device IDs";
		return NULL;
	}
	char    deviceName[512];
	char    deviceVendor[512];
	char    deviceVersion[512];
	errNum = clGetDeviceInfo(devices[0], CL_DEVICE_VENDOR, sizeof(deviceVendor),
		deviceVendor, NULL);
	errNum |= clGetDeviceInfo(devices[0], CL_DEVICE_NAME, sizeof(deviceName),
		deviceName, NULL);
	errNum |= clGetDeviceInfo(devices[0], CL_DEVICE_VERSION, sizeof(deviceVersion),
		deviceVersion, NULL);

	printf("OpenCL Device Vendor = %s,  OpenCL Device Name = %s,  OpenCL Device Version = %s\n", deviceVendor, deviceName, deviceVersion);
	// 在這個例子中，我們只選擇第一個可用的設備。在實際的程序，你可能會使用所有可用的設備或基於OpenCL設備查詢選擇性能最高的設備
	commandQueue = clCreateCommandQueue(context, devices[0], 0, NULL);
	if (commandQueue == NULL)
	{
		delete[] devices;
		std::cerr << "Failed to create commandQueue for device 0";
		return NULL;
	}

	*device = devices[0];
	delete[] devices;
	return commandQueue;
}

//從磁盤加載內核源文件並創建一個程序對象
cl_program CreateProgram(cl_context context, cl_device_id device, const char* fileName)
{
	cl_int errNum;
	cl_program program;

	std::ifstream kernelFile(fileName, std::ios::in);
	if (!kernelFile.is_open())
	{
		std::cerr << "Failed to open file for reading: " << fileName << std::endl;
		return NULL;
	}

	std::ostringstream oss;
	oss << kernelFile.rdbuf();

	std::string srcStdStr = oss.str();
	const char *srcStr = srcStdStr.c_str();
	//創建程序對象
	program = clCreateProgramWithSource(context, 1,
		(const char**)&srcStr,
		NULL, NULL);
	if (program == NULL)
	{
		std::cerr << "Failed to create CL program from source." << std::endl;
		return NULL;
	}
	//編譯內核源代碼
	errNum = clBuildProgram(program, 0, NULL, NULL, NULL, NULL);
	if (errNum != CL_SUCCESS)
	{
		// 編譯失敗可以通過clGetProgramBuildInfo獲取日誌
		char buildLog[16384];
		clGetProgramBuildInfo(program, device, CL_PROGRAM_BUILD_LOG,
			sizeof(buildLog), buildLog, NULL);

		std::cerr << "Error in kernel: " << std::endl;
		std::cerr << buildLog;
		clReleaseProgram(program);
		return NULL;
	}

	return program;
}


//創建內存對象
bool CreateMemObjects(cl_context context, cl_mem memObjects[3],
					  float *a, float *b)
{
	//創建內存對象
	memObjects[0] = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR,
		sizeof(float)* ARRAY_SIZE, a, NULL);
	memObjects[1] = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR,
		sizeof(float)* ARRAY_SIZE, b, NULL);
	memObjects[2] = clCreateBuffer(context, CL_MEM_READ_WRITE,
		sizeof(float)* ARRAY_SIZE, NULL, NULL);

	if (memObjects[0] == NULL || memObjects[1] == NULL || memObjects[2] == NULL)
	{
		std::cerr << "Error creating memory objects." << std::endl;
		return false;
	}

	return true;
}

//清理任何創建OpenCL的資源
void Cleanup(cl_context context, cl_command_queue commandQueue,
			 cl_program program, cl_kernel kernel, cl_mem memObjects[3])
{
	for (int i = 0; i < 3; i++)
	{
		if (memObjects[i] != 0)
			clReleaseMemObject(memObjects[i]);
	}
	if (commandQueue != 0)
		clReleaseCommandQueue(commandQueue);

	if (kernel != 0)
		clReleaseKernel(kernel);

	if (program != 0)
		clReleaseProgram(program);

	if (context != 0)
		clReleaseContext(context);

}

//主函數
int main(int argc, char** argv)
{
	cl_context context = 0;
	cl_command_queue commandQueue = 0;
	cl_program program = 0;
	cl_device_id device = 0;
	cl_kernel kernel = 0;
	cl_mem memObjects[3] = { 0, 0, 0 };
	cl_int errNum;

	// 創建opencl上下文和第一個可用平臺
	context = CreateContext();
	if (context == NULL)
	{
		std::cerr << "Failed to create OpenCL context." << std::endl;
		return 1;
	}

	// 在創建的一個上下文中選擇第一個可用的設備並創建一個命令隊列
	commandQueue = CreateCommandQueue(context, &device);
	if (commandQueue == NULL)
	{
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// 創建一個程序對象 HelloWorld.cl kernel source
	program = CreateProgram(context, device, "HelloWorld.cl");
	if (program == NULL)
	{
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// 創建內核
	kernel = clCreateKernel(program, "hello_kernel", NULL);
	if (kernel == NULL)
	{
		std::cerr << "Failed to create kernel" << std::endl;
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// 創建一個將用作參數內核內存中的對象。首先創建將被用來將參數存儲到內核主機存儲器陣列
	float result[ARRAY_SIZE];
	float a[ARRAY_SIZE];
	float b[ARRAY_SIZE];
	for (int i = 0; i < ARRAY_SIZE; i++)
	{
		a[i] = (float)i;
		b[i] = (float)(i * 2);
	}

	if (!CreateMemObjects(context, memObjects, a, b))
	{
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// 設置內核參數、執行內核並讀回結果
	errNum = clSetKernelArg(kernel, 0, sizeof(cl_mem), &memObjects[0]);
	errNum |= clSetKernelArg(kernel, 1, sizeof(cl_mem), &memObjects[1]);
	errNum |= clSetKernelArg(kernel, 2, sizeof(cl_mem), &memObjects[2]);
	if (errNum != CL_SUCCESS)
	{
		std::cerr << "Error setting kernel arguments." << std::endl;
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	size_t globalWorkSize[1] = { ARRAY_SIZE };//讓之等於數組的大小
	size_t localWorkSize[1] = { 1 };  //讓之等於1

	// 利用命令隊列使將在設備執行的內核排隊
	
	errNum = clEnqueueNDRangeKernel(commandQueue, kernel, 1, NULL,
		globalWorkSize, localWorkSize,
		0, NULL, NULL);
	if (errNum != CL_SUCCESS)
	{
		std::cerr << "Error queuing kernel for execution." << std::endl;
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}
	
	std::cout << "Executed program succesfully." << std::endl;
	// Read the output buffer back to the Host
	
	
	errNum = clEnqueueReadBuffer(commandQueue, memObjects[2], CL_TRUE,
		0, ARRAY_SIZE * sizeof(float), result,
		0, NULL, NULL);
	if (errNum != CL_SUCCESS)
	{
		std::cerr << "Error reading result buffer." << std::endl;
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}
	

	 //輸出結果
	for (int i = 0; i < ARRAY_SIZE; i++)
	{
		std::cout << result[i] << " ";
	}
	std::cout << std::endl;
	std::cout << "Executed program succesfully." << std::endl;
	Cleanup(context, commandQueue, program, kernel, memObjects);

	return 0;
}

配置成功則運行成功如下：