// Host kód
#define CL_USE_DEPRECATED_OPENCL_1_2_APIS
#include <iostream>
#include <fstream>
#include <sstream>

#include <CL/cl.h>
#include <windows.h>

//
//  Tömb méret
//
const int ARRAY_SIZE = 1000;

//
//  OpenCL környezet létrehozása a legelső platformon, akár GPU, akár CPU
//
cl_context CreateContext()
{
	cl_int errNum;
	cl_uint numPlatforms;
	cl_platform_id firstPlatformId;
	cl_context context = NULL;

	// Egy OpenCL platform kiválasztása, itt az első van kiválasztva

	errNum = clGetPlatformIDs(1, &firstPlatformId, &numPlatforms);
	if (errNum != CL_SUCCESS || numPlatforms <= 0)
	{
		std::cerr << "Failed to find any OpenCL platforms." << std::endl;
		return NULL;
	}

	// Környezet létrehozása a platformon
	// Először GPU-st próbál, ha nem sikerül, akkor CPU-s környezet jön létre
	
	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;
}

//
//  Parancssor létrehozása az első eszközön az adott környezetben
//
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;

	// Eszköz puffer méretének lekérdezése
	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;
	}

	// Eszköz puffer lefoglalása a memóriában
	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;
	}

	// Az első lehetséges eszköz kiválasztása és a hozzátartozó parancssor létrehozása
	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;
}

//
//  OpenCL program létrehozása a kernel forrásból
//
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();
	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;
	}

	errNum = clBuildProgram(program, 0, NULL, NULL, NULL, NULL);
	if (errNum != CL_SUCCESS)
	{
		// Hiba okának a kiderítése
		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;
}

//
//  Memória objektumok létrehozása az eredmény és bemeneti argumentumok számára
//
bool CreateMemObjects(cl_context context, cl_mem memObjects[3],
	float *a, float *b)
{
	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;
}

//
//  OpenCL erőforrások felszabadítása 
//
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);

}

//
//	main program
//
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;

	// Opencl környezet létrehozása az első platformon
	context = CreateContext();
	if (context == NULL)
	{
		std::cerr << "Failed to create OpenCL context." << std::endl;
		return 1;
	}

	// Parancssor létrehozása az adott környezeten
	commandQueue = CreateCommandQueue(context, &device);
	if (commandQueue == NULL)
	{
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// OpenCL program létrehozása a device.cl kernel forrásból
	program = CreateProgram(context, device, "device.cl");
	if (program == NULL)
	{
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// OpenCL kernel létrehozása - belépési függvény megadása
	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;
	}

	// Memoria objektumok létrehozása 
	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;
	}

	// Kernel argumentumok beállítása
	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 };
	size_t localWorkSize[1] = { 1 };

	LARGE_INTEGER perfFrequency;
	LARGE_INTEGER performanceCountNDRangeStart;
	LARGE_INTEGER performanceCountNDRangeStop;

	QueryPerformanceCounter(&performanceCountNDRangeStart);
	
	// A kernel elhelyezése a végrehajtási sorban
	errNum = clEnqueueNDRangeKernel(commandQueue, kernel, 1, NULL,
		globalWorkSize, localWorkSize,
		0, NULL, NULL);
		
	clFinish(commandQueue);

	QueryPerformanceCounter(&performanceCountNDRangeStop);

	QueryPerformanceFrequency(&perfFrequency);
	printf("NDRange performance counter time %f ms.\n",
		1000.0f*(float)(performanceCountNDRangeStop.QuadPart - performanceCountNDRangeStart.QuadPart) / (float)perfFrequency.QuadPart);

	if (errNum != CL_SUCCESS)
	{
		std::cerr << "Error queuing kernel for execution." << std::endl;
		Cleanup(context, commandQueue, program, kernel, memObjects);
		return 1;
	}

	// A kimeneti adatok betöltése a host memóriaba
	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;
	}

	// Eredmény kiírasa
	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;
}

Forrás letöltése itt.

// OpenCL kód - két vektor összege

__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];
}

Forrás letöltése itt.