conways-game-of-life-gpu/Conway_OpenCL/HelloWorld.cpp

#include <CL/cl.h>
#include <string.h>
#include <stdio.h>
#include <stdlib.h>
#include <iostream>
#include <string>
#include <fstream>
#include <random>
#include <ctime>
#include <SFML/Graphics.hpp>

#define SUCCESS 0
#define FAILURE 1

using namespace std;

/* convert the kernel file into a string */
int convertToString(const char *filename, std::string& s)
{
	size_t size;
	char*  str;
	std::fstream f(filename, (std::fstream::in | std::fstream::binary));

	if(f.is_open())
	{
		size_t fileSize;
		f.seekg(0, std::fstream::end);
		size = fileSize = (size_t)f.tellg();
		f.seekg(0, std::fstream::beg);
		str = new char[size+1];
		if(!str)
		{
			f.close();
			return 0;
		}

		f.read(str, fileSize);
		f.close();
		str[size] = '\0';
		s = str;
		delete[] str;
		return 0;
	}
	cout<<"Error: failed to open file\n:"<<filename<<endl;
	return FAILURE;
}

int main(int argc, char* argv[])
{

	
	// 1000 x 1000 grid
	std::mt19937 rng(time(NULL));
	std::uniform_int_distribution<int> rgen(0, 4); // 25% chance

	char* grid = new char[1000 * 1000 * 2];

	for (int i = 0; i < 1000 * 1000 * 2; i += 2) {
		if (rgen(rng) == 1) {
			grid[i] = 1;
			grid[i + 1] = 1;
		}
		else {
			grid[i] = 0;
			grid[i + 1] = 0;
		}
	}


	/*Step1: Getting platforms and choose an available one.*/
	cl_uint numPlatforms;	//the NO. of platforms
	cl_platform_id platform = NULL;	//the chosen platform
	cl_int	status = clGetPlatformIDs(0, NULL, &numPlatforms);
	if (status != CL_SUCCESS)
	{
		cout << "Error: Getting platforms!" << endl;
		return FAILURE;
	}

	/*For clarity, choose the first available platform. */
	if(numPlatforms > 0)
	{
		cl_platform_id* platforms = (cl_platform_id* )malloc(numPlatforms* sizeof(cl_platform_id));
		status = clGetPlatformIDs(numPlatforms, platforms, NULL);
		platform = platforms[0];
		free(platforms);
	}

	/*Step 2:Query the platform and choose the first GPU device if has one.Otherwise use the CPU as device.*/
	cl_uint				numDevices = 0;
	cl_device_id        *devices;
	status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 0, NULL, &numDevices);	
	if (numDevices == 0)	//no GPU available.
	{
		cout << "No GPU device available." << endl;
		cout << "Choose CPU as default device." << endl;
		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, 0, NULL, &numDevices);	
		devices = (cl_device_id*)malloc(numDevices * sizeof(cl_device_id));
		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, numDevices, devices, NULL);
	}
	else
	{
		devices = (cl_device_id*)malloc(numDevices * sizeof(cl_device_id));
		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, numDevices, devices, NULL);
	}
	

	/*Step 3: Create context.*/
	cl_context context = clCreateContext(NULL,1, devices,NULL,NULL,NULL);
	
	/*Step 4: Creating command queue associate with the context.*/
	cl_command_queue commandQueue = clCreateCommandQueue(context, devices[0], 0, NULL);

	/*Step 5: Create program object */
	const char *filename = "HelloWorld_Kernel.cl";
	string sourceStr;
	status = convertToString(filename, sourceStr);
	const char *source = sourceStr.c_str();
	size_t sourceSize[] = {strlen(source)};
	cl_program program = clCreateProgramWithSource(context, 1, &source, sourceSize, NULL);
	
	/*Step 6: Build program. */
	status=clBuildProgram(program, 1,devices,NULL,NULL,NULL);

	/*Step 7: Initial input,output for the host and create memory objects for the kernel*/
	const char* input = "GdkknVnqkc";
	size_t strlength = strlen(input);
	cout << "input string:" << endl;
	cout << input << endl;
	char *output = (char*) malloc(strlength + 1);

	cl_mem inputBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY|CL_MEM_COPY_HOST_PTR, (strlength + 1) * sizeof(char),(void *) input, NULL);
	cl_mem outputBuffer = clCreateBuffer(context, CL_MEM_WRITE_ONLY , (strlength + 1) * sizeof(char), NULL, NULL);

	/*Step 8: Create kernel object */
	cl_kernel kernel = clCreateKernel(program,"helloworld", NULL);

	/*Step 9: Sets Kernel arguments.*/
	status = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *)&inputBuffer);
	status = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *)&outputBuffer);
	
	// ======================================= START SFML ==========================================================


	// Spites for drawing, probably where the biggest slowdown is
	sf::RectangleShape live_node;
	live_node.setFillColor(sf::Color(145, 181, 207));
	live_node.setSize(sf::Vector2f(WINDOW_X / Node::x_bound, WINDOW_Y / Node::y_bound));

	// Init window, and loop data
	sf::RenderWindow window(sf::VideoMode(WINDOW_X, WINDOW_Y), "Classic Games");

	float step_size = 0.0005f;
	double frame_time = 0.0, elapsed_time = 0.0, delta_time = 0.0, accumulator_time = 0.0, current_time = 0.0;
	int frame_count = 0;

	std::stack<std::thread> thread_stack;

	while (window.isOpen()) {

		sf::Event event;
		while (window.pollEvent(event)) {
			if (event.type == sf::Event::Closed)
				window.close();
		}

		// Time keeping
		elapsed_time = elap_time();
		delta_time = elapsed_time - current_time;
		current_time = elapsed_time;
		if (delta_time > 0.02f)
			delta_time = 0.02f;
		accumulator_time += delta_time;

		while ((accumulator_time - step_size) >= step_size) {
			accumulator_time -= step_size;

			// Do nothing, FPS tied update()
		}

		// Implicit dead node color
		window.clear(sf::Color(49, 68, 72));

		for (int i = 0; i < 12; i++) {
			thread_stack.emplace(updateRange, &node_vec, (node_vec.size() / 12)* i, (node_vec.size() / 12)* (i + 1));
		}
		while (!thread_stack.empty()) {
			thread_stack.top().join();
			thread_stack.pop();
		}

		//for (int i = 0; i < node_vec.size(); i++) {
		//	node_vec.at(i).Update(&node_vec);
		//}

		for (int i = 0; i < node_vec.size(); i++) {
			node_vec[i].ShiftState();
		}

		for (int i = 0; i < node_vec.size(); i++) {
			if (node_vec.at(i).CurrentState() == true) {
				live_node.setPosition((i % Node::x_bound) * live_node.getGlobalBounds().width, (i / Node::x_bound) * live_node.getGlobalBounds().height);
				window.draw(live_node);
			}
			else {
				//dead_node.setPosition(i % Node::x_bound * dead_node.getGlobalBounds().width, i / Node::x_bound * dead_node.getGlobalBounds().height);
				//window.draw(live_node);
			}
		}

		frame_count++;
		window.display();


	// ======================================= END SFML ==========================================================

	/*Step 10: Running the kernel.*/
	size_t global_work_size[1] = {strlength};
	status = clEnqueueNDRangeKernel(commandQueue, kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL);

	/*Step 11: Read the cout put back to host memory.*/
	status = clEnqueueReadBuffer(commandQueue, outputBuffer, CL_TRUE, 0, strlength * sizeof(char), output, 0, NULL, NULL);
	
	output[strlength] = '\0';	//Add the terminal character to the end of output.
	cout << "\noutput string:" << endl;
	cout << output << endl;

	/*Step 12: Clean the resources.*/
	status = clReleaseKernel(kernel);				//Release kernel.
	status = clReleaseProgram(program);				//Release the program object.
	status = clReleaseMemObject(inputBuffer);		//Release mem object.
	status = clReleaseMemObject(outputBuffer);
	status = clReleaseCommandQueue(commandQueue);	//Release  Command queue.
	status = clReleaseContext(context);				//Release context.

	if (output != NULL)
	{
		free(output);
		output = NULL;
	}

	if (devices != NULL)
	{
		free(devices);
		devices = NULL;
	}

	std::cout<<"Passed!\n";
	return SUCCESS;
}