Doing some OpenGL to OpenCL trickery here, OpenGL is now drawing but the pixel array isn't displaying right. Probably some alignment of the chars being weird

Conway_OpenCL/Conway.cpp

@@ -1,295 +0,0 @@
-#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>
-#include <windows.h>
-
-#define SUCCESS 0
-#define FAILURE 1
-
-float elap_time() {
-	static __int64 start = 0;
-	static __int64 frequency = 0;
-
-	if (start == 0) {
-		QueryPerformanceCounter((LARGE_INTEGER*)&start);
-		QueryPerformanceFrequency((LARGE_INTEGER*)&frequency);
-		return 0.0f;
-	}
-
-	__int64 counter = 0;
-	QueryPerformanceCounter((LARGE_INTEGER*)&counter);
-	return (float)((counter - start) / double(frequency));
-}
-
-// 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;
-	}
-	std::cout << "Error: failed to open file\n:" << filename << std::endl;
-	return FAILURE;
-}
-
-int main(int argc, char* argv[])
-{
-	int WINDOW_X = 1000;
-	int WINDOW_Y = 1000;
-	int GRID_WIDTH = WINDOW_X;
-	int GRID_HEIGHT = WINDOW_Y;
-	int WORKER_SIZE = 2000;
-
-	// ============================== OpenCL Setup ==================================================================
-
-	// Get the platforms
-	cl_uint numPlatforms;
-	cl_platform_id platform = NULL;
-	cl_int	status = clGetPlatformIDs(0, NULL, &numPlatforms); // Retrieve the number of platforms
-	if (status != CL_SUCCESS) {
-		std::cout << "Error: Getting platforms!" << std::endl;
-		return FAILURE;
-	}
-
-	 // Choose the first available platform
-	if(numPlatforms > 0) {
-		cl_platform_id* platforms = new cl_platform_id[numPlatforms]; 
-		status = clGetPlatformIDs(numPlatforms, platforms, NULL);	// Now populate the array with the platforms
-		platform = platforms[0];
-		delete platforms;
-	}
-
-	
-	cl_uint	numDevices = 0;
-	cl_device_id *devices;
-	status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 0, NULL, &numDevices);	
-	if (numDevices == 0) { //no GPU available.
-		std::cout << "No GPU device available." << std::endl;
-		std::cout << "Choose CPU as default device." << std::endl;
-		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, 0, NULL, &numDevices);	
-		devices = new cl_device_id[numDevices];
-		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, numDevices, devices, NULL);
-	}
-	else {
-		devices = new cl_device_id[numDevices];
-		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, numDevices, devices, NULL);
-	}
-	
-	cl_context context = clCreateContext(NULL,1, devices,NULL,NULL,NULL);
-	cl_command_queue commandQueue = clCreateCommandQueue(context, devices[0], 0, NULL);
-
-
-	// ============================== Kernel Compilation, Setup ====================================================
-	
-	// Read the kernel from the file to a string
-	const char *filename = "conway_kernel.cl";
-	std::string sourceStr;
-	status = convertToString(filename, sourceStr);
-
-	// Create a program with the source
-	const char *source = sourceStr.c_str();
-	size_t sourceSize[] = {strlen(source)};
-	cl_program program = clCreateProgramWithSource(context, 1, &source, sourceSize, NULL);
-	
-	// Build the program
-	status = clBuildProgram(program, 1,devices,NULL,NULL,NULL);
-
-	// If the build failed
-	if (status == CL_BUILD_PROGRAM_FAILURE) {
-
-		// Determine the size of the log
-		size_t log_size;
-		clGetProgramBuildInfo(program, devices[0], CL_PROGRAM_BUILD_LOG, 0, NULL, &log_size);
-
-		// Allocate memory for the log
-		char *log = new char[log_size];
-
-		// Get the log
-		clGetProgramBuildInfo(program, devices[0], CL_PROGRAM_BUILD_LOG, log_size, log, NULL);
-
-		// Print the log
-		std::cout << log << std::endl;
-	}
-
-	// Now create the kernel
-	cl_kernel front_kernel = clCreateKernel(program, "conway", NULL);
-	cl_kernel back_kernel = clCreateKernel(program, "conway", NULL);
-
-	// ======================================= Setup grid =========================================================
-
-	// Setup the rng
-	std::mt19937 rng(time(NULL));
-	std::uniform_int_distribution<int> rgen(0, 4); // 25% chance
-
-	// Init the grids
-	unsigned char* front_grid = new unsigned char[GRID_WIDTH * GRID_HEIGHT];
-
-	for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
-		if (rgen(rng) == 1) {
-			front_grid[i] = 1;
-		}
-		else {
-			front_grid[i] = 0;
-		}
-	}
-
-	unsigned char* back_grid = new unsigned char[GRID_WIDTH * GRID_HEIGHT];
-
-	for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
-		back_grid[i] = front_grid[i];
-	}
-
-	// ====================================== Setup SFML ==========================================================
-
-	// Init window, and loop data
-	sf::RenderWindow window(sf::VideoMode(GRID_WIDTH, GRID_HEIGHT), "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;
-
-	sf::Uint8* pixel_array = new sf::Uint8[WINDOW_X * WINDOW_Y * 4];
-
-	for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
-
-		pixel_array[i * 4] = 49; // R?
-		pixel_array[i * 4 + 1] = 68; // G?
-		pixel_array[i * 4 + 2] = 72; // B?
-		pixel_array[i * 4 + 3] = 255; // A?
-	}
-
-	sf::Texture texture;
-	texture.create(WINDOW_X, WINDOW_Y);
-	sf::Sprite sprite(texture);
-
-	// ========================================= Setup the buffers ==================================================
-
-	int err = 0;
-
-	cl_mem frontBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, GRID_WIDTH * GRID_HEIGHT * sizeof(char), (void*)front_grid, &err);
-	cl_mem backBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, GRID_WIDTH * GRID_HEIGHT * sizeof(char), (void*)back_grid, &err);
-	cl_mem pixelBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, GRID_WIDTH * GRID_HEIGHT * sizeof(char), (void*)pixel_array, &err);
-
-	cl_mem workerCountBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &WORKER_SIZE, &err);
-	cl_mem gridWidthBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &GRID_WIDTH, &err);
-	cl_mem gridHeightBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &GRID_HEIGHT, &err);
-
-	// Kernel args for front kernel
-	status = clSetKernelArg(front_kernel, 0, sizeof(cl_mem), (void *)&frontBuffer);
-	status = clSetKernelArg(front_kernel, 1, sizeof(cl_mem), (void *)&backBuffer);
-	status = clSetKernelArg(front_kernel, 2, sizeof(cl_mem), (void *)&pixelBuffer);
-
-	status = clSetKernelArg(front_kernel, 3, sizeof(cl_mem), (void *)&workerCountBuffer);
-	status = clSetKernelArg(front_kernel, 4, sizeof(cl_mem), (void *)&gridWidthBuffer);
-	status = clSetKernelArg(front_kernel, 5, sizeof(cl_mem), (void *)&gridHeightBuffer);
-
-	// Flipped kernel args for the back kernel
-	status = clSetKernelArg(back_kernel, 0, sizeof(cl_mem), (void *)&backBuffer); // Flipped
-	status = clSetKernelArg(back_kernel, 1, sizeof(cl_mem), (void *)&frontBuffer); // Flipped
-	status = clSetKernelArg(back_kernel, 2, sizeof(cl_mem), (void *)&pixelBuffer);
-
-	status = clSetKernelArg(back_kernel, 3, sizeof(cl_mem), (void *)&workerCountBuffer);
-	status = clSetKernelArg(back_kernel, 4, sizeof(cl_mem), (void *)&gridWidthBuffer);
-	status = clSetKernelArg(back_kernel, 5, sizeof(cl_mem), (void *)&gridHeightBuffer);
-
-	bool flipped = false;
-	// ===================================== Loop ==================================================================
-	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()
-		}
-
-		// ======================================= OpenCL Shtuff =============================================
-
-		// Update the data in GPU memory
-		//status = clEnqueueWriteBuffer(commandQueue, frontBuffer, CL_TRUE, 0, GRID_WIDTH * GRID_HEIGHT * 2 * sizeof(char), (void*)grid, NULL, 0, NULL);
-		
-		// Work size, for each y line
-		size_t global_work_size[1] = { WORKER_SIZE };
-
-		if (flipped) {
-			status = clEnqueueNDRangeKernel(commandQueue, back_kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL);
-			status = clEnqueueReadBuffer(commandQueue, pixelBuffer, CL_TRUE, 0, GRID_WIDTH * GRID_HEIGHT * 4 * sizeof(unsigned char), (void*)pixel_array, 0, NULL, NULL);
-		}
-		else {
-			status = clEnqueueNDRangeKernel(commandQueue, front_kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL);
-			status = clEnqueueReadBuffer(commandQueue, pixelBuffer, CL_TRUE, 0, GRID_WIDTH * GRID_HEIGHT * 4 * sizeof(unsigned char), (void*)pixel_array, 0, NULL, NULL);
-		}
-
-		flipped = !flipped;
-
-		texture.update(pixel_array);
-		window.draw(sprite);
-
-		frame_count++;
-		window.display();
-
-	}
-
-
-	
-	// Release the buffers
-	status = clReleaseMemObject(frontBuffer);
-	status = clReleaseMemObject(backBuffer);
-	status = clReleaseMemObject(pixelBuffer);
-	status = clReleaseMemObject(workerCountBuffer);
-	status = clReleaseMemObject(gridWidthBuffer);
-	status = clReleaseMemObject(gridHeightBuffer);
-
-	// And the program stuff
-	status = clReleaseKernel(front_kernel);				//Release kernel.
-	status = clReleaseProgram(program);				//Release the program object.
-	status = clReleaseCommandQueue(commandQueue);	//Release  Command queue.
-	status = clReleaseContext(context);				//Release context.
-
-	if (devices != NULL)
-	{
-		delete devices;
-		devices = NULL;
-	}
-
-	return SUCCESS;
-}

Conway_OpenCL/Conway.hpp

@@ -0,0 +1,401 @@
+#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>
+#include <windows.h>
+#include <GL/glew.h>
+#include <GLFW/glfw3.h>
+#include "Shader.hpp"
+
+#define SUCCESS 0
+#define FAILURE 1
+
+float elap_time() {
+	static __int64 start = 0;
+	static __int64 frequency = 0;
+
+	if (start == 0) {
+		QueryPerformanceCounter((LARGE_INTEGER*)&start);
+		QueryPerformanceFrequency((LARGE_INTEGER*)&frequency);
+		return 0.0f;
+	}
+
+	__int64 counter = 0;
+	QueryPerformanceCounter((LARGE_INTEGER*)&counter);
+	return (float)((counter - start) / double(frequency));
+}
+
+// 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;
+	}
+	std::cout << "Error: failed to open file\n:" << filename << std::endl;
+	return FAILURE;
+}
+
+void key_callback(GLFWwindow* window, int key, int scancode, int action, int mode) {
+	if (key == GLFW_KEY_ESCAPE && action == GLFW_PRESS)
+		glfwSetWindowShouldClose(window, GL_TRUE);
+}
+
+int main(int argc, char* argv[])
+{
+	int WINDOW_X = 1000;
+	int WINDOW_Y = 1000;
+	int GRID_WIDTH = WINDOW_X;
+	int GRID_HEIGHT = WINDOW_Y;
+	int WORKER_SIZE = 2000;
+
+	// ============================== OpenCL Setup ==================================================================
+
+	// Get the platforms
+	cl_uint numPlatforms;
+	cl_platform_id platform = NULL;
+	cl_int	status = clGetPlatformIDs(0, NULL, &numPlatforms); // Retrieve the number of platforms
+	if (status != CL_SUCCESS) {
+		std::cout << "Error: Getting platforms!" << std::endl;
+		return FAILURE;
+	}
+
+	 // Choose the first available platform
+	if(numPlatforms > 0) {
+		cl_platform_id* platforms = new cl_platform_id[numPlatforms]; 
+		status = clGetPlatformIDs(numPlatforms, platforms, NULL);	// Now populate the array with the platforms
+		platform = platforms[0];
+		delete platforms;
+	}
+
+	cl_uint	numDevices = 0;
+	cl_device_id *devices;
+	status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 0, NULL, &numDevices);	
+	if (numDevices == 0) { //no GPU available.
+		std::cout << "No GPU device available." << std::endl;
+		std::cout << "Choose CPU as default device." << std::endl;
+		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, 0, NULL, &numDevices);	
+		devices = new cl_device_id[numDevices];
+		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, numDevices, devices, NULL);
+	}
+	else {
+		devices = new cl_device_id[numDevices];
+		status = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, numDevices, devices, NULL);
+	}
+	
+	cl_context context = clCreateContext(NULL,1, devices,NULL,NULL,NULL);
+	cl_command_queue commandQueue = clCreateCommandQueue(context, devices[0], 0, NULL);
+
+
+	// ============================== Kernel Compilation, Setup ====================================================
+	
+	// Read the kernel from the file to a string
+	const char *compute_kernel_filename = "conway_compute.cl";
+	const char *align_kernel_filename = "conway_align.cl";
+
+	std::string compute_kernel_string;
+	std::string align_kernel_string;
+
+	convertToString(compute_kernel_filename, compute_kernel_string);
+	convertToString(compute_kernel_filename, align_kernel_string);
+
+	// Create a program with the source
+	const char *compute_source = compute_kernel_string.c_str();
+	const char *align_source = align_kernel_string.c_str();
+
+	size_t compute_source_size[] = {strlen(compute_source)};
+	size_t align_source_size[] = { strlen(align_source) };
+
+	cl_program compute_program = clCreateProgramWithSource(context, 1, &compute_source, compute_source_size, NULL);
+	cl_program align_program = clCreateProgramWithSource(context, 1, &align_source, align_source_size, NULL);
+
+	// Build the compute program
+	status = clBuildProgram(compute_program, 1, devices, NULL, NULL, NULL);
+
+	if (status == CL_BUILD_PROGRAM_FAILURE) {
+
+		size_t log_size;
+		clGetProgramBuildInfo(compute_program, devices[0], CL_PROGRAM_BUILD_LOG, 0, NULL, &log_size);
+		char *log = new char[log_size];
+
+		clGetProgramBuildInfo(compute_program, devices[0], CL_PROGRAM_BUILD_LOG, log_size, log, NULL);
+
+		std::cout << log << std::endl;
+	}
+
+	// Build the align program
+	status = clBuildProgram(align_program, 1, devices, NULL, NULL, NULL);
+	
+	if (status == CL_BUILD_PROGRAM_FAILURE) {
+
+		size_t log_size;
+		clGetProgramBuildInfo(align_program, devices[0], CL_PROGRAM_BUILD_LOG, 0, NULL, &log_size);
+		char *log = new char[log_size];
+
+		clGetProgramBuildInfo(align_program, devices[0], CL_PROGRAM_BUILD_LOG, log_size, log, NULL);
+
+		std::cout << log << std::endl;
+	}
+
+	// Now create the kernels
+	cl_kernel front_kernel = clCreateKernel(compute_program, "conway_compute", NULL);
+	cl_kernel back_kernel = clCreateKernel(align_program, "conway_align", NULL);
+
+	// ======================================= Setup OpenGL =======================================================
+	
+	glfwInit();
+	
+	glfwWindowHint(GLFW_CONTEXT_VERSION_MAJOR, 3);
+	glfwWindowHint(GLFW_CONTEXT_VERSION_MINOR, 3);
+	glfwWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE);
+	glfwWindowHint(GLFW_RESIZABLE, GL_FALSE);
+
+	GLFWwindow* gl_window = glfwCreateWindow(GRID_WIDTH, GRID_HEIGHT, "GPU accelerated life", nullptr, nullptr);
+	glfwMakeContextCurrent(gl_window);
+
+	glfwSetKeyCallback(gl_window, key_callback);
+	
+	glewExperimental = GL_TRUE;
+	glewInit();
+
+	glViewport(0, 0, GRID_WIDTH, GRID_HEIGHT);
+
+	glClearColor(0.2f, 0.3f, 0.3f, 1.0f);
+
+	Shader ourShader("Z:\\VS_Projects\\Conway_OpenCL\\Conway_OpenCL\\vertex_shader.sh", "Z:\\VS_Projects\\Conway_OpenCL\\Conway_OpenCL\\fragment_shader.sh");
+
+	GLfloat vertices[] = {
+		// Positions          // Colors           // Texture Coords
+		1.0f,  1.0f, 0.0f,   1.0f, 0.0f, 0.0f,   1.0f, 1.0f, // Top Right
+		1.0f, -1.0f, 0.0f,   0.0f, 1.0f, 0.0f,   1.0f, 0.0f, // Bottom Right
+		-1.0f, -1.0f, 0.0f,   0.0f, 0.0f, 1.0f,   0.0f, 0.0f, // Bottom Left
+		-1.0f,  1.0f, 0.0f,   1.0f, 1.0f, 0.0f,   0.0f, 1.0f  // Top Left 
+	};
+	GLuint indices[] = {
+		0, 1, 3, // First Triangle
+		1, 2, 3  // Second Triangle
+	};
+
+	GLuint VBO, VAO, EBO;
+	glGenVertexArrays(1, &VAO);
+	glGenBuffers(1, &VBO);
+	glGenBuffers(1, &EBO);
+
+	// Bind the Vertex Array Object first, then bind and set vertex buffer(s) and attribute pointer(s).
+	glBindVertexArray(VAO);
+
+	glBindBuffer(GL_ARRAY_BUFFER, VBO);
+	glBufferData(GL_ARRAY_BUFFER, sizeof(vertices), vertices, GL_STATIC_DRAW);
+
+	glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, EBO);
+	glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(indices), indices, GL_STATIC_DRAW);
+
+
+	// Position attribute
+	glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 8 * sizeof(GLfloat), (GLvoid*)0);
+	glEnableVertexAttribArray(0);
+	// Color attribute
+	glVertexAttribPointer(1, 3, GL_FLOAT, GL_FALSE, 8 * sizeof(GLfloat), (GLvoid*)(3 * sizeof(GLfloat)));
+	glEnableVertexAttribArray(1);
+	// TexCoord attribute
+	glVertexAttribPointer(2, 2, GL_FLOAT, GL_FALSE, 8 * sizeof(GLfloat), (GLvoid*)(6 * sizeof(GLfloat)));
+	glEnableVertexAttribArray(2);
+
+	glBindVertexArray(0); // Unbind VAO
+
+
+	// ======================================= Setup grid =========================================================
+
+	// Setup the rng
+	std::mt19937 rng(time(NULL));
+	std::uniform_int_distribution<int> rgen(0, 4); // 25% chance
+
+	// Init the grids
+	unsigned char* front_grid = new unsigned char[GRID_WIDTH * GRID_HEIGHT];
+
+	for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
+		if (rgen(rng) == 1) {
+			front_grid[i] = 1;
+		}
+		else {
+			front_grid[i] = 0;
+		}
+	}
+
+	unsigned char* back_grid = new unsigned char[GRID_WIDTH * GRID_HEIGHT];
+
+	for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
+		back_grid[i] = front_grid[i];
+	}
+
+	// ====================================== Setup Rendering ==========================================================
+
+	unsigned char* pixel_array = new sf::Uint8[WINDOW_X * WINDOW_Y * 4];
+
+	for (int i = 0; i < GRID_WIDTH * GRID_HEIGHT; i++) {
+
+		pixel_array[i * 4] = 49; // R?
+		pixel_array[i * 4 + 1] = 68; // G?
+		pixel_array[i * 4 + 2] = 72; // B?
+		pixel_array[i * 4 + 3] = 255; // A?
+	}
+
+	GLuint texture;
+
+	glGenTextures(1, &texture);
+	glBindTexture(GL_TEXTURE_2D, texture);
+
+	//////////////////////////
+
+	glTexEnvf(GL_TEXTURE_ENV, GL_TEXTURE_ENV_MODE, GL_REPLACE);
+
+	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_DECAL);
+	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_DECAL);
+
+	// when texture area is small, bilinear filter the closest mipmap
+	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR_MIPMAP_NEAREST);
+	// when texture area is large, bilinear filter the first mipmap
+	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
+
+	// texture should tile
+	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
+	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
+
+	glTexImage2D(GL_TEXTURE_2D, 0, GL_RGB, GRID_WIDTH, GRID_HEIGHT, 0, GL_RGB, GL_UNSIGNED_BYTE, pixel_array);
+
+	glGenerateMipmap(GL_TEXTURE_2D);
+
+
+//	delete pixel_array;
+
+
+	//////////////////////
+
+	// ========================================= Setup the buffers ==================================================
+
+	int err = 0;
+
+	cl_mem frontBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, GRID_WIDTH * GRID_HEIGHT * sizeof(char), (void*)front_grid, &err);
+	cl_mem backBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, GRID_WIDTH * GRID_HEIGHT * sizeof(char), (void*)back_grid, &err);
+	//cl_mem pixelBuffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_COPY_HOST_PTR, GRID_WIDTH * GRID_HEIGHT * sizeof(char), (void*)pixel_array, &err);
+
+	cl_mem workerCountBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &WORKER_SIZE, &err);
+	cl_mem gridWidthBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &GRID_WIDTH, &err);
+	cl_mem gridHeightBuffer = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(int), &GRID_HEIGHT, &err);
+
+	// Kernel args for front kernel
+	status = clSetKernelArg(front_kernel, 0, sizeof(cl_mem), (void *)&frontBuffer);
+	status = clSetKernelArg(front_kernel, 1, sizeof(cl_mem), (void *)&backBuffer);
+	//status = clSetKernelArg(front_kernel, 2, sizeof(cl_mem), (void *)&pixelBuffer);
+
+	status = clSetKernelArg(front_kernel, 3, sizeof(cl_mem), (void *)&workerCountBuffer);
+	status = clSetKernelArg(front_kernel, 4, sizeof(cl_mem), (void *)&gridWidthBuffer);
+	status = clSetKernelArg(front_kernel, 5, sizeof(cl_mem), (void *)&gridHeightBuffer);
+
+	// Flipped kernel args for the back kernel
+	status = clSetKernelArg(back_kernel, 0, sizeof(cl_mem), (void *)&backBuffer); // Flipped
+	status = clSetKernelArg(back_kernel, 1, sizeof(cl_mem), (void *)&frontBuffer); // Flipped
+	//status = clSetKernelArg(back_kernel, 2, sizeof(cl_mem), (void *)&pixelBuffer);
+
+	status = clSetKernelArg(back_kernel, 3, sizeof(cl_mem), (void *)&workerCountBuffer);
+	status = clSetKernelArg(back_kernel, 4, sizeof(cl_mem), (void *)&gridWidthBuffer);
+	status = clSetKernelArg(back_kernel, 5, sizeof(cl_mem), (void *)&gridHeightBuffer);
+
+
+	// ===================================== Loop ==================================================================
+
+	while (!glfwWindowShouldClose(gl_window)) {
+
+		//glfwPollEvents();
+		//glClear(GL_COLOR_BUFFER_BIT);
+
+		// ======================================= OpenCL Shtuff ===================================================
+
+		// Update the data in GPU memory
+		//status = clEnqueueWriteBuffer(commandQueue, frontBuffer, CL_TRUE, 0, GRID_WIDTH * GRID_HEIGHT * 2 * sizeof(char), (void*)grid, NULL, 0, NULL);
+
+		// Work size, for each y line
+		size_t global_work_size[1] = { WORKER_SIZE };
+
+
+		status = clEnqueueNDRangeKernel(commandQueue, back_kernel, 1, NULL, global_work_size, NULL, 0, NULL, NULL);
+		//status = clEnqueueReadBuffer(commandQueue, pixelBuffer, CL_TRUE, 0, GRID_WIDTH * GRID_HEIGHT * 4 * sizeof(unsigned char), (void*)pixel_array, 0, NULL, NULL);
+		
+
+		// ======================================= Rendering Shtuff =================================================
+
+		glfwPollEvents();
+
+		// Render
+		// Clear the colorbuffer
+		glClearColor(0.2f, 0.3f, 0.3f, 1.0f);
+		glClear(GL_COLOR_BUFFER_BIT);
+
+		glActiveTexture(GL_TEXTURE0);
+		glBindTexture(GL_TEXTURE_2D, texture);
+		glUniform1i(glGetUniformLocation(ourShader.Program, "ourTexture1"), 0);
+
+		// Draw the triangle
+		ourShader.Use();
+		glBindVertexArray(VAO);
+		glDrawElements(GL_TRIANGLES, 6, GL_UNSIGNED_INT, 0);
+		glBindVertexArray(0);
+
+		// Swap the screen buffers
+		glfwSwapBuffers(gl_window);
+
+
+
+	}
+
+	glfwTerminate();
+	
+	// Release the buffers
+	status = clReleaseMemObject(frontBuffer);
+	status = clReleaseMemObject(backBuffer);
+	//status = clReleaseMemObject(pixelBuffer);
+	status = clReleaseMemObject(workerCountBuffer);
+	status = clReleaseMemObject(gridWidthBuffer);
+	status = clReleaseMemObject(gridHeightBuffer);
+
+	// And the program stuff
+	status = clReleaseKernel(front_kernel);
+	status = clReleaseProgram(compute_program);
+	status = clReleaseProgram(align_program);
+	status = clReleaseCommandQueue(commandQueue);
+	status = clReleaseContext(context);
+
+	if (devices != NULL)
+	{
+		delete devices;
+		devices = NULL;
+	}
+
+	return SUCCESS;
+}

Conway_OpenCL/Conway_OpenCL.vcxproj

@@ -70,27 +70,27 @@
     <LinkIncremental>false</LinkIncremental>
     <OutDir>$(SolutionDir)bin\x86\$(Configuration)\</OutDir>
     <IntDir>temp\x86\$(Configuration)\</IntDir>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\Win32;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <OutDir>$(SolutionDir)bin\x86\$(Configuration)\</OutDir>
     <IntDir>temp\x86\$(Configuration)\</IntDir>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\Win32;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
     <OutDir>$(SolutionDir)bin\x86_64\$(Configuration)\</OutDir>
     <IntDir>temp\x86_64\$(Configuration)\</IntDir>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\x64;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
     <OutDir>$(SolutionDir)bin\x86_64\$(Configuration)\</OutDir>
     <IntDir>temp\x86_64\$(Configuration)\</IntDir>
     <LinkIncremental>false</LinkIncremental>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\x64;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <ClCompile>
@@ -110,15 +110,15 @@
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win32\;$(AMDAPPSDKROOT)\lib\x86\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glew32.lib;glfw3.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
       <AdditionalOptions> /machine:X86 /debug %(AdditionalOptions)</AdditionalOptions>
       <ImportLibrary>$(SolutionDir)bin/x86/Debug/HelloWorld.lib</ImportLibrary>
     </Link>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
@@ -137,15 +137,15 @@
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win64\;$(AMDAPPSDKROOT)\lib\x86_64\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glfw3.lib;glew32.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <ImportLibrary>$(SolutionDir)bin/x86_64/Debug/HelloWorld.lib</ImportLibrary>
       <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
       <AdditionalOptions> /machine:x64 /debug %(AdditionalOptions)</AdditionalOptions>
     </Link>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
@@ -171,7 +171,7 @@
       </EnableCOMDATFolding>
       <OptimizeReferences>
       </OptimizeReferences>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glew32.lib;glfw3.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win32\;$(AMDAPPSDKROOT)\lib\x86\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
       <SubSystem>Console</SubSystem>
       <ImportLibrary>$(SolutionDir)bin/x86/Release/HelloWorld.lib</ImportLibrary>
@@ -182,8 +182,8 @@
       <LinkLibraryDependencies>false</LinkLibraryDependencies>
     </ProjectReference>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
@@ -211,7 +211,7 @@
       <OptimizeReferences>
       </OptimizeReferences>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win64\;$(AMDAPPSDKROOT)\lib\x86_64\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glfw3.lib;glew32.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <LinkTimeCodeGeneration />
       <ImportLibrary>$(SolutionDir)bin/x86_64/Release/HelloWorld.lib</ImportLibrary>
@@ -219,16 +219,21 @@
       <AdditionalOptions> /machine:x64 %(AdditionalOptions)</AdditionalOptions>
     </Link>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemGroup>
-    <ClCompile Include="Conway.cpp" />
+    <ClCompile Include="Conway.hpp" />
   </ItemGroup>
   <ItemGroup>
     <None Include="conway_compute.cl" />
     <None Include="conway_align.cl" />
+    <None Include="fragment_shader.sh" />
+    <None Include="vertex_shader.sh" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="Shader.hpp" />
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">

Conway_OpenCL/Shader.hpp

@@ -0,0 +1,90 @@
+#ifndef SHADER_H
+#define SHADER_H
+
+#include <string>
+#include <fstream>
+#include <sstream>
+#include <iostream>
+
+#include <GL/glew.h>
+
+class Shader {
+public:
+	GLuint Program;
+	// Constructor generates the shader on the fly
+	Shader(const GLchar* vertexPath, const GLchar* fragmentPath) {
+		// 1. Retrieve the vertex/fragment source code from filePath
+		std::string vertexCode;
+		std::string fragmentCode;
+		std::ifstream vShaderFile;
+		std::ifstream fShaderFile;
+		// ensures ifstream objects can throw exceptions:
+		vShaderFile.exceptions(std::ifstream::badbit);
+		fShaderFile.exceptions(std::ifstream::badbit);
+		try {
+			// Open files
+			vShaderFile.open(vertexPath);
+			fShaderFile.open(fragmentPath);
+			std::stringstream vShaderStream, fShaderStream;
+			// Read file's buffer contents into streams
+			vShaderStream << vShaderFile.rdbuf();
+			fShaderStream << fShaderFile.rdbuf();
+			// close file handlers
+			vShaderFile.close();
+			fShaderFile.close();
+			// Convert stream into string
+			vertexCode = vShaderStream.str();
+			fragmentCode = fShaderStream.str();
+		}
+		catch (std::ifstream::failure e) {
+			std::cout << "ERROR::SHADER::FILE_NOT_SUCCESFULLY_READ" << std::endl;
+		}
+		const GLchar* vShaderCode = vertexCode.c_str();
+		const GLchar * fShaderCode = fragmentCode.c_str();
+
+		GLint success = 0;
+		GLchar infoLog[512];
+
+		// Vertex Shader
+		GLuint vertex = glCreateShader(GL_VERTEX_SHADER);
+		glShaderSource(vertex, 1, &vShaderCode, NULL);
+		glCompileShader(vertex);
+		// Print compile errors if any
+		glGetShaderiv(vertex, GL_COMPILE_STATUS, &success);
+		if (!success) {
+			glGetShaderInfoLog(vertex, 512, NULL, infoLog);
+			std::cout << "ERROR::SHADER::VERTEX::COMPILATION_FAILED\n" << infoLog << std::endl;
+		}
+		// Fragment Shader
+		GLuint fragment = glCreateShader(GL_FRAGMENT_SHADER);
+		glShaderSource(fragment, 1, &fShaderCode, NULL);
+		glCompileShader(fragment);
+		// Print compile errors if any
+		glGetShaderiv(fragment, GL_COMPILE_STATUS, &success);
+		if (!success) {
+			glGetShaderInfoLog(fragment, 512, NULL, infoLog);
+			std::cout << "ERROR::SHADER::FRAGMENT::COMPILATION_FAILED\n" << infoLog << std::endl;
+		}
+		// Shader Program
+		this->Program = glCreateProgram();
+		glAttachShader(this->Program, vertex);
+		glAttachShader(this->Program, fragment);
+		glLinkProgram(this->Program);
+		// Print linking errors if any
+		glGetProgramiv(this->Program, GL_LINK_STATUS, &success);
+		if (!success) {
+			glGetProgramInfoLog(this->Program, 512, NULL, infoLog);
+			std::cout << "ERROR::SHADER::PROGRAM::LINKING_FAILED\n" << infoLog << std::endl;
+		}
+		// Delete the shaders as they're linked into our program now and no longer necessery
+		glDeleteShader(vertex);
+		glDeleteShader(fragment);
+
+	}
+	// Uses the current shader
+	void Use() {
+		glUseProgram(this->Program);
+	}
+};
+
+#endif

Conway_OpenCL/conway_align.cl

@@ -1,4 +1,4 @@
-__kernel void conway(__global unsigned char* front_grid, __global unsigned char* rear_grid, __global unsigned char* pixel_out, __global int* num_workers, __global int* grid_width, __global int* grid_height){
+__kernel void conway_align(__global unsigned char* front_grid, __global unsigned char* rear_grid, __global unsigned char* pixel_out, __global int* num_workers, __global int* grid_width, __global int* grid_height){
 
 
 

Conway_OpenCL/conway_compute.cl

@@ -1,4 +1,4 @@
-__kernel void conway(__global unsigned char* front_grid, __global unsigned char* rear_grid, __global unsigned char* pixel_out, __global int* num_workers, __global int* grid_width, __global int* grid_height)
+__kernel void conway_compute(__global unsigned char* front_grid, __global unsigned char* rear_grid, __global unsigned char* pixel_out, __global int* num_workers, __global int* grid_width, __global int* grid_height)
 {
 	// Caclulate the start and end range that this worker will be calculating
 

Conway_OpenCL/fragment_shader.sh

@@ -0,0 +1,15 @@
+#version 330 core
+in vec3 ourColor;
+in vec2 TexCoord;
+
+out vec4 color;
+
+// Texture samplers
+uniform sampler2D ourTexture1;
+uniform sampler2D ourTexture2;
+
+void main()
+{
+	// Linearly interpolate between both textures (second texture is only slightly combined)
+	color = mix(texture(ourTexture1, TexCoord), texture(ourTexture2, TexCoord), 0.2);
+}

Conway_OpenCL/vertex_shader.sh

@@ -0,0 +1,16 @@
+#version 330 core
+layout (location = 0) in vec3 position;
+layout (location = 1) in vec3 color;
+layout (location = 2) in vec2 texCoord;
+
+out vec3 ourColor;
+out vec2 TexCoord;
+
+void main()
+{
+	gl_Position = vec4(position, 1.0f);
+	ourColor = color;
+	// We swap the y-axis by substracing our coordinates from 1. This is done because most images have the top y-axis inversed with OpenGL's top y-axis.
+	// TexCoord = texCoord;
+	TexCoord = vec2(texCoord.x, 1.0 - texCoord.y);
+}

Conway_OpenCL/~AutoRecover.Conway_OpenCL.vcxproj

@@ -70,27 +70,27 @@
     <LinkIncremental>false</LinkIncremental>
     <OutDir>$(SolutionDir)bin\x86\$(Configuration)\</OutDir>
     <IntDir>temp\x86\$(Configuration)\</IntDir>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\Win32;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <OutDir>$(SolutionDir)bin\x86\$(Configuration)\</OutDir>
     <IntDir>temp\x86\$(Configuration)\</IntDir>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx32\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\Win32;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN32\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
     <OutDir>$(SolutionDir)bin\x86_64\$(Configuration)\</OutDir>
     <IntDir>temp\x86_64\$(Configuration)\</IntDir>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\x64;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
     <OutDir>$(SolutionDir)bin\x86_64\$(Configuration)\</OutDir>
     <IntDir>temp\x86_64\$(Configuration)\</IntDir>
     <LinkIncremental>false</LinkIncremental>
-    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;$(IncludePath)</IncludePath>
-    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;$(LibraryPath)</LibraryPath>
+    <IncludePath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\include;Z:\Cpp_Libs\glew-1.13.0\include;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\include;$(IncludePath)</IncludePath>
+    <LibraryPath>Z:\Cpp_Libs\SFML-Visual_Studio2015RCx64\lib;Z:\Cpp_Libs\glew-1.13.0\lib\Release\x64;Z:\Cpp_Libs\glfw-3.1.2.bin.WIN64\lib-vc2015;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <ClCompile>
@@ -110,15 +110,15 @@
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win32\;$(AMDAPPSDKROOT)\lib\x86\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glew32.lib;glfw3.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
       <AdditionalOptions> /machine:X86 /debug %(AdditionalOptions)</AdditionalOptions>
       <ImportLibrary>$(SolutionDir)bin/x86/Debug/HelloWorld.lib</ImportLibrary>
     </Link>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
@@ -137,15 +137,15 @@
     <Link>
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win64\;$(AMDAPPSDKROOT)\lib\x86_64\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glfw3.lib;glew32.lib;sfml-graphics-d.lib;sfml-audio-d.lib;sfml-network-d.lib;sfml-system-d.lib;sfml-window-d.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <ImportLibrary>$(SolutionDir)bin/x86_64/Debug/HelloWorld.lib</ImportLibrary>
       <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
       <AdditionalOptions> /machine:x64 /debug %(AdditionalOptions)</AdditionalOptions>
     </Link>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
@@ -171,7 +171,7 @@
       </EnableCOMDATFolding>
       <OptimizeReferences>
       </OptimizeReferences>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glew32.lib;glfw3.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win32\;$(AMDAPPSDKROOT)\lib\x86\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
       <SubSystem>Console</SubSystem>
       <ImportLibrary>$(SolutionDir)bin/x86/Release/HelloWorld.lib</ImportLibrary>
@@ -182,8 +182,8 @@
       <LinkLibraryDependencies>false</LinkLibraryDependencies>
     </ProjectReference>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
@@ -211,7 +211,7 @@
       <OptimizeReferences>
       </OptimizeReferences>
       <AdditionalLibraryDirectories>..\..\..\..\lib\win64\;$(AMDAPPSDKROOT)\lib\x86_64\;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>kernel32.lib;user32.lib;gdi32.lib;winspool.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;comdlg32.lib;advapi32.lib;OpenCL.lib;opengl32.lib;glfw3.lib;glew32.lib;sfml-graphics.lib;sfml-audio.lib;sfml-network.lib;sfml-system.lib;sfml-window.lib;%(AdditionalDependencies)</AdditionalDependencies>
       <SubSystem>Console</SubSystem>
       <LinkTimeCodeGeneration />
       <ImportLibrary>$(SolutionDir)bin/x86_64/Release/HelloWorld.lib</ImportLibrary>
@@ -219,16 +219,21 @@
       <AdditionalOptions> /machine:x64 %(AdditionalOptions)</AdditionalOptions>
     </Link>
     <PostBuildEvent>
-      <Command>copy conway_kernel.cl "$(OutDir)conway_kernel.cl" /Y
-	  </Command>
+      <Command>copy conway_compute.cl "$(OutDir)conway_kernel.cl" /Y
+copy conway_align.cl "$(OutDir)conway_kernel.cl" /Y</Command>
     </PostBuildEvent>
   </ItemDefinitionGroup>
   <ItemGroup>
-    <ClCompile Include="Conway.cpp" />
+    <ClCompile Include="Conway.hpp" />
   </ItemGroup>
   <ItemGroup>
     <None Include="conway_compute.cl" />
     <None Include="conway_align.cl" />
+    <None Include="fragment_shader.sh" />
+    <None Include="vertex_shader.sh" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="Shader.hpp" />
   </ItemGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
   <ImportGroup Label="ExtensionTargets">