// Sample by Sascha Willems
// Contact: webmaster@saschawillems.de

#define GLFW_INCLUDE_VULKAN
#include <GLFW/glfw3.h>

#define GLM_FORCE_RADIANS
#include <glm/glm.hpp>
#include <glm/gtc/matrix_transform.hpp>

#include <iostream>
#include <fstream>
#include <stdexcept>
#include <algorithm>
#include <chrono>
#include <vector>
#include <cstring>
#include <cstdlib>
#include <cstdint>
#include <limits>
#include <array>
#include <optional>
#include <set>
#include <random>

const uint32_t WIDTH = 800;
const uint32_t HEIGHT = 600;

const uint32_t PARTICLE_COUNT = 8192;

const int MAX_FRAMES_IN_FLIGHT = 2;

const std::vector<const char*> validationLayers = {
    "VK_LAYER_KHRONOS_validation"
};

const std::vector<const char*> deviceExtensions = {
    VK_KHR_SWAPCHAIN_EXTENSION_NAME
};

#ifdef NDEBUG
const bool enableValidationLayers = false;
#else
const bool enableValidationLayers = true;
#endif

VkResult CreateDebugUtilsMessengerEXT(VkInstance instance, const VkDebugUtilsMessengerCreateInfoEXT* pCreateInfo, const VkAllocationCallbacks* pAllocator, VkDebugUtilsMessengerEXT* pDebugMessenger) {
    auto func = (PFN_vkCreateDebugUtilsMessengerEXT) vkGetInstanceProcAddr(instance, "vkCreateDebugUtilsMessengerEXT");
    if (func != nullptr) {
        return func(instance, pCreateInfo, pAllocator, pDebugMessenger);
    } else {
        return VK_ERROR_EXTENSION_NOT_PRESENT;
    }
}

void DestroyDebugUtilsMessengerEXT(VkInstance instance, VkDebugUtilsMessengerEXT debugMessenger, const VkAllocationCallbacks* pAllocator) {
    auto func = (PFN_vkDestroyDebugUtilsMessengerEXT) vkGetInstanceProcAddr(instance, "vkDestroyDebugUtilsMessengerEXT");
    if (func != nullptr) {
        func(instance, debugMessenger, pAllocator);
    }
}

struct QueueFamilyIndices {
    std::optional<uint32_t> graphicsAndComputeFamily;
    std::optional<uint32_t> presentFamily;

    bool isComplete() {
        return graphicsAndComputeFamily.has_value() && presentFamily.has_value();
    }
};

struct SwapChainSupportDetails {
    VkSurfaceCapabilitiesKHR capabilities;
    std::vector<VkSurfaceFormatKHR> formats;
    std::vector<VkPresentModeKHR> presentModes;
};

struct UniformBufferObject {
    float deltaTime = 1.0f;
};

struct Particle {
    glm::vec2 position;
    glm::vec2 velocity;
    glm::vec4 color;

    static VkVertexInputBindingDescription getBindingDescription() {
        VkVertexInputBindingDescription bindingDescription{};
        bindingDescription.binding = 0;
        bindingDescription.stride = sizeof(Particle);
        bindingDescription.inputRate = VK_VERTEX_INPUT_RATE_VERTEX;

        return bindingDescription;
    }

    static std::array<VkVertexInputAttributeDescription, 2> getAttributeDescriptions() {
        std::array<VkVertexInputAttributeDescription, 2> attributeDescriptions{};

        attributeDescriptions[0].binding = 0;
        attributeDescriptions[0].location = 0;
        attributeDescriptions[0].format = VK_FORMAT_R32G32_SFLOAT;
        attributeDescriptions[0].offset = offsetof(Particle, position);

        attributeDescriptions[1].binding = 0;
        attributeDescriptions[1].location = 1;
        attributeDescriptions[1].format = VK_FORMAT_R32G32B32A32_SFLOAT;
        attributeDescriptions[1].offset = offsetof(Particle, color);

        return attributeDescriptions;
    }
};

class ComputeShaderApplication {
public:
    void run() {
        initWindow();
        initVulkan();
        mainLoop();
        cleanup();
    }

private:
    GLFWwindow* window;

    VkInstance instance;
    VkDebugUtilsMessengerEXT debugMessenger;
    VkSurfaceKHR surface;

    VkPhysicalDevice physicalDevice = VK_NULL_HANDLE;
    VkDevice device;

    VkQueue graphicsQueue;
    VkQueue computeQueue;
    VkQueue presentQueue;

    VkSwapchainKHR swapChain;
    std::vector<VkImage> swapChainImages;
    VkFormat swapChainImageFormat;
    VkExtent2D swapChainExtent;
    std::vector<VkImageView> swapChainImageViews;
    std::vector<VkFramebuffer> swapChainFramebuffers;

    VkRenderPass renderPass;
    VkPipelineLayout pipelineLayout;
    VkPipeline graphicsPipeline;

    VkDescriptorSetLayout computeDescriptorSetLayout;
    VkPipelineLayout computePipelineLayout;
    VkPipeline computePipeline;

    VkCommandPool commandPool;

    std::vector<VkBuffer> shaderStorageBuffers;
    std::vector<VkDeviceMemory> shaderStorageBuffersMemory;

    std::vector<VkBuffer> uniformBuffers;
    std::vector<VkDeviceMemory> uniformBuffersMemory;
    std::vector<void*> uniformBuffersMapped;

    VkDescriptorPool descriptorPool;
    std::vector<VkDescriptorSet> computeDescriptorSets;

    std::vector<VkCommandBuffer> commandBuffers;
    std::vector<VkCommandBuffer> computeCommandBuffers;

    std::vector<VkSemaphore> imageAvailableSemaphores;
    std::vector<VkSemaphore> renderFinishedSemaphores;
    std::vector<VkSemaphore> computeFinishedSemaphores;
    std::vector<VkFence> inFlightFences;
    std::vector<VkFence> computeInFlightFences;
    uint32_t currentFrame = 0;

    float lastFrameTime = 0.0f;

    bool framebufferResized = false;

    double lastTime = 0.0f;

    void initWindow() {
        glfwInit();

        glfwWindowHint(GLFW_CLIENT_API, GLFW_NO_API);

        window = glfwCreateWindow(WIDTH, HEIGHT, "Vulkan", nullptr, nullptr);
        glfwSetWindowUserPointer(window, this);
        glfwSetFramebufferSizeCallback(window, framebufferResizeCallback);

        lastTime = glfwGetTime();
    }

    static void framebufferResizeCallback(GLFWwindow* window, int width, int height) {
        auto app = reinterpret_cast<ComputeShaderApplication*>(glfwGetWindowUserPointer(window));
        app->framebufferResized = true;
    }

    void initVulkan() {
        createInstance();
        setupDebugMessenger();
        createSurface();
        pickPhysicalDevice();
        createLogicalDevice();
        createSwapChain();
        createImageViews();
        createRenderPass();
        createComputeDescriptorSetLayout();
        createGraphicsPipeline();
        createComputePipeline();
        createFramebuffers();
        createCommandPool();
        createShaderStorageBuffers();
        createUniformBuffers();
        createDescriptorPool();
        createComputeDescriptorSets();
        createCommandBuffers();
        createComputeCommandBuffers();
        createSyncObjects();
    }

    void mainLoop() {
        while (!glfwWindowShouldClose(window)) {
            glfwPollEvents();
            drawFrame();
            // We want to animate the particle system using the last frames time to get smooth, frame-rate independent animation
            double currentTime = glfwGetTime();
            lastFrameTime = (currentTime - lastTime) * 1000.0;
            lastTime = currentTime;
        }

        vkDeviceWaitIdle(device);
    }

    void cleanupSwapChain() {
        for (auto framebuffer : swapChainFramebuffers) {
            vkDestroyFramebuffer(device, framebuffer, nullptr);
        }

        for (auto imageView : swapChainImageViews) {
            vkDestroyImageView(device, imageView, nullptr);
        }

        vkDestroySwapchainKHR(device, swapChain, nullptr);
    }

    void cleanup() {
        cleanupSwapChain();

        vkDestroyPipeline(device, graphicsPipeline, nullptr);
        vkDestroyPipelineLayout(device, pipelineLayout, nullptr);

        vkDestroyPipeline(device, computePipeline, nullptr);
        vkDestroyPipelineLayout(device, computePipelineLayout, nullptr);

        vkDestroyRenderPass(device, renderPass, nullptr);

        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            vkDestroyBuffer(device, uniformBuffers[i], nullptr);
            vkFreeMemory(device, uniformBuffersMemory[i], nullptr);
        }

        vkDestroyDescriptorPool(device, descriptorPool, nullptr);
      
        vkDestroyDescriptorSetLayout(device, computeDescriptorSetLayout, nullptr);

        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            vkDestroyBuffer(device, shaderStorageBuffers[i], nullptr);
            vkFreeMemory(device, shaderStorageBuffersMemory[i], nullptr);
        }

        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            vkDestroySemaphore(device, renderFinishedSemaphores[i], nullptr);
            vkDestroySemaphore(device, imageAvailableSemaphores[i], nullptr);
            vkDestroySemaphore(device, computeFinishedSemaphores[i], nullptr);
            vkDestroyFence(device, inFlightFences[i], nullptr);
            vkDestroyFence(device, computeInFlightFences[i], nullptr);
        }

        vkDestroyCommandPool(device, commandPool, nullptr);

        vkDestroyDevice(device, nullptr);

        if (enableValidationLayers) {
            DestroyDebugUtilsMessengerEXT(instance, debugMessenger, nullptr);
        }

        vkDestroySurfaceKHR(instance, surface, nullptr);
        vkDestroyInstance(instance, nullptr);

        glfwDestroyWindow(window);

        glfwTerminate();
    }

    void recreateSwapChain() {
        int width = 0, height = 0;
        glfwGetFramebufferSize(window, &width, &height);
        while (width == 0 || height == 0) {
            glfwGetFramebufferSize(window, &width, &height);
            glfwWaitEvents();
        }

        vkDeviceWaitIdle(device);

        cleanupSwapChain();

        createSwapChain();
        createImageViews();
        createFramebuffers();
    }

    void createInstance() {
        if (enableValidationLayers && !checkValidationLayerSupport()) {
            throw std::runtime_error("validation layers requested, but not available!");
        }

        VkApplicationInfo appInfo{};
        appInfo.sType = VK_STRUCTURE_TYPE_APPLICATION_INFO;
        appInfo.pApplicationName = "Hello Triangle";
        appInfo.applicationVersion = VK_MAKE_VERSION(1, 0, 0);
        appInfo.pEngineName = "No Engine";
        appInfo.engineVersion = VK_MAKE_VERSION(1, 0, 0);
        appInfo.apiVersion = VK_API_VERSION_1_0;

        VkInstanceCreateInfo createInfo{};
        createInfo.sType = VK_STRUCTURE_TYPE_INSTANCE_CREATE_INFO;
        createInfo.pApplicationInfo = &appInfo;

        auto extensions = getRequiredExtensions();
        createInfo.enabledExtensionCount = static_cast<uint32_t>(extensions.size());
        createInfo.ppEnabledExtensionNames = extensions.data();

        VkDebugUtilsMessengerCreateInfoEXT debugCreateInfo{};
        if (enableValidationLayers) {
            createInfo.enabledLayerCount = static_cast<uint32_t>(validationLayers.size());
            createInfo.ppEnabledLayerNames = validationLayers.data();

            populateDebugMessengerCreateInfo(debugCreateInfo);
            createInfo.pNext = (VkDebugUtilsMessengerCreateInfoEXT*) &debugCreateInfo;
        } else {
            createInfo.enabledLayerCount = 0;

            createInfo.pNext = nullptr;
        }

        if (vkCreateInstance(&createInfo, nullptr, &instance) != VK_SUCCESS) {
            throw std::runtime_error("failed to create instance!");
        }
    }

    void populateDebugMessengerCreateInfo(VkDebugUtilsMessengerCreateInfoEXT& createInfo) {
        createInfo = {};
        createInfo.sType = VK_STRUCTURE_TYPE_DEBUG_UTILS_MESSENGER_CREATE_INFO_EXT;
        createInfo.messageSeverity = VK_DEBUG_UTILS_MESSAGE_SEVERITY_VERBOSE_BIT_EXT | VK_DEBUG_UTILS_MESSAGE_SEVERITY_WARNING_BIT_EXT | VK_DEBUG_UTILS_MESSAGE_SEVERITY_ERROR_BIT_EXT;
        createInfo.messageType = VK_DEBUG_UTILS_MESSAGE_TYPE_GENERAL_BIT_EXT | VK_DEBUG_UTILS_MESSAGE_TYPE_VALIDATION_BIT_EXT | VK_DEBUG_UTILS_MESSAGE_TYPE_PERFORMANCE_BIT_EXT;
        createInfo.pfnUserCallback = debugCallback;
    }

    void setupDebugMessenger() {
        if (!enableValidationLayers) return;

        VkDebugUtilsMessengerCreateInfoEXT createInfo;
        populateDebugMessengerCreateInfo(createInfo);

        if (CreateDebugUtilsMessengerEXT(instance, &createInfo, nullptr, &debugMessenger) != VK_SUCCESS) {
            throw std::runtime_error("failed to set up debug messenger!");
        }
    }

    void createSurface() {
        if (glfwCreateWindowSurface(instance, window, nullptr, &surface) != VK_SUCCESS) {
            throw std::runtime_error("failed to create window surface!");
        }
    }

    void pickPhysicalDevice() {
        uint32_t deviceCount = 0;
        vkEnumeratePhysicalDevices(instance, &deviceCount, nullptr);

        if (deviceCount == 0) {
            throw std::runtime_error("failed to find GPUs with Vulkan support!");
        }

        std::vector<VkPhysicalDevice> devices(deviceCount);
        vkEnumeratePhysicalDevices(instance, &deviceCount, devices.data());

        for (const auto& device : devices) {
            if (isDeviceSuitable(device)) {
                physicalDevice = device;
                break;
            }
        }

        if (physicalDevice == VK_NULL_HANDLE) {
            throw std::runtime_error("failed to find a suitable GPU!");
        }
    }

    void createLogicalDevice() {
        QueueFamilyIndices indices = findQueueFamilies(physicalDevice);

        std::vector<VkDeviceQueueCreateInfo> queueCreateInfos;
        std::set<uint32_t> uniqueQueueFamilies = {indices.graphicsAndComputeFamily.value(), indices.presentFamily.value()};

        float queuePriority = 1.0f;
        for (uint32_t queueFamily : uniqueQueueFamilies) {
            VkDeviceQueueCreateInfo queueCreateInfo{};
            queueCreateInfo.sType = VK_STRUCTURE_TYPE_DEVICE_QUEUE_CREATE_INFO;
            queueCreateInfo.queueFamilyIndex = queueFamily;
            queueCreateInfo.queueCount = 1;
            queueCreateInfo.pQueuePriorities = &queuePriority;
            queueCreateInfos.push_back(queueCreateInfo);
        }

        VkPhysicalDeviceFeatures deviceFeatures{};

        VkDeviceCreateInfo createInfo{};
        createInfo.sType = VK_STRUCTURE_TYPE_DEVICE_CREATE_INFO;

        createInfo.queueCreateInfoCount = static_cast<uint32_t>(queueCreateInfos.size());
        createInfo.pQueueCreateInfos = queueCreateInfos.data();

        createInfo.pEnabledFeatures = &deviceFeatures;

        createInfo.enabledExtensionCount = static_cast<uint32_t>(deviceExtensions.size());
        createInfo.ppEnabledExtensionNames = deviceExtensions.data();

        if (enableValidationLayers) {
            createInfo.enabledLayerCount = static_cast<uint32_t>(validationLayers.size());
            createInfo.ppEnabledLayerNames = validationLayers.data();
        } else {
            createInfo.enabledLayerCount = 0;
        }

        if (vkCreateDevice(physicalDevice, &createInfo, nullptr, &device) != VK_SUCCESS) {
            throw std::runtime_error("failed to create logical device!");
        }

        vkGetDeviceQueue(device, indices.graphicsAndComputeFamily.value(), 0, &graphicsQueue);
        vkGetDeviceQueue(device, indices.graphicsAndComputeFamily.value(), 0, &computeQueue);
        vkGetDeviceQueue(device, indices.presentFamily.value(), 0, &presentQueue);
    }

    void createSwapChain() {
        SwapChainSupportDetails swapChainSupport = querySwapChainSupport(physicalDevice);

        VkSurfaceFormatKHR surfaceFormat = chooseSwapSurfaceFormat(swapChainSupport.formats);
        VkPresentModeKHR presentMode = chooseSwapPresentMode(swapChainSupport.presentModes);
        VkExtent2D extent = chooseSwapExtent(swapChainSupport.capabilities);

        uint32_t imageCount = swapChainSupport.capabilities.minImageCount + 1;
        if (swapChainSupport.capabilities.maxImageCount > 0 && imageCount > swapChainSupport.capabilities.maxImageCount) {
            imageCount = swapChainSupport.capabilities.maxImageCount;
        }

        VkSwapchainCreateInfoKHR createInfo{};
        createInfo.sType = VK_STRUCTURE_TYPE_SWAPCHAIN_CREATE_INFO_KHR;
        createInfo.surface = surface;

        createInfo.minImageCount = imageCount;
        createInfo.imageFormat = surfaceFormat.format;
        createInfo.imageColorSpace = surfaceFormat.colorSpace;
        createInfo.imageExtent = extent;
        createInfo.imageArrayLayers = 1;
        createInfo.imageUsage = VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT;

        QueueFamilyIndices indices = findQueueFamilies(physicalDevice);
        uint32_t queueFamilyIndices[] = {indices.graphicsAndComputeFamily.value(), indices.presentFamily.value()};

        if (indices.graphicsAndComputeFamily != indices.presentFamily) {
            createInfo.imageSharingMode = VK_SHARING_MODE_CONCURRENT;
            createInfo.queueFamilyIndexCount = 2;
            createInfo.pQueueFamilyIndices = queueFamilyIndices;
        } else {
            createInfo.imageSharingMode = VK_SHARING_MODE_EXCLUSIVE;
        }

        createInfo.preTransform = swapChainSupport.capabilities.currentTransform;
        createInfo.compositeAlpha = VK_COMPOSITE_ALPHA_OPAQUE_BIT_KHR;
        createInfo.presentMode = presentMode;
        createInfo.clipped = VK_TRUE;

        if (vkCreateSwapchainKHR(device, &createInfo, nullptr, &swapChain) != VK_SUCCESS) {
            throw std::runtime_error("failed to create swap chain!");
        }

        vkGetSwapchainImagesKHR(device, swapChain, &imageCount, nullptr);
        swapChainImages.resize(imageCount);
        vkGetSwapchainImagesKHR(device, swapChain, &imageCount, swapChainImages.data());

        swapChainImageFormat = surfaceFormat.format;
        swapChainExtent = extent;
    }

    void createImageViews() {
        swapChainImageViews.resize(swapChainImages.size());

        for (size_t i = 0; i < swapChainImages.size(); i++) {
            VkImageViewCreateInfo createInfo{};
            createInfo.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO;
            createInfo.image = swapChainImages[i];
            createInfo.viewType = VK_IMAGE_VIEW_TYPE_2D;
            createInfo.format = swapChainImageFormat;
            createInfo.components.r = VK_COMPONENT_SWIZZLE_IDENTITY;
            createInfo.components.g = VK_COMPONENT_SWIZZLE_IDENTITY;
            createInfo.components.b = VK_COMPONENT_SWIZZLE_IDENTITY;
            createInfo.components.a = VK_COMPONENT_SWIZZLE_IDENTITY;
            createInfo.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
            createInfo.subresourceRange.baseMipLevel = 0;
            createInfo.subresourceRange.levelCount = 1;
            createInfo.subresourceRange.baseArrayLayer = 0;
            createInfo.subresourceRange.layerCount = 1;

            if (vkCreateImageView(device, &createInfo, nullptr, &swapChainImageViews[i]) != VK_SUCCESS) {
                throw std::runtime_error("failed to create image views!");
            }
        }
    }

    void createRenderPass() {
        VkAttachmentDescription colorAttachment{};
        colorAttachment.format = swapChainImageFormat;
        colorAttachment.samples = VK_SAMPLE_COUNT_1_BIT;
        colorAttachment.loadOp = VK_ATTACHMENT_LOAD_OP_CLEAR;
        colorAttachment.storeOp = VK_ATTACHMENT_STORE_OP_STORE;
        colorAttachment.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
        colorAttachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_DONT_CARE;
        colorAttachment.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
        colorAttachment.finalLayout = VK_IMAGE_LAYOUT_PRESENT_SRC_KHR;

        VkAttachmentReference colorAttachmentRef{};
        colorAttachmentRef.attachment = 0;
        colorAttachmentRef.layout = VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL;

        VkSubpassDescription subpass{};
        subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
        subpass.colorAttachmentCount = 1;
        subpass.pColorAttachments = &colorAttachmentRef;

        VkSubpassDependency dependency{};
        dependency.srcSubpass = VK_SUBPASS_EXTERNAL;
        dependency.dstSubpass = 0;
        dependency.srcStageMask = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
        dependency.srcAccessMask = 0;
        dependency.dstStageMask = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
        dependency.dstAccessMask = VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;

        VkRenderPassCreateInfo renderPassInfo{};
        renderPassInfo.sType = VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO;
        renderPassInfo.attachmentCount = 1;
        renderPassInfo.pAttachments = &colorAttachment;
        renderPassInfo.subpassCount = 1;
        renderPassInfo.pSubpasses = &subpass;
        renderPassInfo.dependencyCount = 1;
        renderPassInfo.pDependencies = &dependency;

        if (vkCreateRenderPass(device, &renderPassInfo, nullptr, &renderPass) != VK_SUCCESS) {
            throw std::runtime_error("failed to create render pass!");
        }
    }

    void createComputeDescriptorSetLayout() {
        std::array<VkDescriptorSetLayoutBinding, 3> layoutBindings{};
        layoutBindings[0].binding = 0;
        layoutBindings[0].descriptorCount = 1;
        layoutBindings[0].descriptorType = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER;
        layoutBindings[0].pImmutableSamplers = nullptr;
        layoutBindings[0].stageFlags = VK_SHADER_STAGE_COMPUTE_BIT;

        layoutBindings[1].binding = 1;
        layoutBindings[1].descriptorCount = 1;
        layoutBindings[1].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
        layoutBindings[1].pImmutableSamplers = nullptr;
        layoutBindings[1].stageFlags = VK_SHADER_STAGE_COMPUTE_BIT;

        layoutBindings[2].binding = 2;
        layoutBindings[2].descriptorCount = 1;
        layoutBindings[2].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
        layoutBindings[2].pImmutableSamplers = nullptr;
        layoutBindings[2].stageFlags = VK_SHADER_STAGE_COMPUTE_BIT;

        VkDescriptorSetLayoutCreateInfo layoutInfo{};
        layoutInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO;
        layoutInfo.bindingCount = 3;
        layoutInfo.pBindings = layoutBindings.data();

        if (vkCreateDescriptorSetLayout(device, &layoutInfo, nullptr, &computeDescriptorSetLayout) != VK_SUCCESS) {
            throw std::runtime_error("failed to create compute descriptor set layout!");
        }
    }


    void createGraphicsPipeline() {
        auto vertShaderCode = readFile("shaders/vert.spv");
        auto fragShaderCode = readFile("shaders/frag.spv");

        VkShaderModule vertShaderModule = createShaderModule(vertShaderCode);
        VkShaderModule fragShaderModule = createShaderModule(fragShaderCode);

        VkPipelineShaderStageCreateInfo vertShaderStageInfo{};
        vertShaderStageInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
        vertShaderStageInfo.stage = VK_SHADER_STAGE_VERTEX_BIT;
        vertShaderStageInfo.module = vertShaderModule;
        vertShaderStageInfo.pName = "main";

        VkPipelineShaderStageCreateInfo fragShaderStageInfo{};
        fragShaderStageInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
        fragShaderStageInfo.stage = VK_SHADER_STAGE_FRAGMENT_BIT;
        fragShaderStageInfo.module = fragShaderModule;
        fragShaderStageInfo.pName = "main";

        VkPipelineShaderStageCreateInfo shaderStages[] = {vertShaderStageInfo, fragShaderStageInfo};

        VkPipelineVertexInputStateCreateInfo vertexInputInfo{};
        vertexInputInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO;

        auto bindingDescription = Particle::getBindingDescription();
        auto attributeDescriptions = Particle::getAttributeDescriptions();

        vertexInputInfo.vertexBindingDescriptionCount = 1;
        vertexInputInfo.vertexAttributeDescriptionCount = static_cast<uint32_t>(attributeDescriptions.size());
        vertexInputInfo.pVertexBindingDescriptions = &bindingDescription;
        vertexInputInfo.pVertexAttributeDescriptions = attributeDescriptions.data();

        VkPipelineInputAssemblyStateCreateInfo inputAssembly{};
        inputAssembly.sType = VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO;
        inputAssembly.topology = VK_PRIMITIVE_TOPOLOGY_POINT_LIST;
        inputAssembly.primitiveRestartEnable = VK_FALSE;

        VkPipelineViewportStateCreateInfo viewportState{};
        viewportState.sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO;
        viewportState.viewportCount = 1;
        viewportState.scissorCount = 1;

        VkPipelineRasterizationStateCreateInfo rasterizer{};
        rasterizer.sType = VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO;
        rasterizer.depthClampEnable = VK_FALSE;
        rasterizer.rasterizerDiscardEnable = VK_FALSE;
        rasterizer.polygonMode = VK_POLYGON_MODE_FILL;
        rasterizer.lineWidth = 1.0f;
        rasterizer.cullMode = VK_CULL_MODE_BACK_BIT;
        rasterizer.frontFace = VK_FRONT_FACE_COUNTER_CLOCKWISE;
        rasterizer.depthBiasEnable = VK_FALSE;

        VkPipelineMultisampleStateCreateInfo multisampling{};
        multisampling.sType = VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO;
        multisampling.sampleShadingEnable = VK_FALSE;
        multisampling.rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;

        VkPipelineColorBlendAttachmentState colorBlendAttachment{};
        colorBlendAttachment.colorWriteMask = VK_COLOR_COMPONENT_R_BIT | VK_COLOR_COMPONENT_G_BIT | VK_COLOR_COMPONENT_B_BIT | VK_COLOR_COMPONENT_A_BIT;
        colorBlendAttachment.blendEnable = VK_TRUE;
        colorBlendAttachment.colorBlendOp = VK_BLEND_OP_ADD;
        colorBlendAttachment.srcColorBlendFactor = VK_BLEND_FACTOR_SRC_ALPHA;
        colorBlendAttachment.dstColorBlendFactor = VK_BLEND_FACTOR_ONE_MINUS_SRC_ALPHA;
        colorBlendAttachment.alphaBlendOp = VK_BLEND_OP_ADD;
        colorBlendAttachment.srcAlphaBlendFactor = VK_BLEND_FACTOR_ONE_MINUS_SRC_ALPHA;
        colorBlendAttachment.dstAlphaBlendFactor = VK_BLEND_FACTOR_ZERO;

        VkPipelineColorBlendStateCreateInfo colorBlending{};
        colorBlending.sType = VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO;
        colorBlending.logicOpEnable = VK_FALSE;
        colorBlending.logicOp = VK_LOGIC_OP_COPY;
        colorBlending.attachmentCount = 1;
        colorBlending.pAttachments = &colorBlendAttachment;
        colorBlending.blendConstants[0] = 0.0f;
        colorBlending.blendConstants[1] = 0.0f;
        colorBlending.blendConstants[2] = 0.0f;
        colorBlending.blendConstants[3] = 0.0f;

        std::vector<VkDynamicState> dynamicStates = {
            VK_DYNAMIC_STATE_VIEWPORT,
            VK_DYNAMIC_STATE_SCISSOR
        };
        VkPipelineDynamicStateCreateInfo dynamicState{};
        dynamicState.sType = VK_STRUCTURE_TYPE_PIPELINE_DYNAMIC_STATE_CREATE_INFO;
        dynamicState.dynamicStateCount = static_cast<uint32_t>(dynamicStates.size());
        dynamicState.pDynamicStates = dynamicStates.data();

        VkPipelineLayoutCreateInfo pipelineLayoutInfo{};
        pipelineLayoutInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO;
        pipelineLayoutInfo.setLayoutCount = 0;
        pipelineLayoutInfo.pSetLayouts = nullptr;

        if (vkCreatePipelineLayout(device, &pipelineLayoutInfo, nullptr, &pipelineLayout) != VK_SUCCESS) {
            throw std::runtime_error("failed to create pipeline layout!");
        }

        VkGraphicsPipelineCreateInfo pipelineInfo{};
        pipelineInfo.sType = VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO;
        pipelineInfo.stageCount = 2;
        pipelineInfo.pStages = shaderStages;
        pipelineInfo.pVertexInputState = &vertexInputInfo;
        pipelineInfo.pInputAssemblyState = &inputAssembly;
        pipelineInfo.pViewportState = &viewportState;
        pipelineInfo.pRasterizationState = &rasterizer;
        pipelineInfo.pMultisampleState = &multisampling;
        pipelineInfo.pColorBlendState = &colorBlending;
        pipelineInfo.pDynamicState = &dynamicState;
        pipelineInfo.layout = pipelineLayout;
        pipelineInfo.renderPass = renderPass;
        pipelineInfo.subpass = 0;
        pipelineInfo.basePipelineHandle = VK_NULL_HANDLE;

        if (vkCreateGraphicsPipelines(device, VK_NULL_HANDLE, 1, &pipelineInfo, nullptr, &graphicsPipeline) != VK_SUCCESS) {
            throw std::runtime_error("failed to create graphics pipeline!");
        }

        vkDestroyShaderModule(device, fragShaderModule, nullptr);
        vkDestroyShaderModule(device, vertShaderModule, nullptr);
    }

    void createComputePipeline() {
        auto computeShaderCode = readFile("shaders/comp.spv");

        VkShaderModule computeShaderModule = createShaderModule(computeShaderCode);

        VkPipelineShaderStageCreateInfo computeShaderStageInfo{};
        computeShaderStageInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
        computeShaderStageInfo.stage = VK_SHADER_STAGE_COMPUTE_BIT;
        computeShaderStageInfo.module = computeShaderModule;
        computeShaderStageInfo.pName = "main";

        VkPipelineLayoutCreateInfo pipelineLayoutInfo{};
        pipelineLayoutInfo.sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO;
        pipelineLayoutInfo.setLayoutCount = 1;
        pipelineLayoutInfo.pSetLayouts = &computeDescriptorSetLayout;

        if (vkCreatePipelineLayout(device, &pipelineLayoutInfo, nullptr, &computePipelineLayout) != VK_SUCCESS) {
            throw std::runtime_error("failed to create compute pipeline layout!");
        }

        VkComputePipelineCreateInfo pipelineInfo{};
        pipelineInfo.sType = VK_STRUCTURE_TYPE_COMPUTE_PIPELINE_CREATE_INFO;
        pipelineInfo.layout = computePipelineLayout;
        pipelineInfo.stage = computeShaderStageInfo;

        if (vkCreateComputePipelines(device, VK_NULL_HANDLE, 1, &pipelineInfo, nullptr, &computePipeline) != VK_SUCCESS) {
            throw std::runtime_error("failed to create compute pipeline!");
        }

        vkDestroyShaderModule(device, computeShaderModule, nullptr);
    }

    void createFramebuffers() {
        swapChainFramebuffers.resize(swapChainImageViews.size());

        for (size_t i = 0; i < swapChainImageViews.size(); i++) {
            VkImageView attachments[] = {
                swapChainImageViews[i]
            };

            VkFramebufferCreateInfo framebufferInfo{};
            framebufferInfo.sType = VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO;
            framebufferInfo.renderPass = renderPass;
            framebufferInfo.attachmentCount = 1;
            framebufferInfo.pAttachments = attachments;
            framebufferInfo.width = swapChainExtent.width;
            framebufferInfo.height = swapChainExtent.height;
            framebufferInfo.layers = 1;

            if (vkCreateFramebuffer(device, &framebufferInfo, nullptr, &swapChainFramebuffers[i]) != VK_SUCCESS) {
                throw std::runtime_error("failed to create framebuffer!");
            }
        }
    }

    void createCommandPool() {
        QueueFamilyIndices queueFamilyIndices = findQueueFamilies(physicalDevice);

        VkCommandPoolCreateInfo poolInfo{};
        poolInfo.sType = VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO;
        poolInfo.flags = VK_COMMAND_POOL_CREATE_RESET_COMMAND_BUFFER_BIT;
        poolInfo.queueFamilyIndex = queueFamilyIndices.graphicsAndComputeFamily.value();

        if (vkCreateCommandPool(device, &poolInfo, nullptr, &commandPool) != VK_SUCCESS) {
            throw std::runtime_error("failed to create graphics command pool!");
        }
    }

    void createShaderStorageBuffers() {

        // Initialize particles
        std::default_random_engine rndEngine((unsigned)time(nullptr));
        std::uniform_real_distribution<float> rndDist(0.0f, 1.0f);

        // Initial particle positions on a circle
        std::vector<Particle> particles(PARTICLE_COUNT);
        for (auto& particle : particles) {
            float r = 0.25f * sqrt(rndDist(rndEngine));
            float theta = rndDist(rndEngine) * 2.0f * 3.14159265358979323846f;
            float x = r * cos(theta) * HEIGHT / WIDTH;
            float y = r * sin(theta);
            particle.position = glm::vec2(x, y);
            particle.velocity = glm::normalize(glm::vec2(x,y)) * 0.00025f;
            particle.color = glm::vec4(rndDist(rndEngine), rndDist(rndEngine), rndDist(rndEngine), 1.0f);
        }

        VkDeviceSize bufferSize = sizeof(Particle) * PARTICLE_COUNT;

        // Create a staging buffer used to upload data to the gpu
        VkBuffer stagingBuffer;
        VkDeviceMemory stagingBufferMemory;
        createBuffer(bufferSize, VK_BUFFER_USAGE_TRANSFER_SRC_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, stagingBuffer, stagingBufferMemory);

        void* data;
        vkMapMemory(device, stagingBufferMemory, 0, bufferSize, 0, &data);
        memcpy(data, particles.data(), (size_t)bufferSize);
        vkUnmapMemory(device, stagingBufferMemory);

        shaderStorageBuffers.resize(MAX_FRAMES_IN_FLIGHT);
        shaderStorageBuffersMemory.resize(MAX_FRAMES_IN_FLIGHT);

        // Copy initial particle data to all storage buffers
        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            createBuffer(bufferSize, VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT, shaderStorageBuffers[i], shaderStorageBuffersMemory[i]);
            copyBuffer(stagingBuffer, shaderStorageBuffers[i], bufferSize);
        }

        vkDestroyBuffer(device, stagingBuffer, nullptr);
        vkFreeMemory(device, stagingBufferMemory, nullptr);

    }

    void createUniformBuffers() {
        VkDeviceSize bufferSize = sizeof(UniformBufferObject);

        uniformBuffers.resize(MAX_FRAMES_IN_FLIGHT);
        uniformBuffersMemory.resize(MAX_FRAMES_IN_FLIGHT);
        uniformBuffersMapped.resize(MAX_FRAMES_IN_FLIGHT);

        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            createBuffer(bufferSize, VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT, VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT, uniformBuffers[i], uniformBuffersMemory[i]);

            vkMapMemory(device, uniformBuffersMemory[i], 0, bufferSize, 0, &uniformBuffersMapped[i]);
        }
    }

    void createDescriptorPool() {
        std::array<VkDescriptorPoolSize, 2> poolSizes{};
        poolSizes[0].type = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER;
        poolSizes[0].descriptorCount = static_cast<uint32_t>(MAX_FRAMES_IN_FLIGHT);
        
        poolSizes[1].type = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
        poolSizes[1].descriptorCount = static_cast<uint32_t>(MAX_FRAMES_IN_FLIGHT) * 2;

        VkDescriptorPoolCreateInfo poolInfo{};
        poolInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO;
        poolInfo.poolSizeCount = 2;
        poolInfo.pPoolSizes = poolSizes.data();
        poolInfo.maxSets = static_cast<uint32_t>(MAX_FRAMES_IN_FLIGHT);

        if (vkCreateDescriptorPool(device, &poolInfo, nullptr, &descriptorPool) != VK_SUCCESS) {
            throw std::runtime_error("failed to create descriptor pool!");
        }
    }

    void createComputeDescriptorSets() {
        std::vector<VkDescriptorSetLayout> layouts(MAX_FRAMES_IN_FLIGHT, computeDescriptorSetLayout);
        VkDescriptorSetAllocateInfo allocInfo{};
        allocInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO;
        allocInfo.descriptorPool = descriptorPool;
        allocInfo.descriptorSetCount = static_cast<uint32_t>(MAX_FRAMES_IN_FLIGHT);
        allocInfo.pSetLayouts = layouts.data();

        computeDescriptorSets.resize(MAX_FRAMES_IN_FLIGHT);
        if (vkAllocateDescriptorSets(device, &allocInfo, computeDescriptorSets.data()) != VK_SUCCESS) {
            throw std::runtime_error("failed to allocate descriptor sets!");
        }

        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            VkDescriptorBufferInfo uniformBufferInfo{};
            uniformBufferInfo.buffer = uniformBuffers[i];
            uniformBufferInfo.offset = 0;
            uniformBufferInfo.range = sizeof(UniformBufferObject);

            std::array<VkWriteDescriptorSet, 3> descriptorWrites{};
            descriptorWrites[0].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
            descriptorWrites[0].dstSet = computeDescriptorSets[i];
            descriptorWrites[0].dstBinding = 0;
            descriptorWrites[0].dstArrayElement = 0;
            descriptorWrites[0].descriptorType = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER;
            descriptorWrites[0].descriptorCount = 1;
            descriptorWrites[0].pBufferInfo = &uniformBufferInfo;

            VkDescriptorBufferInfo storageBufferInfoLastFrame{};
            storageBufferInfoLastFrame.buffer = shaderStorageBuffers[(i - 1) % MAX_FRAMES_IN_FLIGHT];
            storageBufferInfoLastFrame.offset = 0;
            storageBufferInfoLastFrame.range = sizeof(Particle) * PARTICLE_COUNT;

            descriptorWrites[1].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
            descriptorWrites[1].dstSet = computeDescriptorSets[i];
            descriptorWrites[1].dstBinding = 1;
            descriptorWrites[1].dstArrayElement = 0;
            descriptorWrites[1].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
            descriptorWrites[1].descriptorCount = 1;
            descriptorWrites[1].pBufferInfo = &storageBufferInfoLastFrame;

            VkDescriptorBufferInfo storageBufferInfoCurrentFrame{};
            storageBufferInfoCurrentFrame.buffer = shaderStorageBuffers[i];
            storageBufferInfoCurrentFrame.offset = 0;
            storageBufferInfoCurrentFrame.range = sizeof(Particle) * PARTICLE_COUNT;

            descriptorWrites[2].sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
            descriptorWrites[2].dstSet = computeDescriptorSets[i];
            descriptorWrites[2].dstBinding = 2;
            descriptorWrites[2].dstArrayElement = 0;
            descriptorWrites[2].descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
            descriptorWrites[2].descriptorCount = 1;
            descriptorWrites[2].pBufferInfo = &storageBufferInfoCurrentFrame;

            vkUpdateDescriptorSets(device, 3, descriptorWrites.data(), 0, nullptr);
        }
    }


    void createBuffer(VkDeviceSize size, VkBufferUsageFlags usage, VkMemoryPropertyFlags properties, VkBuffer& buffer, VkDeviceMemory& bufferMemory) {
        VkBufferCreateInfo bufferInfo{};
        bufferInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
        bufferInfo.size = size;
        bufferInfo.usage = usage;
        bufferInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;

        if (vkCreateBuffer(device, &bufferInfo, nullptr, &buffer) != VK_SUCCESS) {
            throw std::runtime_error("failed to create buffer!");
        }

        VkMemoryRequirements memRequirements;
        vkGetBufferMemoryRequirements(device, buffer, &memRequirements);

        VkMemoryAllocateInfo allocInfo{};
        allocInfo.sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO;
        allocInfo.allocationSize = memRequirements.size;
        allocInfo.memoryTypeIndex = findMemoryType(memRequirements.memoryTypeBits, properties);

        if (vkAllocateMemory(device, &allocInfo, nullptr, &bufferMemory) != VK_SUCCESS) {
            throw std::runtime_error("failed to allocate buffer memory!");
        }

        vkBindBufferMemory(device, buffer, bufferMemory, 0);
    }

    void copyBuffer(VkBuffer srcBuffer, VkBuffer dstBuffer, VkDeviceSize size) {
        VkCommandBufferAllocateInfo allocInfo{};
        allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
        allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
        allocInfo.commandPool = commandPool;
        allocInfo.commandBufferCount = 1;

        VkCommandBuffer commandBuffer;
        vkAllocateCommandBuffers(device, &allocInfo, &commandBuffer);

        VkCommandBufferBeginInfo beginInfo{};
        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
        beginInfo.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;

        vkBeginCommandBuffer(commandBuffer, &beginInfo);

        VkBufferCopy copyRegion{};
        copyRegion.size = size;
        vkCmdCopyBuffer(commandBuffer, srcBuffer, dstBuffer, 1, &copyRegion);

        vkEndCommandBuffer(commandBuffer);

        VkSubmitInfo submitInfo{};
        submitInfo.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;
        submitInfo.commandBufferCount = 1;
        submitInfo.pCommandBuffers = &commandBuffer;

        vkQueueSubmit(graphicsQueue, 1, &submitInfo, VK_NULL_HANDLE);
        vkQueueWaitIdle(graphicsQueue);

        vkFreeCommandBuffers(device, commandPool, 1, &commandBuffer);
    }

    uint32_t findMemoryType(uint32_t typeFilter, VkMemoryPropertyFlags properties) {
        VkPhysicalDeviceMemoryProperties memProperties;
        vkGetPhysicalDeviceMemoryProperties(physicalDevice, &memProperties);

        for (uint32_t i = 0; i < memProperties.memoryTypeCount; i++) {
            if ((typeFilter & (1 << i)) && (memProperties.memoryTypes[i].propertyFlags & properties) == properties) {
                return i;
            }
        }

        throw std::runtime_error("failed to find suitable memory type!");
    }

    void createCommandBuffers() {
        commandBuffers.resize(MAX_FRAMES_IN_FLIGHT);

        VkCommandBufferAllocateInfo allocInfo{};
        allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
        allocInfo.commandPool = commandPool;
        allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
        allocInfo.commandBufferCount = (uint32_t) commandBuffers.size();

        if (vkAllocateCommandBuffers(device, &allocInfo, commandBuffers.data()) != VK_SUCCESS) {
            throw std::runtime_error("failed to allocate command buffers!");
        }
    }

    void createComputeCommandBuffers() {
        computeCommandBuffers.resize(MAX_FRAMES_IN_FLIGHT);

        VkCommandBufferAllocateInfo allocInfo{};
        allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
        allocInfo.commandPool = commandPool;
        allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
        allocInfo.commandBufferCount = (uint32_t)computeCommandBuffers.size();

        if (vkAllocateCommandBuffers(device, &allocInfo, computeCommandBuffers.data()) != VK_SUCCESS) {
            throw std::runtime_error("failed to allocate compute command buffers!");
        }
    }

    void recordCommandBuffer(VkCommandBuffer commandBuffer, uint32_t imageIndex) {
        VkCommandBufferBeginInfo beginInfo{};
        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;

        if (vkBeginCommandBuffer(commandBuffer, &beginInfo) != VK_SUCCESS) {
            throw std::runtime_error("failed to begin recording command buffer!");
        }

        VkRenderPassBeginInfo renderPassInfo{};
        renderPassInfo.sType = VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO;
        renderPassInfo.renderPass = renderPass;
        renderPassInfo.framebuffer = swapChainFramebuffers[imageIndex];
        renderPassInfo.renderArea.offset = {0, 0};
        renderPassInfo.renderArea.extent = swapChainExtent;

        VkClearValue clearColor = {{{0.0f, 0.0f, 0.0f, 1.0f}}};
        renderPassInfo.clearValueCount = 1;
        renderPassInfo.pClearValues = &clearColor;

        vkCmdBeginRenderPass(commandBuffer, &renderPassInfo, VK_SUBPASS_CONTENTS_INLINE);

            vkCmdBindPipeline(commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, graphicsPipeline);

            VkViewport viewport{};
            viewport.x = 0.0f;
            viewport.y = 0.0f;
            viewport.width = (float) swapChainExtent.width;
            viewport.height = (float) swapChainExtent.height;
            viewport.minDepth = 0.0f;
            viewport.maxDepth = 1.0f;
            vkCmdSetViewport(commandBuffer, 0, 1, &viewport);

            VkRect2D scissor{};
            scissor.offset = {0, 0};
            scissor.extent = swapChainExtent;
            vkCmdSetScissor(commandBuffer, 0, 1, &scissor);            

            VkDeviceSize offsets[] = {0};
            vkCmdBindVertexBuffers(commandBuffer, 0, 1, &shaderStorageBuffers[currentFrame], offsets);

            vkCmdDraw(commandBuffer, PARTICLE_COUNT, 1, 0, 0);

        vkCmdEndRenderPass(commandBuffer);

        if (vkEndCommandBuffer(commandBuffer) != VK_SUCCESS) {
            throw std::runtime_error("failed to record command buffer!");
        }
    }

    void recordComputeCommandBuffer(VkCommandBuffer commandBuffer) {
        VkCommandBufferBeginInfo beginInfo{};
        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;

        if (vkBeginCommandBuffer(commandBuffer, &beginInfo) != VK_SUCCESS) {
            throw std::runtime_error("failed to begin recording compute command buffer!");
        }

        vkCmdBindPipeline(commandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, computePipeline);

        vkCmdBindDescriptorSets(commandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, computePipelineLayout, 0, 1, &computeDescriptorSets[currentFrame], 0, nullptr);

        vkCmdDispatch(commandBuffer, PARTICLE_COUNT / 256, 1, 1);

        if (vkEndCommandBuffer(commandBuffer) != VK_SUCCESS) {
            throw std::runtime_error("failed to record compute command buffer!");
        }

    }

    void createSyncObjects() {
        imageAvailableSemaphores.resize(MAX_FRAMES_IN_FLIGHT);
        renderFinishedSemaphores.resize(MAX_FRAMES_IN_FLIGHT);
        computeFinishedSemaphores.resize(MAX_FRAMES_IN_FLIGHT);
        inFlightFences.resize(MAX_FRAMES_IN_FLIGHT);
        computeInFlightFences.resize(MAX_FRAMES_IN_FLIGHT);

        VkSemaphoreCreateInfo semaphoreInfo{};
        semaphoreInfo.sType = VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO;

        VkFenceCreateInfo fenceInfo{};
        fenceInfo.sType = VK_STRUCTURE_TYPE_FENCE_CREATE_INFO;
        fenceInfo.flags = VK_FENCE_CREATE_SIGNALED_BIT;

        for (size_t i = 0; i < MAX_FRAMES_IN_FLIGHT; i++) {
            if (vkCreateSemaphore(device, &semaphoreInfo, nullptr, &imageAvailableSemaphores[i]) != VK_SUCCESS ||
                vkCreateSemaphore(device, &semaphoreInfo, nullptr, &renderFinishedSemaphores[i]) != VK_SUCCESS ||
                vkCreateFence(device, &fenceInfo, nullptr, &inFlightFences[i]) != VK_SUCCESS) {
                throw std::runtime_error("failed to create graphics synchronization objects for a frame!");
            }
            if (vkCreateSemaphore(device, &semaphoreInfo, nullptr, &computeFinishedSemaphores[i]) != VK_SUCCESS ||
                vkCreateFence(device, &fenceInfo, nullptr, &computeInFlightFences[i]) != VK_SUCCESS) {
                throw std::runtime_error("failed to create compute synchronization objects for a frame!");
            }
        }
    }

    void updateUniformBuffer(uint32_t currentImage) {
        UniformBufferObject ubo{};
        ubo.deltaTime = lastFrameTime * 2.0f;

        memcpy(uniformBuffersMapped[currentImage], &ubo, sizeof(ubo));
    }

    void drawFrame() {
        VkSubmitInfo submitInfo{};
        submitInfo.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;

        // Compute submission        
        vkWaitForFences(device, 1, &computeInFlightFences[currentFrame], VK_TRUE, UINT64_MAX);

        updateUniformBuffer(currentFrame);

        vkResetFences(device, 1, &computeInFlightFences[currentFrame]);

        vkResetCommandBuffer(computeCommandBuffers[currentFrame], /*VkCommandBufferResetFlagBits*/ 0);
        recordComputeCommandBuffer(computeCommandBuffers[currentFrame]);

        submitInfo.commandBufferCount = 1;
        submitInfo.pCommandBuffers = &computeCommandBuffers[currentFrame];
        submitInfo.signalSemaphoreCount = 1;
        submitInfo.pSignalSemaphores = &computeFinishedSemaphores[currentFrame];

        if (vkQueueSubmit(computeQueue, 1, &submitInfo, computeInFlightFences[currentFrame]) != VK_SUCCESS) {
            throw std::runtime_error("failed to submit compute command buffer!");
        };

        // Graphics submission
        vkWaitForFences(device, 1, &inFlightFences[currentFrame], VK_TRUE, UINT64_MAX);

        uint32_t imageIndex;
        VkResult result = vkAcquireNextImageKHR(device, swapChain, UINT64_MAX, imageAvailableSemaphores[currentFrame], VK_NULL_HANDLE, &imageIndex);

        if (result == VK_ERROR_OUT_OF_DATE_KHR) {
            recreateSwapChain();
            return;
        } else if (result != VK_SUCCESS && result != VK_SUBOPTIMAL_KHR) {
            throw std::runtime_error("failed to acquire swap chain image!");
        }

        vkResetFences(device, 1, &inFlightFences[currentFrame]);

        vkResetCommandBuffer(commandBuffers[currentFrame], /*VkCommandBufferResetFlagBits*/ 0);
        recordCommandBuffer(commandBuffers[currentFrame], imageIndex);

        VkSemaphore waitSemaphores[] = { computeFinishedSemaphores[currentFrame], imageAvailableSemaphores[currentFrame] };
        VkPipelineStageFlags waitStages[] = { VK_PIPELINE_STAGE_VERTEX_INPUT_BIT, VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT };
        submitInfo = {};
        submitInfo.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO;

        submitInfo.waitSemaphoreCount = 2;
        submitInfo.pWaitSemaphores = waitSemaphores;
        submitInfo.pWaitDstStageMask = waitStages;
        submitInfo.commandBufferCount = 1;
        submitInfo.pCommandBuffers = &commandBuffers[currentFrame];
        submitInfo.signalSemaphoreCount = 1;
        submitInfo.pSignalSemaphores = &renderFinishedSemaphores[currentFrame];

        if (vkQueueSubmit(graphicsQueue, 1, &submitInfo, inFlightFences[currentFrame]) != VK_SUCCESS) {
            throw std::runtime_error("failed to submit draw command buffer!");
        }

        VkPresentInfoKHR presentInfo{};
        presentInfo.sType = VK_STRUCTURE_TYPE_PRESENT_INFO_KHR;

        presentInfo.waitSemaphoreCount = 1;
        presentInfo.pWaitSemaphores = &renderFinishedSemaphores[currentFrame];

        VkSwapchainKHR swapChains[] = {swapChain};
        presentInfo.swapchainCount = 1;
        presentInfo.pSwapchains = swapChains;

        presentInfo.pImageIndices = &imageIndex;

        result = vkQueuePresentKHR(presentQueue, &presentInfo);

        if (result == VK_ERROR_OUT_OF_DATE_KHR || result == VK_SUBOPTIMAL_KHR || framebufferResized) {
            framebufferResized = false;
            recreateSwapChain();
        } else if (result != VK_SUCCESS) {
            throw std::runtime_error("failed to present swap chain image!");
        }

        currentFrame = (currentFrame + 1) % MAX_FRAMES_IN_FLIGHT;
    }

    VkShaderModule createShaderModule(const std::vector<char>& code) {
        VkShaderModuleCreateInfo createInfo{};
        createInfo.sType = VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO;
        createInfo.codeSize = code.size();
        createInfo.pCode = reinterpret_cast<const uint32_t*>(code.data());

        VkShaderModule shaderModule;
        if (vkCreateShaderModule(device, &createInfo, nullptr, &shaderModule) != VK_SUCCESS) {
            throw std::runtime_error("failed to create shader module!");
        }

        return shaderModule;
    }

    VkSurfaceFormatKHR chooseSwapSurfaceFormat(const std::vector<VkSurfaceFormatKHR>& availableFormats) {
        for (const auto& availableFormat : availableFormats) {
            if (availableFormat.format == VK_FORMAT_B8G8R8A8_SRGB && availableFormat.colorSpace == VK_COLOR_SPACE_SRGB_NONLINEAR_KHR) {
                return availableFormat;
            }
        }

        return availableFormats[0];
    }

    VkPresentModeKHR chooseSwapPresentMode(const std::vector<VkPresentModeKHR>& availablePresentModes) {
        for (const auto& availablePresentMode : availablePresentModes) {
            if (availablePresentMode == VK_PRESENT_MODE_MAILBOX_KHR) {
                return availablePresentMode;
            }
        }

        return VK_PRESENT_MODE_FIFO_KHR;
    }

    VkExtent2D chooseSwapExtent(const VkSurfaceCapabilitiesKHR& capabilities) {
        if (capabilities.currentExtent.width != std::numeric_limits<uint32_t>::max()) {
            return capabilities.currentExtent;
        } else {
            int width, height;
            glfwGetFramebufferSize(window, &width, &height);

            VkExtent2D actualExtent = {
                static_cast<uint32_t>(width),
                static_cast<uint32_t>(height)
            };

            actualExtent.width = std::clamp(actualExtent.width, capabilities.minImageExtent.width, capabilities.maxImageExtent.width);
            actualExtent.height = std::clamp(actualExtent.height, capabilities.minImageExtent.height, capabilities.maxImageExtent.height);

            return actualExtent;
        }
    }

    SwapChainSupportDetails querySwapChainSupport(VkPhysicalDevice device) {
        SwapChainSupportDetails details;

        vkGetPhysicalDeviceSurfaceCapabilitiesKHR(device, surface, &details.capabilities);

        uint32_t formatCount;
        vkGetPhysicalDeviceSurfaceFormatsKHR(device, surface, &formatCount, nullptr);

        if (formatCount != 0) {
            details.formats.resize(formatCount);
            vkGetPhysicalDeviceSurfaceFormatsKHR(device, surface, &formatCount, details.formats.data());
        }

        uint32_t presentModeCount;
        vkGetPhysicalDeviceSurfacePresentModesKHR(device, surface, &presentModeCount, nullptr);

        if (presentModeCount != 0) {
            details.presentModes.resize(presentModeCount);
            vkGetPhysicalDeviceSurfacePresentModesKHR(device, surface, &presentModeCount, details.presentModes.data());
        }

        return details;
    }

    bool isDeviceSuitable(VkPhysicalDevice device) {
        QueueFamilyIndices indices = findQueueFamilies(device);

        bool extensionsSupported = checkDeviceExtensionSupport(device);

        bool swapChainAdequate = false;
        if (extensionsSupported) {
            SwapChainSupportDetails swapChainSupport = querySwapChainSupport(device);
            swapChainAdequate = !swapChainSupport.formats.empty() && !swapChainSupport.presentModes.empty();
        }

        return indices.isComplete() && extensionsSupported && swapChainAdequate;
    }

    bool checkDeviceExtensionSupport(VkPhysicalDevice device) {
        uint32_t extensionCount;
        vkEnumerateDeviceExtensionProperties(device, nullptr, &extensionCount, nullptr);

        std::vector<VkExtensionProperties> availableExtensions(extensionCount);
        vkEnumerateDeviceExtensionProperties(device, nullptr, &extensionCount, availableExtensions.data());

        std::set<std::string> requiredExtensions(deviceExtensions.begin(), deviceExtensions.end());

        for (const auto& extension : availableExtensions) {
            requiredExtensions.erase(extension.extensionName);
        }

        return requiredExtensions.empty();
    }

    QueueFamilyIndices findQueueFamilies(VkPhysicalDevice device) {
        QueueFamilyIndices indices;

        uint32_t queueFamilyCount = 0;
        vkGetPhysicalDeviceQueueFamilyProperties(device, &queueFamilyCount, nullptr);

        std::vector<VkQueueFamilyProperties> queueFamilies(queueFamilyCount);
        vkGetPhysicalDeviceQueueFamilyProperties(device, &queueFamilyCount, queueFamilies.data());

        int i = 0;
        for (const auto& queueFamily : queueFamilies) {
            if ((queueFamily.queueFlags & VK_QUEUE_GRAPHICS_BIT) && (queueFamily.queueFlags & VK_QUEUE_COMPUTE_BIT)) {
                indices.graphicsAndComputeFamily = i;
            }

            VkBool32 presentSupport = false;
            vkGetPhysicalDeviceSurfaceSupportKHR(device, i, surface, &presentSupport);

            if (presentSupport) {
                indices.presentFamily = i;
            }

            if (indices.isComplete()) {
                break;
            }

            i++;
        }

        return indices;
    }

    std::vector<const char*> getRequiredExtensions() {
        uint32_t glfwExtensionCount = 0;
        const char** glfwExtensions;
        glfwExtensions = glfwGetRequiredInstanceExtensions(&glfwExtensionCount);

        std::vector<const char*> extensions(glfwExtensions, glfwExtensions + glfwExtensionCount);

        if (enableValidationLayers) {
            extensions.push_back(VK_EXT_DEBUG_UTILS_EXTENSION_NAME);
        }

        return extensions;
    }

    bool checkValidationLayerSupport() {
        uint32_t layerCount;
        vkEnumerateInstanceLayerProperties(&layerCount, nullptr);

        std::vector<VkLayerProperties> availableLayers(layerCount);
        vkEnumerateInstanceLayerProperties(&layerCount, availableLayers.data());

        for (const char* layerName : validationLayers) {
            bool layerFound = false;

            for (const auto& layerProperties : availableLayers) {
                if (strcmp(layerName, layerProperties.layerName) == 0) {
                    layerFound = true;
                    break;
                }
            }

            if (!layerFound) {
                return false;
            }
        }

        return true;
    }

    static std::vector<char> readFile(const std::string& filename) {
        std::ifstream file(filename, std::ios::ate | std::ios::binary);

        if (!file.is_open()) {
            throw std::runtime_error("failed to open file!");
        }

        size_t fileSize = (size_t) file.tellg();
        std::vector<char> buffer(fileSize);

        file.seekg(0);
        file.read(buffer.data(), fileSize);

        file.close();

        return buffer;
    }

    static VKAPI_ATTR VkBool32 VKAPI_CALL debugCallback(VkDebugUtilsMessageSeverityFlagBitsEXT messageSeverity, VkDebugUtilsMessageTypeFlagsEXT messageType, const VkDebugUtilsMessengerCallbackDataEXT* pCallbackData, void* pUserData) {
        std::cerr << "validation layer: " << pCallbackData->pMessage << std::endl;

        return VK_FALSE;
    }
};

int main() {
    ComputeShaderApplication app;

    try {
        app.run();
    } catch (const std::exception& e) {
        std::cerr << e.what() << std::endl;
        return EXIT_FAILURE;
    }

    return EXIT_SUCCESS;
}