#version 300 es
precision highp float;

layout(location = 0) in vec3 aPosition;
layout(location = 1) in vec2 aTexCoord;

uniform mat4 uModelViewProjection;

out vec2 vTexCoord;

void main() {
    gl_Position = uModelViewProjection * vec4(aPosition, 1.0);
    vTexCoord = aTexCoord;
}

#include <metal_stdlib>
using namespace metal;

struct VertexIn {
    float3 position [[attribute(0)]];
    float2 texCoord [[attribute(1)]];
};

struct VertexOut {
    float4 position [[position]];
    float2 texCoord;
};

struct Uniforms {
    float4x4 modelViewProjection;
};

vertex VertexOut vertexShader(
    VertexIn in [[stage_in]],
    constant Uniforms& uniforms [[buffer(1)]]
) {
    VertexOut out;
    out.position = uniforms.modelViewProjection * float4(in.position, 1.0);
    out.texCoord = in.texCoord;
    return out;
}

#version 300 es
precision highp float;

in vec2 vTexCoord;
uniform sampler2D uTexture;

out vec4 fragColor;

void main() {
    fragColor = texture(uTexture, vTexCoord);
}

fragment float4 fragmentShader(
    VertexOut in [[stage_in]],
    texture2d<float> tex [[texture(0)]],
    sampler samp [[sampler(0)]]
) {
    return tex.sample(samp, in.texCoord);
}

import simd

struct Uniforms {
    var modelViewProjection: simd_float4x4  // Correct alignment
    var cameraPosition: simd_float3         // 16-byte aligned
    var padding: Float = 0                   // Explicit padding if needed
}

struct VertexPacked {
    packed_float3 position;  // 12 bytes, no padding
    packed_float2 texCoord;  // 8 bytes
};

# Step 1: Compile HLSL to DXIL using DXC
dxc -T vs_6_0 -E MainVS -Fo vertex.dxil shader.hlsl
dxc -T ps_6_0 -E MainPS -Fo fragment.dxil shader.hlsl

# Step 2: Convert DXIL to Metal library
metal-shaderconverter vertex.dxil -o vertex.metallib
metal-shaderconverter fragment.dxil -o fragment.metallib

# Step 3: Load in Swift
let vertexLib = try device.makeLibrary(URL: vertexURL)
let fragmentLib = try device.makeLibrary(URL: fragmentURL)

import MetalKit

class GameViewController: UIViewController {
    var metalView: MTKView!
    var renderer: Renderer!

    override func viewDidLoad() {
        super.viewDidLoad()

        // Create Metal view
        guard let device = MTLCreateSystemDefaultDevice() else {
            fatalError("Metal not supported")
        }

        metalView = MTKView(frame: view.bounds, device: device)
        metalView.autoresizingMask = [.flexibleWidth, .flexibleHeight]
        metalView.colorPixelFormat = .bgra8Unorm
        metalView.depthStencilPixelFormat = .depth32Float
        metalView.clearColor = MTLClearColor(red: 0, green: 0, blue: 0, alpha: 1)
        metalView.preferredFramesPerSecond = 60
        view.addSubview(metalView)

        // Create renderer
        renderer = Renderer(metalView: metalView)
        metalView.delegate = renderer
    }
}

class Renderer: NSObject, MTKViewDelegate {
    let device: MTLDevice
    let commandQueue: MTLCommandQueue
    var pipelineState: MTLRenderPipelineState!
    var depthState: MTLDepthStencilState!
    var vertexBuffer: MTLBuffer!

    init(metalView: MTKView) {
        device = metalView.device!
        commandQueue = device.makeCommandQueue()!
        super.init()

        buildPipeline(metalView: metalView)
        buildDepthStencil()
        buildBuffers()
    }

    private func buildPipeline(metalView: MTKView) {
        let library = device.makeDefaultLibrary()!

        let descriptor = MTLRenderPipelineDescriptor()
        descriptor.vertexFunction = library.makeFunction(name: "vertexShader")
        descriptor.fragmentFunction = library.makeFunction(name: "fragmentShader")
        descriptor.colorAttachments[0].pixelFormat = metalView.colorPixelFormat
        descriptor.depthAttachmentPixelFormat = metalView.depthStencilPixelFormat

        // Vertex descriptor (matches shader's VertexIn struct)
        let vertexDescriptor = MTLVertexDescriptor()
        vertexDescriptor.attributes[0].format = .float3
        vertexDescriptor.attributes[0].offset = 0
        vertexDescriptor.attributes[0].bufferIndex = 0
        vertexDescriptor.attributes[1].format = .float2
        vertexDescriptor.attributes[1].offset = MemoryLayout<SIMD3<Float>>.stride
        vertexDescriptor.attributes[1].bufferIndex = 0
        vertexDescriptor.layouts[0].stride = MemoryLayout<Vertex>.stride
        descriptor.vertexDescriptor = vertexDescriptor

        pipelineState = try! device.makeRenderPipelineState(descriptor: descriptor)
    }

    private func buildDepthStencil() {
        let descriptor = MTLDepthStencilDescriptor()
        descriptor.depthCompareFunction = .less
        descriptor.isDepthWriteEnabled = true
        depthState = device.makeDepthStencilState(descriptor: descriptor)
    }

    func mtkView(_ view: MTKView, drawableSizeWillChange size: CGSize) {
        // Handle resize
    }

    func draw(in view: MTKView) {
        guard let drawable = view.currentDrawable,
              let descriptor = view.currentRenderPassDescriptor,
              let commandBuffer = commandQueue.makeCommandBuffer(),
              let encoder = commandBuffer.makeRenderCommandEncoder(descriptor: descriptor) else {
            return
        }

        encoder.setRenderPipelineState(pipelineState)
        encoder.setDepthStencilState(depthState)
        encoder.setVertexBuffer(vertexBuffer, offset: 0, index: 0)
        encoder.drawPrimitives(type: .triangle, vertexStart: 0, vertexCount: vertexCount)
        encoder.endEncoding()

        commandBuffer.present(drawable)
        commandBuffer.commit()
    }
}

import Metal
import QuartzCore

class MetalLayerView: UIView {
    var metalLayer: CAMetalLayer!
    var device: MTLDevice!
    var commandQueue: MTLCommandQueue!
    var displayLink: CADisplayLink?

    override class var layerClass: AnyClass { CAMetalLayer.self }

    override init(frame: CGRect) {
        super.init(frame: frame)
        setup()
    }

    private func setup() {
        device = MTLCreateSystemDefaultDevice()!
        commandQueue = device.makeCommandQueue()!

        metalLayer = layer as? CAMetalLayer
        metalLayer.device = device
        metalLayer.pixelFormat = .bgra8Unorm
        metalLayer.framebufferOnly = true

        displayLink = CADisplayLink(target: self, selector: #selector(render))
        displayLink?.add(to: .main, forMode: .common)
    }

    override func layoutSubviews() {
        super.layoutSubviews()
        metalLayer.drawableSize = CGSize(
            width: bounds.width * contentScaleFactor,
            height: bounds.height * contentScaleFactor
        )
    }

    @objc func render() {
        guard let drawable = metalLayer.nextDrawable(),
              let commandBuffer = commandQueue.makeCommandBuffer() else {
            return
        }

        let descriptor = MTLRenderPassDescriptor()
        descriptor.colorAttachments[0].texture = drawable.texture
        descriptor.colorAttachments[0].loadAction = .clear
        descriptor.colorAttachments[0].storeAction = .store
        descriptor.colorAttachments[0].clearColor = MTLClearColor(red: 0, green: 0, blue: 0, alpha: 1)

        guard let encoder = commandBuffer.makeRenderCommandEncoder(descriptor: descriptor) else {
            return
        }

        // Draw commands here
        encoder.endEncoding()

        commandBuffer.present(drawable)
        commandBuffer.commit()
    }
}

class ComputeProcessor {
    let device: MTLDevice
    let commandQueue: MTLCommandQueue
    var computePipeline: MTLComputePipelineState!

    init() {
        device = MTLCreateSystemDefaultDevice()!
        commandQueue = device.makeCommandQueue()!

        let library = device.makeDefaultLibrary()!
        let function = library.makeFunction(name: "computeKernel")!
        computePipeline = try! device.makeComputePipelineState(function: function)
    }

    func process(input: MTLBuffer, output: MTLBuffer, count: Int) {
        let commandBuffer = commandQueue.makeCommandBuffer()!
        let encoder = commandBuffer.makeComputeCommandEncoder()!

        encoder.setComputePipelineState(computePipeline)
        encoder.setBuffer(input, offset: 0, index: 0)
        encoder.setBuffer(output, offset: 0, index: 1)

        let threadGroupSize = MTLSize(width: 256, height: 1, depth: 1)
        let threadGroups = MTLSize(
            width: (count + 255) / 256,
            height: 1,
            depth: 1
        )

        encoder.dispatchThreadgroups(threadGroups, threadsPerThreadgroup: threadGroupSize)
        encoder.endEncoding()

        commandBuffer.commit()
        commandBuffer.waitUntilCompleted()
    }
}

// Compute shader
kernel void computeKernel(
    device float* input [[buffer(0)]],
    device float* output [[buffer(1)]],
    uint id [[thread_position_in_grid]]
) {
    output[id] = input[id] * 2.0;
}

// Shared: CPU and GPU both access (iOS typical)
let uniformBuffer = device.makeBuffer(length: size, options: .storageModeShared)

// Private: GPU only (best for static geometry)
let vertexBuffer = device.makeBuffer(bytes: vertices, length: size, options: .storageModePrivate)

// Managed: Explicit sync (macOS)
#if os(macOS)
let buffer = device.makeBuffer(length: size, options: .storageModeManaged)
// After CPU write:
buffer.didModifyRange(0..<size)
#endif

let descriptor = MTLTextureDescriptor.texture2DDescriptor(
    pixelFormat: .rgba8Unorm,
    width: 1024,
    height: 1024,
    mipmapped: true
)

// For static textures (loaded once)
descriptor.storageMode = .private
descriptor.usage = [.shaderRead]

// For render targets
descriptor.storageMode = .private
descriptor.usage = [.renderTarget, .shaderRead]

// For CPU-readable (screenshots, readback)
descriptor.storageMode = .shared  // iOS
descriptor.storageMode = .managed  // macOS
descriptor.usage = [.shaderRead, .shaderWrite]