ios - 我的自定义金属图像过滤器很慢。我怎样才能让它更快？

问题描述

我看过很多其他人的在线教程，它们能够在过滤图像时达到 0.0X 秒标记。同时，我的代码在这里花了 1.09 秒来过滤图像。（只是将亮度降低一半）。

在使用 2 种方法测量的第一次评论时间后编辑

Date() timeinterval ，当点击“应用过滤器”按钮并且应用过滤器功能完成运行后
在 iphone 上构建它并使用手表上的计时器手动计数

由于我是金属和内核的新手，我真的不知道我的代码和那些获得更快结果的教程之间的区别。我的代码的哪一部分可以改进/使用不同的方法使其更快。

这是我的内核代码

#include <metal_stdlib>
using namespace metal;
kernel void black(
               texture2d<float, access::write> outTexture [[texture(0)]],
               texture2d<float, access::read> inTexture [[texture(1)]],
               uint2 id [[thread_position_in_grid]]) {
    float3 val = inTexture.read(id).rgb;
    float r = val.r / 4;
    float g = val.g / 4;
float b = val.b / 2;
float4 out = float4(r, g, b, 1.0);
outTexture.write(out.rgba, id);
}

这是我的快速代码

import Metal
import MetalKit

 // UIImage -> CGImage -> MTLTexture -> COMPUTE HAPPENS |
 //                 UIImage <- CGImage <- MTLTexture <--
 class Filter {

var device: MTLDevice
var defaultLib: MTLLibrary?
var grayscaleShader: MTLFunction?
var commandQueue: MTLCommandQueue?
var commandBuffer: MTLCommandBuffer?
var commandEncoder: MTLComputeCommandEncoder?
var pipelineState: MTLComputePipelineState?

var inputImage: UIImage
var height, width: Int

// most devices have a limit of 512 threads per group
let threadsPerBlock = MTLSize(width: 32, height: 32, depth: 1)

init(){
    
    print("initialized")
    self.device = MTLCreateSystemDefaultDevice()!
    print(device)
    
    //changes:  I did do catch try, and use bundle parameter when making make default library
    
    let frameworkBundle = Bundle(for: type(of: self))
    print(frameworkBundle)
    
   
    self.defaultLib = device.makeDefaultLibrary()
   

    
    
    self.grayscaleShader = defaultLib?.makeFunction(name: "black")
    self.commandQueue = self.device.makeCommandQueue()
    
    self.commandBuffer = self.commandQueue?.makeCommandBuffer()
    self.commandEncoder = self.commandBuffer?.makeComputeCommandEncoder()
    
    
    //ERROR HERE
    if let shader = grayscaleShader {
        print("in")
        self.pipelineState = try? self.device.makeComputePipelineState(function: shader)
        
    } else { fatalError("unable to make compute pipeline") }
    
    self.inputImage = UIImage(named: "stockImage")!
    self.height = Int(self.inputImage.size.height)
    self.width = Int(self.inputImage.size.width)
    
}

func getCGImage(from uiimg: UIImage) -> CGImage? {
    
    UIGraphicsBeginImageContext(uiimg.size)
    uiimg.draw(in: CGRect(origin: .zero, size: uiimg.size))
    let contextImage = UIGraphicsGetImageFromCurrentImageContext()
    UIGraphicsEndImageContext()
    
    return contextImage?.cgImage
    
}

func getMTLTexture(from cgimg: CGImage) -> MTLTexture {
    
    let textureLoader = MTKTextureLoader(device: self.device)
    
    do{
        let texture = try textureLoader.newTexture(cgImage: cgimg, options: nil)
        let textureDescriptor = MTLTextureDescriptor.texture2DDescriptor(pixelFormat: texture.pixelFormat, width: width, height: height, mipmapped: false)
        textureDescriptor.usage = [.shaderRead, .shaderWrite]
        return texture
    } catch {
        fatalError("Couldn't convert CGImage to MTLtexture")
    }
    
}

func getCGImage(from mtlTexture: MTLTexture) -> CGImage? {
    
    var data = Array<UInt8>(repeatElement(0, count: 4*width*height))
    
    mtlTexture.getBytes(&data,
                        bytesPerRow: 4*width,
                        from: MTLRegionMake2D(0, 0, width, height),
                        mipmapLevel: 0)
    
    let bitmapInfo = CGBitmapInfo(rawValue: (CGBitmapInfo.byteOrder32Big.rawValue | CGImageAlphaInfo.premultipliedLast.rawValue))
    
    let colorSpace = CGColorSpaceCreateDeviceRGB()
    
    let context = CGContext(data: &data,
                            width: width,
                            height: height,
                            bitsPerComponent: 8,
                            bytesPerRow: 4*width,
                            space: colorSpace,
                            bitmapInfo: bitmapInfo.rawValue)
    
    return context?.makeImage()
}

func getUIImage(from cgimg: CGImage) -> UIImage? {
    return UIImage(cgImage: cgimg)
}

func getEmptyMTLTexture() -> MTLTexture? {
    
    let textureDescriptor = MTLTextureDescriptor.texture2DDescriptor(
        pixelFormat: MTLPixelFormat.rgba8Unorm,
        width: width,
        height: height,
        mipmapped: false)
    
    textureDescriptor.usage = [.shaderRead, .shaderWrite]
    
    return self.device.makeTexture(descriptor: textureDescriptor)
}

func getInputMTLTexture() -> MTLTexture? {
    if let inputImage = getCGImage(from: self.inputImage) {
        return getMTLTexture(from: inputImage)
    }
    else { fatalError("Unable to convert Input image to MTLTexture") }
}

func getBlockDimensions() -> MTLSize {
    let blockWidth = width / self.threadsPerBlock.width
    let blockHeight = height / self.threadsPerBlock.height
    return MTLSizeMake(blockWidth, blockHeight, 1)
}

func applyFilter() -> UIImage? {
    print("start")
    let date = Date()
    print(date)
    
    if let encoder = self.commandEncoder, let buffer = self.commandBuffer,
        let outputTexture = getEmptyMTLTexture(), let inputTexture = getInputMTLTexture() {
        
        encoder.setTextures([outputTexture, inputTexture], range: 0..<2)
        encoder.setComputePipelineState(self.pipelineState!)
        encoder.dispatchThreadgroups(self.getBlockDimensions(), threadsPerThreadgroup: threadsPerBlock)
        encoder.endEncoding()
        
        buffer.commit()
        buffer.waitUntilCompleted()
        
        guard let outputImage = getCGImage(from: outputTexture) else { fatalError("Couldn't obtain CGImage from MTLTexture") }
        
        print("stop")
        
        let date2 = Date()
        print(date2.timeIntervalSince(date))
        return getUIImage(from: outputImage)
        
    } else { fatalError("optional unwrapping failed") }
    
}


}

标签： iosswiftmetalmetalkitmetal-performance-shaders

ios - 我的自定义金属图像过滤器很慢。我怎样才能让它更快？

问题描述

解决方案

推荐阅读