【发布时间】：2017-02-05 01:12:30
【问题描述】：
我正在编写一个视图来在 Metal 中绘制实时数据。我正在使用点图元绘制样本，并对顶点和统一数据进行三重缓冲。我遇到的问题是调用 currentDrawable 返回所需的时间似乎是不可预测的。就好像有时没有准备好可绘制对象，我必须等待一整帧才能有一个可用。通常 currentDrawable 返回的时间约为 0.07 毫秒（这与我预期的差不多），但其他时候是整整 1/60 秒。这会导致整个主线程阻塞，也就是说至少不是很理想。
我在 iPhone 6S Plus 和 iPad Air 上看到了这个问题。我还没有在 Mac 上看到这种行为（我有一个带有 AMD 460 GPU 的 2016 MPB）。我的猜测是，这在某种程度上与 iOS 设备中的 GPU 基于 TBDR 的事实有关。我不认为我受到带宽限制，因为无论我绘制多少样本，我都会得到完全相同的行为。
为了说明这个问题，我编写了一个绘制静态正弦波的最小示例。这是一个简化的示例，因为我通常会将样本 memcpy 到当前的 vertexBuffer 中，就像我对制服所做的那样。这就是为什么我要对顶点数据和制服进行三重缓冲。但这仍然足以说明问题。只需将此视图设置为情节提要中的基本视图，然后运行。在某些运行中，它工作得很好。其他时候 currentDrawable 以 16.67 毫秒的返回时间开始，几秒钟后跳到 0.07 毫秒，然后又回到 16.67。如果出于某种原因旋转设备，它似乎会从 16.67 跳到 0.07。
MTKView 子类
import MetalKit
let N = 500
class MetalGraph: MTKView {
typealias Vertex = Int32
struct Uniforms {
var offset: UInt32
var numSamples: UInt32
}
// Data
var uniforms = Uniforms(offset: 0, numSamples: UInt32(N))
// Buffers
var vertexBuffers = [MTLBuffer]()
var uniformBuffers = [MTLBuffer]()
var inflightBufferSemaphore = DispatchSemaphore(value: 3)
var inflightBufferIndex = 0
// Metal State
var commandQueue: MTLCommandQueue!
var pipeline: MTLRenderPipelineState!
// Setup
override func awakeFromNib() {
super.awakeFromNib()
device = MTLCreateSystemDefaultDevice()
commandQueue = device?.makeCommandQueue()
colorPixelFormat = .bgra8Unorm
setupPipeline()
setupBuffers()
}
func setupPipeline() {
let library = device?.newDefaultLibrary()
let descriptor = MTLRenderPipelineDescriptor()
descriptor.colorAttachments[0].pixelFormat = .bgra8Unorm
descriptor.vertexFunction = library?.makeFunction(name: "vertexFunction")
descriptor.fragmentFunction = library?.makeFunction(name: "fragmentFunction")
pipeline = try! device?.makeRenderPipelineState(descriptor: descriptor)
}
func setupBuffers() {
// Produces a dummy sine wave with N samples, 2 periods, with a range of [0, 1000]
let vertices: [Vertex] = (0..<N).map {
let periods = 2.0
let scaled = Double($0) / (Double(N)-1) * periods * 2 * .pi
let value = (sin(scaled) + 1) * 500 // Transform from range [-1, 1] to [0, 1000]
return Vertex(value)
}
let vertexBytes = MemoryLayout<Vertex>.size * vertices.count
let uniformBytes = MemoryLayout<Uniforms>.size
for _ in 0..<3 {
vertexBuffers .append(device!.makeBuffer(bytes: vertices, length: vertexBytes))
uniformBuffers.append(device!.makeBuffer(bytes: &uniforms, length: uniformBytes))
}
}
// Drawing
func updateUniformBuffers() {
uniforms.offset = (uniforms.offset + 1) % UInt32(N)
memcpy(
uniformBuffers[inflightBufferIndex].contents(),
&uniforms,
MemoryLayout<Uniforms>.size
)
}
override func draw(_ rect: CGRect) {
_ = inflightBufferSemaphore.wait(timeout: .distantFuture)
updateUniformBuffers()
let start = CACurrentMediaTime()
guard let drawable = currentDrawable else { return }
print(String(format: "Grab Drawable: %.3f ms", (CACurrentMediaTime() - start) * 1000))
guard let passDescriptor = currentRenderPassDescriptor else { return }
passDescriptor.colorAttachments[0].loadAction = .clear
passDescriptor.colorAttachments[0].storeAction = .store
passDescriptor.colorAttachments[0].clearColor = MTLClearColorMake(0.2, 0.2, 0.2, 1)
let commandBuffer = commandQueue.makeCommandBuffer()
let encoder = commandBuffer.makeRenderCommandEncoder(descriptor: passDescriptor)
encoder.setRenderPipelineState(pipeline)
encoder.setVertexBuffer(vertexBuffers[inflightBufferIndex], offset: 0, at: 0)
encoder.setVertexBuffer(uniformBuffers[inflightBufferIndex], offset: 0, at: 1)
encoder.drawPrimitives(type: .point, vertexStart: 0, vertexCount: N)
encoder.endEncoding()
commandBuffer.addCompletedHandler { _ in
self.inflightBufferSemaphore.signal()
}
commandBuffer.present(drawable)
commandBuffer.commit()
inflightBufferIndex = (inflightBufferIndex + 1) % 3
}
}
着色器
#include <metal_stdlib>
using namespace metal;
struct VertexIn {
int32_t value;
};
struct VertexOut {
float4 pos [[position]];
float pointSize [[point_size]];
};
struct Uniforms {
uint32_t offset;
uint32_t numSamples;
};
vertex VertexOut vertexFunction(device VertexIn *vertices [[buffer(0)]],
constant Uniforms *uniforms [[buffer(1)]],
uint vid [[vertex_id]])
{
// I'm using the vertex index to evenly spread the
// samples out in the x direction
float xIndex = float((vid + (uniforms->numSamples - uniforms->offset)) % uniforms->numSamples);
float x = (float(xIndex) / float(uniforms->numSamples - 1)) * 2.0f - 1.0f;
// Transforming the values from the range [0, 1000] to [-1, 1]
float y = (float)vertices[vid].value / 500.0f - 1.0f ;
VertexOut vOut;
vOut.pos = {x, y, 1, 1};
vOut.pointSize = 3;
return vOut;
}
fragment half4 fragmentFunction() {
return half4(1, 1, 1, 1);
}
可能与此相关：在我看到的所有示例中，inflightBufferSemaphore 在 commandBuffer 的 completionHandler 中递增，就在信号量发出信号之前（这对我来说很有意义）。当我有那条线时，我会得到一种奇怪的抖动效果，几乎就像帧缓冲区被无序显示一样。将这条线移到绘图函数的底部解决了这个问题，尽管它对我来说没有多大意义。我不确定这是否与 currentDrawable 的返回时间如此不可预测有关，但我感觉这两个问题来自同一个潜在问题。
任何帮助将不胜感激！
【问题讨论】：
标签： ios swift drawable point metal