我正在开发 macOS 项目,该项目使用 Swift 和 Metal 在 GPU 上进行图像处理。上周,我收到了新的 15 英寸 MacBook Pro(2016 年末),并注意到我的代码有一些奇怪的地方:应该写入纹理的内核似乎没有这样做......
经过大量挖掘,我发现问题与 Metal 使用哪个 GPU(AMD Radeon Pro 455 或 Intel(R) HD Graphics 530)进行计算有关。
初始化MTLDevice
using MTLCopyAllDevices()
返回代表 Radeon 和 Intel GPU 的设备数组(同时MTLCreateSystemDefaultDevice()
返回默认设备,即 Radeon)。无论如何,代码在 Intel GPU 上都能按预期工作,但在 Radeon GPU 上却并非如此。
让我给你举个例子。
首先,这是一个简单的内核,它接受输入纹理并将其颜色复制到输出纹理:
kernel void passthrough(texture2d<uint, access::read> inTexture [[texture(0)]],
texture2d<uint, access::write> outTexture [[texture(1)]],
uint2 gid [[thread_position_in_grid]])
{
uint4 out = inTexture.read(gid);
outTexture.write(out, gid);
}
我为了使用这个内核,我使用这段代码:
let devices = MTLCopyAllDevices()
for device in devices {
print(device.name!) // [0] -> "AMD Radeon Pro 455", [1] -> "Intel(R) HD Graphics 530"
}
let device = devices[0]
let library = device.newDefaultLibrary()
let commandQueue = device.makeCommandQueue()
let passthroughKernelFunction = library!.makeFunction(name: "passthrough")
let cps = try! device.makeComputePipelineState(function: passthroughKernelFunction!)
let commandBuffer = commandQueue.makeCommandBuffer()
let commandEncoder = commandBuffer.makeComputeCommandEncoder()
commandEncoder.setComputePipelineState(cps)
// Texture setup
let width = 16
let height = 16
let byteCount = height*width*4
let bytesPerRow = width*4
let region = MTLRegionMake2D(0, 0, width, height)
let textureDescriptor = MTLTextureDescriptor.texture2DDescriptor(pixelFormat: .rgba8Uint, width: width, height: height, mipmapped: false)
// inTexture
var inData = [UInt8](repeating: 255, count: Int(byteCount))
let inTexture = device.makeTexture(descriptor: textureDescriptor)
inTexture.replace(region: region, mipmapLevel: 0, withBytes: &inData, bytesPerRow: bytesPerRow)
// outTexture
var outData = [UInt8](repeating: 128, count: Int(byteCount))
let outTexture = device.makeTexture(descriptor: textureDescriptor)
outTexture.replace(region: region, mipmapLevel: 0, withBytes: &outData, bytesPerRow: bytesPerRow)
commandEncoder.setTexture(inTexture, at: 0)
commandEncoder.setTexture(outTexture, at: 1)
commandEncoder.dispatchThreadgroups(MTLSize(width: 1,height: 1,depth: 1), threadsPerThreadgroup: MTLSize(width: width, height: height, depth: 1))
commandEncoder.endEncoding()
commandBuffer.commit()
commandBuffer.waitUntilCompleted()
// Get the data back from the GPU
outTexture.getBytes(&outData, bytesPerRow: bytesPerRow, from: region , mipmapLevel: 0)
// Validation
// outData should be exactly the same as inData
for (i,outElement) in outData.enumerated() {
if outElement != inData[i] {
print("Dest: \(outElement) != Src: \(inData[i]) at \(i))")
}
}
当运行此代码时let device = devices[0]
(Radeon GPU),outTexture 永远不会被写入(我的假设),因此 outData 保持不变。另一方面,当运行此代码时let device = devices[1]
(Intel GPU),一切都按预期工作,并且 outData 使用 inData 中的值进行更新。