The following minimal snippet SEGFAULTS with SDK 26.0 and 26.1. Won't crash if I remove async from the enclosing function signature - but it's impractical in a real project.
import Metal
import MetalPerformanceShaders
let SEED = UInt64(0x0)
typealias T = Float16
/* Why ran in async context? Because global GPU object,
and async makeMTLFunction,
and async makeMTLComputePipelineState.
Nevertheless, can trigger the bug without using global
@MainActor
let myGPU = MyGPU()
*/
@main
struct CMDLine {
static func main() async {
let ptr = UnsafeMutablePointer<T>.allocate(capacity: 0)
async let future: Void = randomFillOnGPU(ptr, count: 0)
print("Main thread is playing around")
await future
print("Successfully reached the end.")
}
static func randomFillOnGPU(_ buf: UnsafeMutablePointer<T>, count destbufcount: Int) async {
// let (device, queue) = await (myGPU.device, myGPU.commandqueue)
let myGPU = MyGPU()
let (device, queue) = (myGPU.device, myGPU.commandqueue)
// Init MTLBuffer, async let makeFunction, makeComputePipelineState, etc.
let tempDataType = MPSDataType.uInt32
let randfiller = MPSMatrixRandomMTGP32(device: device, destinationDataType: tempDataType, seed: Int(bitPattern:UInt(SEED)))
print("randomFillOnGPU: successfully created MPSMatrixRandom.")
// try await computePipelineState
// ^ Crashes before this could return
// Or in this minimal case, after randomFillOnGPU() returns
// make encoder, set pso, dispatch, commit...
}
}
actor MyGPU {
let device : MTLDevice
let commandqueue : MTLCommandQueue
init() {
guard let dev: MTLDevice = MPSGetPreferredDevice(.skipRemovable),
let cq = dev.makeCommandQueue(),
dev.supportsFamily(.apple6) || dev.supportsFamily(.mac2)
else { print("Unable to get Metal Device! Exiting"); exit(EX_UNAVAILABLE) }
print("Selected device: \(String(format: "%llX", dev.registryID))")
self.device = dev
self.commandqueue = cq
print("myGPU: initialization complete.")
}
}
See FB20916929. Apparently objc autorelease pool is releasing the wrong address during context switch (across suspension points). I wonder why such obvious case has not been caught before.
