@mtlprintf

[tgymnich]

Implement @mtlprintf and friends using os_log

TODO:

• Printing of floats does not work since they will be converted to doubles due to the vararg calling convention which will be caught by our IR checker
• Version check the @mtlprintf macro
• Add tests
• Capturing and logging are mutually exclusive

depends on: JuliaGPU/GPUCompiler.jl#630
notify: #226

[tgymnich]

@maleadt Any idea how we can implement the version check for the @mtlprintf macro? I know we could check the air version inside the kernel but I'd like to avoid that.

Also can we get rid of the double check in check_ir?

[christiangnrd]

Would it be worth benchmarking the performance difference between having logging active vs not?

[tgymnich]

Would it be worth benchmarking the performance difference between having logging active vs not?

@christiangnrd Sure. I don't expect there to be much overhead besides allocation of the log buffer and checking it for logs after running a kernel. But we might want to look into only conditionally adding MTLLogState since logging also prevents GPU frame capture.

[maleadt]

@maleadt Any idea how we can implement the version check for the @mtlprintf macro? I know we could check the air version inside the kernel but I'd like to avoid that.

Given that the macro expands way to early, I don't think there's anything we can do but checking in the kernel. Why are you opposed to that? GPUCompiler.jl has infrastructure to optimize those checks away, see e.g. how CUDA.jl exposes the device capability and PTX ISA version to the kernel.

[tgymnich]

We could also wrap the macro and accompanying functions in if Metal.macos_version() >= v"15".

[christiangnrd]

If we do that we should have definitions in both cases and give an informative error if Metal.macos_version() < v"15".

[maleadt]

Actually, looks like I provided the run-time queries already:

Metal.jl/src/device/intrinsics/version.jl

Lines 64 to 65 in 6c82916

	@device_function @inline metal_version() = SimpleVersion(metal_major(), metal_minor())
	@device_function @inline air_version() = SimpleVersion(air_major(), air_minor())

So we can just use that in the generated code, generating an error when emitting code for an older platform. That of course depends on #416 for meaningful reporting, but we'll get there.

I'd rather not simply check based on the macOS version during macro expansion, since we might want to target older Metal versions than the system supports.

[christiangnrd]

Looks good! However do you know what's causing the tests to hang?

[tgymnich]

Looks good! However do you know what's causing the tests to hang?

@christiangnrd The hangs are caused by this one line:

@print_and_throw "@mtlprintf requires Metal 3.2 (macOS 15) or higher"

[christiangnrd]

@maleadt Could we have one of the Apple Silicon runners upgraded to Sequoia so the output tests don't get ignored? Edit: All the runners are running 13.3.1. Should we also have one on macOS 14?

I would also like to see #420 merged first (with benchmarks run on macOS 15) to see how big the impact of enabling logging is.

[tgymnich]

@christiangnrd I recently made changes so that logging (e.g. MTLLogState and friends) is only enabled whenever we actually use the feature.

[christiangnrd]

Just pushed a whitespace-only formatting commit

[christiangnrd]

@christiangnrd I recently made changes so that logging (e.g. MTLLogState and friends) is only enabled whenever we actually use the feature.

In that case I still think we should be able to test on macOS 15, but I think we should merge this as soon as it's ready.

[maleadt]

I've upgraded one of the workers to macOS 15:

See the macos_version tag which can be used to select on this.

[christiangnrd]

@tgymnich Tests now seem to be passing locally with the 2 suggestions I just made. Is this still blocked?

I'll take care of the rebase since the conflicts are my fault.

[tgymnich]

This is awesome! Thank you so much @christiangnrd.

[christiangnrd]

LGTM. Make sure to check out my commit to make sure I didn't make any undesired changes.

Oh and I guess formatting. I personally wouldn't touch the suggestions for the @objc calls or the test indenting suggestions, but I'll leave it up to you to decide which ones you want to implement (unless @maleadt feels otherwise)

Hopefully #527 will allow us to clean up all the version gates but for now they're necessary.

[maleadt]

How is this not blocked by #433 anymore?

[tgymnich]

@maleadt #433 is still an issue on some older devices.
However the main issue with this PR (mentioned here: #418 (comment)) can be resolved by using Core.print instead of Base.print in the command buffer callback.

[maleadt]

However the main issue with this PR (mentioned here: #418 (comment)) can be resolved by using Core.print instead of Base.print in the command buffer callback.

I'm having a hard time understanding that. If switching to a non-yielding print fixes the issue, it implies we were running into #532. But that doesn't match you mentioning 100% GPU usage in #433?

[christiangnrd]

FWIW I can replicate the hang but not the 100% GPU usage mentioned in #433.