Python 3.13 beta 2 build fails on Windows when using both `--experimental-jit` and `--disable-gil`

[cdgriffith]

Bug report

Bug description:

PCbuild\build.bat --experimental-jit --disable-gil

commit: 14ff4c9

Repeating a lot of the same error:

C:\Users\redacted\Projects\cpython\Include\object.h(249,11): error G10448251: call to undeclared library function '__readgsqword' with type 'unsigned long long (unsigned long)'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] [C:\Users\redacted\Projects\cpython\PCbuild\pythoncore.vcxproj]

build_output.txt

Both --experimental-jit and --disable-gil work on their own.

CPython versions tested on:

3.13

Operating systems tested on:

Windows

Linked PRs

• gh-120326: Include intrin.h on Windows #120329
• [3.13] gh-120326: Include <intrin.h> on Windows with Free Threading (GH-120329) #120363
• [TEST] gh-120326: DEBUG Free Threading Windows 32-bit CI random failure #120407
• [3.13] gh-120326: Include <intrin.h> on Windows with Free Threading (GH-120329) #120414

[Eclips4]

Thanks for the report!
Confirmed on current main and 3.13 branch.

[brandtbucher]

This can probably be fixed by including the header where that function is declared in Tools/jit/template.c (and possibly Python/jit.c).

If it's some sort of compiler intrinsic that isn't supported by Clang, then we might need to update _Py_ThreadId (or whatever it is that's using these intrinsics) to check for _PyJIT_ACTIVE, which is only defined in jitted templates.

Separately, I'm wondering if we should expand the JIT test matrix to include more free-threaded jobs. It seems like we have a lot of missed coverage here, unfortunately.

[brandtbucher]

It seems like intrin.h could be what we're looking for on Windows. Anyone want to give it a shot?

[mdboom]

Separately, I'm wondering if we should expand the JIT test matrix to include more free-threaded jobs. It seems like we have a lot of missed coverage here, unfortunately.

Alternatively, we could consider this combination unsupported for now (and explicitly raise a build-time error). Obviously eventually we want them to play nicely together, but maybe that would be a better experience in the short term until we have all of the CI, testing and fixes in place.

[zooba]

(and explicitly raise a build-time error)

I'd just print a warning. If we add a hard block, someone has to remember to remove it before anyone can test.

[brandtbucher]

We already print a warning telling people to report errors like this. The JIT is thread-safe, and I’d like to keep it that way. Breaking the build would make it much harder to bisect where new errors were introduced down the line.

We already do a debug free-threaded JIT build for Linux in CI. Maybe we should just add others for Windows and macOS (they don’t run on most PRs).