[Bug middle-end/125810] Vector intrinsics are not synthesized from SIMD operations if greater than native register width

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=125810

--- Comment #4 from Drea Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Kuratius from comment #3)
> I'm not sure if this is a separate bug, but the vector extension abi/calling
> convention also appears to be different between clang and gcc. 
> https://godbolt.org/z/74KsK8db5
> *I think* this is also caused by not matching the native register width.

No, that is https://github.com/llvm/llvm-project/issues/78662 .