Re: The Emacs master is much slower than the emacs-27 branch.

[Óscar Fuentes]

Gregory Heytings via "Emacs development discussions."
<emacs-devel@gnu.org> writes:

>>
>> It occurred to me that the differences in the relative performance
>> could be due to a different GCC version and/
>>
>
> GCC is not the problem here, I just ran the same benchmark with Emacs
> 27 compiled with different versions of GCC:
>
>     | GCC 8.4 | GCC 9.3 | GCC 10.2 |
> -Og |    ~67s |    ~68s |     ~67s |
> -O0 |    ~63s |    ~63s |     ~63s |
> -O1 |    ~26s |    ~27s |     ~26s |
> -O2 |    ~18s |    ~18s |     ~18s |
> -O3 |    ~18s |    ~17s |     ~17s |
>
>>
>> or the effect of inlining on 32-bit code vs 64-bit code produced by GCC.
>>
>
> That's possible indeed.

In case you are discussing the origin of the problem, it is clear to me
that it is related to -Og and changing "extern inline" to "static",
which has an impact due to -finline-functions-called-once being disabled
at -Og because those functions are not inlined anymore.