[FFmpeg-devel] [PATCH v5] gcc: Don't disable '-ftree-vectorize' if gcc version higher than 13.

[Alexander Strasser]

On 2025-07-18 17:42 +0200, Kacper Michajlow wrote:
> On Fri, 11 Jul 2025 at 23:41, Michael Niedermayer
> <michael at niedermayer.cc> wrote:
> > On Thu, Jul 10, 2025 at 02:35:10PM +0300, Martin Storsjö wrote:
[...]
> >
> > > I'm unsure if we should allow it everywhere, and just single out loongarch
> > > as a case where it is known broken, or if we should only let GCC enable it
> > > on the major architectures that we've tested.
> >
> > I think for architectures where there is an active maintainer,
> > that maintainer should decide.
> >
> > For architectures where there is noone looking after them, its
> > safer to leave it disabled. Otherwsie users could be having
> > complex to debug issues to deal with and noone in ffmpeg able to
> > replicate
> 
> I agree. In a perfect world we would enable it everywhere, but if
> there is a worry that GCC is not a mature enough compiler to enable
> it, it's better to gradually roll it out on an opt-in basis. We can
> start with major architectures and for other architectures allow
> maintainers to decide.
> 
> Alternatively enable it everywhere for start and selectively disable
> it, once issues are identified. This may cause breakage, but is easy
> to workaround (by adding a compiler flag), and will likely identify
> issues with GCC faster.
> 
> Bottom line is that adding `-fno-tree-vectorize` in current year is
> quite a heavy hammer to avoid possible issues and especially on major
> architectures like x86 it should be safe to enable vectorization. It
> also currently gives clang and advantage over gcc if we compare pure c
> code in some cases.

Do we have concrete numbers how much better it is?
I mean pure C versions of FFmpeg were never really recommended.
Would also need the numbers per architecture.

Otherwise I would argue people that care about it because they
don't have Assembly implementations for their target or use
more C code because of other reasons should just enable vectorization
as well if they think it works for them.

Anyway I see no problem to enable compiler vectorization for compilers
and architectures where it works correctly and active maintainers agree
on it. And act, should it ever break again.


  Alexander