This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Enabling -ftree-slp-vectorize on -O2/Os
- From: Segher Boessenkool <segher at kernel dot crashing dot org>
- To: Allan Sandfeld Jensen <linux at carewolf dot com>
- Cc: gcc at gcc dot gnu dot org
- Date: Sat, 26 May 2018 17:05:32 -0500
- Subject: Re: Enabling -ftree-slp-vectorize on -O2/Os
- References: <2659301.XPQk3P0qmd@twilight>
On Sat, May 26, 2018 at 11:32:29AM +0200, Allan Sandfeld Jensen wrote:
> I brought this subject up earlier, and was told to suggest it again for gcc 9,
> so I have attached the preliminary changes.
>
> My studies have show that with generic x86-64 optimization it reduces binary
> size with around 0.5%, and when optimizing for x64 targets with SSE4 or
> better, it reduces binary size by 2-3% on average. The performance changes are
> negligible however*, and I haven't been able to detect changes in compile time
> big enough to penetrate general noise on my platform, but perhaps someone has
> a better setup for that?
>
> * I believe that is because it currently works best on non-optimized code, it
> is better at big basic blocks doing all kinds of things than tightly written
> inner loops.
>
> Anythhing else I should test or report?
What does it do on other architectures?
Segher