> -----Original Message-----
> From: Cui, Lili
> Sent: Wednesday, January 14, 2026 10:02 AM
> To: 'Uros Bizjak' <[email protected]>
> Cc: [email protected]; Liu, Hongtao <[email protected]>
> Subject: RE: [PATCH] x86: Disable tight loop alignment for m_CORE_ATOM
> 
> 
> 
> > -----Original Message-----
> > From: Uros Bizjak <[email protected]>
> > Sent: Tuesday, January 13, 2026 4:17 PM
> > To: Cui, Lili <[email protected]>
> > Cc: [email protected]; Liu, Hongtao <[email protected]>
> > Subject: Re: [PATCH] x86: Disable tight loop alignment for m_CORE_ATOM
> >
> > On Tue, Jan 13, 2026 at 3:04 AM Cui, Lili <[email protected]> wrote:
> > >
> > > From: Lili Cui <[email protected]>
> > >
> > > Hi,
> > >
> > > This patch is to disable tight loop alignment for m_CORE_ATOM.
> > >
> > > Bootstrapped & regtested on x86-64-pc-linux-gnu.
> > >
> > > Ok for trunk?
> >
> > OK, I hope that tuning patches can still be applied in Stage 4.
> >
> 

Can I backport it to GCC15?

Thanks,
Lili.

> Committed. Thanks, Uros.
> 
> Lili.
> 
> > Thanks,
> > Uros.
> >
> > >
> > > Thanks,
> > > Lili.
> > >
> > >
> > > For the E-core front end, aligning tight loops provides little benefit.
> > >
> > > gcc/ChangeLog:
> > >
> > >         * config/i386/x86-tune.def (X86_TUNE_ALIGN_TIGHT_LOOPS):
> > >         disable tight loop alignment for m_CORE_ATOM.
> > > ---
> > >  gcc/config/i386/x86-tune.def | 3 ++-
> > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/gcc/config/i386/x86-tune.def
> > > b/gcc/config/i386/x86-tune.def index 3298d9daed6..a1944620daf 100644
> > > --- a/gcc/config/i386/x86-tune.def
> > > +++ b/gcc/config/i386/x86-tune.def
> > > @@ -253,7 +253,8 @@ DEF_TUNE (X86_TUNE_FOUR_JUMP_LIMIT,
> > > "four_jump_limit",
> > >
> > >  /* X86_TUNE_ALIGN_TIGHT_LOOPS: if false, tight loops are not aligned.
> > > */  DEF_TUNE (X86_TUNE_ALIGN_TIGHT_LOOPS, "align_tight_loops",
> > > -        ~(m_ZHAOXIN | m_CASCADELAKE | m_SKYLAKE_AVX512))
> > > +        ~(m_ZHAOXIN | m_CASCADELAKE | m_SKYLAKE_AVX512
> > > +          | m_CORE_ATOM))
> > >
> > >
> >
> /***************************************************************
> > **************/
> > >  /* Integer instruction selection tuning                                  
> > >     */
> > > --
> > > 2.34.1
> > >

Reply via email to