This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] powerpc: Add a POWER8-optimized version of powf()
- From: Steven Munroe <munroesj at linux dot vnet dot ibm dot com>
- To: Adhemerval Zanella <adhemerval dot zanella at linaro dot org>
- Cc: libc-alpha at sourceware dot org
- Date: Fri, 26 May 2017 19:37:57 -0500
- Subject: Re: [PATCH] powerpc: Add a POWER8-optimized version of powf()
- Authentication-results: sourceware.org; auth=none
- References: <8c7e16e8-d605-9552-89cc-c658dba81a6f@us.ibm.com> <9d5740ea-fb29-13d9-b71c-de29290350aa@linaro.org>
- Reply-to: munroesj at linux dot vnet dot ibm dot com
On Fri, 2017-05-26 at 16:55 -0300, Adhemerval Zanella wrote:
>
> On 25/05/2017 14:47, Paul Clarke wrote:
> > This implementation is heavily based on sysdeps/ieee754/flt-32/e_powf.c.
> > Most significant changes are code simplification and use of doubles for
> > intermediate values. Also, some rearrangement to move early
> > non-dependent code later, out of the faster paths.
> >
> > 2017-05-25 Paul A. Clarke <pc@us.ibm.com>
> >
> > * sysdeps/powerpc/powerpc64/fpu/multiarch/Makefile
> > [$(subdir) = math] (libm-sysdep_routines): Add e_powf-power8 and
> > e_powf-ppc64.
> > * sysdeps/powerpc/powerpc64/fpu/multiarch/e_powf-power8.c: New file.
> > * sysdeps/powerpc/powerpc64/fpu/multiarch/e_powf-ppc64.c: Likewise.
> > * sysdeps/powerpc/powerpc64/fpu/multiarch/e_powf.c: Likewise.
> > * sysdeps/powerpc/powerpc64/power8/fpu/e_powf.c: Likewise.
>
> This changes seems to be arch independent and I would like to avoid adding
> even more arch specific. Is there any reason why this can't be used as
> the default implementation? Do you have number on different architecture
> for it?
>
If other platform maintainer what to try this implementation and report
that would be OK.
But I don't this it is correct or fair to ask Paul to prove a negative.
These quests tend to be very labor intensive and usually don't work out
(as really common) in the end.