From: Richard Biener <richard.guenther@gmail.com>
To: GT <tnggil@protonmail.com>
Cc: "gcc@gcc.gnu.org" <gcc@gcc.gnu.org>,
Szabolcs Nagy <Szabolcs.Nagy@arm.com>, nd <nd@arm.com>,
Bill Schmidt <wschmidt@linux.ibm.com>
Subject: Re: PPC64 libmvec implementation of sincos
Date: Thu, 05 Dec 2019 09:44:00 -0000 [thread overview]
Message-ID: <CAFiYyc0Fgf+MxZT=aCeAdHthyS3dAze=NNTJ7y+=FvS0RgoyDQ@mail.gmail.com> (raw)
In-Reply-To: <JvY5F5_4p--Fe-1i2REKyVzeb3ullNSJAxBxyiOfT9lxi7r7ho7fgNf4CNQOiBgrmQP5eHUFiHUjRiZScuMRh-myO4lb_EcXkh81WxJwgdk=@protonmail.com>
On Wed, Dec 4, 2019 at 9:53 PM GT <tnggil@protonmail.com> wrote:
>
> ‐‐‐‐‐‐‐ Original Message ‐‐‐‐‐‐‐
> On Wednesday, November 27, 2019 3:19 AM, Richard Biener <richard.guenther@gmail.com> wrote:
>
> ...
>
> > > Questions:
> > >
> > > 1. Should we aim to provide a vectorized version of __builtin_cexpi? If so, it would have
> > > to be a PPC64-only vector __builtin-cexpi, right?
> > >
> > > 2. Or should we require that vectorized sincos be available only when -fno-builtin-sincos flag
> > > is used in compilation?
> > >
> > >
> > > I don't think we need to fix both types of vectorization failures in order to obtain sincos
> > > vectorization.
> >
> > I think we should have a vectorized cexpi since that's having a sane
> > ABI. The complex
> > return type of cexpi makes it a little awkward for the vectorizer but
> > handling this should
> > be manageable. It's a bit difficult to expose complex types to the
> > vectorizer since
> > most cases are lowered early.
> >
>
> I'm trying to identify the source code which needs modification but I need help proceeding.
>
> I am comparing two compilations: The first is a simple file with a call to sin in a loop.
> Vectorization succeeds. The second is an almost identical file but with a call to sincos
> in the loop. Vectorization fails.
>
> In gdb, the earliest code location where the two compilations differ is in function
> number_of_iterations_exit_assumptions in file tree-ssa-loop-niter.c. Line
>
> op0 = gimple_cond_lhs (stmt);
>
> returns a tree which when analyzed in function instantiate_scev_r (in file tree-scalar-evolution.c)
> results in the first branch of the switch being taken for sincos. For sin, the 2nd branch of the
> switch is taken.
>
> How can I correlate stmt in the source line above to the relevant line in any dump among those created
> using debugging dump option -fdump-tree-all?
grep ;)
Can you provide a testcase with a simd attribute annotated cexpi that
one can play with?
Richard.
>
> Thanks.
> Bert.
next prev parent reply other threads:[~2019-12-05 9:44 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-27 19:23 GT
2019-09-30 13:53 ` Szabolcs Nagy
2019-09-30 17:30 ` GT
2019-09-30 18:07 ` Szabolcs Nagy
2019-09-30 18:09 ` Richard Biener
2019-11-25 16:53 ` GT
2019-11-27 8:19 ` Richard Biener
2019-12-04 20:53 ` GT
2019-12-05 9:44 ` Richard Biener [this message]
2019-12-05 17:46 ` GT
2019-12-06 10:48 ` Richard Biener
2019-12-06 11:15 ` Jakub Jelinek
2019-12-06 11:39 ` Richard Biener
2019-12-06 16:50 ` GT
2019-12-06 17:43 ` Richard Biener
2019-12-08 21:40 ` GT
2019-12-09 8:40 ` Richard Biener
2019-12-09 17:36 ` GT
2019-12-11 17:17 ` GT
2019-12-18 16:50 ` GT
2019-12-28 20:01 ` GT
2020-01-09 13:43 ` Richard Biener
2020-01-16 11:40 ` GT
2020-01-17 8:17 ` GT
2020-01-17 16:37 ` Richard Biener
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAFiYyc0Fgf+MxZT=aCeAdHthyS3dAze=NNTJ7y+=FvS0RgoyDQ@mail.gmail.com' \
--to=richard.guenther@gmail.com \
--cc=Szabolcs.Nagy@arm.com \
--cc=gcc@gcc.gnu.org \
--cc=nd@arm.com \
--cc=tnggil@protonmail.com \
--cc=wschmidt@linux.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).