public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/56253] fp-contract does not work with SSE and AVX FMAs (neither FMA4 nor FMA3)
Date: Fri, 08 Feb 2013 14:59:00 -0000	[thread overview]
Message-ID: <bug-56253-4-3Tmj8eKZwC@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-56253-4@http.gcc.gnu.org/bugzilla/>


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=56253

--- Comment #6 from Uros Bizjak <ubizjak at gmail dot com> 2013-02-08 14:58:42 UTC ---
(In reply to comment #5)
> Hmm, I wonder how the vectorizer then accesses add/sub patterns without
> SSE math.  It just queries optabs ...
> 
> We cannot handle the FMA case with standard operations anyway.  But
> if SSE modes are used, why should convert_mult_to_fma have to back off
> (it also just looks at standard optabs)?
> 
> That said - should the above TARGET_SSE_MATH restriction not only
> apply to scalar modes?

Ugh, you are right. TARGET_SSE_MATH should apply to scalar modes only.

Patch in works.


  parent reply	other threads:[~2013-02-08 14:59 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-02-08 12:15 [Bug tree-optimization/56253] New: " kretz at kde dot org
2013-02-08 12:39 ` [Bug target/56253] " rguenth at gcc dot gnu.org
2013-02-08 12:53 ` rguenth at gcc dot gnu.org
2013-02-08 12:59 ` ubizjak at gmail dot com
2013-02-08 13:30 ` rguenth at gcc dot gnu.org
2013-02-08 13:43 ` rguenth at gcc dot gnu.org
2013-02-08 14:59 ` ubizjak at gmail dot com [this message]
2013-02-11 11:36 ` rguenth at gcc dot gnu.org
2014-09-23 16:40 ` agner at agner dot org
2014-09-23 19:14 ` agner at agner dot org
2014-09-23 19:22 ` glisse at gcc dot gnu.org
2014-09-24  5:14 ` agner at agner dot org
2014-09-25  6:37 ` glisse at gcc dot gnu.org
2014-09-25  6:39 ` glisse at gcc dot gnu.org

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=bug-56253-4-3Tmj8eKZwC@http.gcc.gnu.org/bugzilla/ \
    --to=gcc-bugzilla@gcc.gnu.org \
    --cc=gcc-bugs@gcc.gnu.org \
    /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).