public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/51492] vectorizer does not support saturated arithmetic patterns
Date: Thu, 01 Feb 2024 13:42:20 +0000	[thread overview]
Message-ID: <bug-51492-4-HAInHtGJq6@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-51492-4@http.gcc.gnu.org/bugzilla/>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=51492

--- Comment #9 from JuzheZhong <juzhe.zhong at rivai dot ai> ---
Ok. After investigation of LLVM:

Before loop vectorizer:

  %cond12 = tail call i32 @llvm.usub.sat.i32(i32 %conv5, i32 %wsize)
  %conv13 = trunc i32 %cond12 to i16

After loop vectorizer:

  %10 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> %9, <16 x i32>
%broadcast.splat)
  %11 = trunc <16 x i32> %10 to <16 x i16>

I think GCC can follow this approach, that is, first recognize scalar
saturation,
then fall into loop vectorizer to vectorize it into the saturation.

  parent reply	other threads:[~2024-02-01 13:42 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-10  1:38 [Bug tree-optimization/51492] New: vectorizer generates unnecessary code drepper.fsp at gmail dot com
2011-12-12 10:25 ` [Bug tree-optimization/51492] vectorizer does not support saturated arithmetic patterns rguenth at gcc dot gnu.org
2012-01-08 18:57 ` drepper.fsp at gmail dot com
2012-07-13  8:39 ` rguenth at gcc dot gnu.org
2021-08-24 23:44 ` pinskia at gcc dot gnu.org
2021-08-25  3:54 ` pinskia at gcc dot gnu.org
2024-02-01 13:06 ` pan2.li at intel dot com
2024-02-01 13:37 ` juzhe.zhong at rivai dot ai
2024-02-01 13:42 ` juzhe.zhong at rivai dot ai [this message]
2024-02-01 14:40 ` juzhe.zhong at rivai dot ai
2024-02-01 14:41 ` juzhe.zhong at rivai dot ai
2024-02-01 15:10 ` tnfchris at gcc dot gnu.org
2024-02-02  1:04 ` pan2.li at intel dot com
2024-02-02 11:11 ` tnfchris at gcc dot gnu.org
2024-02-03  6:57 ` pan2.li at intel dot com
2024-02-06  1:13 ` pan2.li at intel dot com
2024-02-06 22:11 ` tnfchris at gcc dot gnu.org
2024-02-07  0:57 ` pan2.li at intel dot com
2024-05-16 12:09 ` cvs-commit at gcc dot gnu.org
2024-05-16 12:09 ` cvs-commit at gcc dot gnu.org
2024-05-18  2:17 ` cvs-commit 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-51492-4-HAInHtGJq6@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).