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/103905] [12 Regression] Miscompiled i386-expand.c with -march=bdver1 and -O3 since r12-1789-g836328b2c99f5b8d
Date: Tue, 04 Jan 2022 21:44:07 +0000	[thread overview]
Message-ID: <bug-103905-4-yKxAnLG9ST@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-103905-4@http.gcc.gnu.org/bugzilla/>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103905

--- Comment #6 from Uroš Bizjak <ubizjak at gmail dot com> ---
@Jakub: It looks the problem is in expand_vec_perm_pshufb, where permutation
vector is recalculated for partial vectors:

  if (vmode == V4QImode
      || vmode == V8QImode)
    {
      rtx m128 = GEN_INT (-128);

      /* Remap elements from the second operand, as we have to
         account for inactive top elements from the first operand.  */
      if (!d->one_operand_p)
        {
          int sz = GET_MODE_SIZE (vmode);

          for (i = 0; i < nelt; ++i)
            {
              int ival = INTVAL (rperm[i]);
              if (ival >= sz)
                ival += 16-sz;
              rperm[i] = GEN_INT (ival);
            }
        }

      /* V4QI/V8QI is emulated with V16QI instruction, fill inactive
         elements in the top positions with zeros.  */
      for (i = nelt; i < 16; ++i)
        rperm[i] = m128;

      vpmode = V16QImode;
    }

I must admit I only eyeballed the generated code, so perhaps there lies the
dragon.

  parent reply	other threads:[~2022-01-04 21:44 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-04 19:29 [Bug target/103905] New: " marxin at gcc dot gnu.org
2022-01-04 19:30 ` [Bug target/103905] " pinskia at gcc dot gnu.org
2022-01-04 19:56 ` marxin at gcc dot gnu.org
2022-01-04 20:12 ` ubizjak at gmail dot com
2022-01-04 21:03 ` ubizjak at gmail dot com
2022-01-04 21:14 ` ubizjak at gmail dot com
2022-01-04 21:31 ` jakub at gcc dot gnu.org
2022-01-04 21:44 ` ubizjak at gmail dot com [this message]
2022-01-05  5:43 ` marxin at gcc dot gnu.org
2022-01-05  7:48 ` rguenth at gcc dot gnu.org
2022-01-05  8:57 ` ubizjak at gmail dot com
2022-01-05  9:02 ` marxin at gcc dot gnu.org
2022-01-05  9:17 ` jakub at gcc dot gnu.org
2022-01-05  9:29 ` ubizjak at gmail dot com
2022-01-05 10:01 ` marxin at gcc dot gnu.org
2022-01-05 19:07 ` cvs-commit at gcc dot gnu.org
2022-01-05 19:14 ` ubizjak at gmail dot com
2022-01-06 21:26 ` pinskia 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-103905-4-yKxAnLG9ST@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).