public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "rguenther at suse dot de" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/96789] x264: sub4x4_dct() improves when vectorization is disabled
Date: Mon, 21 Sep 2020 07:14:22 +0000 [thread overview]
Message-ID: <bug-96789-4-tjw0B8bOfk@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-96789-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96789
--- Comment #17 from rguenther at suse dot de <rguenther at suse dot de> ---
On Fri, 18 Sep 2020, linkw at gcc dot gnu.org wrote:
> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96789
>
> --- Comment #15 from Kewen Lin <linkw at gcc dot gnu.org> ---
> (In reply to rguenther@suse.de from comment #14)
> > On Fri, 18 Sep 2020, linkw at gcc dot gnu.org wrote:
> >
> > > https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96789
> > >
> > > --- Comment #13 from Kewen Lin <linkw at gcc dot gnu.org> ---
> > > > 2) on Power, the conversion from unsigned char to unsigned short is nop
> > > > conversion, when we counting scalar cost, it's counted, then add costs 32
> > > > totally onto scalar cost. Meanwhile, the conversion from unsigned short to
> > > > signed short should be counted but it's not (need to check why further).
> > >
> > > UH to SH conversion is true when calling vect_nop_conversion_p, so it's not
> > > even put into the cost vector.
> > >
> > > tree_nop_conversion_p's comments saying:
> > >
> > > /* Return true iff conversion from INNER_TYPE to OUTER_TYPE generates
> > > no instruction. */
> > >
> > > I may miss something here, but UH to SH conversion does need one explicit
> > > extend instruction *extsh*, the precision/mode equality check looks wrong for
> > > this conversion.
> >
> > Well, it isn't a RTL predicate and it only needs extension because
> > there's never a HImode pseudo but always SImode subregs.
>
> Thanks Richi! Should we take care of this case? or neglect this kind of
> extension as "no instruction"? I was intent to handle it in target specific
> code, but it isn't recorded into cost vector while it seems too heavy to do the
> bb_info slp_instances revisits in finish_cost.
I think it's not something we should handle on GIMPLE.
next prev parent reply other threads:[~2020-09-21 7:14 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-26 3:19 [Bug tree-optimization/96789] New: " linkw at gcc dot gnu.org
2020-08-26 6:53 ` [Bug target/96789] " rguenth at gcc dot gnu.org
2020-08-26 7:13 ` linkw at gcc dot gnu.org
2020-08-27 3:28 ` linkw at gcc dot gnu.org
2020-08-27 6:40 ` rguenth at gcc dot gnu.org
2020-08-27 11:16 ` rguenth at gcc dot gnu.org
2020-08-31 4:05 ` linkw at gcc dot gnu.org
2020-09-16 10:03 ` linkw at gcc dot gnu.org
2020-09-16 11:17 ` rguenth at gcc dot gnu.org
2020-09-16 12:25 ` linkw at gcc dot gnu.org
2020-09-16 13:04 ` rguenth at gcc dot gnu.org
2020-09-17 2:50 ` linkw at gcc dot gnu.org
2020-09-17 5:06 ` linkw at gcc dot gnu.org
2020-09-18 9:11 ` linkw at gcc dot gnu.org
2020-09-18 10:30 ` rguenther at suse dot de
2020-09-18 13:40 ` linkw at gcc dot gnu.org
2020-09-19 15:45 ` crazylht at gmail dot com
2020-09-21 7:14 ` rguenther at suse dot de [this message]
2020-09-25 12:46 ` linkw at gcc dot gnu.org
2020-09-25 12:52 ` linkw at gcc dot gnu.org
2020-09-25 12:57 ` rguenth at gcc dot gnu.org
2020-09-25 13:05 ` rguenth at gcc dot gnu.org
2020-09-27 2:56 ` crazylht at gmail dot com
2020-09-27 3:07 ` crazylht at gmail dot com
2020-09-27 6:48 ` rguenther at suse dot de
2020-09-27 10:20 ` linkw at gcc dot gnu.org
2020-09-27 10:36 ` linkw at gcc dot gnu.org
2020-09-27 10:42 ` linkw at gcc dot gnu.org
2020-09-28 5:45 ` crazylht at gmail dot com
2020-09-28 6:40 ` linkw at gcc dot gnu.org
2020-09-28 6:48 ` rguenth at gcc dot gnu.org
2020-09-28 6:59 ` rguenth at gcc dot gnu.org
2020-09-28 12:54 ` linkw at gcc dot gnu.org
2020-09-28 13:27 ` rguenth at gcc dot gnu.org
2020-09-29 2:05 ` crazylht at gmail dot com
2020-09-29 12:27 ` rsandifo at gcc dot gnu.org
2020-11-03 6:28 ` cvs-commit at gcc dot gnu.org
2020-11-05 2:25 ` linkw 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-96789-4-tjw0B8bOfk@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).