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/102811] vcvtph2ps and vcvtps2ph should be used to convert _Float16 to SFmode with -mf16c
Date: Fri, 26 Nov 2021 13:46:43 +0000 [thread overview]
Message-ID: <bug-102811-4-qBW8OSD6Qr@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-102811-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102811
--- Comment #13 from Uroš Bizjak <ubizjak at gmail dot com> ---
(In reply to Hongtao.liu from comment #12)
> >
> > Just noticed that for some reason two VPXORs are emitted. One should be
> > enough for both VPINSRW insns.
>
> With new alternative in your attached match(vpblenw one), RA could reuse
> zero register, w/o that, xmm0/xmm1 need to be explictly clear for the upper
> bits.
> vpblendw $1, %xmm1, %xmm2, %xmm1 # 14 [c=4 l=6] *vec_setv8hf_0/8
True, but I'd expect some post-reload(?) pass to propagate zeros and remove
redundant initializations.
next prev parent reply other threads:[~2021-11-26 13:46 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-18 10:58 [Bug target/102811] New: " ubizjak at gmail dot com
2021-10-18 11:17 ` [Bug target/102811] " ubizjak at gmail dot com
2021-10-18 11:31 ` ubizjak at gmail dot com
2021-10-18 21:20 ` pinskia at gcc dot gnu.org
2021-11-26 1:30 ` cvs-commit at gcc dot gnu.org
2021-11-26 1:32 ` crazylht at gmail dot com
2021-11-26 1:48 ` pinskia at gcc dot gnu.org
2021-11-26 10:41 ` ubizjak at gmail dot com
2021-11-26 10:48 ` ubizjak at gmail dot com
2021-11-26 11:12 ` ubizjak at gmail dot com
2021-11-26 12:27 ` crazylht at gmail dot com
2021-11-26 13:01 ` ubizjak at gmail dot com
2021-11-26 13:28 ` crazylht at gmail dot com
2021-11-26 13:34 ` crazylht at gmail dot com
2021-11-26 13:46 ` ubizjak at gmail dot com [this message]
2021-11-26 15:22 ` crazylht at gmail dot com
2021-11-26 16:00 ` ubizjak at gmail dot com
2021-11-26 16:29 ` crazylht at gmail dot com
2021-11-26 16:49 ` ubizjak at gmail dot com
2021-11-26 16:57 ` ubizjak at gmail dot com
2021-11-29 2:50 ` crazylht at gmail dot com
2021-11-29 3:22 ` crazylht at gmail dot com
2021-11-29 8:03 ` ubizjak at gmail dot com
2021-11-29 9:46 ` cvs-commit at gcc dot gnu.org
2021-11-29 9:46 ` cvs-commit at gcc dot gnu.org
2021-11-29 21:17 ` cvs-commit at gcc dot gnu.org
2021-12-01 22:05 ` cvs-commit at gcc dot gnu.org
2021-12-01 22:15 ` ubizjak at gmail dot com
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-102811-4-qBW8OSD6Qr@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).