public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "jakub at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/63594] [5 Regression] ICE: in ix86_vector_duplicate_value, at config/i386/i386.c:39831 with -mavx512f
Date: Mon, 20 Oct 2014 10:39:00 -0000 [thread overview]
Message-ID: <bug-63594-4-3bmYGYpaxW@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-63594-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63594
--- Comment #3 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
Created attachment 33761
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=33761&action=edit
WIP patch for discussions
>From what I see, if TARGET_AVX512BW is not defined, then we obviously can't use
ix86_vector_duplicate_value, but need two instructions (either it can be
QI->V32QI / HI->V16HI broadcast followed by concat of the two parts, or
QI->V16QI / HI->V8HI broadcast followed by concat of the 4 parts together).
But, it seems even for -mavx2 or -mavx we actually generate terrible code,
for -mavx2 there is no point in using 2 instructions when in theory
vpbroadcast{b,w} should handle it alone just fine.
The patch enables all of that, but unfortunately we generate perhaps not so
good code with it, e.g. for -mavx2 in testchar32, we spill the argument always
to memory, and then broadcast it from memory, even when vmovd + broadcast from
register could have been used.
And in testchar16, for some reason we spill into memory, and broadcast from
vmovd result (so the spill is totally useless).
Uros/Kyrill, any thoughts on this?
next prev parent reply other threads:[~2014-10-20 10:18 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <bug-63594-4@http.gcc.gnu.org/bugzilla/>
2014-10-19 19:04 ` ubizjak at gmail dot com
2014-10-20 9:15 ` jakub at gcc dot gnu.org
2014-10-20 10:39 ` jakub at gcc dot gnu.org [this message]
2014-10-20 12:50 ` kyukhin at gcc dot gnu.org
2014-10-20 17:05 ` jakub at gcc dot gnu.org
2014-10-20 17:16 ` jakub at gcc dot gnu.org
2014-10-21 9:31 ` jakub at gcc dot gnu.org
2014-10-22 7:00 ` jakub at gcc dot gnu.org
2014-10-22 7:24 ` jakub at gcc dot gnu.org
2014-10-24 7:04 ` trippels at gcc dot gnu.org
2014-11-18 14:54 ` jakub at gcc dot gnu.org
2014-11-20 12:38 ` rguenth at gcc dot gnu.org
2014-12-10 9:01 ` jakub 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-63594-4-3bmYGYpaxW@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).