public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "thiago at kde dot org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/59539] Missed optimisation: VEX-prefixed operations don't need aligned data
Date: Wed, 18 Dec 2013 08:49:00 -0000	[thread overview]
Message-ID: <bug-59539-4-6OdOXnaiwu@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-59539-4@http.gcc.gnu.org/bugzilla/>

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59539

--- Comment #2 from Thiago Macieira <thiago at kde dot org> ---
I have to use _mm_loadu_si128 because non-VEX SSE requires explicit unaligned
loads.

Here's more food for thought:

    __m128i result = _mm_cmpeq_epi16((__m128i*)p1, (__m128i*)p2);

For non-VEX code, so far the compiler emitted one MOVDQA and one PCMPEQW if it
could, enforcing that both sources needed to be aligned. With VEX, VPCMPEQW can
do unaligned, so should the other load also be changed to VPMOVDQU instead of
VPMOVDQA?

Similarly, if I use _mm_load_si128 (not loadu), can the compiler combine one
load into the next instruction? Performance-wise, the execution will be the
same, with one fewer instruction to be retired (so, better); but it will not
cause an unaligned fault if the pointer isn't aligned.


  parent reply	other threads:[~2013-12-18  8:49 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-12-18  0:50 [Bug target/59539] New: " thiago at kde dot org
2013-12-18  8:33 ` [Bug target/59539] " jakub at gcc dot gnu.org
2013-12-18  8:49 ` thiago at kde dot org [this message]
2013-12-18  9:38 ` ubizjak at gmail dot com
2013-12-18  9:43 ` jakub at gcc dot gnu.org
2013-12-18  9:50 ` ubizjak at gmail dot com
2013-12-18 10:18 ` jakub at gcc dot gnu.org
2013-12-18 10:39 ` ubizjak at gmail dot com
2013-12-18 11:04 ` ubizjak at gmail dot com
2013-12-18 16:50 ` jakub at gcc dot gnu.org
2013-12-18 16:52 ` jakub at gcc dot gnu.org
2013-12-18 17:36 ` thiago at kde dot org
2013-12-19  0:07 ` thiago at kde dot org
2013-12-19  0:14 ` thiago at kde dot 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-59539-4-6OdOXnaiwu@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).