public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "avi at scylladb dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug target/103554] -mavx generates worse code on scalar code Date: Mon, 06 Dec 2021 09:00:05 +0000 [thread overview] Message-ID: <bug-103554-4-VoLV8d3284@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-103554-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103554 --- Comment #3 from Avi Kivity <avi at scylladb dot com> --- > _Note_ that likely the suboptimal solution presented here is faster because > it avoids STLF penalties from the calls stack setup which very likely uses > scalar or differently aligned vector moves. Interesting point. Agner says (Icelake): > A read that is bigger than the write, or a read that covers both written and unwritten bytes, > fails to forward. The write-to-read latency is 19-20 clock cycles. However, the same code is generated when `in` is a reference, in which case it may not be in the store queue at all, so we're paying two extra instructions for nothing. movhps is also 2 uops, so we're paying 3 uops to load 2 elements.
next prev parent reply other threads:[~2021-12-06 9:00 UTC|newest] Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-12-04 15:37 [Bug target/103554] New: " avi at scylladb dot com 2021-12-04 22:08 ` [Bug target/103554] " pinskia at gcc dot gnu.org 2021-12-06 8:36 ` rguenth at gcc dot gnu.org 2021-12-06 9:00 ` avi at scylladb dot com [this message] 2021-12-06 11:00 ` rguenther at suse dot de 2021-12-06 11:23 ` avi at scylladb dot com 2021-12-06 11:52 ` rguenther at suse dot de 2021-12-06 11:59 ` avi at scylladb dot com 2021-12-07 2:26 ` crazylht at gmail dot com 2021-12-07 8:36 ` rguenth at gcc dot gnu.org 2021-12-07 9:51 ` crazylht at gmail dot com 2021-12-07 10:28 ` rguenther at suse dot de 2021-12-09 3:07 ` crazylht 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-103554-4-VoLV8d3284@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: linkBe 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).