public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "Joey dot ye at intel dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug target/37364] [4.4 Regression] IRA generates inefficient code due to missing regmove pass Date: Sat, 25 Oct 2008 04:15:00 -0000 [thread overview] Message-ID: <20081025041401.11825.qmail@sourceware.org> (raw) In-Reply-To: <bug-37364-682@http.gcc.gnu.org/bugzilla/> ------- Comment #21 from Joey dot ye at intel dot com 2008-10-25 04:14 ------- To me scheduler is irrelevant here. GCC has no core2 pipeline description so the instruction scheduling doesn't looks optimized. But for OOO processor like core2, IMHO scheduling shouldn't make that much difference. Also core2 + no-ira doesn't hurt, which means core2 scheduling is not the root cause. Instead old code uses different register for loading, but IRA code always uses xmm7 as load target. Need to figure out two questions: 1. why instructions from core2+ira runs slower than ira? 2. why core2+ira generate so different code as non-core2? Scheduler dump for core2: ;; insn code bb dep prio cost reservation ;; ---- ---- -- --- ---- ---- ----------- ;; 108 47 4 0 0 0 nothing : 70 109 43 ;; 43 102 4 1 0 0 nothing : 70 51 117 114 67 109 ;; 109 47 4 2 0 0 nothing : 70 44 ;; 44 102 4 1 0 0 nothing : 70 57 55 59 67 ;; 45 102 4 0 0 0 nothing : 70 65 67 112 110 ;; 46 102 4 0 0 0 nothing : 70 55 49 67 61 ;; 110 102 4 1 0 0 nothing : 70 65 61 ;; 61 720 4 2 0 0 nothing : 70 55 62 ;; 62 720 4 1 0 0 nothing : 70 47 111 -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37364
next prev parent reply other threads:[~2008-10-25 4:15 UTC|newest] Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top 2008-09-04 5:45 [Bug middle-end/37364] New: [4.4 Regression] IRA generates ineffient code hjl dot tools at gmail dot com 2008-09-04 9:50 ` [Bug middle-end/37364] " rguenth at gcc dot gnu dot org 2008-09-04 16:04 ` hjl dot tools at gmail dot com 2008-09-04 16:14 ` hjl dot tools at gmail dot com 2008-09-04 17:44 ` hjl dot tools at gmail dot com 2008-09-04 17:55 ` hjl dot tools at gmail dot com 2008-09-04 18:40 ` [Bug middle-end/37364] [4.4 Regression] IRA generates inefficient code hjl dot tools at gmail dot com 2008-09-04 19:26 ` vmakarov at redhat dot com 2008-09-04 19:46 ` hjl dot tools at gmail dot com 2008-09-04 20:14 ` rguenth at gcc dot gnu dot org 2008-09-04 20:18 ` hjl dot tools at gmail dot com 2008-09-04 20:32 ` hjl dot tools at gmail dot com 2008-09-06 15:58 ` [Bug target/37364] [4.4 Regression] IRA generates inefficient code due to missing regmove pass ubizjak at gmail dot com 2008-09-06 16:26 ` ubizjak at gmail dot com 2008-09-06 16:50 ` hjl dot tools at gmail dot com 2008-09-09 16:02 ` hjl dot tools at gmail dot com 2008-09-11 13:47 ` bonzini at gnu dot org 2008-09-11 17:34 ` ubizjak at gmail dot com 2008-10-22 3:19 ` mmitchel at gcc dot gnu dot org 2008-10-23 8:44 ` Joey dot ye at intel dot com 2008-10-24 8:37 ` Joey dot ye at intel dot com 2008-10-24 10:12 ` bonzini at gnu dot org 2008-10-24 10:17 ` bonzini at gnu dot org 2008-10-25 4:15 ` Joey dot ye at intel dot com [this message] 2008-10-28 1:13 ` hjl dot tools at gmail dot com 2008-10-28 1:21 ` Joey dot ye at intel dot com 2008-10-28 1:37 ` hjl dot tools at gmail dot com 2008-11-04 19:30 ` hjl dot tools at gmail dot com 2008-11-30 20:46 ` steven at gcc dot gnu dot org 2008-11-30 20:53 ` hjl dot tools at gmail dot com 2008-11-30 21:20 ` steven at gcc dot gnu dot org 2008-11-30 21:34 ` steven at gcc dot gnu dot org 2008-12-01 18:27 ` ubizjak at gmail dot com 2008-12-21 18:06 ` hjl dot tools at gmail dot com 2009-01-29 17:13 ` hjl dot tools at gmail dot com 2009-01-29 17:57 ` hjl dot tools at gmail dot com 2009-02-04 7:57 ` bonzini at gnu dot org 2009-02-04 7:58 ` bonzini at gnu 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=20081025041401.11825.qmail@sourceware.org \ --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).