public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "amylaar at gcc dot gnu dot org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/38785] huge performance regression on EEMBC bitmnp01 Date: Wed, 14 Jan 2009 18:47:00 -0000 [thread overview] Message-ID: <20090114184707.20557.qmail@sourceware.org> (raw) In-Reply-To: <bug-38785-5394@http.gcc.gnu.org/bugzilla/> ------- Comment #9 from amylaar at gcc dot gnu dot org 2009-01-14 18:47 ------- I think the disregard for conditional execution opportunities and the assumption that phi nodes have no execution cost are two separate issues. I'd like to address the latter first, because it causes exponential code and execution time growth. A phi node joining two constants has at least the cost of a constant load. A phi node joining two different variables which are initialized by a graph with constant leafs costs at least a reg-reg copy on one arm, plus the cost of its parents if these are needed solely for this phi node. Therefore, if an expression is only partially anticipatable, we should compare the cost of any phi node needed to compute it early with the estimated likelyhod that such a computatatio, once done, is actually needed, multiplied with the cost of the replaced operation. Can we use edge probabilities inside tree-pre to calculate execution probabilities? Can we calculate the cost of replaced expressions? -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38785
next prev parent reply other threads:[~2009-01-14 18:47 UTC|newest] Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top 2009-01-09 15:46 [Bug tree-optimization/38785] New: " amylaar at gcc dot gnu dot org 2009-01-09 15:55 ` [Bug tree-optimization/38785] " rguenth at gcc dot gnu dot org 2009-01-09 16:39 ` amylaar at gcc dot gnu dot org 2009-01-09 17:35 ` amylaar at gcc dot gnu dot org 2009-01-09 17:59 ` rguenth at gcc dot gnu dot org 2009-01-09 20:55 ` steven at gcc dot gnu dot org 2009-01-10 16:10 ` amylaar at gcc dot gnu dot org 2009-01-14 10:08 ` Joey dot ye at intel dot com 2009-01-14 10:54 ` steven at gcc dot gnu dot org 2009-01-14 18:47 ` amylaar at gcc dot gnu dot org [this message] 2009-01-14 20:51 ` rguenther at suse dot de 2009-01-14 22:06 ` amylaar at gcc dot gnu dot org 2009-01-15 11:36 ` amylaar at gcc dot gnu dot org 2009-01-20 23:02 ` steven at gcc dot gnu dot org 2009-03-04 22:58 ` amylaar at gcc dot gnu dot org 2009-03-05 0:32 ` amylaar at gcc dot gnu dot org 2009-03-31 16:08 ` [Bug tree-optimization/38785] [4.3/4.4/4.5 Regression] " jsm28 at gcc dot gnu dot org 2009-04-14 9:49 ` jakub at gcc dot gnu dot org 2009-07-15 21:12 ` steven at gcc dot gnu dot org 2009-07-15 21:35 ` steven at gcc dot gnu dot org 2009-07-23 21:51 ` drow at gcc dot gnu dot org 2009-07-23 22:23 ` stevenb dot gcc at gmail dot com 2009-08-04 12:46 ` rguenth at gcc dot gnu dot org 2010-01-29 20:33 ` amylaar at gcc dot gnu dot org 2010-02-19 12:18 ` rguenth at gcc dot gnu dot org 2010-02-19 12:29 ` amylaar at gcc dot gnu dot org 2010-02-19 13:19 ` matz at gcc dot gnu dot org 2010-02-19 14:08 ` drow at gcc dot gnu dot org 2010-02-19 23:33 ` stevenb dot gcc at gmail dot com 2010-05-22 18:28 ` [Bug tree-optimization/38785] [4.3/4.4/4.5/4.6 " rguenth at gcc dot 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=20090114184707.20557.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).