public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug testsuite/63175] [4.9/5 regression] FAIL: gcc.dg/vect/costmodel/ppc/costmodel-bb-slp-9a.c scan-tree-dump-times slp2" basic block vectorized using SLP" 1 Date: Tue, 03 Mar 2015 09:42:00 -0000 [thread overview] Message-ID: <bug-63175-4-jXPdBiXjrb@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-63175-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63175 --- Comment #26 from Richard Biener <rguenth at gcc dot gnu.org> --- David - please clarify the cost of misaligned stores/loads. I tried to understand the PPC ISA document but can't really find the appropriate place where it talks about misalign cost (I only can see it still assumes element alignment). Btw with double-word alignment I get t.c:10:10: note: Cost model analysis: Vector inside of basic block cost: 8 Vector prologue cost: 0 Vector epilogue cost: 0 Scalar cost of basic block: 8 t.c:10:10: note: not vectorized: vectorization is not profitable. So currently on a tie we don't vectorize basic-blocks (same with GCC 4.8). That's kind of arbitrary, but given instruction encoding size on x86 for example it makes sense. Note that we seem to prefer optimized re-alignment loads over misaligned loads (even if double-word aligned) - the vectorizer is not set up to decide that based on costs (the misaligned load would cost 2 while the optimized re-aligned load costs 6 - two aligned loads (2), one vector stmt for mask compute (1) and one permute (3)). I think we are regression free compared to 4.8 (if you enable -fvect-cost-model there).
next prev parent reply other threads:[~2015-03-03 9:42 UTC|newest] Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top [not found] <bug-63175-4@http.gcc.gnu.org/bugzilla/> 2014-09-05 8:47 ` rguenth at gcc dot gnu.org 2014-10-30 10:42 ` jakub at gcc dot gnu.org 2014-11-24 13:16 ` rguenth at gcc dot gnu.org 2015-02-21 20:07 ` msebor at gcc dot gnu.org 2015-02-22 20:38 ` macro@linux-mips.org 2015-02-24 6:56 ` msebor at gcc dot gnu.org 2015-02-25 20:45 ` msebor at gcc dot gnu.org 2015-02-26 10:19 ` rguenth at gcc dot gnu.org 2015-02-26 10:56 ` rguenth at gcc dot gnu.org 2015-02-27 9:18 ` rguenth at gcc dot gnu.org 2015-02-27 9:49 ` rguenth at gcc dot gnu.org 2015-02-27 11:23 ` rguenth at gcc dot gnu.org 2015-02-27 11:24 ` rguenth at gcc dot gnu.org 2015-02-28 9:26 ` msebor at gcc dot gnu.org 2015-03-02 14:14 ` rguenth at gcc dot gnu.org 2015-03-02 14:24 ` rguenth at gcc dot gnu.org 2015-03-02 16:24 ` msebor at gcc dot gnu.org 2015-03-02 16:48 ` rguenther at suse dot de 2015-03-02 16:50 ` rguenther at suse dot de 2015-03-02 16:58 ` msebor at gcc dot gnu.org 2015-03-02 17:47 ` rguenther at suse dot de 2015-03-02 18:13 ` msebor at gcc dot gnu.org 2015-03-02 18:23 ` rguenther at suse dot de 2015-03-03 5:10 ` msebor at gcc dot gnu.org 2015-03-03 9:21 ` rguenther at suse dot de 2015-03-03 9:42 ` rguenth at gcc dot gnu.org [this message] 2015-03-03 15:05 ` dje at gcc dot gnu.org 2015-03-03 16:19 ` wschmidt at gcc dot gnu.org 2015-03-03 16:22 ` wschmidt at gcc dot gnu.org 2015-03-04 1:15 ` msebor at gcc dot gnu.org 2015-03-04 9:17 ` rguenth at gcc dot gnu.org 2015-03-04 13:42 ` dje at gcc dot gnu.org 2015-03-04 13:55 ` rguenther at suse dot de 2015-03-06 18:44 ` msebor at gcc dot gnu.org 2015-03-07 16:19 ` [Bug testsuite/63175] [4.9 " law at redhat dot com 2015-03-10 21:07 ` msebor at gcc dot gnu.org 2015-03-11 10:09 ` rguenth at gcc dot gnu.org 2015-03-23 18:58 ` msebor at gcc dot gnu.org 2015-05-29 16:49 ` wschmidt 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-63175-4-jXPdBiXjrb@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).