From: Eric Botcazou <ebotcazou@libertysurf.fr>
To: Richard Henderson <rth@redhat.com>
Cc: gcc-patches@gcc.gnu.org, Dale Johannesen <dalej@apple.com>
Subject: Re: Patch: fix SPEC regressions
Date: Thu, 19 Dec 2002 13:40:00 -0000 [thread overview]
Message-ID: <200212192236.38886.ebotcazou@libertysurf.fr> (raw)
In-Reply-To: <20021219211442.GA10484@redhat.com>
> Why doesn't this test case fail on mainline?
Because of your patch on mainline:
2002-07-21 Richard Henderson <rth@redhat.com>
* loop.h (LOOP_AUTO_UNROLL): Rename from LOOP_FIRST_PASS.
* loop.c (strength_reduce): Update.
* toplev.c (rest_of_compilation): Do unrolling in the first
loop pass, not the second.
On the 3.2 branch, we generate very bad code for
for (i = 0; i < 4; i++)
array[i] = 0;
on K6 at -O2 -funroll-loops: we first strength-reduce, which makes us lose the
number of iterations, then unroll using the default number of iterations (8),
which is later changed to 4 because we are preconditioning the loop. Then we
generate a runtime calculation of the number of iterations really needed (!).
With your patch we unroll 4 times, period.
--
Eric Botcazou
next prev parent reply other threads:[~2002-12-19 21:40 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-10-28 11:40 Dale Johannesen
2002-10-29 7:46 ` Richard Henderson
2002-10-29 9:40 ` Dale Johannesen
2002-10-29 10:38 ` Richard Henderson
2002-10-29 15:10 ` Dale Johannesen
2002-10-31 15:18 ` Richard Henderson
2002-10-31 15:22 ` Dale Johannesen
2002-10-31 17:41 ` Richard Henderson
2002-11-01 15:56 ` Patch: fix SPEC regressions (rewrite) Dale Johannesen
2002-11-03 15:32 ` Richard Henderson
2002-11-21 10:18 ` Patch: fix SPEC regressions Eric Botcazou
2002-11-21 13:52 ` Richard Henderson
2002-12-14 14:48 ` Eric Botcazou
2002-12-17 5:35 ` Eric Botcazou
2002-12-19 13:15 ` Richard Henderson
2002-12-19 13:40 ` Eric Botcazou [this message]
2002-12-19 13:20 ` Richard Henderson
2002-12-21 12:34 ` Eric Botcazou
2002-12-21 4:16 ` Eric Botcazou
2002-12-21 11:19 ` Richard Henderson
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=200212192236.38886.ebotcazou@libertysurf.fr \
--to=ebotcazou@libertysurf.fr \
--cc=dalej@apple.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=rth@redhat.com \
/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).