public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "paolo dot bonzini at lu dot unisi dot ch" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/19653] x87 reg allocated for constants for -mfpmath=sse
Date: Wed, 21 Sep 2005 06:52:00 -0000 [thread overview]
Message-ID: <20050921065206.8381.qmail@sourceware.org> (raw)
In-Reply-To: <20050127083359.19653.uros@kss-loka.si>
------- Additional Comments From paolo dot bonzini at lu dot unisi dot ch 2005-09-21 06:51 -------
Subject: Re: x87 reg allocated for constants for -mfpmath=sse
>Note that in this pattern cost computation of MMX_REGS are all ignored ('*' in front of y). So, the cost
>which is computed is for 'r' which is GENERAL_REGS. This cost is too high and eventually results in
>memory cost to be lower than register cost. I tried the following simple patch as experiment and got all
>the performance back (it is now comparable with 4.0). Note that in this patch, I removed the '*' in the
>2nd alternative so cost of keeping the operand in mmx_regs class is factored in. This resulted in a
>lower cost than that of memory. Is this the way to go? This is just an experiment which seems to work.
>
>
I think it makes sense. The x86 back-end is playing too many tricks
(such as the # classes) with the register allocator and regclass
especially, and they are biting back.
Still, I'd rather hear from an expert as to why the classes were written
like this.
Paolo
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19653
next prev parent reply other threads:[~2005-09-21 6:52 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-27 8:34 [Bug target/19653] New: " uros at kss-loka dot si
2005-01-27 8:35 ` [Bug target/19653] " uros at kss-loka dot si
2005-01-27 9:14 ` uros at kss-loka dot si
2005-01-27 13:28 ` pinskia at gcc dot gnu dot org
2005-01-28 6:24 ` uros at kss-loka dot si
2005-02-08 16:46 ` steven at gcc dot gnu dot org
2005-02-09 13:11 ` uros at kss-loka dot si
2005-06-19 14:58 ` pinskia at gcc dot gnu dot org
2005-07-13 11:33 ` pinskia at gcc dot gnu dot org
2005-07-13 12:06 ` bonzini at gcc dot gnu dot org
2005-07-13 14:03 ` matz at suse dot de
2005-07-13 14:16 ` bonzini at gcc dot gnu dot org
2005-07-13 14:43 ` bonzini at gcc dot gnu dot org
2005-07-14 8:55 ` bonzini at gcc dot gnu dot org
2005-07-27 15:57 ` bonzini at gcc dot gnu dot org
2005-08-01 20:56 ` dalej at gcc dot gnu dot org
2005-08-02 22:58 ` dalej at gcc dot gnu dot org
2005-08-22 22:09 ` bonzini at gcc dot gnu dot org
2005-09-21 6:52 ` paolo dot bonzini at lu dot unisi dot ch [this message]
2005-09-21 17:23 ` dalej at gcc dot gnu dot org
[not found] <bug-19653-1649@http.gcc.gnu.org/bugzilla/>
2005-11-22 9:21 ` bonzini at gcc dot gnu dot org
2006-04-03 11:20 ` bonzini at gnu dot org
2006-04-03 11:20 ` bonzini at gcc dot gnu dot org
2006-04-18 8:23 ` bonzini 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=20050921065206.8381.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: 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).