From: <tm_gccmail@mail.kloo.net>
To: Reza Roboubi <reza@linisoft.com>
Cc: Bonzini <bonzini@gnu.org>, gcc@gcc.gnu.org, gcc-help@gcc.gnu.org
Subject: Re: optimizations
Date: Thu, 16 Jan 2003 11:03:00 -0000 [thread overview]
Message-ID: <Pine.LNX.4.21.0301151338040.30377-100000@mail.kloo.net> (raw)
In-Reply-To: <3E25C06E.4E7D37E8@linisoft.com>
On Wed, 15 Jan 2003, Reza Roboubi wrote:
> Bonzini wrote:
>
> CHANGE:
> -------
> .L2:
> movl -4(%ebp), %eax <== still does the load
> cmpl $16, %eax
> je .L7
> incl %eax
> movl %eax, -4(%ebp) <== and store
> jmp .L2
> .L7:
>
> TO:
> -------
> movl -4(%ebp), %eax
> .L2:
> cmpl $16, %eax
> je .L7
> incl %eax
> jmp .L2
> .L7:
> movl %eax, -4(%ebp)
The optimization you are suggesting is called "load hoist/store sink" if I
remember correctly.
Here is the story as I remember it:
When egcs-1.0 or 1.1 was released, people noticed a large performance
drop from gcc-2.7.2. I did a little investigation, and verified a large
performanc drop on Whetstone. I did a comprehensive analysis of it, and
isolated a case similar to yours where a variable in a critical loop was
entirely contained in registers in 2.7.2 but was loaded/save from/to
memory in gcc-2.95.
I mentioned this on the gcc-bugs mailing list, and Mark Mitchell
contributed a fairly simple load hoisting improvement to the loop
optmiizer which restored performance on Whetstone.
If you look at the gcc-bugs archives for 1998, you may be able to find
this message thread.
This load-hoisting optimization seems to be responsible for the hoisted
load in your testcase. However, the corresponding store sink portion of
the optimizer has never been written, and I believe that is why the store
is not sunk out of the loop on your testcase.
Toshi
next prev parent reply other threads:[~2003-01-15 21:52 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-01-15 23:20 optimizations Bonzini
2003-01-16 10:53 ` optimizations Reza Roboubi
2003-01-16 11:03 ` tm_gccmail [this message]
2003-01-16 12:34 ` optimizations Reza Roboubi
2003-02-18 18:13 ` optimizations Håkan Hjort
2003-02-18 18:16 ` optimizations Andrew Pinski
2003-02-18 18:17 ` optimizations Zack Weinberg
2003-02-18 18:40 ` optimizations Håkan Hjort
2003-02-19 5:02 ` optimizations David Edelsohn
2003-01-16 11:53 ` optimizations Paolo Bonzini
-- strict thread matches above, loose matches on Subject: below --
2003-01-14 22:58 optimizations Reza Roboubi
2003-01-15 0:15 ` optimizations Andrew Pinski
2003-01-15 5:10 ` optimizations Reza Roboubi
2003-01-15 6:31 ` optimizations Reza Roboubi
2003-01-15 17:37 ` optimizations Andrew Pinski
2003-01-15 17:46 ` optimizations Reza Roboubi
2000-03-10 1:46 Optimizations Virgil Palanciuc
1997-12-14 14:30 [EGCS] Optimizations meissner
1997-12-15 5:38 ` Optimizations Marc Lehmann
1997-12-15 11:29 ` Optimizations Dave Love
1997-12-15 15:43 ` Optimizations Marc Lehmann
[not found] ` <19971216000653.24186.cygnus.egcs@cerebro.laendle>
1997-12-23 7:51 ` Optimizations Stan Cox
1997-12-09 9:52 Optimizations David M. Ronis
1997-12-09 11:19 ` Optimizations Jeffrey A Law
1997-12-10 10:46 ` [EGCS] Optimizations Marc Lehmann
1997-12-14 5:39 ` Philipp Thomas
1997-12-14 15:14 ` Optimizations Marc Lehmann
1997-12-14 20:14 ` Optimizations Jeffrey A Law
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=Pine.LNX.4.21.0301151338040.30377-100000@mail.kloo.net \
--to=tm_gccmail@mail.kloo.net \
--cc=bonzini@gnu.org \
--cc=gcc-help@gcc.gnu.org \
--cc=gcc@gcc.gnu.org \
--cc=reza@linisoft.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).