From: Chris Lattner <clattner@apple.com>
To: Vladimir Makarov <vmakarov@redhat.com>
Cc: Duncan Sands <baldrick@free.fr>,
Steven Bosscher <stevenb.gcc@gmail.com>,
gcc@gcc.gnu.org
Subject: Re: Some benchmark comparison of gcc4.5 and dragonegg (was dragonegg in FSF gcc?)
Date: Wed, 21 Apr 2010 18:25:00 -0000 [thread overview]
Message-ID: <11E59EFE-7FDB-4AC9-A1D2-E401DF5BDD70@apple.com> (raw)
In-Reply-To: <4BCF3FCD.4010203@redhat.com>
On Apr 21, 2010, at 11:11 AM, Vladimir Makarov wrote:
>>
>> This is definitely interesting, but you're also comparing apples and oranges here (for both compile time and performance). Can you get numbers showing GCC -O3 and dragonegg with LTO to get a better comparison?
>>
>>
> Dragonegg does not work with -flto. It generates assembler code on which gas complaints (a lot of non-assembler code like target data-layout which are not in comments).
Ok, I didn't know that didn't get wired up. I'm not familiar with dragonegg, it might require gold with the llvm lto gold plugin or something.
> So I'll do gcc -O3 without -flto. I don't think it will change average SPECINT2000 rate significantly (although it can change separte benchmark significantly) but it will make gcc compiler much faster (may be 2 times because I did not use -fwhole-program). I'll post the results in an hour.
Sounds good, thanks! I suspect the gcc build times will improve.
-Chris
next prev parent reply other threads:[~2010-04-21 18:23 UTC|newest]
Thread overview: 104+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-09 16:44 dragonegg in FSF gcc? Jack Howarth
2010-04-09 18:16 ` Basile Starynkevitch
2010-04-10 13:37 ` Duncan Sands
2010-04-11 12:54 ` Steven Bosscher
2010-04-11 14:17 ` Duncan Sands
2010-04-11 14:57 ` Eric Botcazou
2010-04-11 15:41 ` Duncan Sands
2010-04-11 15:56 ` Robert Dewar
2010-04-11 16:02 ` Grigori Fursin
2010-04-11 16:02 ` Robert Dewar
2010-04-11 16:28 ` Duncan Sands
2010-04-11 16:31 ` Robert Dewar
2010-04-13 16:58 ` Paolo Bonzini
2010-04-11 18:15 ` Andi Kleen
2010-04-11 16:26 ` Duncan Sands
2010-04-11 16:26 ` Robert Dewar
2010-04-11 16:34 ` Duncan Sands
2010-04-11 17:47 ` Robert Dewar
2010-04-11 16:37 ` Grigori Fursin
2010-04-11 18:50 ` Toon Moene
2010-04-11 21:43 ` Eric Botcazou
2010-04-11 16:32 ` Basile Starynkevitch
2010-04-21 16:52 ` Some benchmark comparison of gcc4.5 and dragonegg (was dragonegg in FSF gcc?) Vladimir Makarov
2010-04-21 17:00 ` Robert Dewar
2010-04-21 17:09 ` Steven Bosscher
2010-04-21 17:57 ` Paolo Bonzini
2010-04-21 18:28 ` Robert Dewar
2010-04-21 18:09 ` Robert Dewar
2010-04-22 10:24 ` Laurent GUERBY
2010-04-21 18:37 ` Basile Starynkevitch
2010-04-21 18:40 ` Robert Dewar
2010-04-21 17:21 ` Vladimir Makarov
2010-04-21 18:23 ` Robert Dewar
2010-04-21 20:54 ` Vladimir Makarov
2010-04-22 6:19 ` Robert Dewar
2010-04-22 18:44 ` Vladimir Makarov
2010-04-21 20:58 ` Toon Moene
2010-04-22 6:29 ` Robert Dewar
2010-04-21 17:05 ` Steven Bosscher
2010-04-21 17:10 ` Vladimir Makarov
2010-04-21 17:55 ` Manuel López-Ibáñez
2010-04-21 18:32 ` Robert Dewar
2010-04-21 19:03 ` Eric Botcazou
2010-04-21 17:42 ` Chris Lattner
2010-04-21 18:19 ` Vladimir Makarov
2010-04-21 18:25 ` Chris Lattner [this message]
2010-04-21 18:41 ` Vladimir Makarov
2010-04-21 19:35 ` Duncan Sands
2010-04-21 18:01 ` Duncan Sands
2010-04-21 18:19 ` Vladimir Makarov
2010-04-11 14:30 ` dragonegg in FSF gcc? Jack Howarth
2010-04-11 15:36 ` Manuel López-Ibáñez
2010-04-11 16:33 ` Dave Korn
2010-04-11 19:06 ` Laurent GUERBY
2010-04-11 22:19 ` Manuel López-Ibáñez
2010-04-11 22:26 ` Dave Korn
2010-04-12 7:34 ` Manuel López-Ibáñez
2010-04-12 13:38 ` Jack Howarth
2010-04-12 13:42 ` Robert Dewar
2010-04-12 13:52 ` Richard Guenther
2010-04-12 14:00 ` Jack Howarth
2010-04-12 15:59 ` Steven Bosscher
2010-04-12 16:03 ` Jack Howarth
2010-04-12 16:27 ` Steven Bosscher
2010-04-12 18:03 ` Dave Korn
2010-04-12 14:00 ` Dave Korn
2010-04-12 14:47 ` Manuel López-Ibáñez
2010-04-12 17:58 ` Weddington, Eric
2010-04-12 21:13 ` Toon Moene
2010-04-12 22:51 ` Ian Lance Taylor
2010-04-23 13:50 ` Poor internal documentation (was: dragonegg in FSF gcc?) Philipp Thomas
2010-04-23 14:26 ` Manuel López-Ibáñez
2010-04-24 19:07 ` Documentation legal issues (Was: Re: Poor internal documentation) Joern Rennecke
2010-06-05 10:10 ` Poor internal documentation (was: dragonegg in FSF gcc?) Philipp Thomas
2010-06-05 13:17 ` Jonathan Wakely
2010-04-13 17:15 ` dragonegg in FSF gcc? Paolo Bonzini
2010-04-13 17:18 ` Jack Howarth
2010-04-13 17:22 ` Paolo Bonzini
2010-04-13 19:19 ` Jack Howarth
2010-04-13 19:43 ` Paolo Bonzini
2010-04-13 20:29 ` Diego Novillo
2010-04-13 21:04 ` Steven Bosscher
2010-04-13 21:16 ` Diego Novillo
2010-04-14 14:06 ` Grigori Fursin
2010-04-13 18:05 ` Steven Bosscher
2010-04-13 19:26 ` Andrew Pinski
2010-04-13 19:28 ` Jack Howarth
2010-04-13 17:05 ` Paolo Bonzini
2010-04-13 21:06 ` Testing GCC on Cygwin made substantially easier [was Re: dragonegg in FSF gcc?] Dave Korn
2010-05-26 9:37 ` Laurynas Biveinis
2010-04-13 23:11 ` dragonegg in FSF gcc? Steven Bosscher
2010-04-13 23:43 ` Jack Howarth
2010-04-14 6:48 ` Duncan Sands
2010-04-14 13:54 ` Jack Howarth
2010-04-14 13:59 ` Paolo Bonzini
2010-04-11 14:33 ` Jack Howarth
2010-04-11 15:06 ` David Edelsohn
2010-04-11 15:24 ` Jack Howarth
2010-04-11 16:17 ` Duncan Sands
2010-04-11 16:20 ` Jack Howarth
2010-04-11 22:48 ` Jonathan Wakely
2010-04-12 13:35 ` Duncan Sands
2010-04-12 15:03 ` Alfred M. Szmidt
2010-04-12 15:34 ` Jack Howarth
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=11E59EFE-7FDB-4AC9-A1D2-E401DF5BDD70@apple.com \
--to=clattner@apple.com \
--cc=baldrick@free.fr \
--cc=gcc@gcc.gnu.org \
--cc=stevenb.gcc@gmail.com \
--cc=vmakarov@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).