From: Ville-Pertti Keinonen <will@exomi.com>
To: Xavier Leroy <Xavier.Leroy@inria.fr>
Cc: Christophe TROESTLER <Christophe.Troestler@umh.ac.be>,
"O'Caml Mailing List" <caml-list@inria.fr>
Subject: Re: [Caml-list] [Benchmark] NBody
Date: Tue, 08 Feb 2005 13:26:36 +0200 [thread overview]
Message-ID: <1107861996.654.50.camel@localhost> (raw)
In-Reply-To: <20050208104312.GA10035@yquem.inria.fr>
On Tue, 2005-02-08 at 11:43 +0100, Xavier Leroy wrote:
> The best gcc output is faster than the best OCaml output by about 30%.
> Looking at the asm code, the main difference is that gcc keeps some
> float variables (dx, dy, dz, etc) in the floating-point stack while
> OCaml stores them (unboxed) to the stack. Maybe the Java
> implementation you used manages to use the float stack. Who knows.
An interesting question is whether Java aligns allocations and stack to
4-byte or 8-byte boundaries on x86.
A few years ago, when keeping the stack aligned for better floating
point performance was a new gcc feature, and only worked as long as it
was aligned initially (and consistently kept it misaligned if it
wasn't), I played around with a floating point intensive C program that
would exhibit an almost 40% difference in performance depending on what
the binary was called...
next prev parent reply other threads:[~2005-02-08 11:26 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-02-07 18:57 Christophe TROESTLER
2005-02-07 19:16 ` [Caml-list] " Will M. Farr
2005-02-07 19:36 ` Christophe TROESTLER
2005-02-07 19:55 ` Will M. Farr
2005-02-08 10:34 ` Olivier Andrieu
2005-02-08 10:52 ` Micha
2005-02-07 20:16 ` Markus Mottl
2005-02-07 19:37 ` Martin Jambon
2005-02-07 19:46 ` Christophe TROESTLER
2005-02-07 20:22 ` Martin Jambon
2005-02-07 20:04 ` sejourne_kevin
2005-02-07 20:32 ` Robert Roessler
2005-02-07 22:57 ` Oliver Bandel
2005-02-08 1:29 ` skaller
2005-02-08 1:48 ` Will M. Farr
2005-02-08 9:01 ` Ville-Pertti Keinonen
2005-02-08 9:37 ` skaller
2005-02-08 10:10 ` Ville-Pertti Keinonen
2005-02-08 16:36 ` skaller
2005-02-08 12:04 ` Marcin 'Qrczak' Kowalczyk
2005-02-08 17:06 ` skaller
2005-02-08 10:25 ` Xavier Leroy
2005-02-08 18:34 ` skaller
2005-02-08 10:43 ` Xavier Leroy
2005-02-08 11:26 ` Ville-Pertti Keinonen [this message]
2005-02-08 15:59 ` Florian Hars
2005-02-13 16:40 ` Christoph Bauer
2005-02-13 18:13 ` Christophe TROESTLER
2005-02-24 22:18 ` NBody (one more question) Christophe TROESTLER
2005-02-25 17:06 ` [Caml-list] " John Carr
2005-02-25 17:17 ` Christophe TROESTLER
2005-02-26 16:08 ` John Carr
2005-02-25 17:24 ` Ken Rose
2005-02-25 17:42 ` Oliver Bandel
2005-02-25 17:57 ` Xavier Leroy
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=1107861996.654.50.camel@localhost \
--to=will@exomi.com \
--cc=Christophe.Troestler@umh.ac.be \
--cc=Xavier.Leroy@inria.fr \
--cc=caml-list@inria.fr \
/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 NNTP newsgroup(s).