delorie.com/archives/browse.cgi | search |
Message-ID: | <384EE9D0.D583BFE3@maths.unine.ch> |
Date: | Thu, 09 Dec 1999 00:29:21 +0100 |
From: | Gautier <Gautier DOT deMontmollin AT maths DOT unine DOT ch> |
X-Mailer: | Mozilla 4.51 (Macintosh; I; PPC) |
X-Accept-Language: | en |
MIME-Version: | 1.0 |
Newsgroups: | comp.os.msdos.djgpp |
Subject: | Re: fftw give nonsense with float ok with double |
References: | <Pine DOT SUN DOT 3 DOT 91 DOT 991207120322 DOT 29709E-100000 AT is> <384e8f71 DOT 5388976 AT news DOT clara DOT net> |
NNTP-Posting-Host: | mac13-29.unine.ch |
Lines: | 12 |
To: | djgpp AT delorie DOT com |
DJ-Gateway: | from newsgroup comp.os.msdos.djgpp |
Reply-To: | djgpp AT delorie DOT com |
> I am wondering in what way does -O2 yield better results than -O3, are > you refering to code size or is there another consideration? Too much inlining might affect processor cache windowing because of code size. It is better (for speed) to tune manually which procedures will be inlined and which not... -- Gautier _____\\________________\_______\_________ http://members.xoom.com/gdemont/gsoft.htm
webmaster | delorie software privacy |
Copyright © 2019 by DJ Delorie | Updated Jul 2019 |