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>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
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