This is the mail archive of the crossgcc@sourceware.cygnus.com mailing list for the crossgcc project.

See the CrossGCC FAQ for lots more infromation.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]

Re: Floating point optimisation.

To: robert dot melchers at drives dot eurotherm dot co dot uk
Subject: Re: Floating point optimisation.
From: Luke Diamand <lgd at virata dot com>
Date: Thu, 23 Sep 1999 16:59:18 +0000
CC: crossgcc at sourceware dot cygnus dot com
Organization: Virata
References: <000801bf05e2$b7009640$c9a87995@drives.eurotherm.co.uk>

Robert Melchers wrote:
> 
> I am using 2.95.1 compiler built for SH-COFF, Hitachi SH, and am finding the floating point code
> very inefficient, I would like to make all the trivial functions inline, A==B, A>B etc.

Are you talking about the floating point emulation code (fp-bit.c,
-msoft-float) ?

If so, you might like to try using a package called 'softfloat' instead,
which is about 2x faster (but you have rather more legwork).

http://HTTP.CS.Berkeley.EDU/~jhauser/arithmetic/SoftFloat.html

HTH!
Luke Diamand


> 
> Does any one have any ideas ?
> 
> The Cygnus build, 98r2 also has the same issues.
> 
> Thanks in advance.
> Robert Melchers
> ======================================
> mailto:robert.melchers@bigfoot
> 
> ------
> Want more information?  See the CrossGCC FAQ, http://www.objsw.com/CrossGCC/
> Want to unsubscribe? Send a note to crossgcc-unsubscribe@sourceware.cygnus.com

-- 
Virata http://www.virata.com
Cambridge
Tel: +44 1223 566919      Fax: +44 1223 566915

------
Want more information?  See the CrossGCC FAQ, http://www.objsw.com/CrossGCC/
Want to unsubscribe? Send a note to crossgcc-unsubscribe@sourceware.cygnus.com

References:
- Floating point optimisation.
  - From: Robert Melchers

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]