linux-mips
[Top] [All Lists]

Re: Soft floating point on 5K

To: Dennis Castleman <DennisCastleman@oaktech.com>
Subject: Re: Soft floating point on 5K
From: Justin Carlson <justinca@cs.cmu.edu>
Date: 15 Apr 2003 11:49:38 -0400
Cc: linux-mips@linux-mips.org
In-reply-to: <16027.58679.576152.853200@gladsmuir.mips.com>
Organization:
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <56BEF0DBC8B9D611BFDB00508B5E2634102F07@TLEXMAIL> <16027.58679.576152.853200@gladsmuir.mips.com>
Sender: linux-mips-bounce@linux-mips.org
On Tue, 2003-04-15 at 06:55, Dominic Sweetman wrote:
> Dennis Castleman (DennisCastleman@oaktech.com) writes:
> 
> > I'm trying to run soft-floating point functions on a r5000 core with
> > a FPU. Without having to take the overhead of using a trap.  Using
> > the files fp-bit.c and dp-bit.c from the gcc source as a floating
> > point lib.  This implementation lack in accuracy in the least
> > signeficant bit multiplication in division operations.
> 
> There's an IEEE-compatible set of software floating point routines in
> the Linux kernel, invoked by the trap handler.  The routines were
> donated by Algorithmics (now part of MIPS Technologies).
>
> If you wrapped them in the appropriate GCC skins, they should give you
> a soft-float library which works better.
> 

I've found John Hauser's softfloat package to be an excellent resource
for such applications.  It's under a BSD licence, and can be found here:

http://www.jhauser.us/arithmetic/SoftFloat.html

I've been very happy with it in a couple of projects.  

-Justin



<Prev in Thread] Current Thread [Next in Thread>