Re: Floating point/math support implementation

2008-09-18 Thread Harald Welte
On Wed, Sep 17, 2008 at 09:50:49PM +1000, Carsten Haitzler wrote: > > > > I have a few questions about the math support. I've noticed that > > > > math functions such as sin() are very slow on the OpenMoko. How > > > > is the math support implemented? Are all floating point operations > > > > impl

Re: Floating point/math support implementation

2008-09-17 Thread The Rasterman
On Wed, 17 Sep 2008 12:29:27 +0300 Kostis Anagnostopoulos <[EMAIL PROTECTED]> babbled: > On Wed 17 Sep 2008 00:57:15 Carsten Haitzler wrote: > > On Tue, 16 Sep 2008 23:17:52 +0200 "Anton Persson" <[EMAIL PROTECTED]> > > > > babbled: > > > Hi, > > > > > > I have a few questions about the math suppo

Re: Floating point/math support implementation

2008-09-17 Thread Kostis Anagnostopoulos
On Wed 17 Sep 2008 00:57:15 Carsten Haitzler wrote: > On Tue, 16 Sep 2008 23:17:52 +0200 "Anton Persson" <[EMAIL PROTECTED]> > > babbled: > > Hi, > > > > I have a few questions about the math support. I've noticed that > > math functions such as sin() are very slow on the OpenMoko. How > > is the m

Re: Floating point/math support implementation

2008-09-16 Thread The Rasterman
On Tue, 16 Sep 2008 23:17:52 +0200 "Anton Persson" <[EMAIL PROTECTED]> babbled: > Hi, > > I have a few questions about the math support. I've noticed that > math functions such as sin() are very slow on the OpenMoko. How > is the math support implemented? Are all floating point operations > imple

Floating point/math support implementation

2008-09-16 Thread Anton Persson
Hi, I have a few questions about the math support. I've noticed that math functions such as sin() are very slow on the OpenMoko. How is the math support implemented? Are all floating point operations implemented in software, or is there hardware support for float multiplication, and trigonometric