Fast Floating Point Alternatives for 68K and GCC?

David J. Fiddes D.J@fiddes.surfaid.org
Sat Apr 1 00:00:00 GMT 2000


Hi,

>I would like to hear about any alternative floating point libaries for
>GCC that provide faster floating point support?
>I am interested in 32bit only (float) as well as 32/64 bit
>(float/double) alternatives.
>It would also be nice to know about accuracy of any alternatives.

Wayne Deeter [wrd@logical-co.com] has recently done quite a bit of work in
speeding up the 68000/ColdFire floating point. He claims a x2 speed increase
on double multiplies... You can get his code from
http://www.deetour.net/coldfire/lb1sf68/ and I have some blurb on my
coldfire web page at http://fiddes.net/coldfire/

The code is not a patch against gcc yet and has to be compiled separately
and added to libgcc.a using ar but it does show promise.

Dave


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



More information about the crossgcc mailing list