RE: [fpu] Rounding of Floating Point Numbers

[Damjan Lampret <damjanlampret@yahoo.com>]

> So I guess I have to implement ALL of those modes :*(

I really care only for default. Afterall other three are optional. So
if they are optional it means they are optional. Why should they be
implemented if they are optional? And who is ever changing this
rounding modes. I don't think other three are even used (at least not
in 99% of cases).

> Instead of sitting down and figuring this all out, I thought there
> might be
> already some white papers or other information that describes the
> rounding
> technique and perhaps has some efficient implementation suggestions.
> 

I know what your question was and I might have some answers. Actually
the book in front of me has them. But I am too lazy to copy a couple of
pages (and the author of the book wouldn't be too _happy_ about this).

You have a section on FP rounding schemes and how to implement them. I
can try to extract for default rounding but everything is quite mixed
together with other rounding schemes (and I am not yet used to typing
on my new Sony VAIO SuperSlim Pro laptop ;-). If you really need this
I'll try to extract. But for a start I can give you title and author:

Computer Arithmetic
Algorithms and /hardware designs

Behrooz Parhami
Oxford University Press, 2000
ISBN 0-19-512583-5

regards,
Damjan


__________________________________________________
Do You Yahoo!?
Kick off your party with Yahoo! Invites.
http://invites.yahoo.com/