Gacquer William wrote:
>
> What was wrong with this question? No one answered!
>
> Le Lundi 10 Septembre 2001 13:03, Gacquer William a �crit :
> > Hello
> > Does FASTFPE emulate both single and double precision? ( if yes, was it
> > true also for the 2.4.2 kernel ?)
> > Other than precision uncertainties, what are FASTFPE limitations?
> > Does FASTFPE compete against a fixed point math implementation from the
> > performance point of view? I mean : is it as fast as a fixed point
> > implementation?
How could a system that simulates floating point operations by
peforming multiple fixed point operations possibly be faster than using
fixed point operations directly?
That's what's wrong with your question.
- Eric
_______________________________________________
http://lists.arm.linux.org.uk/mailman/listinfo/linux-arm
Please visit the above address for information on this list.
