Paul Davis wrote:
> 
> >Wow! It's wonderful.
> >
> >I think that now we have proved that:
> >- multiprocess approach is relatively cheap
> >- whole object size has dramatic effect
> 
> *cough* *cough*
> 
> We've proved that:
>  - multiprocess approach is relatively cheap when used with small objects

Why you say that "when"? Please give a look again to graphs for UP: as
far as I can see the whole things becomes to be unstable and fast
increasing when the footprint is greater than a certain threshold.

This has nothing to do with mp or st (consider that mp has an increased
footprint in stack use of 4 * bytes). Consider also that stack use
inside a component may be kept very slow (definitely under 8Kb).

-- 
Abramo Bagnara                       mailto:[EMAIL PROTECTED]

Opera Unica                          Phone: +39.546.656023
Via Emilia Interna, 140
48014 Castel Bolognese (RA) - Italy

ALSA project               http://www.alsa-project.org
It sounds good!

Reply via email to