> Hmm, does this approach make sense in the context of systems with say N
> or more CPU's?  The MP performance of Solaris has been getting better 
> and better each release, or so sun says. 

yes, well, sun is doubtless one suspects committing the old felony: take 
your MP code on 1 CPU, then see how much faster on N cpus, then claim you 
scale by that factor. 

instead of the right way: take 1 CPU running good scalar code (sunos 3.5? 
sunos 4.1.2 before the strange MP hacks crept in?  netbsd? linux?) then
compare to MP code on N cpus, then claim you scale by that factor. 

Which looks from this dicussion like the MP "improvement" is overstated 
by as much as a factor of 2?

ron