is maxima suitable for multiprocessor computations?

My recollection is that parallel GB is not particularly fruitful, and that
adding processors after about 6 or 10 is pointless.  Doing reductions in
parallel is mostly wasteful, since the computations done in parallel turn
out to be redundant and are avoided if done in serial. Perhaps someone has
better results recently that I have not seen.  
RJF
 

> -----Original Message-----
> From: Andrey G. Grozin [mailto:A.G.Grozin at inp.nsk.su] 
> Sent: Tuesday, November 13, 2007 8:36 PM
> To: Raymond Toy (RT/EUS)
> Cc: Richard Fateman; Stavros Macrakis; maxima at math.utexas.edu
> Subject: Re: [Maxima] is maxima suitable for multiprocessor 
> computations?
> 
> On Tue, 13 Nov 2007, Raymond Toy (RT/EUS) wrote:
> > Are there interesting symbolic problems that would really 
> benefit from
> > parallelism?  So what if I can do parallel polynomial multiplication
> > really fast?  Does that lead to some interesting result?
> Groebner bases calculations can be parallelised rather easily 
> (computing 
> and reducing several S-polynomials in parallel). There were 
> many papers 
> published on this subject, and there are some implementations (not in 
> lisp).
> 
> Andrey
>