> Date: Thu, 31 Mar 2005 12:22:00 -0500
> From: Timothy Sloane <[EMAIL PROTECTED]>
> Subject: Re: [Prime] Tip: 2^31-1 = Mersenne exponent
> To: Michael Vang <[EMAIL PROTECTED]>,  

> 2)  The Lucas-Lehmer test is sequential, and I've seen it
stated that
> you can't split up a single exponent across multiple
processors in a
> multi-CPU machine, so I doubt you could split a single
exponent across
> multiple computers.

Not really.
The GLucas program is multi-threaded: it divides the work of
the FFT between several threads on several processors on the
same computer.
IF the amount of data to be shared and exchanged between all
threads does not exceed some maximum, GLucas work could be
divided between several processes on several machines, using
MPI plus a very fast inter-connect like Quadrics.
And thus, computing the LTT for a big exponent could be done
much faster than on a single mono-processor machine.

Tony

Acc�dez au courrier �lectronique de La Poste : www.laposte.net ; 
3615 LAPOSTENET (0,34�/mn) ; t�l : 08 92 68 13 50 (0,34�/mn)



_______________________________________________
Prime mailing list
[email protected]
http://hogranch.com/mailman/listinfo/prime

Reply via email to