(j3.2006) (SC22WG5.4117) Parallel random numbers
Thu Oct 22 14:00:49 EDT 2009
On Thursday 22 October 2009, Bill Long wrote:
> You want the "same default seed", right? Each image should be able
> to independently change its own seed.
Do we say anything now about default seed? What I meant was that if each
image sets the seed identically and then calls random_number the same
number of times, they all get the same sequence. Or, we explicitly say
they may be different even if seeded identically (but why would we say
that?). As to default seed, perhaps we could suggest vendors seed the
generators differently so that different images give different streams?
Aleksandar Donev, Ph.D.
Luis W. Alvarez Postdoctoral Fellow
Center for Computational Sciences and Engineering (https://ccse.lbl.gov)
Lawrence Berkeley National Laboratory (http://www.lbl.gov)
E-mail: adonev at lbl.gov
Phone: (510) 486-5782 Fax: (510) 486-6900
Address: MS 50A-1148, LBL, 1 Cyclotron Rd., Berkeley, CA 94720
More information about the J3