Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Run time for GLLAMM multilevel modeling


From   Michael Ingre <Michael.Ingre@ipm.ki.se>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Run time for GLLAMM multilevel modeling
Date   Wed, 24 Nov 2004 10:19:03 +0100

On 2004-11-22, at 22.12, Stas Kolenikov wrote:

A UNIX cluster however can provide
the reliability and uptime measured in months rather than in hours for
a Windows machine. Besides, if one is estimating five or ten models in
-gllamm-, that can easily be put into separate do-files thus using
multiple processors more efficiently.
I see what you mean. I could really have made use of a cluster a few months ago. I ran 10 models on 4 computers in parallel for the better part of a week. It was a bit complicated copying files making sure not to overwrite an estimated model, because I used Macintoshes, at least I benefited from the reliability and uptime of UNIX. And many thanks to Michael Blasnik for -estsave-. Without it it ... I don't know what I would have done.


although I heard that Stata Corp. has been looking into
multithreading some of  their code.
That's interesting. If you a right then I hope they will focus on -gllamm- related code. This could mean a considerable performance boost for anyone with a dual or multiprocessor system.

Michael

*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index