Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: gllamm and computational speed


From   "Martin Weiss" <Martin.Weiss1@gmx.de>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: gllamm and computational speed
Date   Sun, 27 Dec 2009 23:06:31 +0100

<>


What do "high performance computer resources" mean to you? Probably Stata/MP? If so, the authors of the command probably need to make an effort to take advantage of several processors. Official Stata`s -xtmixed- does not seem to benefit from multiple processors, though: See http://www.stata.com/statamp/report.pdf, page 112. Probable reason: Its code is not amenable to parallelization. The same may well apply to -gllamm-.


HTH
Martin

-------- Original-Nachricht --------
> Datum: Sun, 27 Dec 2009 14:14:26 -0500
> Von: Hillel Alpert <HALPERT@hsph.harvard.edu>
> An: statalist@hsphsun2.harvard.edu
> Betreff: st: gllamm and computational speed

> Could anyone please advise how much of an increase in speed of gllamm be
> expected with use of high performance computer resources? The data set is
> very large and processing is prohibitively slow using Stata SE and 64 bit
> computer. Will it run fast enough to compare models within an hour or so?
>  
> Hillel Alpert
>  
>  
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

-- 
Jetzt kostenlos herunterladen: Internet Explorer 8 und Mozilla Firefox 3.5 -
sicherer, schneller und einfacher! http://portal.gmx.net/de/go/chbrowser
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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