Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: Efficient parallel computing in Stata/MP
From
Daniel Feenberg <[email protected]>
To
[email protected]
Subject
Re: st: RE: Efficient parallel computing in Stata/MP
Date
Fri, 27 Sep 2013 08:36:46 -0400 (EDT)
On Fri, 27 Sep 2013, Demian Panigo wrote:
Thank you very much Daniel:
Just one more question.
You finally used 24 cores (cores and hypercores) to run 3 parallel
Stata MP/8 jobs with interesting time saving outcomes.
But, did you compared these results with those obtained by just run 24
parallel Stata SE jobs in, for example, batch mode?
No, but in other experiments I found that the wall clock time for a large
(many observations and many variables) -reg- in Stata/MP8 is one eigth the
time for Stata/SE. This is close to the result reported by Stata - they do
find some fall-off as the number of cores increases.
You should experiment.
Dan Feenberg
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/