[R] Benchmarks

ripley@stats.ox.ac.uk ripley at stats.ox.ac.uk
Tue Apr 16 17:40:31 CEST 2002

On Tue, 16 Apr 2002, Thomas Lumley wrote:

> On Tue, 16 Apr 2002 Lennart.Araskoug at astrazeneca.com wrote:
> > Hi !
> >
> > Is there anyone that has any current benchmark results from Sparc CPU's ?
> >
> > I'm mostly interested of US-III 750 and US-II 450, But any US-II/III would
> > be interesting.
> We used to have some UltraSparc II machines, I believe at 450MHz.  R ran
> very slightly faster on a 450MHz Pentium III than on the UltraSparc, based
> on make check and on the survival package tests. I don't have any absolute
> figures, but they would be obsolete anyway.

We have what I believe is a dual 400MHz UltraSparc box.  It's a server,
and uname -a says it is Ultra-4.  With the native compilers (especially
f77/f95) it is quite a bit faster (maybe 50%) running R than our (dual)
450MHz Pentium III server.  But this is irrelevant given the price and
speed of, say, an Athlon XP1800.

One issue is that R runs slower (say 10%) when targetted at v9 (64-bit
mode) chips (and hence compiled to use 64-bit pointers and longs).

Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list