[Date Index] [Thread Index] [Author Index]

Re: MacOS vs. Windows PC for Mathematica?

• To: mathgroup at smc.vnet.net
• Subject: [mg13897] Re: MacOS vs. Windows PC for Mathematica?
• From: Josip Loncaric <josip at icase.edu>
• Date: Sun, 6 Sep 1998 02:55:34 -0400
• Organization: ICASE
• References: <6s5l6q$c84@smc.vnet.net> <6s8ed9$ijr@smc.vnet.net>
• Sender: owner-wri-mathgroup at wolfram.com

Harald Giese wrote:
> 
> ...
> sometimes I am also thinking about a switch, but to Linux, because
> Mathematica runs there twice as fast as on a Mac or NT: "Speed
> comparison of Mathematica on various machines":
> http://www.informatik.uni-frankfurt.de/~stst/mathstef2.html)
> ...

Indeed, this speed comparison in Stefan Steinhaus' benchmark shows a
dramatic difference between Linux and NT.  For example, the overall
performance index for Pentium Pro 200 MHz machines is listed as follows
(lower is better):

Linux 2.0.33        252.110
NT 4.0              623.782

This huge 2.5:1 advantage of Linux is typical for Pentium based systems
in Stefan's tests.  HOWEVER, there is NO hint of ANY Linux advantage in
another benchmark by Karl Unterkofler (see
http://fampm201.tu-graz.ac.at/karl/timings30.html data).  

Why this inconsistency?  The benchmarks are rather different, and
Stefan's requires more memory to run.  Could this be the main source of
NT's lackluster performance?  There is a bug fix for "Out of memory"
errors reported by Mathematica 3.0 and 3.0.1 under NT (see
http://www.wolfram.com/support/Systems/Windows/OutOfMemory.html page). 
Were Stefan's results affected by this in any way?

I do not know if this NT performance penalty is unavoidable (I use UNIX
and Mac versions of Mathematica).  If anyone can shed some light on
this question, please do so.  

-- 
Dr. Josip Loncaric, Senior Staff Scientist ICASE, M/S 403, NASA Langley
Research Center, Hampton, VA 23681-2199 Phone: (757) 864-2192          
mailto:josip at icase.edu Fax:   (757) 864-6134                  
http://www.icase.edu/~josip/