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

Re: Multi-core Support in Mathematica 5.2

• To: mathgroup at smc.vnet.net
• Subject: [mg74225] Re: Multi-core Support in Mathematica 5.2
• From: Jean-Marc Gulliet <jeanmarc.gulliet at gmail.com>
• Date: Thu, 15 Mar 2007 04:54:13 -0500 (EST)
• Organization: The Open University, Milton Keynes, UK
• References: <esu68d$rn9$1@smc.vnet.net><200703130303.WAA11010@smc.vnet.net> <et8d0i$oe2$1@smc.vnet.net>

Neri wrote:
> Thanks, Chris. I wasn't familiar with the technical term but suspected
> the answer was something like you wrote.
> 
> Still, wouldn't you say that in most everyday uses the iterations in
> the Table function are independent? Wouldn't it be nice to have the
> ability to tell Mathematica that I mean them to be independent
> (perhaps through an option or attribute?) so Mathematica knows it is
> safe to parallelize the function? 
[snip]

As a rule of thumb, multicore support is not parallelizing support. 
Usually, by parallelizing one means running code on *multiple 
Mathematica kernels* (themselves running on multiple CPUs or cores). 
Mathematica cannot parallelize natively: to do so, one must use 
gridMathematica [1], or Mathematica Personal Grid Edition [2], or 
Mathematica Parallel Computing Toolkit [3]. Only than, one can gain 
access to fine control and tunning which operations and functions can be 
safely parallelized.

Regards,
Jean-Marc

[1] http://wolfram.com/products/gridmathematica/features.html

[2] http://www.wolfram.com/products/personalgrid/

[3] http://www.wolfram.com/products/applications/parallel/

• References:
  • Re: Multi-core Support in Mathematica 5.2
    • From: "Neri" <nkafkafi@yahoo.com>