MathGroup Archive 2008

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

Search the Archive

Re: GPU vs CPU in Mathematica 6

  • To: mathgroup at smc.vnet.net
  • Subject: [mg91091] Re: GPU vs CPU in Mathematica 6
  • From: Jens-Peer Kuska <kuska at informatik.uni-leipzig.de>
  • Date: Wed, 6 Aug 2008 05:03:28 -0400 (EDT)
  • References: <g791df$9i3$1@smc.vnet.net>

Hi,

write a CUDA program + the MathLink templates, preprocess
it with mprep and compile the output with nvcc. Install it in a 
Mathematica session and you are done ...

But keep in mind, that if you can only parallelize 50 % of your code,
than an infinite number of processors will speed up you calculation
only by a factor of 2.

Regards
   Jens

Antonio wrote:
> Dear All,
> 
> Is it possible, or has anyone already tried, to use the GPU processing
> instead of the CPU in Mathematica 6?
> 
> I ask this question in particular for these new graphic boards (Nvidia
> series 8x)
> http://en.wikipedia.org/wiki/Comparison_of_Nvidia_Graphics_Processing_Units#GeForce_8_series
> 
> It should be advantageous to exploit the parallel processing
> capabilities of the GPU. Any hint as to access these Graphics
> functions via Mathematica?
> 
> Antonio
> 


  • Prev by Date: Re: Derivative of Dot[]
  • Next by Date: Re: Evaluate part of rhs of RuleDelayed
  • Previous by thread: GPU vs CPU in Mathematica 6
  • Next by thread: Re: GPU vs CPU in Mathematica 6