Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > comp.soft-sys.math.mathematica > #5027

Re: CUDA computing

From David Bailey <dave@removedbailey.co.uk>
Newsgroups comp.soft-sys.math.mathematica
Subject Re: CUDA computing
Date 2011-09-18 08:11 +0000
Organization Steven M. Christensen and Associates, Inc and MathTensor, Inc.
Message-ID <j5493a$667$1@smc.vnet.net> (permalink)
References <j51sl8$pdq$1@smc.vnet.net>

Show all headers | View raw


On 17/09/2011 11:26, dan jack wrote:
> Do anyone use Nvidia GEForce GT520 or GT540 to perform parallel
> computation with CUDAlink?
> I search for a hint to buy one of these with 48 or 96 cores, but don't
> know how much improvement in calculations I will benefit.
> I'm involved with learning algorithms and neural netoworks so I think
> there is room for parallelization.
> What do you think about?
> And do you think it's better invest money on big CPU or big GPU or
> both?
>
> thank you all
>
In my opinion, the first step should be to ensure your code is 
efficient. The speed of Mathematica code can vary enormously with quite 
subtle changes.

For example, if the critical part of your NN calculation can be 
expressed as matrix multiplication, try to do that, and make sure you 
use packed arrays, or sparse arrays as appropriate.

David Bailey
http://www.dbaileyconsultancy.co.uk

Back to comp.soft-sys.math.mathematica | Previous | Next — Previous in thread | Find similar | Unroll thread


Thread

CUDA computing dan jack <dan.spectrix@gmail.com> - 2011-09-17 10:26 +0000
  Re: CUDA computing David Bailey <dave@removedbailey.co.uk> - 2011-09-18 08:11 +0000

csiph-web