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


Groups > comp.soft-sys.math.mathematica > #5014 > unrolled thread

CUDA computing

Started bydan jack <dan.spectrix@gmail.com>
First post2011-09-17 10:26 +0000
Last post2011-09-18 08:11 +0000
Articles 2 — 2 participants

Back to article view | Back to comp.soft-sys.math.mathematica


Contents

  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

#5014 — CUDA computing

Fromdan jack <dan.spectrix@gmail.com>
Date2011-09-17 10:26 +0000
SubjectCUDA computing
Message-ID<j51sl8$pdq$1@smc.vnet.net>
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

[toc] | [next] | [standalone]


#5027

FromDavid Bailey <dave@removedbailey.co.uk>
Date2011-09-18 08:11 +0000
Message-ID<j5493a$667$1@smc.vnet.net>
In reply to#5014
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

[toc] | [prev] | [standalone]


Back to top | Article view | comp.soft-sys.math.mathematica


csiph-web