[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: CUDA in Octave 322
|
From: |
Corrado |
|
Subject: |
Re: CUDA in Octave 322 |
|
Date: |
Fri, 11 Sep 2009 13:53:32 +0100 |
|
User-agent: |
KMail/1.11.4 (Linux/2.6.28-13-generic; KDE/4.2.4; x86_64; ; ) |
On Friday 11 September 2009 13:15:04 Thomas Ilnseher wrote:
> Problem here is that you have to copy data to the GPU's memory nad
> back, call the GPU and so on. This probably gives a reasonable overhead,
> so you'd only accelerate things this way when operating with *LARGE*
> vectors / matrices.
Yes, this is the situation here (very large matrices). The fact that CUDA is
not FS/OS is still a problem though. That was the reason for mentioning
OpenCL.
Regards
--
Corrado Topi
Global Climate Change & Biodiversity Indicators
Area 18,Department of Biology
University of York, York, YO10 5YW, UK
Phone: + 44 (0) 1904 328645, E-mail: address@hidden