Welcome, Guest. Please login or register.
Amiga Kit Amiga Store Iridium Banner AMIStore App Store A1200/A600 4xIDE Interface

AuthorTopic: /  (Read 810 times)

0 Members and 1 Guest are viewing this topic.

Offline Lorraine

/
« on: January 15, 2009, 02:26:00 AM »
/
 

Offline persia

Re: OpenCL
« Reply #1 on: January 15, 2009, 12:09:49 PM »
There is the Condor Project.
[SIGPIC][/SIGPIC]

What we\'re witnessing is the sad, lonely crowing of that last, doomed cock.
 

Offline Zac67

Re: OpenCL
« Reply #2 on: January 15, 2009, 12:19:12 PM »
It's been adopted by Apple, not trademarked.

Of course GPGPUs, Cells and such can tremendously improve performace and efficiency. My GF9800GT crunches 4500 Folding@Home PPDs or 5500 distributed.net WUs/day on ~100 Watts. That's nearly tenfold of a really fast system using quite a bit more power.

Of course the clients are currently using CUDA, but an open standard like OpenCL is definitely a step forward to broader support.
 

Offline AJCopland

Re: OpenCL
« Reply #3 on: January 15, 2009, 12:36:04 PM »
Quote

Zac67 wrote:
It's been adopted by Apple, not trademarked.


To be preceise it was started by Apple and then submitted to Khronos as a potential standard. Apple still have some trademarks and rights over it but that standard itself is fully open and can be implemented by anyone.

A GPU agnostic solution like OpenCL will be very nice when it's actually available for people on nVidia, ATi etc hardware but there's no available implementations yet for the end user.

Actually GPGPU stuff has been available for quite a while now with nVidia pushing CUDA and ATi supporting a customised version of Brook+.

Andy

Offline Karlos

Re: OpenCL
« Reply #4 on: January 15, 2009, 12:51:42 PM »
CUDA is a lot of fun, I've been playing with it for a while on my gtx260 :)
int p; // A
 

Offline AJCopland

Re: OpenCL
« Reply #5 on: January 15, 2009, 02:09:51 PM »
I've been wanting to speed up our build process for some data that involves a pretty good fit for something like CUDA et al. the only problem being that we run a mixed gpu environment, some Ati some nVidia.

So it'd become a maintenance headache because I'd have to support CUDA+cpu only, or only half the team would be able to build all of the data :/

Role on OpenCL so I can have some fun playing with it too!
I have written some GPGPU stuff but just using vertex and fragment shaders in OpenGL. Getting it to work like that should be possible and portable enough to run on Ati/nVidia. Unfortunately as soon as you say "should" my boss won't give me work time to investigate.

Andy

Offline keropi

Re: OpenCL
« Reply #6 on: January 15, 2009, 02:29:15 PM »
hmmm can you give some examples of CUDA usage? any progs for everyday usage perhaps? I have one of those 216cores GTX260 gigabyte cards on my pc now...
 :-D

edit: a RAR cuda engine would be awesome! :-P