AGEILA PhysX Card

Message boards : Number crunching : AGEILA PhysX Card
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Michael Muench
Avatar

Send message
Joined: 22 Aug 99
Posts: 4
Credit: 1,336,051
RAC: 0
Germany
Message 390053 - Posted: 6 Aug 2006, 13:46:10 UTC
Last modified: 6 Aug 2006, 13:51:55 UTC

Hi
i have a question

i have a AGEILA PhysX Card,can we use this card
for Boinc too!!


has someone an idea ??

it´s only an idea but this card has a lot power where we can us and we need all power where we can get !

ID: 390053 · Report as offensive
Profile Chilean
Volunteer tester
Avatar

Send message
Joined: 6 Apr 03
Posts: 498
Credit: 3,200,504
RAC: 0
Chile
Message 390243 - Posted: 6 Aug 2006, 16:56:08 UTC

i dont know what that is... but if its a graphics card then no. At least thats as far as I know.
ID: 390243 · Report as offensive
Profile KWSN - Chicken of Angnor
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 9 Jul 99
Posts: 1199
Credit: 6,615,780
RAC: 0
Austria
Message 390247 - Posted: 6 Aug 2006, 17:02:53 UTC

It's a PPU (Physics Processing Unit) - a relatively new concept, it makes for more realistic physics effects in games (although current games really do not take advantage of it yet with very few exceptions).

So it's not really a graphics card, but it enhances graphic effects and gameplay by offloading some of the calculations from the main CPU and enabling better AI, for example.

HTH,
Simon.
Donate to SETI@Home via PayPal!

Optimized SETI@Home apps + Information
ID: 390247 · Report as offensive
OzzFan Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Apr 02
Posts: 15691
Credit: 84,761,841
RAC: 28
United States
Message 390366 - Posted: 6 Aug 2006, 20:07:57 UTC

Mr. Chicken is right on the nose. The Ageia not, Ageila, card is a PPU designed to make physics more realistic in games. I'm not sure of it's capabilities, but if it can't do the right calculations with the right amount of acuracy, then I doubt it will be supported, just like graphics cards.
ID: 390366 · Report as offensive
MGCJerry
Avatar

Send message
Joined: 8 Dec 02
Posts: 37
Credit: 3,174,560
RAC: 0
United States
Message 392466 - Posted: 9 Aug 2006, 1:43:47 UTC

From my understanding of the PPU, it specializes in calculations needed for physics effects which I believe SETI could really benefit from if there was a way to use the hardware since it is VERY efficient and fast at processing multiple (2000+) physics calcuations simulatenously.

Would be nice to see, though I'm not a PPU owner.
ID: 392466 · Report as offensive
Profile mikey
Volunteer tester
Avatar

Send message
Joined: 17 Dec 99
Posts: 4215
Credit: 3,474,603
RAC: 0
United States
Message 392520 - Posted: 9 Aug 2006, 3:12:00 UTC - in response to Message 392468.  

Yeah I'd buy a few, If It could be of help to Me when crunching for Seti.

You could always compile a verison of the program so it will run on the card. Of course that involves stuff waaaay beyond my capabilities. People have compiled versions for all the different OS's, at least most of them. The problem is, and always has been, that this card, and video cards like it, are not in wide spread use, as compared to OS's, so the application is limited in its potential users.

ID: 392520 · Report as offensive
Team AUSTRALIA (AlexD)

Send message
Joined: 1 Jun 99
Posts: 54
Credit: 66,602
RAC: 0
Australia
Message 392523 - Posted: 9 Aug 2006, 3:17:17 UTC
Last modified: 9 Aug 2006, 3:29:49 UTC

But isn't S@H more about "pattern searching" than any sort of physics calculations? Ie, is looking for a signature pattern of frequency changes which would indicate stronger than expected (non background noise) originating from another point of origin (ie, not from our own little blue-green marble).

Maybe for some of the other BOINC projects yes, but don't see how it could help S@H crunching?


ID: 392523 · Report as offensive
trlauer

Send message
Joined: 6 May 04
Posts: 106
Credit: 1,021,816
RAC: 0
Message 393111 - Posted: 9 Aug 2006, 17:13:43 UTC

This is an interesting topic. I'd be interested to know if anyone knows whether the Ageia PhysX accelerator accelerates FFTW? If it does, it'll help with a lot of scientific projects. I know ClearSpeed does have an accelerator that will accelerate FFTW and claims up to 50Gigaflops per second, but it's too high priced for the majority of us at the moment. There are talks that AMD is looking to add a ClearSpeed accelerator for AMD that would have direct access to Hypertransport, but we'll see if that really ever happens.

Torrey Lauer
Modern Travel Services / Rainbow Sky Travel
moderntravel d01.t net / RainbowSkyTravel d01.t com
ID: 393111 · Report as offensive
Profile mikey
Volunteer tester
Avatar

Send message
Joined: 17 Dec 99
Posts: 4215
Credit: 3,474,603
RAC: 0
United States
Message 396479 - Posted: 13 Aug 2006, 14:41:31 UTC - in response to Message 392523.  

But isn't S@H more about "pattern searching" than any sort of physics calculations? Ie, is looking for a signature pattern of frequency changes which would indicate stronger than expected (non background noise) originating from another point of origin (ie, not from our own little blue-green marble).
Maybe for some of the other BOINC projects yes, but don't see how it could help S@H crunching?

Yes Seti is about 'pattern searching' but it does it thru highly intensive mat calculations. It calculates one item, calculates a second item, then compares the two. It is not about pictures.

ID: 396479 · Report as offensive
Profile Misfit
Volunteer tester
Avatar

Send message
Joined: 21 Jun 01
Posts: 21804
Credit: 2,815,091
RAC: 0
United States
Message 400340 - Posted: 18 Aug 2006, 0:52:56 UTC
Last modified: 18 Aug 2006, 0:53:46 UTC

AGEIA PhysX
me@rescam.org
ID: 400340 · Report as offensive

Message boards : Number crunching : AGEILA PhysX Card


 
©2025 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.