GPU Folding on ATI - its coming!!!
Krazeyivan
Newcastle, UK
The F@H ATI FAQ wrote:
We are primarily beta testing the ATI GPU client software internally at the moment, but gradually releasing the client to collaborators and other closed beta testers. We will make a formal announcement of the client at the ATI Stream Computing Event in San Francisco on Friday September 29, 2006 (this is open for press personnel, not for the general public), and then (assuming everything looks reasonable), start an open beta for the console client on Monday October 2 with the GUI GPU client (with real time visualization) to follow.
Great news - especially if you have an overclocked X1900XT ready to go!
http://folding.stanford.edu/FAQ-ATI.html
We are primarily beta testing the ATI GPU client software internally at the moment, but gradually releasing the client to collaborators and other closed beta testers. We will make a formal announcement of the client at the ATI Stream Computing Event in San Francisco on Friday September 29, 2006 (this is open for press personnel, not for the general public), and then (assuming everything looks reasonable), start an open beta for the console client on Monday October 2 with the GUI GPU client (with real time visualization) to follow.
Great news - especially if you have an overclocked X1900XT ready to go!
http://folding.stanford.edu/FAQ-ATI.html
0
Comments
But the question arrises, why no nVidia client?
ask one of the programmers
From Stanford:
"Which GPUs will be supported? We have not made any final decisions on this issue. However, our software will likely require the very latest GPUs from ATI (especially now that the newest ATI GPUs support 32 bit floating point operations). Previous work of ours used NVIDIA GPUs as well, but we have now concentrated on ATI GPU's as they allow for significant performance increases for FAH over NVIDIA's GPU's (at least at the current generation). Our GPU cluster has 25 1900XT's and 25 1900 XTX's. We find a considerable performance increase of 1900XT's even over 1800XT's, due to the architectural differences between the R580 and R520 GPU's. Our code will run on R520's, but considerably more slowly than R580. We're very much looking forward to trying out R600's."
No more horn blowing than nVidia would do if it were them. I can think of worse places to hand some finance too. nVidia is not in the picture yet because their GPU does not have what it takes to do the job.
Qoute from Stanford:
Look for it in maybe their next GPU.
The FAH ckient should run on 1xxx boards, but I think the more pipes it has the better- and that is the reason 1900s do better than the 18s.
Well, this might finally justify two-card video and that 2nd 16x PCI Ex slot after all!
I know what you are talking about, prime. Both in initial outlay for the card and also in operating costs. I went with a 7900GTX for my Conroe build over the X1900XTX due to it drawing quite a bit less power than ATI's GPU and it's performance is more than enough for me. The ATI cards are also noisier than the Nvidia based cards too, from what I've read.
And I also can't see keeping my $400-500 vid card under a 100% load 24/7/365 either. The cooling on vid cards doesn't hold a candle to the high performance hsf's we have available for our processors.
That will be my main platform - hope to get it going Feb time.
I also have 4 - playstation 3 on order (europe launch in march sucks) and aim to have them just folding in a mini-farm.