GPU2 open beta

[dicecca112]

We're (finally) ready to start the QA process outside Stanford & ATI for the next generation GPU client (nicknamed FAH GPU2). We've gone through a limited alpha and a larger closed beta test, and we think the client is now ready for an open beta, i.e. a public release of the software that's still in an early stage. That's not to say that it's flawless, but there don't appear to be any "show stoppers" so far.

If you have a 2xxx or 3xxx card, please feel free to check out the new GPU client? You can download it from here

http://www.stanford.edu/~beberg/Folding ... ystray.zip

and a FAQ is here

http://folding.stanford.edu/English/FAQ-ATI2

We will next put this on our main download page, assuming that this stage of beta testing looks good.

Please keep in mind that this is beta software. The client/core may be unstable (although it looks ok so far), the points benchmarking may change due to software or policy changes, etc. With that in mind, we'd appreciate any comments you may have -- please post them in this forum section. Thanks!

[Bwall]

I've been following a couple of threads and the GPU client is a great option for high clocked Core 2's. It's extremely dependent on CPU power when you're using a 3850/70/2900XT.

[skier]

I've been following a couple of threads and the GPU client is a great option for high clocked Core 2's. It's extremely dependent on CPU power when you're using a 3850/70/2900XT.

what about say.. a 3870X2 with either a P4 or 64 X2 3800+?

[Jeff_Grant]

I wouldn't think a P4 could keep up with the 3870X2. My [email protected] is only getting about 73% GPU usage according to ATI CC with a 3850 512MB. Now my other card is working @ 99% with a 1.9ghz Athlon X2, but it's a 2600XT 512MB card with a lot less shader power.

[dicecca112]

To answer many of the potential questions, I will give you the result of benchmarking I did ...

Number from HD3870.

Q6600 @ 2.4 GHz (266 * 9), GPU @ 780 MHz : 1310 PPD
Q6600 @ 3.4 GHz (485 * 7), GPU @ 780 MHz : 1860 PPD
Q6600 @ 3.4 GHz (485 * 7), GPU @ 850 MHz : 1860 PPD

More numbers with the 2900XT ...

Dual Opteron 2212 @ 2.7 GHz : 1350 PPD (with GPU @ 739 and 847 MHz)
Q6600 @ 3.4 GHz (485 * 7), GPU @ 739 and 847 MHz : 1860 PPD
Q6600 @ 3.8 GHz (475 * , GPU @ 739 MHz : 1860 PPD
Q6600 @ 3.8 GHz (475 * , GPU @ 847 MHz : 2100 PPD
Q6600 @ 3.8 GHz (475 * , GPU @ 860 MHz : 2100 PPD

Yes, most people are going to be CPU limited with the GPU2 client ...

As you can see the bottleneck with the 3870x2 is the CPU

[skier]

was slighlty expecting that, but hey, im not going to be getting a QX9770 any time soon so the CPU will limit me for many many days coming

i'll fold the 3870 X2 as soon as i get a PSU in(provided i don't get sucked into the insane graphics booost and decide to game on that right away)at least 1 WU i promise

[Bwall]

I think the CPU bottleneck eases at around 3.6GHz on a core 2 with a 3870. I put a 3870 in my machine at 4.0 GHz and had full GPU usage....and of course I couldn't leave well enough alone and overclocked the GPU to 850/1351. It's now at only 92% usage so it looks like I need to overclock my CPU a little more. ;) Currently it's running 40 seconds /percent, or ~2100ppd. The work units are extremely small and are meant for testing, larger and higher value units should be coming soon I would guess.