[NEWS] Open Beta for nVidia GPU3

Associate
Joined
29 Jun 2009
Posts
710
Location
West Sussex
Folding is now available on nVidia 4xx GPUs. :)

Originally Posted by Vijay Pande
We have a new GPU core (core 15) going into an open beta test for NVIDIA clients. This core requires a new client (see below) as well as the latest drivers (197.45). This core is the first run of the GPU3 technology, derived from the OpenMM project at Stanford (http://simtk.org/home/openmm). You can find more information in our GPU3 FAQ (see url below).

While this release is for NVIDIA only to start, we are actively pushing ATI support (with the help of AMD/ATI), although we have no ETA at the moment. However, please do not use this client with an ATI GPU at the moment.

This is the first open beta test of this new client and core, so there are likely bugs to be found as more donors try this out on more diverse sets of hardware. Also, the documentation (GPU3 FAQ) is new too and there are possibly some errors there too. However, the client has been QA'd both internally at Stanford and with our closed group of beta testers and is looking pretty good so far. Please post bugs or issues in the GPU section of this forum.

Source.

http://www.overclock.net/overclock-net-folding-home-team/739885-news-open-beta-nvidia-gpu3.html
 
Last edited:
Cool can't wait to see what the 4xx are getting PPD wise. I might wait a while before I swap everything over to see if any issues come out.
 
Just downloaded and running now. On a GTX260, shaders 1350 Fahmon gives:

Project : 10626
Core : Unknown
Frames : 100
Credit : 610


-- 260 GPU3 --

Min. Time / Frame : 1mn 32s - 5728.70 ppd
Avg. Time / Frame : 1mn 32s - 5728.70 ppd
Cur. Time / Frame : 1mn 33s - 5667.10 ppd
R3F. Time / Frame : 1mn 33s - 5667.10 ppd
Eff. Time / Frame : 1mn 35s - 5547.79 ppd

First work unit is not looking too good for PPD :( I'll do a few more but might have to switch back.
 
That's looking a bit pants. GPU2 managed a solid 7k minimum for me on vast majority of WUs with a GTX260 and 1500 on shaders.
 
I had a few yesterday and, although they weren't on psummary at the time so I couldn't get benchmarks from HFM, I worked out manually I was getting ~7400 ppd on each client on my GTX295 - about 2,500 less than the GPU2 units. Seem to have dried up just now as I've only had GPU2 WUs all night.
 
Well completed 7 wu on the new client, it now seems to have dried up and PPD remained pretty pants throughout. Swapping back over now until things improve.

Anyone got a 4xx doing anything yet?
 
Was hoping to see more from the fermi cards.

I have been thinking what to do with my rigs and this doesn't help me make up my mind. At the price they are and the amount of power they consume and they are supposed to be really hot and noisy. Maybe I will have to be more patient and wait a little longer...
 
I guess I could if I could stomach the leccy bill :(
I'm getting 13-16K on my i7 on an A3 WU.. the 480 wouldn't help much but would probably triple my power useage.
 
Back
Top Bottom