Nvidia And Stanford Finalizing Folding@Home Client For GeForce GPUs

[Guest]

Santa Clara (CA) - During Nvidia Editor's Day, we learned that Nvidia and the

 

[ilovebarny]

man those cards sound awesome!!!

 

[Lozil]

Amazing.....163 times faster than Quadcore....?? Astonishing...

http://free-and-useful.blogspot.com

 

[A_Dying_Wren]

Hmm... next gen ATI are much better in terms of GFLOPS so this should be interesting...

 

[Guest]

When's SETI@HOME coming out with this?

 

[heffeque]

I've got a 8600 GT on my MacBookPro. Will it work on MacOS X or only on Windows?

 

[Wheat_Thins]

I am assuming the speed boost comes from the built in physics processing that is shipping with the new cards courtesy of the Ageia buyout?

 

[Fadamor]

I posted a reference to this article on Stanford's Folding Forum, and Vijay Pande replied that they are HOPING the client can be released "soon", but that it is still in QA at this time. He also specifically addressed this article as follows:

"PS Note that Tom's H numbers are a bit misleading. We're not getting 650ns/day (yet) on the gtx280 (more like 550) and we're now getting 250ns/day on 3870's in the lab (perhaps 300ns/day in time), and the 3870's are the previous gen ATI cards. The gtx280 is going to be really great at folding though."

 

[Fadamor]

Heffeque, Based on the article, as long as the card can understand nVidia's CUDA programming language, it should work. Whether PandeGroup provides a Mac installer to go with a Win installer is up to them.

Everyone, please note that the performance specs they're quoting in the article (and in Vijay Pande's response above) are based on the new GPU nVidia is releasing next week. Those of us with the older GPUs will not have the same performance boost but it still should be much better than the SMP or single core clients.

 

[Guest]

whats folding@home do?

 

[Fadamor]

Stanford University has a Distributed Computing project ongoing to predict the causes of protein mis-folding... the suspected causes of fatal diseases such as Amalydosis, Alzheimer's, and Mad Cow.

You can find all sorts of information on their website: http://folding.stanford.edu

Basically, they use your computer when it's "twiddling its thumbs" to crunch a minute portion of a protein's normal (or abnormal) folding process. The result is sent back to Stanford, where they add it into the results returned by other participants. There are over one million participants from all parts of the world, so Stanford is able to get faster results than if they used a supercomputer!

 

[mr roboto]

Bought time! Nvidia has been dragging their collective ass's on this for years. My 8800GTX just sits here when I could be using it to possibly help cure diseases. I honestly believe that they waited until they knew they could take the performance crown in F@H from ATI with the new cards. Instead of releasing something in the meantime to hold us over and at least contribute something. As usual it's always about marketing and money. Super lame. I love their cards but seriously question their motives at times.

 

[Fadamor]

Somehow I doubt that F@H figures strongly in any decisions that nVidia makes regarding their products. I'm not going to give any conspiracy theories much credit in this situation.

 

[martel80]

I would really like to know whether the electric power wasted by those cards and just emitted to space is actually worth the discovery potential. Perhaps it is just a waste of money and resources (if the power comes from coal/oil/fission power plants).
Think more before praising similar projects.

 

[heimie]

Electric Power emitted into space? Wasted? It amazes me that people will use a PC (that wastes power and evidentaly "emitts" electric power into space) to post uninformed and negative posts about how wasteful using a PC for medical research is. It takes all kind I guess.

 

[martel80]

"Electric Power emitted into space? Wasted? It amazes me that people will use a PC (that wastes power and evidentaly "emitts" electric power into space) to post uninformed and negative posts about how wasteful using a PC for medical research is. It takes all kind I guess."
If you're SO informed, are you really sure that the folding research results will be worth more than its electricity bill and environmental damage caused when producing electricity for it? If not, it WILL be a waste.

 

[heffeque]

Well... maybe not in the US, but other countries are starting to have a pretty big production of electricity with renewable energies instead of on oil, coal, etc.

 

[heffeque]

Spain produces more electricity with solar panels than the whole of the United States. This doesn't mean that Spain is the best on earth (actually Germany produces more), what it sais is that the US isn't doing their homework.

 

[martel80]

I'm not bashing the project. I know I'm asking an awkward question but someone needed to ask it anyway.
Perhaps this project will be worth the invested resources but SETI@HOME, for example, will probably cause more damage than benefit.

 

[lobofanina]

Here's hoping that the point allocation system makes more sense this time around or else the people that primarily care about the points, I mean science, might not ever leave the SMP clients. Team Wackbag.com lobofanina