Best offers
Exclusive Interview: Nvidia's Ian Buck Talks GPGPU
With Snow Leopard and Windows 7 both offering GPGPU capabilities, we wanted to talk to Nvidia's Ian Buck. Not only is he one of the fathers of Brook, the programming language ultimately adopted by AMD/ATI, but the head of Nvidia's CUDA group as well. Read More
-
Beamforming: The Best WiFi You’ve Never Seen
Forget 802.11n Draft 2.0. The future of video-capable WiFi depends on a signal-boosting technique called beamforming. We put the pioneers in this frontier through some real-world testing to find out which technology is going to change the wireless world. Read More
-
Exclusive Interview: Going Three Levels Beyond Kernel Rootkits
Today we have the pleasure of chatting with Joanna Rutkowska, one of the top computing security innovators in the world. She is the founder and CEO of Invisible Things Lab (ITL), a boutique computer security consulting and research firm. Read More
Partners
The Games selection
action :
Yoyo the Star
Yoyo is a young girl who recently graduated and dreams to become a movie star (don't we all). You'll have to guide her on the path to stardom,...
|
crazy :
Xiao Xiao 7
A great fight scene from the animation movies Xiao Xiao.
|
Sponsored links
Nvidia And Stanford Finalizing Folding@Home Client For GeForce GPUs
Next news- Email |
- Print |
- Comments (21) |
- Share
Santa Clara (CA) - During Nvidia Editor’s Day, we learned that Nvidia and the Folding@Home research group led by Vijay Pande are making final preparation to launch the first version of the Folding@Home client for Nvidia graphics processors.
The unveiling of the client is set for the next week as part of the launch of Nvidia’s GT200 GPU series. Owning such a card will have its benefits in Folding@Home and will outrun Radeon 3870 cards. The new GeForce cards are expected to hit more than 650 nanoseconds of protein simulation in a single day, while the Radeon HD 3870 is stuck at about 170 ns. The Playstation 3 is able to produce "only" 100 ns of simulation, while a quad-core CPU creates an output of just four nanoseconds. For those who are keeping count: The GeForce GPU will be about 163 times faster than a quad-core processor in this specific application.
Nvidia founded Team "Whoopass", which consists only of several computers that are running the Folding@Home GPU client. Even with just 4-5 test machines, the team quickly moved into the top 5% of all contributors by sheer processing power. Dr. Vijay told us that if only 1% of all CUDA-capable users would start using Folding@Home in their spare time, the Folding@Home machine would quickly be considered the fastest performing HPC computer in the whole world - hitting about 60-80 Peta FLOPS of processing power.
Folding@Home for Nvidia CUDA-capable graphics cards (GeForce 8 and above) should become available next week. The codename for this client is GPU2/NVIDIA. The GPU1 client was retired, while GPU2 client will continue to be updated for both Nvidia and ATI cards.
ATI was first with a client for the Folding@Home project, which was released back in September of 2006 for the X1900 series of cards. Back then, the cards topped out at 375 GFlops. The next GPU generation should provide more than double the horsepower.
Source : Tom's Hardware US
Woot! I have been waiting for this for a while.
man those cards sound awesome!!!
Amazing.....163 times faster than Quadcore....?? Astonishing...
http://free-and-useful.blogspot.com
Hmm... next gen ATI are much better in terms of GFLOPS so this should be interesting...
When's SETI@HOME coming out with this?
I've got a 8600 GT on my MacBookPro. Will it work on MacOS X or only on Windows?
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?
^That's for the net gen cards. Current 8x00 cards don't have built in PPU. The performance comes from the GPU architecture itself.
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."
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.
whats folding@home do?
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!
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.
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.
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.
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.
"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.
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.
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.
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.
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