Wednesday, 26 May 2010



GPUs and PhysX

Posted: 26 May 2010 09:36 AM PDT

There's been a lot of chatter about GPU physics over the last couple years….but the best way to understand it, is to see it in action. EVGA compiled a great pair of videos showing the differences in game play experience on GeForce graphics cards, with NVIDIA PhysX turned on (and off). Take a look at one of the videos below.

Quick Tip: You can also use a GeForce graphics card as a dedicated PhysX card, while using your other, higher-end, GeForce card to drive 100% graphics. EVGA shows a great example of that in the video after the jump, by pairing up a GT 240 with a GTX 480 card.

Content Drives Netbook, Tablet Growth

Posted: 25 May 2010 03:53 PM PDT

Whither netbooks in the age of the tablet? In this behind-the-scenes video, Rene Haas, general manager of notebook GPUs, shares his thoughts on the future of netbooks and tablets, following his keynote at the Netbook Summit.

IBM Embraces GPUs for High Performance Computing

Posted: 25 May 2010 03:35 PM PDT

Last week was a milestone for the Tesla business. We announced that IBM has integrated our Tesla 20-series GPUs into its new iDataPlex servers. IBM released data that shows the big difference that Tesla GPUs make. Check out the data below, that shows a 4x or more increase in both single and double precision performance per rack for a little over 10% increase in power consumption:

IBM perf graph 
Data Courtesy of IBM

Really exciting times for the Tesla business. And for researchers worldwide. The global race for better science begins this summer as GPU-based hybrid systems replace traditional CPU clusters for large scale computational science. Dave Turek, vice president of Deep Computing at IBM explained their decision to embrace GPUs in an interview he gave HPCwire last week. The punchline is that this is all about meeting the growing customer demand:

"I think what's changed is that customers have been experimenting for a long time and now they're getting ready to buy. It wasn't the technology that drove us to do this. It was the maturation of the marketplace and the attitude toward using this technology. It's as simple as that."

Scott Denham, also from IBM's Deep Computing group was kind enough to allow us to film a short interview with him about their adoption of Fermi-based Tesla GPUs and the impact on HPC. Enjoy.

Folding@Home Releases Beta Client for NVIDIA GTX 400 GPUs

Posted: 25 May 2010 03:04 PM PDT

Folding@home is a distributed computing project run by Stanford University. By running software in the background, people around the globe can combine their computing power to help scientists understand how proteins fold. This is critical to understanding diseases such as Alzheimer's, ALS, Huntington's, Parkinson's disease and many cancers.

Since NVIDIA started working with the Stanford University Folding@home team, NVIDIA GPUs have grown to the point that they now contribute over 45% of the x86 TeraFLOPS while accounting for less than 4% of the active processors.

With the introduction of Fermi and the GeForce GTX 400 GPUs, we recognized we had the opportunity to raise the bar even higher, and began working closely with the Folding@home team to jointly craft an efficient client tuned to the Fermi architecture. Now that client is available in Beta, and it's the first Folding@home GPU client to achieve more than 1 microsecond per day performance. We look forward to continued positive collaboration with the Folding@home team, and know that with the help of the thousands of volunteers that contribute to the project, we're shedding light on important questions that will hopefully lead to advances in medicine and health for all of us.

For more information about the Folding@home project and to download the client, please visit:

No comments:

Post a Comment