Press release
GPU Computing Delivers Over a Petaflop to put NVIDIA in Top Spot in Distributed Computing Application
SANTA CLARA, Calif., Aug. 26 /PRNewswire-FirstCall/ -- NVIDIA GPUs are contributing over 1 petaflop[1] of processing power to Stanford University's Folding@home distributed computing application as of last week, according to the statistics published by Stanford. Active NVIDIA(R) GPUs deliver over 1.25 petaflops, or 42% of the total processing power of the application which seeks to understand how proteins affect the human body.
NVIDIA's petaflop contribution, nearly half of the processing power on Folding@home, is delivered by just 11,370 of the total active processors used in the project. In comparison, 208,268 CPUs running Windows were active, contributing just 198 teraflops -- just 6% of the total processing power in the project.
Stanford University released a Folding@home client specifically for NVIDIA GPUs in June, so this staggering advance has been achieved in only a few months. Developed using NVIDIA CUDA(TM), a C language programming environment for many-core parallel architectures, the CUDA port of the Folding@home client has delivered more processing power than any other architecture in the history of the project.
"As these statistics show, the impact of NVIDIA GPUs on protein folding simulations has been extraordinary," said Vijay Pande, associate professor of chemistry, Stanford University and director of the Folding@home project. "Teams that are folding with NVIDIA GPUs are seeing huge boosts to their production and this is helping to accelerate the project significantly."
"Applications like Folding@home are just the beginning, every day we are seeing more and more examples of computing problems that are benefitting from CUDA and our GPU technologies," said Michael Steele, general manager of visual consumer solutions at NVIDIA. "I know everyone at NVIDIA has been closely tracking the progress of the Folding@home project since the release of the CUDA port for our GPUs and we are delighted to see them making such a significant and meaningful contribution to what is extremely valuable work."
Stanford University's distributed computing program Folding@home has become a major force in researching cures to life-threatening diseases such as cancer, cystic fibrosis, and Parkinson's disease by combining the computing horsepower of millions of processors to simulate protein folding. The Folding@home project is the latest example in the expanding list of non-gaming applications for graphics processing units (GPU). By running the Folding@home client on an NVIDIA GPUs, protein-folding simulations can be done 140 times faster than on some of today's traditional CPUs.
Full table of statistics below:
OS Type Current Active Total
TFLOPS Processors Processors
Windows 198 208,268 2,134,966
Mac OS X / Power PC 7 8,226 118,817
Mac OS X / Intel 19 6,264 58,856
Linux 61 35,903 325,643
ATI GPU 334 3,032 6,148
NVIDIA GPU 1,251 11,370 17,152
PlayStation 3 1,080 38,286 582,800
Total 2,950 311,349 3,244,382
Source: http://fah-web.stanford.edu/cgi-bin/main.py?qtype=osstats, as of August 19, 2008.
[1] A flops is a floating point operation per second, a standard measure of processing power. A teraflop is 1,000 billion flops and a petaflop is 1,000 trillion flops.
