New [email protected] Client For ATI X1900 And X1950 Graphics Cards Due Monday Page: 1

ATI Logo Stanford Logo

In addition to news previously posted in our news section, Stanford University are on the lookout for faster ways and means of collecting quantitative data, in the search for curing illness that afflict mankind.

Currently computer simulation of folding processes consume huge amounts of processing power. "This scenario has become a 25-year nightmare," Associate Professor Vijay Pande said. Researchers are far away from being able to calculate folding processes in real time: In fact, 1 ns of folding currently takes about 1 day to calculate - or 1 second will take more than 2700 years on "one fast processor," he said.

Dual-core processors promised to bring another increase in horsepower, but Pande said that "twice" the performance doesn't cut it: "We need 30 or 40 times the speed to turn months into days," he said.

After an exhaustive search, including the $5000 Clearspeed accelerator card, it appears that Pande has found a solution - tapping into the floating point performance of a modern graphics card.

A new client released today supports ATI's X1900 and X1950 graphics cards, which can unleash about 375 GFlops, which is about 20 to 40 times more speed than what the project has seen so far. The group has also improved the software algorithm of [email protected], which he expects will bring another 10 - 15x improvement for a total maximum performance increase of about 500x - when ATI's graphics cards are used. However, Pande conceded that the graphics may only be able to deliver a sustained 100 GFlops of speed.

Currently only ATI X1900 or X1950 GPU's are supported, but owners of X1800's reportedly will be able to utilise their GPU in the future. Nvidia cards, as it stands are unsupported, but Nvidia is apparently willing to work with the Pande Group to rectify the problem.

According to the Stanford [email protected] Forum, the new ATI beta client is due out Monday

ATI had previously hinted on its GPU's capability for Stream Computing

Feel free to discuss this exciting news in our forum