ATI Stream Computing lets GPU do some of the CPU's tasks to boost performance

Posted on Friday, September 29 2006 @ 23:55 CEST by Thomas De Maesschalck
Today ATI announced that it is pioneering a new technology known as Stream Computing, that has the potential to dramatically impact almost every sector of the market. Along with leading companies and academic institutions worldwide, ATI is working to build a stream computing ecosystem, one that delivers the performance, applications, software and tools necessary to turn ATI's vision into reality.

Stream computing allows ATI graphics processors (GPUs) to work in concert with today's high-performance, low-latency computer processors (CPUs) to solve complex computational problems. Using stream computing, in simulations today processing of risk assessment models similar to those used by financial institutions' were completed 16 times faster than traditional methods, oil and gas companies are seeing seismic model processing increased by more than 20 times, and Stanford University is seeing disease research accelerated by as much as 40 times, giving them the ability to process three years worth of research data in just one month.

Stream computing makes use of ATI's sophisticated graphics processors (GPUs) that have until now, been used solely to calculate and render millions of pixels onto computer monitors, hundreds of times each second. Stream computing harnesses that tremendous processing power for a wide range of scientific, business and consumer computing applications, providing organizations the ability to process incredible amounts of information in significantly less time.

"ATI processors are some of the most technologically advanced computing architectures on the planet," said Dave Orton, president and CEO, ATI Technologies Inc. "They were designed with more than just graphics in mind, and today we're seeing the initial fruits of those labors with the introduction of our stream computing initiatives. Fortune 1000 companies, leading software developers, and academic institutions are demonstrating today that stream computing is they key to tremendous performance in a number of applications. Today's announcement is part of our vision of becoming a processing powerhouse in the months and years to come - we're beginning to build the stream computing platform today."

"Stream computing is a great representation of the vision of AMD's Torrenza platform strategy - bringing the unique capabilities of two heterogeneous processing solutions together to solve complex problem sets and change the game," said Marty Seyer, senior vice president, Commercial Segment, AMD. "Combining AMD64 with stream computing from ATI to address specific application workloads will open up new innovation possibilities in markets such as high-performance computing environments. Torrenza-based technologies have the potential to enable information to flow seamlessly between them in order to solve problems in the most cost-effective and timely manner. We see the potential over time for these two processing elements to become even more tightly coupled."

"The raw computational power of these DirectX-based processors is incredible and harnessing those capabilities for general purpose applications makes a lot of sense," said Dean Lester, general manager of the Graphics Platforms Unit, Microsoft Corp. "Stream computing has the potential to positively impact how organizations analyze data by improving the accuracy and efficiency with which critical business decisions are made, as well as enhancing the overall consumer experience by enabling compelling, high-fidelity environments to gamers today. Microsoft is working closely with ATI towards a future where all of our customers can experience the benefits that stream computing has to offer."

"The combined power of ATI processors and Havok FX enables physical realism only dreamed of by today's game designers," said Jeff Yates, vice president, product management, Havok. "Realistic physics is the future of videogames and together we're making it possible. Just as real-time lighting and shadows are standard in today's games, there will come a time when no game is without this level of immersive, true-to-life physics."

ATI's high-end processor today makes use of 48 compute cores that results in an order of magnitude processing speed-up. In certain applications, ATI processors perform up to 40 times faster than competing processors. The accelerated processing associated with stream computing has implications for a number of fields now and in the future, as the ecosystem around stream computing matures:

Scientific research - Today ATI's stream computing efforts are helping to save lives by driving life sciences to produce results faster in areas such as disease research, giving organizations the option to do more granular studies in the same amount of time as in the past. ATI announced today that Stanford University will make available a new distributed computing application that takes advantage of ATI processors for disease research. In the future, climate research may also benefit from stream computing as analysis of large data sets for storm and hurricane forecasting can be done faster or in more detail, potentially resulting in the issuing of warnings longer in advance of severe weather, and ultimately a better understanding of the world's climate.

Homeland security - Communications analysis and facial recognition can be drastically improved using stream computing, with implications for airport security, as well as photograph and video analysis.

Financial forecasting - Major institutions have been using server farms to do risk assessment using Monte Carlo simulations, and for derivatives pricing using models like Black-Scholes. Simulations conducted by PeakStream, Inc. using ATI hardware shows that stream computing can provide these companies with more detailed answers in significantly less time, letting them make the business decisions they need to faster, and giving them a leg up on their competition.

Oil and gas - Companies are using stream computing to analyze more data in shorter periods of time to more quickly and reliably discover where resources lie, speeding discoveries of crude oil deposits. ATI graphic processors in concert with PeakStream's software platform are allowing oil and gas companies to achieve significantly faster seismic data modeling.

Database searching - For search companies with incredibly large databases to organize and sort through, stream computing may offer a compelling business case providing increased processing power in less space.

Consumer applications - Software used by millions of people around the world, such as operating systems, office applications, and graphics applications, can benefit from stream computing. Any graphics-laden software that requires heavy processing can be accelerated.

Videogames - An area where ATI processors are already heavily used for graphics purposes, working with Havok, premier provider of software and services to interactive digital media creators, stream computing is resulting in life-like modeling of hair, cloth, smoke, liquid, and the physics behind them, giving gamers the most immersive experience possible.

Other areas that stream computing has the potential to impact in the future include enterprise software, product design and manufacturing, and digital media encoding among others.

With this new opportunity, ATI is also announcing a specific focus on enterprise stream computing in an effort to drive commercial adoption of stream computing with the help of its partners. For more information on ATI's stream computing initiatives, please see related company announcements made today on the topics of enterprise stream computing, and Stanford University's Folding@home program.

Loading Comments