AMD Introduces World's First Dedicated Enterprise Stream Processor.

New Stream Processor Delivers Enterprise-Class Computing Performance and Support, Available Now

TAMPA, Fla. -- At the Supercomputing 2006 show today, AMD (NYSE: AMD) introduced the worldeIUs first dedicated stream processor designed to meet the specific hardware demands of high-performance computing (HPC) applications. Engineered specifically for compute-only systems such as workstations and servers, the AMD Stream Processore makes use of AMDeIUs new thin hardware interface called CTMe to drive substantial performance gains in areas such as financial analysis, seismic migration analysis, and life sciences research, among others.

Stream computing leverages sophisticated massively parallel processors generally used to calculate and render millions of pixels onto computer monitors, hundreds of times each second for 3D graphics applications. 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.1 The AMD Stream Processor is the first hardware of its kind dedicated to addressing stream computing problems in the enterprise space.

Using professional-grade technology derived from AMDeIUs Graphics Product Group, the AMD Stream Processor is a PCI Express-based add-in board designed with higher memory densities than any consumer graphics card eI a full 1 GB of GDDR3 memory for stream computing applications. The processor also features HPC-optimized memory performance designed to best handle unique stream computing problem sets. The AMD Stream Processor also includes broad operating system support for server implementations; full-service, enterprise-class technical support; and a limited three-year warranty. The AMD Stream Processor is available now from distributors.

Leading hardware platform providers, including GraphStream Inc., PANTA Systems, and Rackable Systems, also introduced new stream servers to the market today. Stream servers make use of the new AMD Stream Processor to deliver enterprise-class performance for the HPC and enterprise markets in industry standard form factors.

"AMD stream computing represents a bold, new direction for high performance computing," said Tom Barton, CEO of Rackable Systems. "By leveraging the AMD Stream Processor, Rackable Systems will be able to deliver a new class of stream servers in familiar form factors that maximize performance and reduce costs. We are excited by the prospects of using stream computing to create application-specific platforms that offer improved price/performance."

"Stream computing is in line with our Torrenza initiative, delivering on AMDeIUs vision for co-processing and open innovation," said Marty Seyer, senior vice president, Computational Product Group, AMD. "AMD recognizes that HPC applications have specific hardware demands not met by standard, off-the-shelf graphics products. The AMD Stream Processor has been designed to address the HPC market with higher memory densities and HPC-optimized memory performance. The AMD Stream Processor embodies the perfect platform to run todayeIUs stream computing applications."

For more information about the AMD Stream Processor, visit http://ati.amd.com. For more information on AMDeIUs new thin hardware interface called CTM please see the relevant press release.

About AMD

Advanced Micro Devices (NYSE: AMD) is a leading global provider of innovative processing solutions in the computing, graphics and consumer electronics markets. AMD is dedicated to driving open innovation, choice and industry growth by delivering superior customer-centric solutions that empower consumers and businesses worldwide. For more information, visit www.amd.com.

Cautionary Statement

This press release contains forward-looking statements which are made pursuant to the safe harbor provisions of the U.S. Private Securities Litigation Reform Act of 1995. Forward-looking statements are generally preceded by words such as "plans," "expects," "believes," "anticipates" or "intends." In particular, statements in this press release including but not limited to the performance, capabilities, market potential, applications for stream computing and availability, including statements relating to accelerated processing and reduced processing times, exponential performance gains, enhanced problem-solving and ease of programming, may be considered "forward-looking." Such forward-looking statements are based on current expectations and assumptions and, accordingly, entail various risks and uncertainties. Assumptions applied in making, and potential risks that could cause actual results to differ materially from such forward looking statements include, among others, the ability to drive commercial adoption of enterprise stream computing and to build a stream computing ecosystem, software and/or hardware-related issues and conflicts, the development of new products or technologies, overall system performance and continued market demand for accelerated processing. We therefore cannot provide any assurance that such forward-looking statements will materialize. We assume no obligation to update or revise any forward-looking statement, whether as a result of new information, future events or any other reason. Additional information concerning risks and uncertainties affecting our business and other factors that could cause actual results to differ materially from any forward-looking statement is contained in our filings with Canadian and U.S. securities regulatory authorities.

AMD, the AMD Arrow logo, AMD Opteron and combinations thereof, are trademarks of Advanced Micro Devices, Inc. Other names are for informational purposes only and may be trademarks of their respective owners.

1. Based on simulations using traditional processing models vs. using AMD stream processors. Simulations show processing of Kirschoff Migration used for seismic modeling being completed as much as 20 times faster using AMD stream processors vs. processing done using CPUs.