NVIDIA To Adopt AMD HyperTransport Technology; Industry Leaders Collaborate To Accelerate Internal Communications Across Computer and Network Applications.

Business Editors/High-Tech Writers

TAIPEI, Taiwan--(BUSINESS WIRE)--June 4, 2001

NVIDIA(R) Corporation (Nasdaq:NVDA) and AMD (Nasdaq:AMD) today announced that NVIDIA will be among the first adopters of AMD's new HyperTransport(TM) technology. This technology will increase the performance of the new NVIDIA nForce(TM) Platform Processing Architecture, a revolutionary new system architecture integrating the nForce Integrated Graphics Processor (IGP) and the nForce Media and Communications Processor (MCP) for the fastest, most robust, and feature-rich PC platform available.

NVIDIA's nForce architecture utilizes AMD's HyperTransport I/O bus interface, to deliver the highest continuous throughput -- up to 800 MB/sec. -- between NVIDIA's platform processors. Using this state-of-the-art I/O bus as the main conduit between the IGP and MCP ensures data and information is relayed through the system as quickly as possible.

"The combination of NVIDIA and AMD breakthrough technologies like HyperTransport and DDR is expected to result in a significant impact on system performance for both AMD Athlon(TM) and AMD Duron(TM) processor-based systems," said Richard Heye, Vice President, Platform Engineering & Infrastructure of AMD's Computation Products Group. "Today's announcement again reinforces our commitment to help drive state-of-the-art technology into the market."

HyperTransport technology, formerly code-named Lightning Data Transport (LDT), is an innovative new technology that moves information faster. With a peak data transfer rate of up to 12.8GB per second possible, HyperTransport technology is designed to enable the chips inside of PCs, networking and communications devices to communicate with each other up to 48 times faster than with existing bus technologies.

"NVIDIA's incorporation of AMD's HyperTransport technology is critical in our quest to deliver unmatched system performance," said Dan Vivoli, vice president of marketing at NVIDIA. "Today's PC applications are increasingly complex with advanced 3D graphics, high speed networking, streaming video, and cinematic 3D audio. The nForce architecture was designed specifically to bridge the gap between user expectations and the limitations of current and future technologies."

About HyperTransport Technology

HyperTransport is a new high-speed, high-performance, point-to-point link for integrated circuits. It was developed to enable the chips inside of PCs, networking and communications devices to communicate with each other up to 48 times faster than with existing technologies. Compared with existing system interconnects that provide bandwidth up to 266MB/sec., HyperTransport technology's bandwidth of 12.8GB/sec. represents up to a 48-fold increase in data throughput. HyperTransport technology provides an extremely fast connection that complements externally visible bus standards like the Peripheral Component Interconnect (PCI), as well as emerging technologies like InfiniBand. The HyperTransport connection is designed to provide the bandwidth that the new InfiniBand standard requires to communicate with memory and system components inside of next-generation servers and computing devices that may power the backbone infrastructure of the telecom industry.

About NVIDIA

The computing industry recognizes NVIDIA as the global leader in advanced graphics processing technology for mainstream platforms, honoring the company with the most graphics awards in the history of the PC industry. The unmatched breadth of the NVIDIA product family enables gripping multimedia experiences for the entire desktop computer market from workstations to internet-enabled appliances. PC OEMs, add-in card manufacturers, system builders, and consumer electronics companies worldwide choose NVIDIA GPUs as the core component of their graphics processing solutions. NVIDIA GPUs are used by large corporations, small- to medium-sized businesses, and home-based consumers. NVIDIA graphics processors deliver superior performance and crisp visual quality for PC-based applications such as manufacturing, science, e-business, entertainment and education. For more information, please visit the Company's web site at http://www.nvidia.com.

Certain statements in this press release, including the statements relating to the Company's performance expectations for NVIDIA's family of products and expectations of continued revenue growth, are forward-looking statements that are subject to risks and uncertainties that could cause results to be materially different than expectations. Such risks and uncertainties include, but are not limited to, manufacturing and other delays relating to new products, difficulties in the fabrication process and dependence of the Company on third-party manufacturers, general industry trends including cyclical trends in the PC and semiconductor industries, the impact of competitive products and pricing alternatives, market acceptance of the Company's new products, and the Company's dependence on third-party developers and publishers. Investors are advised to read the Company's Annual Report on Form 10-K and quarterly reports on Form 10-Q filed with the Securities and Exchange Commission, particularly those sections entitled "Factors Affecting Operating Results," for a fuller discussion of these and other risks and uncertainties.

Registered trademark NVIDIA(R) Corporation, 2001. AMD, the AMD logo, and combinations thereof, and HyperTransport are trademarks of Advanced Micro Devices, Inc. All company and/or product names are trademarks and/or registered trademarks of their respective manufacturers. Features, pricing, availability, and specifications are subject to change without notice.