By Mark Papermaster CTO for AMD
- AMD will receive more than $32 million to fund exascale research;
- The research will focus on Heterogeneous Systems Architecture (HSA)-based Accelerated Processing Units (APUs), and a new generation of memory interfaces;
- The goal of the research is eventual commercial applications, so the IP created as part of this research will make its way into various future AMD products.
This is part of the DOE FastForward 2 program, which seeks to fund innovative new and/or accelerated R&D for technologies targeted for commercial use in in the 2020-2023 timeframe. AMD’s FastForward 2 research will focus on node architecture based on our HSA-based APUs, and for a new generation of memory interfaces.
This is a big deal for the industry. Exascale supercomputers will be capable of performing more than one quintillion (or a billion billion) calculations per second, roughly 30-60 times faster than today’s fastest available supercomputers. This research aims to deliver those huge increases in performance – without significant increases in energy consumption – to enable advances in diverse fields ranging from medical science to astrophysics and climate modeling. These could arrive as prototypes over the next several years, with full production units early in the next decade.
This is a big achievement for AMD, and marks the third consecutive year we’ve received these awards – a claim only two other companies can make. Our previous research for this initiative includes processor and memory-related investigations, including interconnect architectures and associated execution models that tie together thousands of processing nodes while optimizing for performance and energy efficiency. The DOE clearly values AMD intellectual property and research contributions.
We’ve a number of industry firsts and engineering breakthroughs in our history. So it’s no surprise that AMD is a key partner for the DOE in developing the next generation of high-performance computing. Even better, the DOE fully expects the research from FastForward 2 to finds its way into commercial products. This means the research we perform can directly influence our product strategy and development, and then customer solutions. So it’s a win-win, for FastForward 2 and exascale computing, the industry and AMD.
The research to create exascale supercomputers will undoubtedly lead to breakthroughs that will permeate all levels of computing. Certainly, this will aid any form of high-performance computing, including managing vast quantities of information for Big Data analytics and for rapidly processing the massive wave of anticipated Web requests. Ultimately, that improvement will be felt by users of personal devices who could receive nearly instant responses from a Cloud-based server.
Congratulations to Alan Lee, Mike Schulte, Mike Ignatowski and everyone else on the AMD Research and Exascale teams who led this important work.
Mark Papermaster is the CTO for AMD. His postings are his own opinions and may not represent AMD’s positions, strategies, or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only. Unless explicitly state, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.
*Originally Posted by Guest Blogger in AMD on Nov 14, 2014 10:42:24 AM