Streaming architectures and technology trends

ABSTRACT

Modern technology allows the designers of today's processors to incorporate enormous computation resources into their latest chips. The challenge for these architects is to translate the increase in capability to an increase in performance. The last decade of graphics processor development shows that GPU designers have succeeded spectacularly at this task. In this chapter, we analyze the technology and architectural trends that motivate the way GPUs are built today and what we might expect in the future.

REFERENCES

• 1: William J. Dally , John W. Poulton, Digital systems engineering, Cambridge University Press, New York, NY, 1998
• 2: ITRS. 2003. International Technology Roadmap for Semiconductors. http://public.itrs.net
• 3: Ujval J. Kapasi , Scott Rixner , William J. Dally , Brucek Khailany , Jung Ho Ahn , Peter Mattson , John D. Owens, Programmable Stream Processors, Computer, v.36 n.8, p.54-62, August 2003 [doi>10.1109/MC.2003.1220582]
• 4: Moore, Gordon. 1965. "Cramming More Components onto Integrated Circuits." Electronics 38(8). More information is available at http://www.intel.com/research/silicon/mooreslaw.htm
• 5: Owens, John D. 2002. "Computer Graphics on a Stream Architecture." Ph.D. Thesis, Stanford University, November 2002.
• 6: David A. Patterson, Latency lags bandwith, Communications of the ACM, v.47 n.10, p.71-75, October 2004 [doi>10.1145/1022594.1022596]