The Community for Technology Leaders
Green Image
Issue No. 08 - August (2003 vol. 36)
ISSN: 0018-9162
pp: 54-62
Scott Rixner , Rice University
Peter Mattson , Reservoir Labs
William J. Dally , Stanford University
Ujval J. Kapasi , Stanford University
Jung Ho Ahn , Stanford University
John D. Owens , University of California, Davis
Brucek Khailany , Stanford University
<p>The demand for flexibility in media processing motivates the use of programmable processors. However, very large-scale integration constraints limit the performance of traditional programmable architectures. In modern VLSI technology, computation is relatively cheap?thousands of arithmetic logic units operating at multigigahertz rates can fit on a modestly sized 1 square centimeter die. Yet delivering instructions and data to those ALUs is prohibitively expensive.</p><p>The Imagine media processor validates the hypothesis that careful management of bandwidth and parallelism, from the programming language to the hardware, results in both high performance and high performance per unit of power.</p>
Scott Rixner, Peter Mattson, William J. Dally, Ujval J. Kapasi, Jung Ho Ahn, John D. Owens, Brucek Khailany, "Programmable Stream Processors", Computer, vol. 36, no. , pp. 54-62, August 2003, doi:10.1109/MC.2003.1220582
99 ms
(Ver 3.1 (10032016))