The Community for Technology Leaders
Green Image
Issue No. 12 - December (2003 vol. 36)
ISSN: 0018-9162
pp: 49-58
Michael C. Huang , University of Rochester
Greg Semeraro , University of Rochester
Grigorios Magklis , University of Rochester
Peter W. Cook , IBM T.J. Watson Research Center
David H. Albonesi , University of Rochester
Stanley E. Schuster , IBM T.J. Watson Research Center
Sandhya Dwarkadas , University of Rochester
Rajeev Balasubramonian , University of Rochester
Volkan Kursun , University of Rochester
Alper Buyuktosunoglu , IBM T.J. Watson Research Center
Pradip Bose , IBM T.J. Watson Research Center
Michael L. Scott , University of Rochester
Steven G. Dropsho , University of Rochester
Eby G. Friedman , University of Rochester
<p>The <em>adaptive processing approach</em> improves microprocessor energy efficiency by dynamically tuning major resources during execution to better match varying application needs. This tuning usually involves reducing a resource's size when its full capabilities are not needed, then restoring the disabled portions when they are needed again.</p><p>Adaptive processors require few additional transistors. Further, because adaptation occurs only in response to infrequent trigger events, the decision logic can be placed into a low-leakage state until such events occur.</p>
Michael C. Huang, Greg Semeraro, Grigorios Magklis, Peter W. Cook, David H. Albonesi, Stanley E. Schuster, Sandhya Dwarkadas, Rajeev Balasubramonian, Volkan Kursun, Alper Buyuktosunoglu, Pradip Bose, Michael L. Scott, Steven G. Dropsho, Eby G. Friedman, "Dynamically Tuning Processor Resources with Adaptive Processing", Computer, vol. 36, no. , pp. 49-58, December 2003, doi:10.1109/MC.2003.1250883
78 ms
(Ver 3.3 (11022016))