By Topic

Power-performance optimization using fuzzy control of simultaneous supply voltage and body biasing scaling

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Pourshaghaghi, H.R. ; Electron. Syst. Group, Eindhoven Univ. of Technol., Eindhoven, Netherlands ; de Gyvez, J.P.

Adaptive voltage scaling (AVS) leads to considerable power consumption savings in processors when maximum performance is not necessary. Simultaneous use of body biasing techniques and AVS can be used to reduce power in high performance processors without performance penalty. We present a new strategy for employing simultaneous AVS and forward body biasing (FBB) in determining the optimal trade-off between supply voltage and body bias voltage such that power consumption at a particular performance is minimized. For this purpose, an adaptive fuzzy logic controller is designed to make decision for optimal pair of supply and body bias voltage without sacrificing circuit performance. We evaluate usefulness of the method by applying it on real-time monitoring of a processor's supply current when it executes an MPEG 2-decoding application. We achieved an average of 10.03% power reduction without performance penalty and 20.13% power saving at less than 5% performance penalty using proposed simultaneous AVS and FBB compare to fixed supply and body bias voltage.

Published in:

Electronics, Circuits, and Systems (ICECS), 2010 17th IEEE International Conference on

Date of Conference:

12-15 Dec. 2010