Q-learning based dynamic voltage scaling for designs with graceful degradation

Yu Guang Chen, Wan Yu Wen, Tao Wang, Yiyu Shi, Shih Chieh Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Dynamic voltage scaling (DVS) has been widely used to suppress power consumption in modern designs. The decision of optimal operating voltage at runtime should consider the variations in workload, process as well as environment. As these variations are hard to predict accurately at design time, various reinforcement learning based DVS schemes have been proposed in the literature. However, none of them can be readily applied to designs with graceful degradation, where timing errors are allowed with bounded probability to trade for further power reduction. In this paper, we propose a Q-learning based DVS scheme dedicated to the designs with graceful degradation. We compare it with two deterministic DVS schemes, i.e., a stepping based scheme and a statistical modeling based scheme. Experimental results on three 45nm industrial designs show that the proposed Q-learning based scheme can achieve up to 83.9% and 29.1% power reduction respectively with 0.01 timing error probability bound. To the best of the authors' knowledge, this is the first in-depth work to explore reinforcement learning based DVS schemes for designs with graceful degradation.

Original languageEnglish
Title of host publicationISPD 2015 - Proceedings of the ACM International Symposium on Physical Design 2015
PublisherAssociation for Computing Machinery
Pages41-48
Number of pages8
ISBN (Electronic)9781450333993
DOIs
StatePublished - 29 Mar 2015
Event18th ACM International Symposium on Physical Design, ISPD 2015 - Monterey, United States
Duration: 29 Mar 20151 Apr 2015

Publication series

NameProceedings of the International Symposium on Physical Design
Volume29-March-2015

Conference

Conference18th ACM International Symposium on Physical Design, ISPD 2015
Country/TerritoryUnited States
CityMonterey
Period29/03/151/04/15

Keywords

  • Dynamic voltage scaling
  • Graceful degradation
  • Q-learning

Fingerprint

Dive into the research topics of 'Q-learning based dynamic voltage scaling for designs with graceful degradation'. Together they form a unique fingerprint.

Cite this