Empirical analysis of power management schemes for multi-core smartphones

  • Sangwook Kim
  • , Hwanju Kim
  • , Jongwon Kim
  • , Joonwon Lee
  • , Euiseong Seo

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

12 Scopus citations

Abstract

Dynamic power management schemes in mobile devices such as smartphones and tablet PCs enhance battery life at the cost of prolonged user-perceived response time while the response time is a crucial factor for user experience. This paper presents systematic analysis of existing power management schemes adopted in recent smartphones in terms of user-perceived response time and energy consumption. For this analysis, we developed a latency measurement benchmark tool to quantify responsiveness to user inputs and used it with an externally-connected power meter to concurrently measure energy consumption and response latency. The evaluation showed that some existing DVFS schemes can significantly harm the response time. More seriously, the analysis revealed that the processor hotplug technique for multi-core systems may reduce responsiveness even without any gain in energy savings.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013
DOIs
StatePublished - 2013
Event7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013 - Kota Kinabalu, Malaysia
Duration: 17 Jan 201319 Jan 2013

Publication series

NameProceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013

Conference

Conference7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013
Country/TerritoryMalaysia
CityKota Kinabalu
Period17/01/1319/01/13

Keywords

  • Benchmarks
  • DVFS
  • Measurement
  • Multi-core
  • Power management
  • Smartphones

Fingerprint

Dive into the research topics of 'Empirical analysis of power management schemes for multi-core smartphones'. Together they form a unique fingerprint.

Cite this