A Middleware for Power Management in Multicore Smartphones

Abstract

Increased power consumption is a critical concern for smartphone users. While multi-core processors in smartphones have already emerged in market, current applications are yet to take full advantage of this new architecture, particularly in the area of managing power consumption. This paper addresses the issue of managing power consumption in multicore smartphones via a middleware layer that schedules optimal number of cores for currently running applications taking into account the tradeoff between power consumption, performance and user experience. The paper first describes a simple and accurate method to measure the overall power consumption and then studies the impact of scheduling seven different popular applications over one to four cores on the overall power consumption. Based on this study, the paper proposes three new power-aware scheduling algorithms that dynamically schedule optimal number of cores as well as dynamically adjust the voltage frequency of each online core to achieve the best tradeoff between power consumption, application performance and user experience under the current context. Evaluation from a prototype implementation of the middleware on a quad-core HTC One shows that these algorithms result in significant reduction in power consumption while ensuring good performance and user experience.