Demo abstract: Power aware core scheduling in multicore smartphones

Abstract

Modern smartphones are increasingly equipped with mul-ticore processors. However, current applications are yet to take full advantage of this new architecture, particularly in the area of managing power consumption. This demo demonstrates three new scheduling algorithms that dynamically schedule an optimal number of cores with each core running at an optimal frequency. A unique feature of these scheduling algorithms is that they take into account the tradeoff between power consumption, performance and user experience. They achieve the best tradeoff under the current context. A prototype implementation on a quad-core HTC One smartohone shows that these algorithms result in significant reduction in power consumption while ensuring good performance and user experience. The demo includes several different popular smartphone applications such as video streaming using YouTube, Candy Crush game, audio streaming using Pandora, navigation using Google Maps, and converting video from .avi to .mp4 format. Users can run these applications using one of the three new scheduling algorithms under different tradeoff scenarios and observe the amount of power savings achieved by the new algorithms.