Energy-Efficient Execution for Repetitive App Usages on big.LITTLE Architectures

Smartphones are now equipped with high-performance processors to meet the increasing complexity of apps. However, these processors drain the battery quickly, which has become a major concern for Smartphone users. The latest big.LITTLE multicore architecture provides new energy-saving facilities in addition to traditional DVFS technique. But this mechanism has not been well exploited by current Smartphones. In this paper, we propose a framework that records the performance demands for repetitive app usage scenarios, and adjusts the big.LITTLE processor to an energy-efficient configuration for subsequent executions of these scenarios. We implemented our framework on Android Smartphones, and the experiments achieve 30% energy saving on average without compromising user experience.