•  
  •  
 

Applied Mathematics & Information Sciences

Author Country (or Countries)

Taiwan

Abstract

The growing functionality of mobile devices explains increasing system performance requirements and the subsequent wide adoption of multicore processors. As mobile systems are battery powered, battery life largely limits these high performing multicore mobile devices. Developing an efficient power-aware processor manager for mobile multicore systems has received considerable attention. The conventional processor management system of embedded systems e.g., the Linux kernel scheduler incorporates an automatic scheme to control peripheral operations and processor frequency. However, this mechanism fails to consider user requirements, task loading, and operating status of processors in the multicore system to satisfy operating requirements. Therefore, this work presents a novel power-aware multicore processor manager, referred to herein as a comprehensive power-aware processor manager (CPPM), which integrates a system configuration selection algorithm (BPM-DFS), task re-scheduling mechanism (CTM), and precise system power estimation mechanism (PPM). The CPPM manager can dynamically set system configurations and rearrange executed tasks among multiple cores to comply with the limitation of power consumption that is assigned by the user. Moreover, the proposed CPPM is implemented on quad-core x86 Android system to compare with the capabilities of other scheduling mechanisms.

Suggested Reviewers

N/A

Download

Share

COinS