Loading...

A Dynamic Slack Management Technique for Low Energy Consumption in Real-time Multi-core Embedded Systems

Fathi, Mohammad Hossein | 2014

632 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 46500 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Ejlali, Alireza
  7. Abstract:
  8. Due to the increasing development of digital systems based on limited energy sources (i.e. battery), energy efficiency has become one of the most important concerns in the design of these systems. The use of multi-core architecture is an effective solution for the problem of reducing energy consumption. Hence using it in digital systems has become more common. In addition, enabling methods for reducing energy consumption on processor, helps in making energy more efficient. DVFS and DPM are the two major methods used for reducing dynamic and static energy consumption of processors. The using of multi-core architecture due to the higher chip density, results the static and dynamic energy factors contribute almost equally in total processor energy consumption. Because of higher chip density, the result of using multi-core architecture is that the static and the dynamic energy factors contribute almost equally in total processor energy consumption. Hence there is a need to provide appropriate combination of the two methods DVFS and DPM. Since the Scheduling method used by system, effects on the opportunity of using energy reduction methods and the real-time nature of system provides timing constraints that must be considered in scheduling process, we need to develop a scheduling method that in addition to ensuring compliance with the time limits of the system, provides more opportunities for energy reduction. In this study, we introduced a method for managing energy consumption of the real-time multi-core processor that takes benefit from dynamic slack and provides an energy efficient combination of DVFS and DPM techniques. A new approach to use both DPM and DVFS techniques considering energy overhead is introduced. Also, a new task migration approach with less overhead is proposed to balance the processor task-load. We examined the performance of proposed techniques by simulation of the processor in MATLAB. The simulation results show that the proposed method outperform existing methods up to 12.7 percent
  9. Keywords:
  10. Embedded Real-Time System ; Dynamic Slack Time ; Dynamic Voltage Scaling ; Multicore Processors ; Energy Reduction ; Dynamic Energy Management ; Dynamic Voltage and Ferquency Scaling (DVFS)

 Digital Object List

 Bookmark

No TOC