Affiliation:
1. Indian Institute of Information Technology, Guwahati, India
Abstract
Most battery-powered real-time systems today rely on a combination of specialised multicore to satisfy the needs of modern programs, which has changed the design of processing platforms dramatically in recent years. For such platforms, developing energy and thermally aware schedulers has become a top priority. As a consequence, this study presents HEAT, energy and thermal aware heuristic scheme for scheduling a group of periodic tasks on a DVFS enabled heterogeneous platform. Deadline Partitioning, Core Clustering, Temperature-Aware Scheduling, and Energy-Aware Scheduling are the four steps of the proposed scheme. In comparison to state-of-the-art, our experimental review reveals that HEAT not only enhances task set acceptance rate (as high as 3.44%) but also boosts energy savings (as high as 10.71%) and decreases temperature (as high as 7.14%) in the system.
Publisher
Association for Computing Machinery (ACM)
Subject
Industrial and Manufacturing Engineering
Reference29 articles.
1. Necessary and Sufficient Conditions for Thermal Schedulability of Periodic Real-Time Tasks Under Fluid Scheduling Model
2. TaSaT
3. A. Bastoni , B. B. Brandenburg , and J. H. Anderson . Cache-related preemption and migration delays: Empirical approximation and impact on schedulability . In OSPERT , 2010 . A. Bastoni, B. B. Brandenburg, and J. H. Anderson. Cache-related preemption and migration delays: Empirical approximation and impact on schedulability. In OSPERT, 2010.
4. The PARSEC benchmark suite
5. The gem5 simulator
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献