Loading...

On the scheduling of energy-aware fault-tolerant mixed-criticality multicore systems with service guarantee exploration

Safari, S ; Sharif University of Technology | 2019

499 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TPDS.2019.2907846
  3. Publisher: IEEE Computer Society , 2019
  4. Abstract:
  5. Advancement of Cyber-Physical Systems has attracted attention to Mixed-Criticality Systems (MCSs), both in research and in industrial designs. As multicore platforms are becoming the dominant trend in MCSs, joint energy and reliability management is a crucial issue. In addition, providing guaranteed service level for low-criticality tasks in critical mode is of great importance. To address these problems, we propose LETR-MC scheme that simultaneously supports certification, energy management, fault-tolerance, and guaranteed service level in mixed-criticality multicore systems. In this paper, we exploit task-replication to not only satisfy reliability requirements, but also to improve the QoS of low-criticality tasks in overrun situation. Our proposed LETR-MC scheme determines the number of replicas, and reduces the execution time overlap between the primary tasks and replicas. Moreover, instead of ignoring low-criticality tasks or selectively executing them without any guaranteed service level in overrun mode, it mathematically explores the minimum achievable service guarantee for each low-criticality task in different execution modes, i.e., normal, fault-occurrence, overrun and critical operation modes. We develop novel unified demand bound functions (DBF), along with a DVFS method based on the proposed DBF analysis. Our experimental results show that LETR-MC provides up to 59 percent (24 percent on average) energy saving, and significantly improves the service levels of low-criticality tasks compared to the state-of-the-art schemes. © 1990-2012 IEEE
  6. Keywords:
  7. DBF ; Guaranteed service level ; Mixed-criticality systems ; Multicores ; Task replication ; Criticality (nuclear fission) ; Embedded systems ; Energy conservation ; Energy management ; Fault tolerance ; Industrial research ; Power management ; Guaranteed service ; Multi-core platforms ; Multi-cores ; Reliability management ; Reliability requirements ; State-of-the-art scheme ; Task replications ; Energy management systems
  8. Source: IEEE Transactions on Parallel and Distributed Systems ; Volume 30, Issue 10 , 2019 , Pages 2338-2354 ; 10459219 (ISSN)
  9. URL: https://ieeexplore.ieee.org/abstract/document/8675526