Hatefi, P.; Salehi, M. PFA-TP3M: Permanent Fault Aware Two-Phase Peak-Power Management in Fault-Tolerant Multi-Core Systems. Preprints2024, 2024010103. https://doi.org/10.20944/preprints202401.0103.v1
APA Style
Hatefi, P., & Salehi, M. (2024). PFA-TP3M: Permanent Fault Aware Two-Phase Peak-Power Management in Fault-Tolerant Multi-Core Systems. Preprints. https://doi.org/10.20944/preprints202401.0103.v1
Chicago/Turabian Style
Hatefi, P. and Mohammad Salehi. 2024 "PFA-TP3M: Permanent Fault Aware Two-Phase Peak-Power Management in Fault-Tolerant Multi-Core Systems" Preprints. https://doi.org/10.20944/preprints202401.0103.v1
Abstract
It is necessary to manage the power consumption and use fault-tolerance techniques to meet high reliability in Real-Time Embedded Systems, . Hence, in recent years, this is the main reason for providing an ideal approach to decrease power consumption through the worst-case behavior of instantaneous power management (peak-power management), while observing the Thermal Design Power (TDP). Although the multi-core chips in real-time embedded systems provide great opportunity for implementation of Two-phase Triple modular redundancy to meet high reliability, the energy overhead management of concurrently executing tasks is one of the challenges facing designers. In this article, we propose a scheme named Permanent Fault Aware, Two-Phase Peak-Power Management (PFA-TP3M), for scheduling real-time tasks in multi-core systems to eliminate peak power overlap from concurrent running tasks to maintain peak power consumption at the chip TDP. and through mapping different parts of each task on separate cores, prevents consecutive conflicts on cores, which have faced permanent faults to design the fault-tolerant system. Our simulation results show that our proposed scheme provides up to 700x fault tolerance increase (630x on average) compared to the state-of-the-art power management algorithm, an achievement costs up to 14%. (average 11%) increase the length of the task graph compared to it.
Keywords
Peak-Power; Replication; Fault-Tolerance; Multi-Core Systems
Subject
Computer Science and Mathematics, Hardware and Architecture
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
