Triple Speed: Energy-Aware Real-Time Task Synchronization in Homogeneous Multi-Core Systems

Abstract

Dynamic voltage scaling techniques are widely used in multicore embedded systems for energy conservation. The tasks of such systems are synchronized through the mutually exclusive access of shared resources, meaning that some tasks are blocked by other tasks. Thus, the problem of energy-aware real-time task synchronization in multicore systems is compounded by the trade-off between run-time blocking effects and energy minimization. This paper proposes a triple speed algorithm for enabling energy-awareness in existing multicore real-time synchronization protocols. Algorithms are presented to assign the required core frequencies to minimize energy consumption and meet timing constraints by evaluating schedulability tests in existing synchronization protocols extended using the proposed triple speed algorithm. Dynamic slack reclaiming is also discussed for superior run-time energy management. Finally, several extensive experiments and a real-life case study are reported for evaluating the proposed methodology. The results indicate that the triple speed algorithm registered $30$ percent savings in energy consumption compared with those of simple extensions of the existing synchronization protocols for single-core systems.