Power-efficient scheduling of parallel real-time tasks on performance asymmetric multicore processors

Abstract The use of computing devices has increased dramatically in recent time, which results in huge power consumption. This situation has made the power consumption a critical metric for evaluating the performance of a computing device. In this paper, we have addressed the real-time scheduling problem of parallel tasks on a performance asymmetric multicore processor with m cores with intent to reduce the power consumption. The proposed algorithm – parallel EDF – first divides the tasks into m segments and then executes these distributed tasks in earliest deadline first (EDF) fashion. Dynamic voltage and frequency scaling (DVFS) is also applied for power savings. We have evaluated the performance of the parallelEDF scheduling algorithm with Equally Fit (EF) algorithm on 70 nm based performance asymmetric multicore processor. The results reveal that up to 28% power can be saved at high system utilization level (about 80% system utilization). We have formally modeled the parallelEDF algorithm using high-level Petri nets (HLPN) while these models are also verified using the Satisfiability Modulo Theory (SMT), and Z3 Solver.