No abstract

Modern real-time systems are based on heterogeneous multicore platforms, which help them productively meet the applications' diverse and high computational requirements. Managing the energy and temperature of these computational platforms has become a topic of inconceivable enthusiasm for researchers and specialists over recent years. This paper presents a heuristic technique, named ETA-HP, for energy and temperature efficient scheduling of a set of real-time periodic tasks on a DVFS empowered heterogeneous multicore system. The proposed strategy operates in four stages, namely Deadline Partitioning, Task-to-Core Allocation, Temperature-Aware Scheduling, and Energy-Aware Scheduling. Our empirical analysis shows that with a variation in system workload from 50% to 100%, ETA-HP can schedule more tasks (2.52% on an average) compared to the stateof-the-art while achieving 7.29% average energy savings with 9.59 °C reduction in the average temperature of our considered heterogeneous chip-multiprocessor consisting 4 in-order and 4 out-of-order cores.

No abstract

No abstract