Dynamic Partitioned Scheduling of Real-Time DAG Tasks on ARM big.LITTLE Architectures*
Agostino Mascitti, Tommaso Cucinotta · 2021
This paper evaluates the combination of a Directed Acyclic Graph (DAG) task splitting technique already proposed in the literature and the state-of-the-art, energy-aware version of the well-known CBS server (BL-CBS), which dynamically partitions and schedules real-time task sets in an energy-efficient way on multi-core platforms based on the ARM big.LITTLE architecture. The approach is designed to be used with any DAG in a transparent way as an on-line and adaptive scheduler supporting “open” systems. The approach is validated and evaluated through the open-source RTSim simulator, which has been extended integrating an energy model of the ODROID-XU3 board and the code-base needed to perform the DAG task decomposition and scheduling. Simulations on randomly generated DAGs show that the approach leads to promising results.