High-Reliability and Energy-Saving DAG Scheduling in Heterogeneous Multi-Core Systems Based on Task Replication
Han Yu, Jing Liu, Wei Hu, Yu Gan · 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC) · 2021
With the gradual complexity and high parallelization of computing tasks, people have higher and higher requirements for the reliability and energy-saving performance of embedded systems. In this paper, we focus on the scheduling of parallel application in heterogeneous systems. Based on task replication and DVFS techniques, we propose two algorithms ERO and ORO that could reduce energy consumption while meeting the task reliability requirements. Comparative experiments with EFSRG and HRRM shown that ERO and ORO algorithms provide more energy savings and lower schedule lengths for the given reliability requirement.