Abstract On-line energy-efficient real-time task scheduling for a heterogeneous dual-core system-on-a-chip is a challenging problem due to precedence constraints and the varied properties of the general-purpose processor core and the synergistic processor core. This study proposes an on-line heterogeneous dual-core energy-efficient scheduling framework for dynamic workloads with real-time constraints. The energy efficiency ratio is presented to manage energy consumption while considering of the varied properties of the cores, while precedence constraints among the tasks are dealt with through interaction between bandwidth servers. This framework is configurable for low energy consumption and high system utilization. The capability of the proposed methodology is evaluated by a series of experiments and the results obtained are encouraging.
Read full abstract