C28. Energy-efficient task assignment on asymmetric multiprocessor platforms

Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.