This paper presents heuristics to optimize the energy consumption of multicore systems with wake-up overhead. A multicore system can optimize its energy consumption by strategically (de)activating itself. Given the task information of the system, OSPA...
This paper presents heuristics to optimize the energy consumption of multicore systems with wake-up overhead. A multicore system can optimize its energy consumption by strategically (de)activating itself. Given the task information of the system, OSPAL algorithm was previously known to find a schedule that maximizes the common idle time. However, this schedule does not necessarily minimize energy consumption because of the wake-up overhead associated with the storage of memory footprint to non-volatile memory. Previous research proposed to address this issue by modifying their algorithm so that it does not keep common idle times shorter than a threshold. We observe that their choice of threshold is not optimal and propose a randomized heuristic to improve the energy consumption. We also present a dynamic-programming-based postprocessing heuristic to adjust common idle times. We conducted computational experiments to measure the performance of the proposed heuristics, which indicated an average improvement of 37.69% in energy consumption compared to the previous algorithm.