In sensory swarms, minimizing energy consumption under performance constraint\nis one of the key objectives. One possible approach to this problem is to monitor application\nworkload that is subject to change at runtime, and to adjust system configuration adaptively to\nsatisfy the performance goal. As today�s sensory swarms are usually implemented using multi-core\nprocessors with adjustable clock frequency, we propose to monitor the CPU workload periodically\nand adjust the task-to-core allocation or clock frequency in an energy-efficient way in response\nto the workload variations. In doing so, we present an online heuristic that determines the most\nenergy-efficient adjustment that satisfies the performance requirement. The proposed method is\nbased on a simple yet effective energy model that is built upon performance prediction using IPC\n(instructions per cycle) measured online and power equation derived empirically. The use of IPC\naccounts for memory intensities of a given workload, enabling the accurate prediction of execution\ntime. Hence, the model allows us to rapidly and accurately estimate the effect of the two control\nknobs, clock frequency adjustment and core allocation. The experiments show that the proposed\ntechnique delivers considerable energy saving of up to 45%compared to the state-of-the-art multi-core\nenergy management technique.
Loading....