Nawaf Almoosa, William Song, Yorai Wardi, Sudhakar Yalamanchili,
A Power Capping Controller For Multicore Processors
This paper presents an online controller for tracking power-budgets in multicore processors using dynamic voltage-frequency scaling. The proposed control law comprises an integral controller whose gain is adjusted online based on the derivative of the power-frequency relationship. The control law is designed to achieve rapid settling time, and its tracking property is formally proven. Importantly, the controller design does not require off-line analysis of application workloads making it feasible for emerging heterogeneous and asymmetric multicore processors. Simulation results are presented for controlling power dissipation in multiple cores of an asymmetric multicore processor. Each core is i) equipped with the controller, ii) assigned a power budget, and iii) operates independently in tracking to its power budget. We use a cycle-level multi- core simulator driven by traces from SPEC2006 benchmarks demonstrating that the proposed algorithm achieves a faster settling time than
examples of a static setting of the controller gain.