GIT-CERCS-10-02
Hrishikesh Amur, Karsten Schwan, Milos Prvulovic,
Towards Optimal Power Management: Estimation of Performance Degradation due to DVFS on Modern Processors
The alarming growth of the power consumption of data centers coupled with low average utilization of servers suggests the use of power management strategies. Such actions, however, require the understanding of the effects of the power
management actions on the performance of data-center applications running on managed platforms. The goal of our research is to accurately estimate power savings and consequent performance degradation from voltage and frequency scaling (DVFS) and thereby better guide the optimization of a performance/power metric of a platform. Towards that end, this paper presents precise performance and power models for DVFS strategies. Precise models are attained by better modeling the performance behaviour of modern out-of-order processors, by
taking into account, for instance, the effects of cache miss overlapping. Models are validated using benchmarks from the SPEC CPU2006 suite, which show that the observed degradation always falls within the predicted bounds. Also,
the upper bound degradation estimates were up to 43% less than those due to a linear degradation model which allows for the aggressive use of DVFS.