Multi-Core Power Management through Deep Reinforcement Learning

Achieving high energy efficiency is a primary design objective for multi-core systems. Dynamic voltage and frequency scaling (DVFS) is one of the most widely-adopted low-power techniques. In this paper, we present a reinforcement learning-based DVFS control approach to reduce energy consumption under user-specified performance requirements. The learning agent periodically selects the voltage and frequency level for all cores based on observations of their computation intensiveness, memory behaviors as well as synchronization among cores. Experimental results on multiple real applications show that the proposed method can achieve significant energy reduction.