Q-Learning-Based Voltage-Swing Tuning and Compensation for 2.5-D Memory-Logic Integration

Dongjun Xu, Ningmei Yu, Hantao Huang, Sai Manoj Pudukotai Dinakarrao, Hao Yu

Abstract: In this paper, an efficient I/Q management with Q-learning-based transmitter swing adjustment and receiver compensation is developed for energy-efficient 2.5-D memory-logic integration. The proposed approach is able to achieve significant power reduction over other state-of-the-art methods.