A Q-Learning Based Self-Adaptive I/O Communication for 2.5D Integrated Many-Core Microprocessor and Memory

Abstract

A self-adaptive output-voltage swing adjustment is introduced in the design of energy-efficient I/O communication for 2.5D integrated many-core microprocessor and memory. Instead of transmitting signal with large voltage swing, a Q-learning based I/O management is deployed to adaptively adjust the I/O output-voltage swing under constraints of both communication power and bit error rate (BER). Simulation results show that the proposed adaptive 2.5D I/Os (in 65nm CMOS) can achieve an average of 12.5mW I/O power, 4GHz bandwidth and 3.125pJ/bit energy efficiency for one channel under 10 −6 BER. With the use of conventional Q-learning and further accelerated Q-learning, we can achieve 12.95% and 18.89% power reduction and 14% and 15.11% energy efficiency improvement when compared to the use of uniform output-voltage swing based I/O communication.

Recent Trends in Artificial Intelligence-inspired Electronic Thermal Management

“…In contrast, machine learning-based techniques can observe, learn, and adapt to different working environments, making them a potential choice to be employed in varying conditions and workloads. Machine learning (ML) based predictors such as neural networks (Rong Ye and Qiang Xu, 2012), Bayesian learning (Jung and Pedram, 2010;Yanzhi Wang et al, 2013), reinforcement learning (Hantao et al, 2014;Xu et al, 2014Xu et al, , 2018Lu, Tessier and Burleson, 2015;D. et al, 2016), and regression analysis (Manoj P. D., Yu, and Wang, 2015;Sheng Yang et al, 2015;Sayadi et al, 2017) are also widely utilized for prediction and to perform Dynamic voltage and frequency scaling (DVFS).…”