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

被引：4

作者：

Xu, Dongjun ^{[1
]}

Yu, Ningmei ^{[2
]}

Huang, Hantao ^{[3
]}

Manoj, Sai P. D. ^{[4
]}

Yu, Hao ^{[5
]}

机构：

[1] Xian Univ Technol, Xian 710048, Shaanxi, Peoples R China

[2] Xian Univ Technol, Dept Elect Engn, Xian, Shaanxi, Peoples R China

[3] Nanyang Technol Univ, Singapore, Singapore

[4] Tech Univ Wien, Inst Comp Tech, Vienna, Austria

[5] Southern Univ Sci & Technol, Shenzhen, Peoples R China

来源：

IEEE DESIGN & TEST | 2018年 / 35卷 / 02期

基金：

中国国家自然科学基金;

关键词：

low power I/O; memory-logic integration; Q-learning; receiver compensation; Through-silicon interposer (TSI); voltage-swing tuning;

D O I：

10.1109/MDAT.2017.2764075

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

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. © 2013 IEEE.

引用

页码：91 / 99

页数：9

共 3 条

[1] A 2.5-D Memory-Logic Integration With Data-Pattern-Aware Memory Controller
Xu, Dongjun
Manoj, Sai P. D.
Wang, Kanwen
Yu, Hao
Yu, Ningmei
Yu, Mingbin
IEEE DESIGN & TEST, 2015, 32 (04) : 49 - 58
[2] Reinforcement Learning based Self-adaptive Voltage-swing Adjustment of 2.5D I/Os for Many-core Microprocessor and Memory Communication
Huang Hantao
Manoj, Sai P. D.
Xu, Dongjun
Yu, Hao
Hao, Zhigang
2014 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD), 2014, : 224 - 229
[3] A Q-Learning Based Self-Adaptive I/O Communication for 2.5D Integrated Many-Core Microprocessor and Memory
Manoj, Sai
Yu, Hao
Huang, Hantao
Xu, Dongjun
IEEE TRANSACTIONS ON COMPUTERS, 2016, 65 (04) : 1185 - 1196

← 1 →