Stateful Logic Operation of Gated Silicon Diodes for In‐Memory Computing

Author:

Son Jaemin1,Jeon Juhee1,Cho Kyoungah1,Kim Sangsig1

Affiliation:

1. Department of Electrical Engineering Korea University 145 Anam‐ro, Seongbuk‐gu Seoul 02841 Republic of Korea

Abstract

AbstractIn‐memory computing significantly reduces workload and energy cost of data access in the traditional von Neumann computing architecture. Using various memristors, stateful logic is developed to realize in‐memory computing. However, memristors have encountered critical issues in terms of device variation and reliability, and therefore, fundamental device solutions are required to realize practical stateful logic. In this study, NAND, NOR, and half‐adder stateful logic operations of gated silicon diodes with a p+npn+ structure are demonstrated to achieve in‐memory computing. Gated diodes have bistable, steep switching, and quasi‐nonvolatile memory characteristics, enabling reliable stateful logic operation. The uniformity of their device characteristics overcomes the inherent stochastic characteristics of memristors that are widely researched for stateful logic. The sequential multiread logic operation simplifies the complex state logic scheme. In particular, a nondestructive half‐adder operation can be executed in five sequential steps using six parallel diodes. Thus, the stateful logic of gated diodes can be a potential building block for in‐memory computing.

Funder

Ministry of Science and ICT, South Korea

Korea University

Publisher

Wiley

Reference36 articles.

1. In-memory computing with resistive switching devices

2. Logic-in-memory based on an atomically thin semiconductor

3. In-memory computing with ferroelectrics

4. 90% yield production of polymer nano-memristor for in-memory computing

5. M.Horowitz presented at 2014 IEEE International Solid‐State Circuits Conference Digest of Technical Papers (ISSCC) San Francisco CA USA February 2014.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3