Article
Engineering, Electrical & Electronic
Cesar de S. Dias, Felipe S. Marranghello, Raphael Martins Brum, Paulo F. Butzen
Summary: This paper proposes a new method to reduce the length of material implication sequences in memristive devices for stateful logic circuits. By using an auxiliary circuit to predict and execute each material implication based on its necessity, the computing time can be significantly reduced.
IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS
(2022)
Review
Automation & Control Systems
Young Seok Kim, Myeong Won Son, Kyung Min Kim
Summary: Memristive stateful logic enables complete in-memory computing for low-power and low-cost Boolean computing, meeting the requirements of edge computing devices in the upcoming IoT era. Recent developments in stateful logic technology, including evolution of logic gates, cascading strategies, array-level data manipulation, and solutions for logic operation error issues, are intensively explored in this review.
ADVANCED INTELLIGENT SYSTEMS
(2021)
Article
Physics, Multidisciplinary
Xi Zhu, Hui Xu, Weiping Yang, Zhiwei Li, Haijun Liu, Sen Liu, Yinan Wang, Hongchang Long
Summary: This paper presents the theory of Memristive stateful logic and proposes a high-throughput logic error correction scheme to improve the reliability of the logic.
Article
Automation & Control Systems
Zhiwei Li, Hongchang Long, Xi Zhu, Yinan Wang, Haijun Liu, Qingjiang Li, Nuo Xu, Hui Xu
Summary: This paper proposes a method of error detection and correction (EDC) based on memristor-based stateful logic operation, which improves accuracy by leveraging the concept of redundancy, and demonstrates the feasibility of the proposed method in practical devices.
ADVANCED INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Information Systems
Wenlong Cai, Mengxing Wang, Kaihua Cao, Huaiwen Yang, Shouzhong Peng, Huisong Li, Weisheng Zhao
Summary: This paper proposes and experimentally demonstrates a new spintronic implication logic gate. The gate consists of two perpendicular magnetic anisotropy magnetic tunnel junctions with different diameters, and material implication and NAND logic functions are achieved through electrically-controlled operations. The reliability of this structure is verified, particularly in sub-20 nm node, indicating its great potential for large-density processing-in-memory applications.
SCIENCE CHINA-INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Chunyang Liu, Pengpeng Ren, Bo Zhou, Jianfu Zhang, Hui Fang, Zhigang Ji
Summary: In-memory computing based on memristors is a promising approach to address the delay and power consumption issues of traditional computing structures in the Internet of Things and big data era. However, it presents challenges in terms of device electrical characteristics.
Article
Engineering, Electrical & Electronic
Francesco Maria Puglisi, Tommaso Zanotti, Paolo Pavan
Summary: This paper proposes a new synthesis method for implication logic circuits based on memristors by revisiting Boole's expansion theorem. The method optimizes the operation sequence and reduces the number of memristors, while leveraging well-established logic circuit optimization methods. It outperforms existing approaches and allows for a fair comparison between CMOS and implication logic implementations under the same level of optimization, with possible device-circuit co-design strategies discussed for optimizing circuit performance.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2021)
Article
Chemistry, Multidisciplinary
Young Seok Kim, Jangho An, Jae Bum Jeon, Myeong Won Son, Seoil Son, Woojoon Park, Younghyun Lee, Juseong Park, Geun Young Kim, Gwangmin Kim, Hanchan Song, Kyung Min Kim
Summary: A ternary-state memristor device has been proposed for ternary stateful logic, capable of operating 157 ternary logic gates in one clock cycle and demonstrating a complete Lukasiewicz logic system experimentally. An optimized logic cascading strategy with possible ternary gates shows around 20% more efficiency than conventional binary stateful logic, indicating potential for higher performance in-memory computing.
Article
Computer Science, Artificial Intelligence
Michael Jahn, Matthias Scheutz
Summary: This paper focuses on the probabilistic interpretation of conditional statements and explores a generalized approach that combines probabilistic material implication and Bayesian conditionals, proving the basic properties of the generalized implication.
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING
(2023)
Review
Chemistry, Multidisciplinary
Wenxiao Wang, Song Gao, Yaqi Wang, Yang Li, Wenjing Yue, Hongsen Niu, Feifei Yin, Yunjian Guo, Guozhen Shen
Summary: Emerging photonic memristive and memristive-like devices possess high efficiency, low consumption, and versatility, making them highly attractive for constructing novel neuromorphic computing and miniaturized bionic electronic systems. However, due to the ambiguity of the mechanism and the reliability of the material, the development and commercialization of these devices are still limited. Therefore, a detailed and systematic review is needed to promote their further development, understanding the resistive switching mechanisms, evaluating the active materials, and summarizing recent applications.
Article
Engineering, Mechanical
Meiqi Jiang, Jingru Sun, Chunhua Wang, Ziyao Liao, Yichuang Sun, Qinghui Hong, Jiliang Zhang
Summary: This paper studies the design method of high-efficiency logic circuit based on memristor. A multiple-input-multiple-output (MIMO) logic circuit design scheme based on IMPLY and AND logic is proposed, which can derive multiple new efficient logic operation methods and complete complex logic with fewer steps and memristors. An alternating crossbar array structure is designed to perform rapid interactive operations between different rows, and a high-efficient full adder (FA) based on MIMO logic and alternating crossbar array is proposed.
NONLINEAR DYNAMICS
(2023)
Article
Engineering, Electrical & Electronic
Muayad J. Aljafar, John M. Acken
Summary: The paper introduces a novel 3D memristive crossbar architecture that allows for flexible configuration and reorganization of crossbar arrays, creating 1D arrays with adjustable sizes. This architecture enables parallel and pipeline computations, where data can be moved or processed in planes perpendicular to the stacked crossbar arrays.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2021)
Review
Materials Science, Multidisciplinary
Nuo Xu, Taegyun Park, Kyung Jean Yoon, Cheol Seong Hwang
Summary: Memristor-based stateful logic circuits combine Boolean logic and nonvolatile memory functions to achieve futuristic in-memory computing, potentially solving the von Neumann bottleneck in current computing architecture. Recent developments in memristor-based stateful logic computation are discussed from various perspectives, summarizing the progress in stateful logic primitive gates over the past decade and discussing influential factors in their implementation. Methods for allocating logic gates into crossbar arrays for complex computing instances are explained, along with discussions on data-intensive applications achieved using in-memory computing methods for practical application of stateful logic in future computing systems.
PHYSICA STATUS SOLIDI-RAPID RESEARCH LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Vivek Parmar, Manan Suri
Summary: The study introduces a new approach for implementing hybrid CMOS-memristive-based deep generative models, utilizing RBMs for deep learning paradigms. The proposed architecture extensively uses HfOx-based memristive devices for computational and storage functions, achieving high performance with pretraining in different architectures.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Theory & Methods
Li-Wei Chen, Ziang Chen, Werner Schindler, Xianyue Zhao, Heidemarie Schmidt, Nan Du, Ilia Polian
Summary: Memristive technologies offer fascinating opportunities for unconventional computing architectures and emerging applications. However, the security vulnerabilities of memristive technologies for implementing cryptographic circuits have been largely neglected. This article provides the first in-depth analysis of power side-channel analysis against memristive cryptographic implementations, and proposes a power estimation model and effective attack countermeasures.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)