Spin-NeuroMem: a low-power neuromorphic associative memory design based on spintronic devices

IF 2.5 4区工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC

Journal of Computational Electronics Pub Date : 2025-09-16 DOI:10.1007/s10825-025-02415-1

Siqing Fu, Lizhou Wu, Tiejun Li, Chunyuan Zhang, Jianmin Zhang, Sheng Ma

{"title":"Spin-NeuroMem: a low-power neuromorphic associative memory design based on spintronic devices","authors":"Siqing Fu, Lizhou Wu, Tiejun Li, Chunyuan Zhang, Jianmin Zhang, Sheng Ma","doi":"10.1007/s10825-025-02415-1","DOIUrl":null,"url":null,"abstract":"<div><p>Biologically inspired computing models have made significant progress in recent years, but the conventional von Neumann architecture is inefficient for the large-scale matrix operations and massive parallelism required by these models. This paper presents Spin-NeuroMem, a low-power circuit design of a Hopfield network for the function of associative memory. Spin-NeuroMem is equipped with energy-efficient spintronic synapses which utilize magnetic tunnel junctions (MTJs) to store weight matrices of multiple associative memories. The proposed synapse design achieves as low as 17.4% power consumption compared to the state-of-the-art synapse designs. Spin-NeuroMem also encompasses a novel voltage converter with a 53.3% reduction in transistor usage for effective Hopfield network computation. In addition, we propose an associative memory simulator for the first time, which achieves a 5 M<span>\\(\\times\\)</span> speedup with a comparable associative memory effect. By harnessing the potential of spintronic devices, this work paves the way for the development of energy-efficient and scalable neuromorphic computing systems.</p></div>","PeriodicalId":620,"journal":{"name":"Journal of Computational Electronics","volume":"24 6","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Computational Electronics","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s10825-025-02415-1","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Biologically inspired computing models have made significant progress in recent years, but the conventional von Neumann architecture is inefficient for the large-scale matrix operations and massive parallelism required by these models. This paper presents Spin-NeuroMem, a low-power circuit design of a Hopfield network for the function of associative memory. Spin-NeuroMem is equipped with energy-efficient spintronic synapses which utilize magnetic tunnel junctions (MTJs) to store weight matrices of multiple associative memories. The proposed synapse design achieves as low as 17.4% power consumption compared to the state-of-the-art synapse designs. Spin-NeuroMem also encompasses a novel voltage converter with a 53.3% reduction in transistor usage for effective Hopfield network computation. In addition, we propose an associative memory simulator for the first time, which achieves a 5 M\(\times\) speedup with a comparable associative memory effect. By harnessing the potential of spintronic devices, this work paves the way for the development of energy-efficient and scalable neuromorphic computing systems.

Abstract Image

查看原文本刊更多论文

基于自旋电子器件的低功耗神经形态联想记忆设计

生物启发的计算模型近年来取得了重大进展，但传统的冯·诺伊曼架构对于这些模型所需的大规模矩阵运算和大规模并行性是低效的。本文提出了一种用于联想记忆功能的Hopfield网络的低功耗电路设计Spin-NeuroMem。Spin-NeuroMem配备了高效能的自旋电子突触，利用磁隧道结（MTJs）存储多重联想记忆的权重矩阵。所提出的突触设计达到低至17.4% power consumption compared to the state-of-the-art synapse designs. Spin-NeuroMem also encompasses a novel voltage converter with a 53.3% reduction in transistor usage for effective Hopfield network computation. In addition, we propose an associative memory simulator for the first time, which achieves a 5 M\(\times\) speedup with a comparable associative memory effect. By harnessing the potential of spintronic devices, this work paves the way for the development of energy-efficient and scalable neuromorphic computing systems.

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Computational Electronics ENGINEERING, ELECTRICAL & ELECTRONIC-PHYSICS, APPLIED

CiteScore

4.50

自引率

4.80%

发文量

142

审稿时长

>12 weeks

期刊介绍： he Journal of Computational Electronics brings together research on all aspects of modeling and simulation of modern electronics. This includes optical, electronic, mechanical, and quantum mechanical aspects, as well as research on the underlying mathematical algorithms and computational details. The related areas of energy conversion/storage and of molecular and biological systems, in which the thrust is on the charge transport, electronic, mechanical, and optical properties, are also covered. In particular, we encourage manuscripts dealing with device simulation; with optical and optoelectronic systems and photonics; with energy storage (e.g. batteries, fuel cells) and harvesting (e.g. photovoltaic), with simulation of circuits, VLSI layout, logic and architecture (based on, for example, CMOS devices, quantum-cellular automata, QBITs, or single-electron transistors); with electromagnetic simulations (such as microwave electronics and components); or with molecular and biological systems. However, in all these cases, the submitted manuscripts should explicitly address the electronic properties of the relevant systems, materials, or devices and/or present novel contributions to the physical models, computational strategies, or numerical algorithms.