{"title":"Halide Perovskite: The Key to Overcoming von Neumann Bottlenecks in AI Workloads","authors":"Geon Kim, Sunghyun Jang, Hyojung Kim","doi":"10.1007/s13391-025-00597-1","DOIUrl":null,"url":null,"abstract":"<div><p>The well-known von Neumann bottleneck has emerged as a significant obstacle in computationally demanding AI tasks, as frequent data transfers between logic and memory impair system performance and reduce energy efficiency, thereby motivating the exploration of in-memory and neuromorphic computing as potential solutions. Among emerging material options, halide perovskites (HPs) exhibit a tunable bandgap, rapid ion migration, mechanical pliability, and facile low-temperature processing, making them particularly advantageous for next-generation computing. This article surveys HP-based memristors and synaptic transistors, emphasizing their underlying physical mechanisms, capacity to replicate synaptic behavior, and multilevel memory functionality within novel computing architectures. Additionally, we address integration challenges, particularly regarding stability, variability, and scalability. By examining recent advances, we highlight HPs as a promising materials platform for next-generation AI hardware that can overcome the limitations of traditional von Neumann architectures.</p><h3>Graphical Abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":536,"journal":{"name":"Electronic Materials Letters","volume":"21 6","pages":"756 - 783"},"PeriodicalIF":3.1000,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronic Materials Letters","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s13391-025-00597-1","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The well-known von Neumann bottleneck has emerged as a significant obstacle in computationally demanding AI tasks, as frequent data transfers between logic and memory impair system performance and reduce energy efficiency, thereby motivating the exploration of in-memory and neuromorphic computing as potential solutions. Among emerging material options, halide perovskites (HPs) exhibit a tunable bandgap, rapid ion migration, mechanical pliability, and facile low-temperature processing, making them particularly advantageous for next-generation computing. This article surveys HP-based memristors and synaptic transistors, emphasizing their underlying physical mechanisms, capacity to replicate synaptic behavior, and multilevel memory functionality within novel computing architectures. Additionally, we address integration challenges, particularly regarding stability, variability, and scalability. By examining recent advances, we highlight HPs as a promising materials platform for next-generation AI hardware that can overcome the limitations of traditional von Neumann architectures.
期刊介绍：
Electronic Materials Letters is an official journal of the Korean Institute of Metals and Materials. It is a peer-reviewed international journal publishing print and online version. It covers all disciplines of research and technology in electronic materials. Emphasis is placed on science, engineering and applications of advanced materials, including electronic, magnetic, optical, organic, electrochemical, mechanical, and nanoscale materials. The aspects of synthesis and processing include thin films, nanostructures, self assembly, and bulk, all related to thermodynamics, kinetics and/or modeling.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
