{"title":"IGZO DRAM in three dimensions","authors":"Matthew Parker","doi":"10.1038/s41928-025-01413-2","DOIUrl":null,"url":null,"abstract":"<p>The researchers — who are based at Huazhong University of Science and Technology and Peking University — create an 8 × 8 array of stacked DRAM. Each cell has two layers with an IGZO transistor that act as read and write transistors, achieving 3-bit memory storage and retention time of 100 s. By converging the current across multiple DRAM columns, it is also possible to achieve in-memory accumulation, reducing the number of computations that occur outside the memory for tasks such as image recognition. This is demonstrated in a neural network model for handwritten digit recognition that achieves 95% accuracy.</p><p><b>Original reference:</b> <i>Sci. Adv</i>. <b>11</b>, eadu4323 (2025)</p>","PeriodicalId":19064,"journal":{"name":"Nature Electronics","volume":"653 1","pages":""},"PeriodicalIF":40.9000,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nature Electronics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1038/s41928-025-01413-2","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
The researchers — who are based at Huazhong University of Science and Technology and Peking University — create an 8 × 8 array of stacked DRAM. Each cell has two layers with an IGZO transistor that act as read and write transistors, achieving 3-bit memory storage and retention time of 100 s. By converging the current across multiple DRAM columns, it is also possible to achieve in-memory accumulation, reducing the number of computations that occur outside the memory for tasks such as image recognition. This is demonstrated in a neural network model for handwritten digit recognition that achieves 95% accuracy.
期刊介绍:
Nature Electronics is a comprehensive journal that publishes both fundamental and applied research in the field of electronics. It encompasses a wide range of topics, including the study of new phenomena and devices, the design and construction of electronic circuits, and the practical applications of electronics. In addition, the journal explores the commercial and industrial aspects of electronics research.
The primary focus of Nature Electronics is on the development of technology and its potential impact on society. The journal incorporates the contributions of scientists, engineers, and industry professionals, offering a platform for their research findings. Moreover, Nature Electronics provides insightful commentary, thorough reviews, and analysis of the key issues that shape the field, as well as the technologies that are reshaping society.
Like all journals within the prestigious Nature brand, Nature Electronics upholds the highest standards of quality. It maintains a dedicated team of professional editors and follows a fair and rigorous peer-review process. The journal also ensures impeccable copy-editing and production, enabling swift publication. Additionally, Nature Electronics prides itself on its editorial independence, ensuring unbiased and impartial reporting.
In summary, Nature Electronics is a leading journal that publishes cutting-edge research in electronics. With its multidisciplinary approach and commitment to excellence, the journal serves as a valuable resource for scientists, engineers, and industry professionals seeking to stay at the forefront of advancements in the field.