计算机科学
瓶颈
闪存
冯·诺依曼建筑
闪光灯(摄影)
计算机数据存储
嵌入式系统
常规存储器
计算机存储器
计算机体系结构
并行计算
半导体存储器
计算机硬件
交错存储器
操作系统
艺术
视觉艺术
作者
Guilherme Migliato Marega,Z. Wang,Yanfei Zhao,Hyun Goo Ji,Asmund Ottesen,Mukesh Tripathi,Aleksandra Rađenović,András Kis
出处
期刊:IEEE Nanotechnology Magazine
[Institute of Electrical and Electronics Engineers]
日期:2023-09-20
卷期号:17 (5): 39-43
被引量:3
标识
DOI:10.1109/mnano.2023.3297118
摘要
Memory devices have returned to the spotlight due to increasing interest in using in-memory computing architectures to make data-driven algorithms more energy-efficient. One of the main advantages of this architecture is the efficient performance of vector-matrix multiplications while avoiding the "von Neumann bottleneck." Despite these promises, no single material platform meets all the requirements for the fabrication of this new processor technology. Recently, flash memories based on monolayer MoS2 have been shown to achieve ultra-fast operation, overcoming one of the main drawbacks of this memory type. Together with its other characteristics, this makes them a promising candidate for the base elements of this technology. However, the question remains of how to achieve large-area ultra-fast operation of MoS2 monolayer flash memories. In this work, we will compare large-area flash memories based on MoS2 used in past realizations of in-memory systems and analyze the improvements needed to achieve ultra-fast performance for in-memory applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI