Ferroelectric-defined reconfigurable homojunctions for in-memory sensing and computing

Recently, the increasing demand for data-centric applications is driving the elimination of image sensing, memory and computing unit interface, thus promising for latency- and energy-strict applications. Although dedicated electronic hardware has inspired the development of in-memory computing and i...

Full description

Saved in:
Bibliographic Details
Published in:Nature materials 2023-12, Vol.22 (12), p.1499-1506
Main Authors: Wu, Guangjian, Zhang, Xumeng, Feng, Guangdi, Wang, Jingli, Zhou, Keji, Zeng, Jinhua, Dong, Danian, Zhu, Fangduo, Yang, Chenkai, Zhao, Xiaoming, Gong, Danni, Zhang, Mengru, Tian, Bobo, Duan, Chungang, Liu, Qi, Wang, Jianlu, Chu, Junhao, Liu, Ming
Format: Article
Language:English
Subjects:
639/925/927
639/925/927/1007
Arrays
Biomaterials
Chemistry and Materials Science
Computation
Computer architecture
Condensed Matter Physics
Energy consumption
Ferroelectric domains
Ferroelectric materials
Ferroelectricity
Hardware
Homojunctions
Image manipulation
Materials Science
Memory
Nanotechnology
Optical and Electronic Materials
Photodiodes
Photoelectric effect
Reconfiguration
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, the increasing demand for data-centric applications is driving the elimination of image sensing, memory and computing unit interface, thus promising for latency- and energy-strict applications. Although dedicated electronic hardware has inspired the development of in-memory computing and in-sensor computing, folding the entire signal chain into one device remains challenging. Here an in-memory sensing and computing architecture is demonstrated using ferroelectric-defined reconfigurable two-dimensional photodiode arrays. High-level cognitive computing is realized based on the multiplications of light power and photoresponsivity through the photocurrent generation process and Kirchhoff’s law. The weight is stored and programmed locally by the ferroelectric domains, enabling 51 (>5 bit) distinguishable weight states with linear, symmetric and reversible manipulation characteristics. Image recognition can be performed without any external memory and computing units. The three-in-one paradigm, integrating high-level computing, weight memorization and high-performance sensing, paves the way for a computing architecture with low energy consumption, low latency and reduced hardware overhead. It remains challenging to integrate memory, sensing and computing in one device. Here a compact in-memory sensing and computing architecture based on ferroelectric-defined reconfigurable two-dimensional photodiode arrays has been reported.
ISSN:1476-1122
1476-4660
DOI:10.1038/s41563-023-01676-0