Monolithic 3D Integration of Analog RRAM‐Based Computing‐in‐Memory and Sensor for Energy‐Efficient Near‐Sensor Computing
Advanced Materials · 2024-05 · 36 (22)
DOI: 10.1002/adma.202302658 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 25.10.2023. Verfasst von Yiwei Du und 12 weiteren Autor:innen. Beteiligte Einrichtung: School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, Beijing National Research Center for Information Science a…. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Natural Science Foundation of China, STI 2030-Major Projects, National Natural Science Foundation of China.
Abstract (Originalsprache)
In the era of the Internet of Things, vast amounts of data generated at sensory nodes impose critical challenges on the data‐transfer bandwidth and energy efficiency of computing hardware. A near‐sensor computing (NSC) architecture places the processing units closer to the sensors such that the generated data can be processed almost in situ with high efficiency. This study demonstrates the monolithic three‐dimensional (M3D) integration of a photosensor array, analog computing‐in‐memory (CIM), and Si complementary metal‐oxide‐semiconductor (CMOS) logic circuits, named M3D‐SAIL. This approach exploits the high‐bandwidth on‐chip data transfer and massively parallel CIM cores to realize an energy‐efficient NSC architecture. The 1st layer of the Si CMOS circuits serves as the control logic and peripheral circuits. The 2nd layer comprises a 1 k‐bit one‐transistor‐one‐resistor (1T1R) array with InGaZnO x field‐effect transistor (IGZO‐FET) and resistive random‐access memory (RRAM) for analog CIM. The 3rd layer comprises multiple IGZO‐FET‐based photosensor arrays for wavelength‐dependent optical sensing. The structural integrity and function of each layer are comprehensively verified. Furthermore, NSC is implemented using the M3D‐SAIL architecture for a typical video keyframe‐extraction task, achieving a high classification accuracy of 96.7% as well as a 31.5× lower energy consumption and 1.91× faster computing speed compared to its 2D counterpart.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, China.
ORCID-Profile: Jianshi Tang
Förderung
- Natural Science Foundation of China
- STI 2030-Major Projects
- National Natural Science Foundation of China
Zitieren
APA
Du, Y., Tang, J., Li, Y., Xi, Y., Li, Y., Li, J., Huang, H., Qin, Q., Zhang, Q., Gao, B., Deng, N., Qian, H., & Wu, H. (2024). Monolithic 3D Integration of Analog RRAM‐Based Computing‐in‐Memory and Sensor for Energy‐Efficient Near‐Sensor Computing. Advanced Materials, 36(22). https://doi.org/10.1002/adma.202302658
Vancouver
Du Y, Tang J, Li Y, Xi Y, Li Y, Li J, et al. Monolithic 3D Integration of Analog RRAM‐Based Computing‐in‐Memory and Sensor for Energy‐Efficient Near‐Sensor Computing. Advanced Materials. 2024;36(22). doi:10.1002/adma.202302658
BibTeX
@article{Du2024,
author = {Du, Yiwei and Tang, Jianshi and Li, Yijun and Xi, Yue and Li, Yuankun and Li, Jiaming and Huang, Heyi and Qin, Qi and Zhang, Qingtian and Gao, Bin and Deng, Ning and Qian, He and Wu, Huaqiang},
title = {Monolithic 3D Integration of Analog RRAM‐Based Computing‐in‐Memory and Sensor for Energy‐Efficient Near‐Sensor Computing},
journal = {Advanced Materials},
year = {2024},
volume = {36},
number = {22},
doi = {10.1002/adma.202302658}
}
EUVIMED