Fusion of memristor and digital compute-in-memory processing for energy-efficient edge computing
Science · 19.04.2024 · 384 (6693) · 325-332
DOI: 10.1126/science.adf5538 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 19.04.2024. Verfasst von Tai-Hao Wen und 19 weiteren Autor:innen. Beteiligte Einrichtung: Taiwan Semiconductor Manufacturing Company Limited (TSMC), No. 8, Li-Hsin Rd. 6, Hsinchu Science Park, Hsinchu 300, Taiwan, R.O.C. Die Arbeit wurde bisher 138-mal zitiert (Crossref) und nennt 38 Literaturangaben.
Abstract (Originalsprache)
Artificial intelligence (AI) edge devices prefer employing high-capacity nonvolatile compute-in-memory (CIM) to achieve high energy efficiency and rapid wakeup-to-response with sufficient accuracy. Most previous works are based on either memristor-based CIMs, which suffer from accuracy loss and do not support training as a result of limited endurance, or digital static random-access memory (SRAM)–based CIMs, which suffer from large area requirements and volatile storage. We report an AI edge processor that uses a memristor-SRAM CIM-fusion scheme to simultaneously exploit the high accuracy of the digital SRAM CIM and the high energy-efficiency and storage density of the resistive random-access memory memristor CIM. This also enables adaptive local training to accommodate personalized characterization and user environment. The fusion processor achieved high CIM capacity, short wakeup-to-response latency (392 microseconds), high peak energy efficiency (77.64 teraoperations per second per watt), and robust accuracy (
Autor:innen und Institutionen
- Taiwan Semiconductor Manufacturing Company Limited (TSMC), No. 8, Li-Hsin Rd. 6, Hsinchu Science Park, Hsinchu 300, Taiwan, R.O.C.
- Department of Electrical Engineering, National Tsing Hua University (NTHU), No. 101, Sec. 2, Guangfu Rd., East Dist., Hsinchu City, Hsinchu 300, Taiwan, R.O.C.
- Department of Life Science, National Tsing Hua University (NTHU), No. 101, Sec. 2, Guangfu Rd., East Dist., Hsinchu City, Hsinchu 300, Taiwan, R.O.C.
- Department of Physics, National Chung Hsing University (NCHU), No. 145, Xingda Rd., South Dist., Taichung City 402, Taiwan, R.O.C.
ORCID-Profile: Tai-Hao Wen, Wei-Hsing Huang, Chuan-Jia Jhang, Yun-Chen Lo, Hung-Hsi Hsu, Yu-Chiao Chen, Win-San Khwa, Chung-Chuan Lo, Mon-Shu Ho, Chung-Cheng Chou, Meng-Fan Chang
Zitieren
APA
Wen, T. H., Hung, J. M., Huang, W. H., Jhang, C. J., Lo, Y. C., Hsu, H. H., Ke, Z. E., Chen, Y. C., Chin, Y. H., Su, C. I., Khwa, W. S., Lo, C. C., Liu, R. S., Hsieh, C. C., Tang, K. T., Ho, M. S., Chou, C. C., Chih, Y. D., Chang, T. J., & Chang, M. F. (2024). Fusion of memristor and digital compute-in-memory processing for energy-efficient edge computing. Science, 384(6693), 325-332. https://doi.org/10.1126/science.adf5538
Vancouver
Wen TH, Hung JM, Huang WH, Jhang CJ, Lo YC, Hsu HH, et al. Fusion of memristor and digital compute-in-memory processing for energy-efficient edge computing. Science. 2024;384(6693):325-332. doi:10.1126/science.adf5538
BibTeX
@article{Wen2024,
author = {Wen, Tai-Hao and Hung, Je-Min and Huang, Wei-Hsing and Jhang, Chuan-Jia and Lo, Yun-Chen and Hsu, Hung-Hsi and Ke, Zhao-En and Chen, Yu-Chiao and Chin, Yu-Hsiang and Su, Chin-I and Khwa, Win-San and Lo, Chung-Chuan and Liu, Ren-Shuo and Hsieh, Chih-Cheng and Tang, Kea-Tiong and Ho, Mon-Shu and Chou, Chung-Cheng and Chih, Yu-Der and Chang, Tsung-Yung Jonathan and Chang, Meng-Fan},
title = {Fusion of memristor and digital compute-in-memory processing for energy-efficient edge computing},
journal = {Science},
year = {2024},
volume = {384},
number = {6693},
pages = {325--332},
doi = {10.1126/science.adf5538}
}
EUVIMED