Sparse matrix multiplication in a record-low power self-rectifying memristor array for scientific computing
Science Advances · 23.06.2023 · 9 (25)
DOI: 10.1126/sciadv.adf7474 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 23.06.2023. Verfasst von Jiancong Li und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Integrated Circuits, Hubei Key Laboratory for Advanced Memories, Huazhong University of Science and Technology, Wuhan 430074, China. Die Arbeit wurde bisher 82-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Memristor-enabled in-memory computing provides an unconventional computing paradigm to surpass the energy efficiency of von Neumann computers. Owing to the limitation of the computing mechanism, while the crossbar structure is desirable for dense computation, the system’s energy and area efficiency degrade substantially in performing sparse computation tasks, such as scientific computing. In this work, we report a high-efficiency in-memory sparse computing system based on a self-rectifying memristor array. This system originates from an analog computing mechanism that is motivated by the device’s self-rectifying nature, which can achieve an overall performance of ~97 to ~11 TOPS/W for 2- to 8-bit sparse computation when processing practical scientific computing tasks. Compared to previous in-memory computing system, this work provides over 85 times improvement in energy efficiency with an approximately 340 times reduction in hardware overhead. This work can pave the road toward a highly efficient in-memory computing platform for high-performance computing.
Autor:innen und Institutionen
- School of Integrated Circuits, Hubei Key Laboratory for Advanced Memories, Huazhong University of Science and Technology, Wuhan 430074, China.
- Hubei Yangtze Memory Laboratories, Wuhan 430205, China.
- AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong, China.
ORCID-Profile: Jiancong Li, Sheng-Guang Ren, Yi Li, Yinjie Yu, Yuhui He, Xiangshui Miao
Zitieren
APA
Li, J., Ren, S. G., Li, Y., Yang, L., Yu, Y., Ni, R., Zhou, H., Bao, H., He, Y., Chen, J., Jia, H., & Miao, X. (2023). Sparse matrix multiplication in a record-low power self-rectifying memristor array for scientific computing. Science Advances, 9(25). https://doi.org/10.1126/sciadv.adf7474
Vancouver
Li J, Ren SG, Li Y, Yang L, Yu Y, Ni R, et al. Sparse matrix multiplication in a record-low power self-rectifying memristor array for scientific computing. Science Advances. 2023;9(25). doi:10.1126/sciadv.adf7474
BibTeX
@article{Li2023,
author = {Li, Jiancong and Ren, Sheng-Guang and Li, Yi and Yang, Ling and Yu, Yinjie and Ni, Run and Zhou, Houji and Bao, Han and He, Yuhui and Chen, Jia and Jia, Han and Miao, Xiangshui},
title = {Sparse matrix multiplication in a record-low power self-rectifying memristor array for scientific computing},
journal = {Science Advances},
year = {2023},
volume = {9},
number = {25},
doi = {10.1126/sciadv.adf7474}
}
EUVIMED