Fusion of memristor and digital compute-in-memory processing for energy-efficient edge computing

• 成果类型: Article
• 署名作者: Wen, Tai-Hao; Hung, Je-Min; Huang, Wei-Hsing; Jhang, Chuan-Jia; Lo, Yun-Chen; Hsu, Hung-Hsi; Ke, Zhao-En; Chen, Yu-Chiao; Chin, Yu-Hsiang; Su, Chin-, I; Khwa, Win-San; Lo, Chung-Chuan; Liu, Ren-Shuo; Hsieh, Chih-Cheng; Tang, Kea-Tiong; Ho, Mon-Shu; Chou, Chung-Cheng; Chih, Yu-Der; Chang, Tsung-Yung Jonathan; Chang, Meng-Fan
• 署名单位: Taiwan Semiconductor Manufacturing Company
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-8549
• DOI: 10.1126/science.adf5538
• 发表日期: 2024-04-19
• 页码: 325-332
• 关键词: cmos

摘要

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 (<0.5% accuracy loss). This work demonstrates that memristor technology has moved beyond in-lab development stages and now has manufacturability for AI edge processors.