Work

Lemem: A 179.8TFLOPS/W, 24.21TFLOPS Learning-In-Memory Processor with Layer-Fused Forward/Backward Pipeline for Edge DNN/SNN Training/Inference

Year: 2025

Type: conference-paper

Source: IEEE Asian Solid-State Circuits Conference (A-SSCC)

DOI: 10.1109/a-sscc67472.2025.11349463

Authors: Fengshi Tian, Kunming Shao, Jiakun Zheng, Zilu Liu, Hui Wu, Zhipeng Liao, Jingyu He, Xihao Guan, Pingcheng Dong, Chaoming Fang, Ziyang Shen, Shiqi Zhao, Jie Yang, Mohamad Sawan, Chi-Ying Tsui, Kwang-Ting Tim Cheng

Institutions: Hong Kong University of Science and Technology, The Hong Kong University of Science and Technology (Guangzhou), Westlake University, Northeastern University

Language: English

Topic: Advanced Memory and Neural Computing

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: closed

Funder: National Natural Science Foundation of China

OpenAlex ID: W7125982967

FWCI:

Cites: 10

Cited by:

Related to: