Sub-10nm Ultra-thin ZnO Channel FET with Record-High 561 µA/µm ION at VDS 1V, High µ-84 cm2/V-s and1T-1RRAM Memory Cell Demonstration Memory Implications for Energy-Efficient Deep-Learning Computing
Umesh Chand Mohamed M Sabry Aly Manohar Lal Chen Chun-Kuei Sonu Hooda Shih-Hao Tsai Zihang Fang Hasita Veluri Aaron Voon-Yew Thean
Mohamed M Sabry Aly
Chen Chun-Kuei
Sonu Hooda
Shih-Hao Tsai
Zihang Fang
Hasita Veluri
Citations
Altmetric:
Alternative Title
Abstract
For the first time, we investigated ultra-short-channel ZnO thin-film FETs with Lch = 8 nm with extremely scaled channel thickness tZnO of 3nm, the device exhibits ultra-low sub-pA/µm off leakage (1.2 pA/µm), high electron mobility (µeff = 84 cm2/V•s) with record peak transconductance (Gm,) of 254 μS/μm at VDS = 1 V wrt. reported oxide-based transistors, to date, leading to high on-state current (ION) of 561 μA/μm. We demonstrated the integration of a ZnO access transistor with Al2O3 RRAM to enable a 1T-1R memory cell, suitable for BEOL-embedded memory. We evaluate the system-level benefits of a hardware accelerator for deep learning to employ FET-RRAM as working memory—up to 10X energy-efficiency benefits can be achieved over current baseline configurations.
Keywords
Source Title
2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)
Publisher
IEEE
Series/Report No.
Collections
Rights
CC0 1.0 Universal
Date
2022-06-12
DOI
10.1109/VLSITechnologyandCir46769.2022.9830250
Type
Conference Paper