2022 International Conference on Solid State Devices and Materials

講演情報

Oral Presentation

12: Advanced Circuits / Systems Interacting with Innovative Devices and Materials

[K-5] Advanced Neuron and AI Systems

2022年9月28日(水) 10:45 〜 12:00 304 (3F)

Session Chair: Takeshi Yoshida (Hiroshima Univ.), Yitao Ma (Tohoku Univ.)

11:45 〜 12:00

[K-5-04] Design of an Energy-Efficient Nonvolatile Lookup Table Circuit Using Active-Load-Localized Circuitry with Self-Terminated Writing/Reading

〇Daisuke Suzuki1, Takahiro Hanyu2 (1. The University of Aizu (Japan), 2. Tohoku University (Japan))

Presentation style: On-site (in-person)

https://doi.org/10.7567/SSDM.2022.K-5-04

An energy-efficient nonvolatile lookup table (LUT) circuit, where both write and read currents are automatically terminated if desired write/read operations are completed, is proposed. The use of self-terminated writing makes it possible to cut off wasted write current by continuously monitoring voltage transition due to the resistance change in the storage element. Moreover, wasted read current can also be cut off by utilizing voltage drop in active-load-localized circuitry as read completion signal. In fact, the proposed 6-input LUT circuit reduces 59% of write energy and 38% read energy with only 5% of hardware overhead compared to those of a conventional circuitry under 45nm CMOS technology.

Abstract password authentication.
Password to download abstracts has been informed in the confirmation mail.

パスワード