Multi-Level Analog Computing-In-Memory FeFET-based Unit Cell for Deep Learning
(2025) 2025 IEEE International Symposium on Circuits and Systems, ISCAS 2025 In Proceedings - IEEE International Symposium on Circuits and Systems- Abstract
This paper shows a FeFET-based analog multi-level unit cell for computing-in-memory applications for Deep Neural Networks (DNN). The FeFET-based unit cell performs input-weight multiplication with a Back-End-Of-Line (BEOL) ferro-electric HZO FeFET device on top of standard 180 nm CMOS circuits. The unit cell works with a feedback mechanism which combines an in-house FeFET device to store weights and CMOS transistors underneath to provide outputs in current mode to be integrated over time on a capacitor. Said feedback mechanism compensates for device-to-device variability, and would permit to calibrate a system against time variations, something not usually included in cross-bar solutions. Joint electrical simulations of the FeFET-CMOS... (More)
This paper shows a FeFET-based analog multi-level unit cell for computing-in-memory applications for Deep Neural Networks (DNN). The FeFET-based unit cell performs input-weight multiplication with a Back-End-Of-Line (BEOL) ferro-electric HZO FeFET device on top of standard 180 nm CMOS circuits. The unit cell works with a feedback mechanism which combines an in-house FeFET device to store weights and CMOS transistors underneath to provide outputs in current mode to be integrated over time on a capacitor. Said feedback mechanism compensates for device-to-device variability, and would permit to calibrate a system against time variations, something not usually included in cross-bar solutions. Joint electrical simulations of the FeFET-CMOS circuit are performed with a compact Verilog-A model extracted from the experimental characterization of the FeFET devices. Electrical simulations show that our feedback approach leads to a multi-bit cell with 5-bits of resolution, superior to that of state-of-the-art solutions.
(Less)
- author
- Pereira-Rial ; Dahlberg, Hannes LU ; García-Lesta, D. LU ; Brea, V. M. ; López, P. ; Cabello, D. and Wernersson, Lars Erik LU
- organization
- publishing date
- 2025-06-27
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- BEOL, CIM macro, Deep Neural Networks, FeFET
- host publication
- ISCAS 2025 - IEEE International Symposium on Circuits and Systems, Proceedings
- series title
- Proceedings - IEEE International Symposium on Circuits and Systems
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2025 IEEE International Symposium on Circuits and Systems, ISCAS 2025
- conference location
- London, United Kingdom
- conference dates
- 2025-05-25 - 2025-05-28
- external identifiers
-
- scopus:105010654100
- ISSN
- 0271-4310
- ISBN
- 9798350356830
- DOI
- 10.1109/ISCAS56072.2025.11043743
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 IEEE.
- id
- 2a00a4e2-9c7e-4d24-8d2f-bb63dcae1e9c
- date added to LUP
- 2026-01-15 16:27:37
- date last changed
- 2026-01-15 16:27:49
@inproceedings{2a00a4e2-9c7e-4d24-8d2f-bb63dcae1e9c,
abstract = {{<p>This paper shows a FeFET-based analog multi-level unit cell for computing-in-memory applications for Deep Neural Networks (DNN). The FeFET-based unit cell performs input-weight multiplication with a Back-End-Of-Line (BEOL) ferro-electric HZO FeFET device on top of standard 180 nm CMOS circuits. The unit cell works with a feedback mechanism which combines an in-house FeFET device to store weights and CMOS transistors underneath to provide outputs in current mode to be integrated over time on a capacitor. Said feedback mechanism compensates for device-to-device variability, and would permit to calibrate a system against time variations, something not usually included in cross-bar solutions. Joint electrical simulations of the FeFET-CMOS circuit are performed with a compact Verilog-A model extracted from the experimental characterization of the FeFET devices. Electrical simulations show that our feedback approach leads to a multi-bit cell with 5-bits of resolution, superior to that of state-of-the-art solutions.</p>}},
author = {{Pereira-Rial and Dahlberg, Hannes and García-Lesta, D. and Brea, V. M. and López, P. and Cabello, D. and Wernersson, Lars Erik}},
booktitle = {{ISCAS 2025 - IEEE International Symposium on Circuits and Systems, Proceedings}},
isbn = {{9798350356830}},
issn = {{0271-4310}},
keywords = {{BEOL; CIM macro; Deep Neural Networks; FeFET}},
language = {{eng}},
month = {{06}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{Proceedings - IEEE International Symposium on Circuits and Systems}},
title = {{Multi-Level Analog Computing-In-Memory FeFET-based Unit Cell for Deep Learning}},
url = {{http://dx.doi.org/10.1109/ISCAS56072.2025.11043743}},
doi = {{10.1109/ISCAS56072.2025.11043743}},
year = {{2025}},
}