[paper] in-memory computing using FeFET

Taha Soliman, Swetaki Chatterjee, Nellie Laleni, Franz Müller, Tobias Kirchner, Norbert Wehn, Thomas Kämpfe, Yogesh Singh Chauhan and Hussam Amrouch

First demonstration of in-memory computing crossbar using multi-level Cell FeFET

Nat Commun 14, 6348 (2023)

DOI: 10.1038/s41467-023-42110-y

1 Robert Bosch GmbH, Renningen, Germany
2 Semiconducture Test and Reliability, University of Stuttgart, Stuttgart, Germany
3 Department of Electrical Engineering, IIK, Kanpur, India
4 Fraunhofer IPMS, Dresden, Germany
5 RPTU Kaiserslautern-Landau, Kaiserslautern, Germany
6 MIRMI; Technical University of Munich, Germany

Abstract: Advancements in AI led to the emergence of in-memory-computing architectures as a promising solution for the associated computing and memory challenges. This study introduces a novel in-memory-computing (IMC) crossbar macro utilizing a multi-level ferroelectric field-effect transistor (FeFET) cell for multi-bit multiply and accumulate (MAC) operations. The proposed 1FeFET-1R cell design stores multi-bit information while minimizing device variability effects on accuracy. Experimental validation was performed using 28 nm HKMG technology-based FeFET devices. Unlike traditional resistive memory-based analog computing, our approach leverages the electrical characteristics of stored data within the memory cell to derive MAC operation results encoded in activation time and accumulated current. Remarkably, our design achieves 96.6% accuracy for handwriting recognition and 91.5% accuracy for image classification without extra training. Furthermore, it demonstrates exceptional performance, achieving 885.4 TOPS/W–nearly double that of existing designs. This study represents the first successful implementation of an in-memory macro using a multi-state FeFET cell for complete MAC operations, preserving crossbar density without additional structural overhead.

FIG: a.) The material stack of FeFETs. 

b.) The multi-bit FeFET can be programmed to different states

to store the weight of the synapse

Acknowledgements: This work has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826655 and No 876925. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Belgium, France, Germany, Portugal, Spain, The Netherlands, Switzerland. Open Access funding enabled and organized by Projekt DEAL.