Toggle Main Menu Toggle Search

Open Access padlockePrints

IMBUE: In-Memory Boolean-to-CUrrent Inference ArchitecturE for Tsetlin Machines

Lookup NU author(s): Omar AwfORCiD, Tousif Rahman, Dr Shengqi Yu, Yujin ZhengORCiD, Dr Domenico Balsamo, Dr Farhad Merchant, Dr Fei Xia, Professor Alex Yakovlev, Professor Rishad ShafikORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


Abstract

In-memory computing for Machine Learning (ML) applications remedies the von Neumann bottlenecks by organizing computation to exploit parallelism and locality. Non-volatile memory devices such as Resistive RAM (ReRAM) offer integrated switching and storage capabilities showing promising performance for ML applications. However, ReRAM devices have design challenges, such as nonlinear digital-analog conversion and circuit overheads. This paper proposes an In-Memory Boolean-to-Current Inference Architecture (IMBUE) that uses ReRAM-transistor cells to eliminate the need for such conversions. IMBUE processes Boolean feature inputs expressed as digital voltages and generates parallel current paths based on resistive memory states. The proportional column current is then translated back to the Boolean domain for further digital processing. The IMBUE architecture is inspired by the Tsetlin Machine (TM), an emerging ML algorithm based on intrinsically Boolean logic. The IMBUE architecture demonstrates significant performance improvements over binarized convolutional neural networks and digital TM in-memory implementations, achieving up to a 12.99x and 5.28x increase, respectively.


Publication metadata

Author(s): Ghazal O, Singh S, Rahman T, Yu S, Zheng Y, Balsamo D, Patkar S, Merchant F, Xia F, Yakovlev A, Shafik R

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED 2023)

Year of Conference: 2023

Pages: 1-6

Online publication date: 19/09/2023

Acceptance date: 22/05/2023

Publisher: IEEE

URL: https://doi.org/10.1109/ISLPED58423.2023.10244315

DOI: 10.1109/ISLPED58423.2023.10244315

Library holdings: Search Newcastle University Library for this item

ISBN: 9798350311754


Share