Salvato in:
Dettagli Bibliografici
Autori principali: Foster, Patrick, Papandroulidakis, Georgios, Serb, Alex, Prodromakis, Spyros Stathopoulos Themis
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2303.02651
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915128425840640
author Foster, Patrick
Papandroulidakis, Georgios
Serb, Alex
Prodromakis, Spyros Stathopoulos Themis
author_facet Foster, Patrick
Papandroulidakis, Georgios
Serb, Alex
Prodromakis, Spyros Stathopoulos Themis
contents Recent advances in machine learning and neuro-inspired systems enabled the increased interest in efficient pattern recognition at the edge. A wide variety of applications, such as near-sensor classification, require fast and low-power approaches for pattern matching through the use of associative memories and their more well-known implementation, Content Addressable Memories (CAMs). Towards addressing the need for low-power classification, this work showcases an RRAM-based analogue CAM (ACAM) intended for template matching applications, providing a low-power reconfigurable classification engine for the extreme edge. The circuit uses a low component count at 6T2R2M, comparable with the most compact existing cells of this type. In this work, we demonstrate a hardware prototype, built with commercial off-the-shelf (COTS) components for the MOSFET-based circuits, that implements rows of 6T2R2M employing TiOx-based RRAM devices developed in-house, showcasing competitive matching window configurability and definition. Furthermore, through simulations, we validate the performance of the proposed circuit by using a commercially available 180nm technology and in-house RRAM data-driven model to assess the energy dissipation, exhibiting 60 pJ per classification event.
format Preprint
id arxiv_https___arxiv_org_abs_2303_02651
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle An RRAM-Based Implementation of a Template Matching Circuit for Low-Power Analogue Classification
Foster, Patrick
Papandroulidakis, Georgios
Serb, Alex
Prodromakis, Spyros Stathopoulos Themis
Signal Processing
Recent advances in machine learning and neuro-inspired systems enabled the increased interest in efficient pattern recognition at the edge. A wide variety of applications, such as near-sensor classification, require fast and low-power approaches for pattern matching through the use of associative memories and their more well-known implementation, Content Addressable Memories (CAMs). Towards addressing the need for low-power classification, this work showcases an RRAM-based analogue CAM (ACAM) intended for template matching applications, providing a low-power reconfigurable classification engine for the extreme edge. The circuit uses a low component count at 6T2R2M, comparable with the most compact existing cells of this type. In this work, we demonstrate a hardware prototype, built with commercial off-the-shelf (COTS) components for the MOSFET-based circuits, that implements rows of 6T2R2M employing TiOx-based RRAM devices developed in-house, showcasing competitive matching window configurability and definition. Furthermore, through simulations, we validate the performance of the proposed circuit by using a commercially available 180nm technology and in-house RRAM data-driven model to assess the energy dissipation, exhibiting 60 pJ per classification event.
title An RRAM-Based Implementation of a Template Matching Circuit for Low-Power Analogue Classification
topic Signal Processing
url https://arxiv.org/abs/2303.02651