Design and Evaluation of a Near-Sensor Magneto-Electric FET-Based Event Detector

Mehrdad Morsali; Sepehr Tabrizchi; Andrew Marshall; Arman Roohi; Durga Misra; Shaahin Angizi

doi:10.1109/TED.2023.3296389

Design and Evaluation of a Near-Sensor Magneto-Electric FET-Based Event Detector

Mehrdad Morsali, Sepehr Tabrizchi, Andrew Marshall, Arman Roohi, Durga Misra, Shaahin Angizi

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

As a recently developed post-CMOS FET, magneto-electric FETs (MEFETs) offer high-speed and low-power design characteristics for logic and memory applications. In this article, a near-sensor processing (NSP) platform leveraging the MEFETs is presented that enables event detection for edge vision sensors at a low cost by eliminating the need for power-hungry analog-to-digital circuits (ADCs). Besides, an efficient background comparison method is presented with adjustable precision that offers the output quality efficiency tradeoff, depending on the application's needs. Our device-to-architecture evaluations show that the proposed hardware-software codesign reduces the energy consumption and execution time on average by a factor of ∼ 15× and ∼ 2.4× compared to the SOT-MRAM counterpart running employing the same method.

Original language	English (US)
Pages (from-to)	4822-4828
Number of pages	7
Journal	IEEE Transactions on Electron Devices
Volume	70
Issue number	9
DOIs	https://doi.org/10.1109/TED.2023.3296389
State	Published - Sep 1 2023

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Keywords

Magneto-electric FET (MEFET)
near-sensor computing
nonvolatile memory

Access to Document

10.1109/TED.2023.3296389

Cite this

@article{736a59246af0418c876aff4bc695a529,

title = "Design and Evaluation of a Near-Sensor Magneto-Electric FET-Based Event Detector",

abstract = "As a recently developed post-CMOS FET, magneto-electric FETs (MEFETs) offer high-speed and low-power design characteristics for logic and memory applications. In this article, a near-sensor processing (NSP) platform leveraging the MEFETs is presented that enables event detection for edge vision sensors at a low cost by eliminating the need for power-hungry analog-to-digital circuits (ADCs). Besides, an efficient background comparison method is presented with adjustable precision that offers the output quality efficiency tradeoff, depending on the application's needs. Our device-to-architecture evaluations show that the proposed hardware-software codesign reduces the energy consumption and execution time on average by a factor of ∼ 15× and ∼ 2.4× compared to the SOT-MRAM counterpart running employing the same method.",

keywords = "Magneto-electric FET (MEFET), near-sensor computing, nonvolatile memory",

author = "Mehrdad Morsali and Sepehr Tabrizchi and Andrew Marshall and Arman Roohi and Durga Misra and Shaahin Angizi",

note = "Publisher Copyright: {\textcopyright} 1963-2012 IEEE.",

year = "2023",

month = sep,

day = "1",

doi = "10.1109/TED.2023.3296389",

language = "English (US)",

volume = "70",

pages = "4822--4828",

journal = "IEEE Transactions on Electron Devices",

issn = "0018-9383",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "9",

}

TY - JOUR

T1 - Design and Evaluation of a Near-Sensor Magneto-Electric FET-Based Event Detector

AU - Morsali, Mehrdad

AU - Tabrizchi, Sepehr

AU - Marshall, Andrew

AU - Roohi, Arman

AU - Misra, Durga

AU - Angizi, Shaahin

PY - 2023/9/1

Y1 - 2023/9/1

N2 - As a recently developed post-CMOS FET, magneto-electric FETs (MEFETs) offer high-speed and low-power design characteristics for logic and memory applications. In this article, a near-sensor processing (NSP) platform leveraging the MEFETs is presented that enables event detection for edge vision sensors at a low cost by eliminating the need for power-hungry analog-to-digital circuits (ADCs). Besides, an efficient background comparison method is presented with adjustable precision that offers the output quality efficiency tradeoff, depending on the application's needs. Our device-to-architecture evaluations show that the proposed hardware-software codesign reduces the energy consumption and execution time on average by a factor of ∼ 15× and ∼ 2.4× compared to the SOT-MRAM counterpart running employing the same method.

AB - As a recently developed post-CMOS FET, magneto-electric FETs (MEFETs) offer high-speed and low-power design characteristics for logic and memory applications. In this article, a near-sensor processing (NSP) platform leveraging the MEFETs is presented that enables event detection for edge vision sensors at a low cost by eliminating the need for power-hungry analog-to-digital circuits (ADCs). Besides, an efficient background comparison method is presented with adjustable precision that offers the output quality efficiency tradeoff, depending on the application's needs. Our device-to-architecture evaluations show that the proposed hardware-software codesign reduces the energy consumption and execution time on average by a factor of ∼ 15× and ∼ 2.4× compared to the SOT-MRAM counterpart running employing the same method.

KW - Magneto-electric FET (MEFET)

KW - near-sensor computing

KW - nonvolatile memory

UR - http://www.scopus.com/inward/record.url?scp=85166356491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85166356491&partnerID=8YFLogxK

U2 - 10.1109/TED.2023.3296389

DO - 10.1109/TED.2023.3296389

M3 - Article

AN - SCOPUS:85166356491

SN - 0018-9383

VL - 70

SP - 4822

EP - 4828

JO - IEEE Transactions on Electron Devices

JF - IEEE Transactions on Electron Devices

IS - 9

ER -

Design and Evaluation of a Near-Sensor Magneto-Electric FET-Based Event Detector

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this