Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga2O3 RRAM

Mehrdad Morsali; Sepehr Tabrizchi; Ravi Teja Velpula; Mano Bala Sankar Muthu; Hieu Pham Trung Nguyen; Mohsen Imani; Arman Roohi; Shaahin Angizi

doi:10.1109/ISVLSI61997.2024.00067

Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga₂O₃ RRAM

Mehrdad Morsali, Sepehr Tabrizchi, Ravi Teja Velpula, Mano Bala Sankar Muthu, Hieu Pham Trung Nguyen, Mohsen Imani, Arman Roohi, Shaahin Angizi

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

In this paper, a cost-effective Near-Sensor Processing (NSP) platform is developed based on an experimentally-measured TiTiN/Ga₂O₃/Ti/Pt Resistive Random Access Memory (RRAM) device that facilitates event detection for edge vision sensors without the requirement for power-intensive Analog-to-Digital Converters (ADCs). The platform is supported with a hardware-friendly background comparison technique providing adjustable precision that allows for a dynamic balance between accuracy and efficiency at runtime. Our device-to-architecture simulation results demonstrate that the proposed platform achieves on average 66% and 63% energy saving over STT-MRAM and SOT-MRAM counterparts due to utilizing the ADC-less method.

Original language	English (US)
Title of host publication	2024 IEEE Computer Society Annual Symposium on VLSI
Subtitle of host publication	Emerging VLSI Technologies and Architectures, ISVLSI 2024
Editors	Himanshu Thapliyal, Jurgen Becker
Publisher	IEEE Computer Society
Pages	331-336
Number of pages	6
ISBN (Electronic)	9798350354119
DOIs	https://doi.org/10.1109/ISVLSI61997.2024.00067
State	Published - 2024
Event	2024 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2024 - Knoxville, United States Duration: Jul 1 2024 → Jul 3 2024

Publication series

Name	Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
ISSN (Print)	2159-3469
ISSN (Electronic)	2159-3477

Conference

Conference	2024 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2024
Country/Territory	United States
City	Knoxville
Period	7/1/24 → 7/3/24

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ISVLSI61997.2024.00067

Cite this

Morsali, M., Tabrizchi, S., Velpula, R. T., Sankar Muthu, M. B., Trung Nguyen, H. P., Imani, M., Roohi, A., & Angizi, S. (2024). Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga₂O₃ RRAM. In H. Thapliyal, & J. Becker (Eds.), 2024 IEEE Computer Society Annual Symposium on VLSI: Emerging VLSI Technologies and Architectures, ISVLSI 2024 (pp. 331-336). (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI). IEEE Computer Society. https://doi.org/10.1109/ISVLSI61997.2024.00067

Morsali, Mehrdad ; Tabrizchi, Sepehr ; Velpula, Ravi Teja et al. / Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga₂O₃ RRAM. 2024 IEEE Computer Society Annual Symposium on VLSI: Emerging VLSI Technologies and Architectures, ISVLSI 2024. editor / Himanshu Thapliyal ; Jurgen Becker. IEEE Computer Society, 2024. pp. 331-336 (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI).

@inproceedings{b9d4c5021fd34b6fbc8709b6ed61a9a8,

title = "Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga2O3 RRAM",

abstract = "In this paper, a cost-effective Near-Sensor Processing (NSP) platform is developed based on an experimentally-measured TiTiN/Ga2O3/Ti/Pt Resistive Random Access Memory (RRAM) device that facilitates event detection for edge vision sensors without the requirement for power-intensive Analog-to-Digital Converters (ADCs). The platform is supported with a hardware-friendly background comparison technique providing adjustable precision that allows for a dynamic balance between accuracy and efficiency at runtime. Our device-to-architecture simulation results demonstrate that the proposed platform achieves on average 66\% and 63\% energy saving over STT-MRAM and SOT-MRAM counterparts due to utilizing the ADC-less method.",

author = "Mehrdad Morsali and Sepehr Tabrizchi and Velpula, \{Ravi Teja\} and \{Sankar Muthu\}, \{Mano Bala\} and \{Trung Nguyen\}, \{Hieu Pham\} and Mohsen Imani and Arman Roohi and Shaahin Angizi",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2024 ; Conference date: 01-07-2024 Through 03-07-2024",

year = "2024",

doi = "10.1109/ISVLSI61997.2024.00067",

language = "English (US)",

series = "Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI",

publisher = "IEEE Computer Society",

pages = "331--336",

editor = "Himanshu Thapliyal and Jurgen Becker",

booktitle = "2024 IEEE Computer Society Annual Symposium on VLSI",

address = "United States",

}

Morsali, M, Tabrizchi, S, Velpula, RT, Sankar Muthu, MB, Trung Nguyen, HP, Imani, M, Roohi, A & Angizi, S 2024, Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga₂O₃ RRAM. in H Thapliyal & J Becker (eds), 2024 IEEE Computer Society Annual Symposium on VLSI: Emerging VLSI Technologies and Architectures, ISVLSI 2024. Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI, IEEE Computer Society, pp. 331-336, 2024 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2024, Knoxville, United States, 7/1/24. https://doi.org/10.1109/ISVLSI61997.2024.00067

Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga₂O₃ RRAM. / Morsali, Mehrdad; Tabrizchi, Sepehr; Velpula, Ravi Teja et al.
2024 IEEE Computer Society Annual Symposium on VLSI: Emerging VLSI Technologies and Architectures, ISVLSI 2024. ed. / Himanshu Thapliyal; Jurgen Becker. IEEE Computer Society, 2024. p. 331-336 (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga2O3 RRAM

AU - Morsali, Mehrdad

AU - Tabrizchi, Sepehr

AU - Velpula, Ravi Teja

AU - Sankar Muthu, Mano Bala

AU - Trung Nguyen, Hieu Pham

AU - Imani, Mohsen

AU - Roohi, Arman

AU - Angizi, Shaahin

PY - 2024

Y1 - 2024

N2 - In this paper, a cost-effective Near-Sensor Processing (NSP) platform is developed based on an experimentally-measured TiTiN/Ga2O3/Ti/Pt Resistive Random Access Memory (RRAM) device that facilitates event detection for edge vision sensors without the requirement for power-intensive Analog-to-Digital Converters (ADCs). The platform is supported with a hardware-friendly background comparison technique providing adjustable precision that allows for a dynamic balance between accuracy and efficiency at runtime. Our device-to-architecture simulation results demonstrate that the proposed platform achieves on average 66% and 63% energy saving over STT-MRAM and SOT-MRAM counterparts due to utilizing the ADC-less method.

AB - In this paper, a cost-effective Near-Sensor Processing (NSP) platform is developed based on an experimentally-measured TiTiN/Ga2O3/Ti/Pt Resistive Random Access Memory (RRAM) device that facilitates event detection for edge vision sensors without the requirement for power-intensive Analog-to-Digital Converters (ADCs). The platform is supported with a hardware-friendly background comparison technique providing adjustable precision that allows for a dynamic balance between accuracy and efficiency at runtime. Our device-to-architecture simulation results demonstrate that the proposed platform achieves on average 66% and 63% energy saving over STT-MRAM and SOT-MRAM counterparts due to utilizing the ADC-less method.

UR - https://www.scopus.com/pages/publications/85206166131

UR - https://www.scopus.com/inward/citedby.url?scp=85206166131&partnerID=8YFLogxK

U2 - 10.1109/ISVLSI61997.2024.00067

DO - 10.1109/ISVLSI61997.2024.00067

M3 - Conference contribution

AN - SCOPUS:85206166131

T3 - Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI

SP - 331

EP - 336

BT - 2024 IEEE Computer Society Annual Symposium on VLSI

A2 - Thapliyal, Himanshu

A2 - Becker, Jurgen

PB - IEEE Computer Society

T2 - 2024 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2024

Y2 - 1 July 2024 through 3 July 2024

ER -

Morsali M, Tabrizchi S, Velpula RT, Sankar Muthu MB, Trung Nguyen HP, Imani M et al. Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga₂O₃ RRAM. In Thapliyal H, Becker J, editors, 2024 IEEE Computer Society Annual Symposium on VLSI: Emerging VLSI Technologies and Architectures, ISVLSI 2024. IEEE Computer Society. 2024. p. 331-336. (Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI). doi: 10.1109/ISVLSI61997.2024.00067