Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga2O3 RRAM
Document Type
Conference Proceeding
Publication Date
1-1-2024
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.
Identifier
85206166131 (Scopus)
ISBN
[9798350354119]
Publication Title
Proceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
External Full Text Location
https://doi.org/10.1109/ISVLSI61997.2024.00067
e-ISSN
21593477
ISSN
21593469
First Page
331
Last Page
336
Grant
2228028
Fund Ref
Semiconductor Research Corporation
Recommended Citation
Morsali, Mehrdad; Tabrizchi, Sepehr; Velpula, Ravi Teja; Sankar Muthu, Mano Bala; Trung Nguyen, Hieu Pham; Imani, Mohsen; Roohi, Arman; and Angizi, Shaahin, "Energy-Efficient Near-Sensor Event Detector Based on Multilevel Ga2O3 RRAM" (2024). Faculty Publications. 852.
https://digitalcommons.njit.edu/fac_pubs/852
