Abstract

The desire to empower resource-limited edge devices with computer vision (CV) must overcome the high energy consumption of collecting and processing vast sensory data. To address the challenge, this work proposes an energy-efficient non-von-Neumann in-pixel processing solution for neuromorphic vision sensors employing emerging (X) magnetic domain wall magnetic tunnel junction (MDWMTJ) for the first time, in conjunction with CMOS-based neuromorphic pixels. Our hybrid CMOS+ X approach performs in-situ massively parallel asynchronous analog convolution, exhibiting low power consumption and high accuracy across various CV applications by leveraging the non-volatility and programmability of the MDWMTJ. Moreover, our developed device-circuit-algorithm co-design framework captures device constraints (low tunnel-magnetoresistance, low dynamic range) and circuit constraints (non-linearity …

Metadata

publication

arXiv e-prints, arXiv: 2402.15121, 2024

year

2024

publication date

2024/2

authors

Md Abdullah-Al Kaiser, Gourav Datta, Peter A Beerel, Akhilesh R Jaiswal

link

https://ui.adsabs.harvard.edu/abs/2024arXiv240215121A/abstract

journal

arXiv e-prints

pages

arXiv: 2402.15121