Aug 2026· Midwest Symposium on Circuits and Systems· pp. 972-976· 0 citations· 23 references
Abstract
Neuromorphic computing has made significant strides over the past few years by mapping functional primitives of neurons and synapses to nanoelectronic devices, yet most implementations do not tap into the temporal non-linear dynamics of the devices. We argue that spintronic devices, specifically magnetic tunnel junctions (MTJs), offer a palette of intrinsic physical phenomena that can serve as native computational primitives. Spin-transfer torque (STT), spin-orbit torque (SOT), voltage-controlled magnetic anisotropy (VCMA), magnetoelectric effect (ME) and stochastic superparamagnetic dynamics each enable functionalities difficult to replicate in deterministic CMOS. We underscore this perspective through two specific systemlevel instances focusing on the synapse and neuron: selectorless synaptic crossbar arrays that exploit a VCMA-driven switchingmechanism to eliminate per-cell selectors, and temporal information encoding through superparamagnetic neuronal MTJs that achieves significant network-level spiking sparsity via stochastic dynamics. Building on these exemplars, we envision how these primitives compose with the broader spintronic ecosystem — domain-wall synapses, oscillatory primitives, and stochastic neurons — toward neuromorphic systems that are simultaneously sparser, denser, and more functionally diverse.
Artificial intelligence applications require energy-efficient computing architectures beyond conventional von Neumann systems. Neuromorphic computing (NC) has emerged as a promising alternative, where spintronic domain wall (DW) devices are particularly attractive owing to their low-energy operation, non-volatility, an...
Hasibur Rahaman, Durgesh Kumar, R. Maddu et al.· ACS Applied Materials and In...· 0 citations
The explosive growth of artificial intelligence (AI), edge computing, and brain-inspired algorithms has spurred the development of neuromorphic systems that mimic biological information processing. Achieving such functionality at the hardware level requires materials that exhibit neuron- and synapse-like behaviors in a...
Abdullah Marzouq Alharbi· International Journal of Mod...· 0 citations
The escalating energy demands of modern artificial intelligence have exposed fundamental limitations in conventional computing architectures. Neuromorphic computing, which seeks to emulate the brain’s massively parallel and energy-efficient information processing, offers a compelling alternative, but its realization re...
J. Ram'irez, Pedro Prieto, M. Gómez et al.· Revista de la Academia Colom...· 0 citations
The development of energy-efficient neuromorphic computing (NC) hardware has stimulated growing interest in spintronic platforms capable of emulating the functionality of biological neural networks. In this context, magnetic skyrmioniums have emerged as attractive candidates because they combine a negligible skyrmion H...
Inspired by modern artificial intelligence paradigms based on adaptive multi-level resistive synaptic weights, engineering multi-resistive states via spin-dependent quantum transport offers a viable route toward integrated memory–computation architectures. multilevel resistive nanochip integrated with spin-dependent qu...
This review surveys recent advances in vdW spintronics toward neuromorphic computing and reviews prototype applications of spintronics for in‑memory and in‑sensor computing, highlighting the potential of vdW spintronics as a platform for neuromorphic computing.
Yuan-He Li, Jinli Chen, Pei Liu et al.· Advanced Functional Material...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.