Voltage-Controlled Domain Wall Motion-Based Neuron and Stochastic Magnetic Tunnel Junction Synapse for Neuromorphic Computing Applications

Aijaz H. Lone,H. Fariborzi,S. Amara

doi:10.1109/jxcdc.2021.3138038

Abstract

This work discusses the proposal of a spintronic neuromorphic system with spin orbit torque-driven domain wall motion (DWM)-based neurons and synapses. We propose a voltage-controlled magnetic anisotropy DWM-based magnetic tunnel junction (MTJ) neuron. We investigate how the electric field at the gate (pinning site), generated by the voltage signals from pre-neurons, modulates the DWM, which reflects in the nonlinear switching behavior of neuron magnetization. For the implementation of synaptic weights, we propose a 3-terminal MTJ with stochastic DWM in the free layer. We incorporate intrinsic pinning effects by creating triangular notches on the sides of the free layer. The pinning of the domain wall and intrinsic thermal noise of the device lead to the stochastic behavior of DWM. The control of this stochasticity by the spin orbit torque is shown to realize the potentiation and depression of the synaptic weight. The micromagnetics and spin transport studies in synapses and neurons are carried out by developing a coupled micromagnetic non-equilibrium Green’s function ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MuMag-NEGF</i> ) model. The minimization of the writing current pulsewidth by leveraging the thermal noise and demagnetization energy is also presented. Finally, we discuss the implementation of digit recognition by the proposed system using a spike time-dependent algorithm.

Highlights

THE highly energy efficient computational power of brain has inspired a paradigm shift in hardware implementation of computing systems [1][2]
The magnetic tunnel junctions (MTJ) with the domain wall motion-based magnetization switching of the free layer has been shown to provide multilevel weights for a spin-based neuron model [26]. These devices have been used for energy efficient implementation of the neuromorphic computing solutions such as spike time dependent plasticity STDP [27] and unsupervised spintronic clustering [28]
The combined neuromorphic unit consisting of domain wall motionbased synapse and nanomagnet neurons has shown 95% lower power consumption compared to CMOS counterparts [26]

Summary

INTRODUCTION

THE highly energy efficient computational power of brain has inspired a paradigm shift in hardware implementation of computing systems [1][2]. The MTJ with the domain wall motion-based magnetization switching of the free layer has been shown to provide multilevel weights for a spin-based neuron model [26]. These devices have been used for energy efficient implementation of the neuromorphic computing solutions such as spike time dependent plasticity STDP [27] and unsupervised spintronic clustering [28]. The present work discusses the proposal of a spintronic neuromorphic system with a spin orbit torque driven domain wall motion-based neuron and synapse. In presence of thermal noise and pinning, the DWM becomes stochastic but, by applying a proper number of positive and/or negative SOT pulses, the DW ends up either in right end with current in -x axis or it moves left in the presence of +x directed current pulses

VOLTAGE CONTROLLED NEURON AND STOCHASTIC SYNAPSE DEVICES

SYNAPSE AND NEURON MODELING

RESULTS AND DISCUSSION

NEUROMORPHIC CIRCUIT IMPLEMENTATION

CONCLUSION