A Comprehensive Convolutional Neural Network Architecture Design using Magnetic Skyrmion and Domain Wall

TL;DR

This paper introduces a novel spintronic CNN hardware architecture utilizing skyrmions and domain walls, achieving high accuracy and ultra-low energy consumption for pattern recognition tasks.

Contribution

It presents the first integrated design of skyrmion-based synapses and domain wall circuits for CNNs, demonstrating scalable, energy-efficient neuromorphic hardware.

Findings

Achieved 6-bit skyrmion synapses with 0.87 fJ per update.

Implemented ReLU and max pooling with 4.73 μW power consumption.

Attained 98.07% accuracy in pattern recognition.

Abstract

Spintronic-based neuromorphic hardware offers high-density and rapid data processing at nanoscale lengths by leveraging magnetic configurations like skyrmion and domain walls. Here, we present the maximal hardware implementation of a convolutional neural network (CNN) based on a compact multi-bit skyrmion-based synapse and a hybrid CMOS domain wall-based circuit for activation and max-pooling functionalities. We demonstrate the micromagnetic design and operation of a circular bilayer skyrmion system mimicking a scalable artificial synapse, demonstrated up to 6-bit (64 states) with an ultra-low energy consumption of 0.87 fJ per state update. We further show that the synaptic weight modulation is achieved by the perpendicular current interaction with the labyrinth-maze like uniaxial anisotropy profile, inducing skyrmionic gyration, thereby enabling long-term potentiation (LTP) and long-term depression (LTD) operations. Furthermore, we present a simultaneous rectified linear (ReLU) activation and max pooling circuitry featuring a SOT-based domain wall ReLU with a power consumption of 4.73 $\mu$W. The ReLU function, stabilized by a parabolic uniaxial anisotropy profile, encodes domain wall positions into continuous resistance states coupled with the HSPICE circuit simulator. Our integrated skyrmion and domain wall-based spintronic hardware achieves 98.07% accuracy in convolutional neural network (CNN) based pattern recognition task, consuming 110 mW per image.