Magnetic skyrmion-domain wall hybrid based synapse and ReLU-maxpooling function for convolutional neural network

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 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 and long-term depression operations. Furthermore, we present a simultaneous rectified linear (ReLU) activation and Max Pooling circuitry featuring a self-reset spin–orbit torque-based domain wall ReLU with an energy consumption of 9.16 fJ. 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 a CNN-based pattern recognition task, consuming 0.21 nJ per image.