Magnetic domain wall based synaptic and activation function generator for neuromorphic accelerators

TL;DR

This paper demonstrates magnetic domain wall devices capable of implementing programmable linear and nonlinear functions for neuromorphic accelerators, offering fast, energy-efficient synaptic and activation functions with potential biological energy efficiency.

Contribution

It introduces magnetic domain wall-based devices for neuromorphic computing, capable of both linear and nonlinear function implementation, with promising speed and energy efficiency advantages.

Findings

Prototype devices operate with 8 ns pulses

Energy consumption for weight modulation is less than 16 pJ

Comparable speed and energy efficiency to biological neurons

Abstract

Magnetic domain walls are information tokens in both logic and memory devices, and hold particular interest in applications such as neuromorphic accelerators that combine logic in memory. Here, we show that devices based on the electrical manipulation of magnetic domain walls are capable of implementing linear, as well as programmable nonlinear, functions. Unlike other approaches, domain-wall-based devices are ideal for application to both synaptic weight generators and thresholding in deep neural networks. Prototype micrometer-size devices operate with 8 ns current pulses and the energy consumption required for weight modulation is < 16 pJ. Both speed and energy consumption compare favorably to other synaptic nonvolatile devices, with the expected energy dissipation for scaled 20 nm devices close to that of biological neurons.