A Proposal for Energy-Efficient Cellular Neural Network based on Spintronic Devices

TL;DR

This paper proposes a hybrid spintronic-CMOS cellular neural network design that significantly reduces energy consumption while maintaining performance, leveraging magnetic components for improved efficiency.

Contribution

It introduces a novel hybrid structure with digitally programmable magnetic synapses, enabling energy-efficient CNN implementation with optimized parameters.

Findings

Over an order of magnitude energy reduction compared to CMOS CNNs.

Achieves optimal energy efficiency through parameter tuning.

Maintains comparable footprint and speed with enhanced energy performance.

Abstract

Due to the massive parallel computing capability and outstanding image and signal processing performance, cellular neural network (CNN) is one promising type of non-Boolean computing system that can outperform the traditional digital logic computation and mitigate the physical scaling limit of the conventional CMOS technology. The CNN was originally implemented by VLSI analog technologies with operational amplifiers and operational transconductance amplifiers as neurons and synapses, respectively, which are power and area consuming. In this paper, we propose a hybrid structure to implement the CNN with magnetic components and CMOS peripherals with a complete driving and sensing circuitry. In addition, we propose a digitally programmable magnetic synapse that can achieve both positive and negative values of the templates. After rigorous performance analyses and comparisons, optimal energy is achieved based on various design parameters, including the driving voltage and the CMOS driving size. At a comparable footprint area and operation speed, a spintronic CNN is projected to achieve more than one order of magnitude energy reduction per operation compared to its CMOS counterpart.