Ultra Low Power Associative Computing with Spin Neurons and Resistive Crossbar Memory

TL;DR

This paper introduces a low-power, spin-neuron based associative memory system utilizing resistive crossbar memory for face recognition, achieving significant energy efficiency improvements over traditional CMOS circuits.

Contribution

It proposes a novel spin-neuron based analog associative memory design that drastically reduces power consumption in RCM-based pattern matching.

Findings

Achieves ~100x lower power than conventional analog circuits.

Enhances energy efficiency by ~1000x compared to 45nm CMOS digital ASIC.

Demonstrates effective face recognition with ultra low-power hardware.

Abstract

Emerging resistive-crossbar memory (RCM) technology can be promising for computationally-expensive analog pattern-matching tasks. However, the use of CMOS analog-circuits with RCM would result in large power-consumption and poor scalability, thereby eschewing the benefits of RCM-based computation. We propose the use of low-voltage, fast-switching, magneto-metallic spin-neurons for ultra low-power non-Boolean computing with RCM. We present the design of analog associative memory for face recognition using RCM, where, substituting conventional analog circuits with spin-neurons can achieve ~100x lower power. This makes the proposed design ~1000x more energy-efficient than a 45nm-CMOS digital ASIC, thereby significantly enhancing the prospects of RCM based computational hardware.