Enhanced Read Resolution in Reconfigurable Memristive Synapses for Spiking Neural Networks

TL;DR

This paper proposes methods to significantly improve the read resolution of memristive synapses in neuromorphic systems, enhancing reliability and classification accuracy by device scaling and adaptive techniques like voltage scaling and body biasing.

Contribution

It introduces a step-by-step analysis and techniques to enhance read current resolution in memristive synapses, including device scaling and adaptive methods, validated on a neuromorphic framework.

Findings

Device scaling improves read margin by up to 4.3x.

Read voltage scaling enhances resolution by about 46%.

Higher read resolution leads to better classification accuracy.

Abstract

Synapse is a key element of any neuromorphic computing system which is mostly constructed with memristor devices. A memristor is a two-terminal analog memory device. Memristive synapse suffers from various challenges such as forming at high voltage, SET, RESET failure, and READ margin or resolution issue between two weights. Enhanced READ resolution is very important to make a memristive synapse functionally reliable. Usually, the READ resolution is very small for a memristive synapse with 4-bit data precision. This work considers a step-by-step analysis to enhance the READ current resolution for a current-controlled memristor-based synapse. An empirical model is used to characterize the HfO2-based memristive device. 1st and 2nd stage device of our proposed synapse can be scaled to enhance the READ current margin up to ~ 4.3x and ~ 21% respectively. Moreover, READ current resolution can be enhanced with run-time adaptation features such as READ voltage scaling and body biasing. The READ voltage scaling and body biasing can improve the READ current resolution by about 46% and 15% respectively. TENNLabs' neuromorphic computing framework is leveraged to evaluate the effect of READ current resolution on classification applications. Higher READ current resolution shows better accuracy than lower resolution with different percentages of read noise scenarios.