Investigating the impact of BTI, HCI and time-zero variability on neuromorphic spike event generation circuits

TL;DR

This paper examines how reliability issues like BTI, HCI, and time-zero variability affect the performance of CMOS-based neuromorphic spike generation circuits, using simulations and industry-standard tools.

Contribution

It provides a detailed analysis of reliability challenges in neuromorphic circuits and evaluates their impact using 45nm technology and Monte Carlo simulations.

Findings

BTI and HCI significantly affect circuit reliability.

Time-zero variability causes notable performance variations.

Analysis guides design improvements for neuromorphic circuits.

Abstract

Neuromorphic computing refers to brain-inspired computers, that differentiate it from von Neumann architecture. Analog VLSI based neuromorphic circuits is a current research interest. Two simpler spiking integrate and fire neuron model namely axon-Hillock (AH) and voltage integrate, and fire (VIF) circuits are commonly used for generating spike events. This paper discusses the impact of reliability issues like Bias Temperature instability (BTI) and Hot Carrier Injection (HCI), and timezero variability on these CMOS based neuromorphic circuits. AH and VIF circuits are implemented using HKMG based 45nm technology. For reliability analysis, industry standard Cadence RelXpert tool is used. For time-zero variability analysis, 1000 Monte-Carlo simulations are performed.