A Pipelined Memristive Neural Network Analog-to-Digital Converter

TL;DR

This paper introduces a scalable, pipelined memristive neural network ADC architecture that enhances resolution and throughput while maintaining low power and noise tolerance, advancing neuromorphic data conversion technology.

Contribution

It proposes a modular pipeline design for memristive neural network ADCs that scales beyond four bits, improving resolution and performance in neuromorphic converters.

Findings

Achieves 8-bit resolution with 0.18 LSB INL and 0.20 LSB DNL

Attains 7.6 ENOB and 0.97 fJ/conv FOM

Demonstrates scalability and high performance in SPICE simulations

Abstract

With the advent of high-speed, high-precision, and low-power mixed-signal systems, there is an ever-growing demand for accurate, fast, and energy-efficient analog-to-digital (ADCs) and digital-to-analog converters (DACs). Unfortunately, with the downscaling of CMOS technology, modern ADCs trade off speed, power and accuracy. Recently, memristive neuromorphic architectures of four-bit ADC/DAC have been proposed. Such converters can be trained in real-time using machine learning algorithms, to break through the speedpower-accuracy trade-off while optimizing the conversion performance for different applications. However, scaling such architectures above four bits is challenging. This paper proposes a scalable and modular neural network ADC architecture based on a pipeline of four-bit converters, preserving their inherent advantages in application reconfiguration, mismatch selfcalibration, noise tolerance, and power optimization, while approaching higher resolution and throughput in penalty of latency. SPICE evaluation shows that an 8-bit pipelined ADC achieves 0.18 LSB INL, 0.20 LSB DNL, 7.6 ENOB, and 0.97 fJ/conv FOM. This work presents a significant step towards the realization of large-scale neuromorphic data converters.