Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks

TL;DR

This paper addresses the challenge of parasitic resistances in resistive crossbar circuits used for CNNs, proposing a new mapping scheme and mitigation algorithm to preserve accuracy in large-scale implementations.

Contribution

It introduces a novel mitigation algorithm and a high-utilization mapping scheme for resistive crossbar CNNs, effectively reducing parasitic effects and maintaining accuracy.

Findings

Mitigation algorithm reduces errors caused by parasitic resistances.

Proposed methods maintain CNN accuracy comparable to software implementations.

Effective on large-scale CNNs like ResNet on CIFAR-10.

Abstract

Traditional computing hardware often encounters on-chip memory bottleneck on large scale Convolution Neural Networks (CNN) applications. With its unique in-memory computing feature, resistive crossbar-based computing attracts researchers' attention as a promising solution to the memory bottleneck issue in von Neumann architectures. However, the parasitic resistances in the crossbar deviate its behavior from the ideal weighted summation operation. In large-scale implementations, the impact of parasitic resistances must be carefully considered and mitigated to ensure circuits' functionality. In this work, we implemented and simulated CNNs on resistive crossbar circuits with consideration of parasitic resistances. Moreover, we carried out a new mapping scheme for high utilization of crossbar arrays on convolution, and a mitigation algorithm to mitigate parasitic resistances in CNN applications. The mitigation algorithm considers parasitic resistances as well as data/kernel patterns of each layer to minimize the computing error in crossbar-based convolutions of CNNs. We demonstrated the proposed methods with implementations of a 4-layer CNN on MNIST and ResNet(20, 32, and 56) on CIFAR-10. Simulation results show the proposed methods well mitigate the parasitic resistances in crossbars. With our methods, modern CNNs on crossbars can preserve ideal(software) level classification accuracy with 6-bit ADCs and DACs implementation.