Boolean-aware Boolean Circuit Classification: A Comprehensive Study on Graph Neural Network

TL;DR

This paper explores Boolean circuit classification using graph neural networks, focusing on the impact of structure and functionality, and introduces a new class of circuits with a comprehensive analysis of classification factors.

Contribution

It defines a new matching-equivalent class of Boolean circuits based on Boolean-aware properties and analyzes key factors affecting their classification with GNNs.

Findings

Empirical results verify the analysis of classification factors.

The study highlights opportunities for improving Boolean circuit classification.

Framework demonstrates the effectiveness of GNNs in this context.

Abstract

Boolean circuit is a computational graph that consists of the dynamic directed graph structure and static functionality. The commonly used logic optimization and Boolean matching-based transformation can change the behavior of the Boolean circuit for its graph structure and functionality in logic synthesis. The graph structure-based Boolean circuit classification can be grouped into the graph classification task, however, the functionality-based Boolean circuit classification remains an open problem for further research. In this paper, we first define the proposed matching-equivalent class based on its ``Boolean-aware'' property. The Boolean circuits in the proposed class can be transformed into each other. Then, we present a commonly study framework based on graph neural network~(GNN) to analyze the key factors that can affect the Boolean-aware Boolean circuit classification. The empirical experiment results verify the proposed analysis, and it also shows the direction and opportunity to improve the proposed problem. The code and dataset will be released after acceptance.