CircuitNet: An Open-Source Dataset for Machine Learning Applications in Electronic Design Automation (EDA)

TL;DR

CircuitNet is the first large-scale open-source dataset designed for machine learning applications in VLSI CAD, enabling more effective data-driven research in electronic design automation.

Contribution

This paper introduces CircuitNet, the first publicly available large dataset for ML in VLSI CAD, facilitating broader research and development in EDA.

Findings

Provides a comprehensive dataset for ML in VLSI CAD

Enables new research directions in EDA with data-driven methods

Supports cross-stage prediction tasks in VLSI design

Abstract

The electronic design automation (EDA) community has been actively exploring machine learning (ML) for very large-scale integrated computer-aided design (VLSI CAD). Many studies explored learning-based techniques for cross-stage prediction tasks in the design flow to achieve faster design convergence. Although building ML models usually requires a large amount of data, most studies can only generate small internal datasets for validation because of the lack of large public datasets. In this essay, we present the first open-source dataset called CircuitNet for ML tasks in VLSI CAD.