OpenROAD and CircuitOps: Infrastructure for ML EDA Research and Education

Vidya A. Chhabria, Wenjing Jiang, Andrew B. Kahng, Rongjian Liang, Haoxing Ren, Sachin S. Sapatnekar, Bing Yue Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Traditional electronic design automation (EDA) techniques struggle to fulfill the stringent efficiency and quick turnaround demands of complex integrated systems. Machine learning (ML) strategies for EDA ('ML EDA') are pivotal in transforming EDA to address these challenges. However, they encounter significant obstacles due to inadequate infrastructure, ranging from datasets to software interfaces. This paper demonstrates a software infrastructure for ML EDA built on two key technologies: (i) OpenROAD's Python APIs, and (ii) NVIDIA's CircuitOps, an EDA data representation format tailored for ML, facilitating ML EDA applications. The paper illustrates three ML EDA examples that utilize the established OpenROAD and CircuitOps infrastructure.

Original languageEnglish (US)
Title of host publicationProceedings - 2024 IEEE 42nd VLSI Test Symposium, VTS 2024
PublisherIEEE Computer Society
ISBN (Electronic)9798350363784
StatePublished - 2024
Event42nd IEEE VLSI Test Symposium, VTS 2024 - Tempe, United States
Duration: Apr 22 2024Apr 24 2024

Publication series

NameProceedings of the IEEE VLSI Test Symposium
ISSN (Electronic)2375-1053


Conference42nd IEEE VLSI Test Symposium, VTS 2024
Country/TerritoryUnited States

Bibliographical note

Publisher Copyright:
© 2024 IEEE.


Dive into the research topics of 'OpenROAD and CircuitOps: Infrastructure for ML EDA Research and Education'. Together they form a unique fingerprint.

Cite this