EDA-Schema-V2: A Multimodal Schema, Open Datasets, and Benchmarks for Machine Learning in Digital Physical Design

TL;DR

This paper introduces EDA-Schema-V2, a comprehensive multimodal dataset schema and open datasets for ML in digital physical design, enabling standardized benchmarking and reproducible research.

Contribution

It provides a new structured schema, generates extensive open datasets from multiple design stages, and establishes benchmarks for ML applications in electronic design automation.

Findings

Generated datasets include over 275 million gates and 75 million nets.

Stage-resolved representations enable analysis of predictability across design stages.

Baseline analyses support reproducibility and comparison of ML methods.

Abstract

The continuous scaling of CMOS technology has significantly increased the complexity of very large-scale integrated circuits, driving interest in applying machine learning (ML) to electronic design automation (EDA). However, the limited availability of open and standardized datasets limits interoperability, comparability, and reproducibility in ML-based research. This paper introduces EDA-Schema-V2, an open multimodal schema that provides a structured framework for representing and analyzing datasets in digital physical design. The schema includes representations of physical attributes and quality-of-results metrics across multiple stages of the design flow, including logic synthesis, floorplanning, placement, clock network synthesis, and routing. Utilizing the SkyWater 130nm, Nangate 45nm, IHP SG13G2 130nm, and ASAP 7nm open-source process design kits with the OpenROAD tool flow, datasets of physical circuit designs from the IWLS'05 benchmark suite are generated and analyzed. The dataset comprises 7,776 design instances spanning 18 benchmark circuits and includes stage-resolved representations from synthesis through detailed routing, generated through parameter sweeps over clock period, core utilization, and aspect ratio. The dataset contains over 275 million gates, 75 million nets, and more than 36 million extracted timing paths. In addition, twelve representative prediction tasks spanning timing, power, area, and routing metrics are identified, along with baseline analyses that characterize stage-to-stage predictability across the design flow. The resulting datasets and baselines are publicly released to support reproducible ML research and establish standardized benchmarks for evaluating ML-based approaches in digital physical design.