DeepCell: Multiview Representation Learning for Post-Mapping Netlists

2025-02-05

AI Summary

This work addresses the challenge of post-mapping (PM) netlist representation learning in electronic design automation (EDA), where existing methods—largely confined to AIG-based intermediate representations—struggle to generalize to post-synthesis stages. We propose a multi-level joint representation framework that unifies PM netlists and AIGs via dual-view modeling. Our method introduces Masked Circuit Modeling (MCM), a novel self-supervised pretraining mechanism integrated with a pretrained AIG encoder, enabling the first-ever structural–functional co-learning across representation levels. Built upon graph neural networks and multi-view representation fusion, our approach significantly outperforms state-of-the-art methods in both prediction accuracy and reconstruction fidelity. In functional engineering change order (ECO) scenarios, it substantially reduces patch generation cost and runtime while improving patch quality.

Technology Category

• Machine Learning: Representation Learning
• Computer Vision: Representation Learning for Vision
• Multiagent Systems: Multiagent Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Representation learning for post-mapping (PM) netlists is a critical challenge in Electronic Design Automation (EDA), driven by the diverse and complex nature of modern circuit designs. Existing approaches focus on intermediate representations like And-Inverter Graphs (AIGs), limiting their applicability to post-synthesis stages. We introduce DeepCell, a multiview representation learning framework that integrates structural and functional insights from both PM netlists and AIGs to learn rich, generalizable embeddings. At its core, DeepCell employs the novel Mask Circuit Modeling (MCM) mechanism, which refines PM netlist representations in a self-supervised manner using pretrained AIG encoders. DeepCell sets a new benchmark in PM netlist representation, outperforming existing methods in predictive accuracy and reconstruction fidelity. To validate its efficacy, we apply DeepCell to functional Engineering Change Orders (ECO), achieving significant reductions in patch generation costs and runtime while improving patch quality.

Problem

• Multiview representation learning for PM netlists
• Integrates structural and functional insights
• Reduces patch generation costs and runtime

Innovation

• Multiview representation learning framework
• Mask Circuit Modeling mechanism
• Self-supervised learning with pretrained encoders