DeepCell: Self-Supervised Multiview Fusion for Circuit Representation Learning

TL;DR

DeepCell is a self-supervised framework that fuses multiview circuit representations from AIGs and PM netlists, achieving superior accuracy and efficiency in EDA tasks like ECO and technology mapping.

Contribution

DeepCell introduces the first PM netlist representation learning framework using self-supervised Mask Circuit Modeling, setting new benchmarks in circuit embedding quality.

Findings

Outperforms existing tools in accuracy and efficiency

Effective multiview fusion improves circuit embeddings

Sets new standards in EDA predictive tasks

Abstract

We introduce DeepCell, a novel circuit representation learning framework that effectively integrates multiview information from both And-Inverter Graphs (AIGs) and Post-Mapping (PM) netlists. At its core, DeepCell employs a self-supervised Mask Circuit Modeling (MCM) strategy, inspired by masked language modeling, to fuse complementary circuit representations from different design stages into unified and rich embeddings. To our knowledge, DeepCell is the first framework explicitly designed for PM netlist representation learning, setting new benchmarks in both predictive accuracy and reconstruction quality. We demonstrate the practical efficacy of DeepCell by applying it to critical EDA tasks such as functional Engineering Change Orders (ECO) and technology mapping. Extensive experimental results show that DeepCell significantly surpasses state-of-the-art open-source EDA tools in efficiency and performance.