Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI

TL;DR

Pieceformer is a scalable, self-supervised graph similarity framework for VLSI design that improves accuracy and efficiency in knowledge transfer, enabling better reuse of design solutions and reducing engineering effort.

Contribution

It introduces a hybrid message-passing and graph transformer model with a linear backbone and partitioned training for scalable, accurate similarity assessment in VLSI design.

Findings

Reduces MAE by 24.9% over baseline

Correctly clusters all real-world design groups

Achieves up to 89% runtime reduction in partitioning task

Abstract

Accurate graph similarity is critical for knowledge transfer in VLSI design, enabling the reuse of prior solutions to reduce engineering effort and turnaround time. We propose Pieceformer, a scalable, self-supervised similarity assessment framework, equipped with a hybrid message-passing and graph transformer encoder. To address transformer scalability, we incorporate a linear transformer backbone and introduce a partitioned training pipeline for efficient memory and parallelism management. Evaluations on synthetic and real-world CircuitNet datasets show that Pieceformer reduces mean absolute error (MAE) by 24.9% over the baseline and is the only method to correctly cluster all real-world design groups. We further demonstrate the practical usage of our model through a case study on a partitioning task, achieving up to 89% runtime reduction. These results validate the framework's effectiveness for scalable, unbiased design reuse in modern VLSI systems.