Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.15907 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913901071826944 |
|---|---|
| author | Yang, Hang Hu, Yusheng Liu, Yong Cong Hao |
| author_facet | Yang, Hang Hu, Yusheng Liu, Yong Cong Hao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15907 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI Yang, Hang Hu, Yusheng Liu, Yong Cong Hao Machine Learning Systems and Control 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. |
| title | Pieceformer: Similarity-Driven Knowledge Transfer via Scalable Graph Transformer in VLSI |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2506.15907 |