DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908648821751808 |
|---|---|
| author | Ma, Ruiyang Zhou, Yunhao Wang, Yipeng Liu, Yi Shi, Zhengyuan Zheng, Ziyang Chen, Kexin He, Zhiqiang Yan, Lingwei Chen, Gang Xu, Qiang Luo, Guojie |
| author_facet | Ma, Ruiyang Zhou, Yunhao Wang, Yipeng Liu, Yi Shi, Zhengyuan Zheng, Ziyang Chen, Kexin He, Zhiqiang Yan, Lingwei Chen, Gang Xu, Qiang Luo, Guojie |
| contents | There is a growing body of work on using Graph Neural Networks (GNNs) to learn representations of circuits, focusing primarily on their static characteristics. However, these models fail to capture circuit runtime behavior, which is crucial for tasks like circuit verification and optimization. To address this limitation, we introduce DR-GNN (DynamicRTL-GNN), a novel approach that learns RTL circuit representations by incorporating both static structures and multi-cycle execution behaviors. DR-GNN leverages an operator-level Control Data Flow Graph (CDFG) to represent Register Transfer Level (RTL) circuits, enabling the model to capture dynamic dependencies and runtime execution. To train and evaluate DR-GNN, we build the first comprehensive dynamic circuit dataset, comprising over 6,300 Verilog designs and 63,000 simulation traces. Our results demonstrate that DR-GNN outperforms existing models in branch hit prediction and toggle rate prediction. Furthermore, its learned representations transfer effectively to related dynamic circuit tasks, achieving strong performance in power estimation and assertion prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09593 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior Ma, Ruiyang Zhou, Yunhao Wang, Yipeng Liu, Yi Shi, Zhengyuan Zheng, Ziyang Chen, Kexin He, Zhiqiang Yan, Lingwei Chen, Gang Xu, Qiang Luo, Guojie Machine Learning There is a growing body of work on using Graph Neural Networks (GNNs) to learn representations of circuits, focusing primarily on their static characteristics. However, these models fail to capture circuit runtime behavior, which is crucial for tasks like circuit verification and optimization. To address this limitation, we introduce DR-GNN (DynamicRTL-GNN), a novel approach that learns RTL circuit representations by incorporating both static structures and multi-cycle execution behaviors. DR-GNN leverages an operator-level Control Data Flow Graph (CDFG) to represent Register Transfer Level (RTL) circuits, enabling the model to capture dynamic dependencies and runtime execution. To train and evaluate DR-GNN, we build the first comprehensive dynamic circuit dataset, comprising over 6,300 Verilog designs and 63,000 simulation traces. Our results demonstrate that DR-GNN outperforms existing models in branch hit prediction and toggle rate prediction. Furthermore, its learned representations transfer effectively to related dynamic circuit tasks, achieving strong performance in power estimation and assertion prediction. |
| title | DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.09593 |