VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913916430319616 |
|---|---|
| author | Hemadri, Raghu Vamshi Bhandari, Jitendra Nakkab, Andre Knechtel, Johann Gopalan, Badri P Narayanaswamy, Ramesh Karri, Ramesh Garg, Siddharth |
| author_facet | Hemadri, Raghu Vamshi Bhandari, Jitendra Nakkab, Andre Knechtel, Johann Gopalan, Badri P Narayanaswamy, Ramesh Karri, Ramesh Garg, Siddharth |
| contents | Modern chip design is complex, and there is a crucial need for early-stage prediction of key design-quality metrics like timing and routing congestion directly from Verilog code (a commonly used programming language for hardware design). It is especially important yet complex to predict individual lines of code that cause timing violations or downstream routing congestion. Prior works have tried approaches like converting Verilog into an intermediate graph representation and using LLM embeddings alongside other features to predict module-level quality, but did not consider line-level quality prediction. We propose VeriLoC, the first method that predicts design quality directly from Verilog at both the line- and module-level. To this end, VeriLoC leverages recent Verilog code-generation LLMs to extract local line-level and module-level embeddings, and train downstream classifiers/regressors on concatenations of these embeddings. VeriLoC achieves high F1-scores of 0.86-0.95 for line-level congestion and timing prediction, and reduces the mean average percentage error from 14% - 18% for SOTA methods down to only 4%. We believe that VeriLoC embeddings and insights from our work will also be of value for other predictive and optimization tasks for complex hardware design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07239 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code Hemadri, Raghu Vamshi Bhandari, Jitendra Nakkab, Andre Knechtel, Johann Gopalan, Badri P Narayanaswamy, Ramesh Karri, Ramesh Garg, Siddharth Hardware Architecture Artificial Intelligence Modern chip design is complex, and there is a crucial need for early-stage prediction of key design-quality metrics like timing and routing congestion directly from Verilog code (a commonly used programming language for hardware design). It is especially important yet complex to predict individual lines of code that cause timing violations or downstream routing congestion. Prior works have tried approaches like converting Verilog into an intermediate graph representation and using LLM embeddings alongside other features to predict module-level quality, but did not consider line-level quality prediction. We propose VeriLoC, the first method that predicts design quality directly from Verilog at both the line- and module-level. To this end, VeriLoC leverages recent Verilog code-generation LLMs to extract local line-level and module-level embeddings, and train downstream classifiers/regressors on concatenations of these embeddings. VeriLoC achieves high F1-scores of 0.86-0.95 for line-level congestion and timing prediction, and reduces the mean average percentage error from 14% - 18% for SOTA methods down to only 4%. We believe that VeriLoC embeddings and insights from our work will also be of value for other predictive and optimization tasks for complex hardware design. |
| title | VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code |
| topic | Hardware Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2506.07239 |