Abstract
Routing is a crucial but complex stage in physical synthesis, where detailed routing (DR) is further known as the bottleneck for accelerating design cycles and improving circuit quality. Its difficulty lies mainly in the need to well organize numerous nets under various design rule constraints, leading to time-consuming iterative processes, e.g., rip-up and reroute (RRR), to achieve a convergent state. In this paper, we pioneer a new approach to assist DR with detailed AI guidance, where all nets are co-planned in advance to provide respective route guides to regulate the corresponding maze routing process. The proposed framework named Dr. Guide can be used as a flexible plug-in to existing routers and enjoys good interpretability. Incorporating it with one SOTA academic detailed router reveals its effectiveness and potential in accelerating/improving the DR process.
| Original language | English |
|---|---|
| Title of host publication | 2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD) |
| Place of Publication | California |
| Publisher | IEEE |
| Number of pages | 7 |
| ISBN (Electronic) | 9798331537623 |
| ISBN (Print) | 9798331537630 |
| DOIs | |
| Publication status | Published - 10 Sept 2025 |
| Event | 2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD) - Chaminade Resort, Santa Cruz, United States Duration: 8 Sept 2025 → 10 Sept 2025 https://mlcad.org/symposium/2025/ (Conference website) https://mlcad.org/symposium/2025/program/ (Conference program) https://ieeexplore.ieee.org/xpl/conhome/11189084/proceeding (Conference proceeding) |
Publication series
| Name | ACM/IEEE Symposium on Machine Learning for CAD (MLCAD) |
|---|---|
| Publisher | IEEE |
Conference
| Conference | 2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD) |
|---|---|
| Abbreviated title | MLCAD 2025 |
| Country/Territory | United States |
| City | Santa Cruz |
| Period | 8/09/25 → 10/09/25 |
| Other | The symposium focuses on Machine Learning (ML) applications to all aspects of CAD for electronic circuits, chips and systems. It is sponsored by IEEE CEDA (Council on Electronic Design Automation) and ACM SIGDA (Special Interest Group on Design Automation). MLCAD 2025 will start with the welcome reception in the evening of September 7, 2025. Papers and presentations should cover one or more aspects of applying machine learning and AI to enhance CAD of chip designs. Such aspects include, but are not limited to, algorithms, software, models, example applications, benchmarking, and innovative solutions such as Large Language Models for CAD. |
| Internet address |
|
User-Defined Keywords
- AI
- generative model
- physical design
- routing
