Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.13582 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910026372743168 |
|---|---|
| author | Kang, Andrew B. Kahng. Seokhyeong Park, Seonghyeon Yoon, Dooseok |
| author_facet | Kang, Andrew B. Kahng. Seokhyeong Park, Seonghyeon Yoon, Dooseok |
| contents | In advanced nodes, optimization of power, performance and area (PPA) has become highly complex and challenging. Machine learning (ML) and design-technology co-optimization (DTCO) provide promising mitigations, but face limitations due to a lack of diverse training data as well as long design flow turnaround times (TAT). We propose ArtNet, a novel artificial netlist generator designed to tackle these issues. Unlike previous methods, ArtNet replicates key topological characteristics, enhancing ML model generalization and supporting broader design space exploration for DTCO. By producing realistic artificial datasets that moreclosely match given target parameters, ArtNet enables more efficient PPAoptimization and exploration of flows and design enablements. In the context of CNN-based DRV prediction, ArtNet's data augmentationimproves F1 score by 0.16 compared to using only the original (real) dataset. In the DTCO context, ArtNet-generated mini-brains achieve a PPA match up to 97.94%, demonstrating close alignment with design metrics of targeted full-scale block designs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13582 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ArtNet: Hierarchical Clustering-Based Artificial Netlist Generator for ML and DTCO Application Kang, Andrew B. Kahng. Seokhyeong Park, Seonghyeon Yoon, Dooseok Machine Learning Hardware Architecture In advanced nodes, optimization of power, performance and area (PPA) has become highly complex and challenging. Machine learning (ML) and design-technology co-optimization (DTCO) provide promising mitigations, but face limitations due to a lack of diverse training data as well as long design flow turnaround times (TAT). We propose ArtNet, a novel artificial netlist generator designed to tackle these issues. Unlike previous methods, ArtNet replicates key topological characteristics, enhancing ML model generalization and supporting broader design space exploration for DTCO. By producing realistic artificial datasets that moreclosely match given target parameters, ArtNet enables more efficient PPAoptimization and exploration of flows and design enablements. In the context of CNN-based DRV prediction, ArtNet's data augmentationimproves F1 score by 0.16 compared to using only the original (real) dataset. In the DTCO context, ArtNet-generated mini-brains achieve a PPA match up to 97.94%, demonstrating close alignment with design metrics of targeted full-scale block designs. |
| title | ArtNet: Hierarchical Clustering-Based Artificial Netlist Generator for ML and DTCO Application |
| topic | Machine Learning Hardware Architecture |
| url | https://arxiv.org/abs/2510.13582 |