DiffuSE: Cross-Layer Design Space Exploration of DNN Accelerator via Diffusion-Driven Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908291997630464 |
|---|---|
| author | Ren, Yi Xue, Chenhao Zhang, Jiaxing Zhang, Chen Xu, Qiang Lin, Yibo Zhang, Lining Sun, Guangyu |
| author_facet | Ren, Yi Xue, Chenhao Zhang, Jiaxing Zhang, Chen Xu, Qiang Lin, Yibo Zhang, Lining Sun, Guangyu |
| contents | The proliferation of deep learning accelerators calls for efficient and cost-effective hardware design solutions, where parameterized modular hardware generator and electronic design automation (EDA) tools play crucial roles in improving productivity and final Quality-of-Results (QoR). To strike a good balance across multiple QoR of interest (e.g., performance, power, and area), the designers need to navigate a vast design space, encompassing tunable parameters for both hardware generator and EDA synthesis tools. However, the significant time for EDA tool invocations and complex interplay among numerous design parameters make this task extremely challenging, even for experienced designers. To address these challenges, we introduce DiffuSE, a diffusion-driven design space exploration framework for cross-layer optimization of DNN accelerators. DiffuSE leverages conditional diffusion models to capture the inverse, one-to-many mapping from QoR objectives to parameter combinations, allowing for targeted exploration within promising regions of the design space. By carefully selecting the conditioning QoR values, the framework facilitates an effective trade-off among multiple QoR metrics in a sample-efficient manner. Experimental results under 7nm technology demonstrate the superiority of the proposed framework compared to previous arts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23945 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffuSE: Cross-Layer Design Space Exploration of DNN Accelerator via Diffusion-Driven Optimization Ren, Yi Xue, Chenhao Zhang, Jiaxing Zhang, Chen Xu, Qiang Lin, Yibo Zhang, Lining Sun, Guangyu Hardware Architecture The proliferation of deep learning accelerators calls for efficient and cost-effective hardware design solutions, where parameterized modular hardware generator and electronic design automation (EDA) tools play crucial roles in improving productivity and final Quality-of-Results (QoR). To strike a good balance across multiple QoR of interest (e.g., performance, power, and area), the designers need to navigate a vast design space, encompassing tunable parameters for both hardware generator and EDA synthesis tools. However, the significant time for EDA tool invocations and complex interplay among numerous design parameters make this task extremely challenging, even for experienced designers. To address these challenges, we introduce DiffuSE, a diffusion-driven design space exploration framework for cross-layer optimization of DNN accelerators. DiffuSE leverages conditional diffusion models to capture the inverse, one-to-many mapping from QoR objectives to parameter combinations, allowing for targeted exploration within promising regions of the design space. By carefully selecting the conditioning QoR values, the framework facilitates an effective trade-off among multiple QoR metrics in a sample-efficient manner. Experimental results under 7nm technology demonstrate the superiority of the proposed framework compared to previous arts. |
| title | DiffuSE: Cross-Layer Design Space Exploration of DNN Accelerator via Diffusion-Driven Optimization |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2503.23945 |