ADEPT-Z: Zero-Shot Automated Circuit Topology Search for Pareto-Optimal Photonic Tensor Cores
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929524020609024 |
|---|---|
| author | Jiang, Ziyang Ma, Pingchuan Zhang, Meng Huang, Rena Gu, Jiaqi |
| author_facet | Jiang, Ziyang Ma, Pingchuan Zhang, Meng Huang, Rena Gu, Jiaqi |
| contents | Photonic tensor cores (PTCs) are essential building blocks for optical artificial intelligence (AI) accelerators based on programmable photonic integrated circuits. Most PTC designs today are manually constructed, with low design efficiency and unsatisfying solution quality. This makes it challenging to meet various hardware specifications and keep up with rapidly evolving AI applications. Prior work has explored gradient-based methods to learn a good PTC structure differentiably. However, it suffers from slow training speed and optimization difficulty when handling multiple non-differentiable objectives and constraints. Therefore, in this work, we propose a more flexible and efficient zero-shot multi-objective evolutionary topology search framework ADEPT-Z that explores Pareto-optimal PTC designs with advanced devices in a larger search space. Multiple objectives can be co-optimized while honoring complicated hardware constraints. With only <3 hours of search, we can obtain tens of diverse Pareto-optimal solutions, 100x faster than the prior gradient-based method, outperforming prior manual designs with 2x higher accuracy weighted area-energy efficiency. The code of ADEPT-Z is available at https://github.com/ScopeX-ASU/ADEPT-Z. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01313 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ADEPT-Z: Zero-Shot Automated Circuit Topology Search for Pareto-Optimal Photonic Tensor Cores Jiang, Ziyang Ma, Pingchuan Zhang, Meng Huang, Rena Gu, Jiaqi Emerging Technologies Neural and Evolutionary Computing Optics Photonic tensor cores (PTCs) are essential building blocks for optical artificial intelligence (AI) accelerators based on programmable photonic integrated circuits. Most PTC designs today are manually constructed, with low design efficiency and unsatisfying solution quality. This makes it challenging to meet various hardware specifications and keep up with rapidly evolving AI applications. Prior work has explored gradient-based methods to learn a good PTC structure differentiably. However, it suffers from slow training speed and optimization difficulty when handling multiple non-differentiable objectives and constraints. Therefore, in this work, we propose a more flexible and efficient zero-shot multi-objective evolutionary topology search framework ADEPT-Z that explores Pareto-optimal PTC designs with advanced devices in a larger search space. Multiple objectives can be co-optimized while honoring complicated hardware constraints. With only <3 hours of search, we can obtain tens of diverse Pareto-optimal solutions, 100x faster than the prior gradient-based method, outperforming prior manual designs with 2x higher accuracy weighted area-energy efficiency. The code of ADEPT-Z is available at https://github.com/ScopeX-ASU/ADEPT-Z. |
| title | ADEPT-Z: Zero-Shot Automated Circuit Topology Search for Pareto-Optimal Photonic Tensor Cores |
| topic | Emerging Technologies Neural and Evolutionary Computing Optics |
| url | https://arxiv.org/abs/2410.01313 |