Research on distributed cooperative silicon based photonic computing chip
In this paper, an architecture of a photonic neural network chip with distributed multi-scenarios is presented. The distributed computing chip has five computing modules, which are characterized by three-dimensional imaging processing, convolutional operation, matrix operation, low-energy operation, and high-speed operation, respectively. Through the cooperative work of multiple modules, self-adaptive high-speed and energy-efficient computation of large-scale computing tasks can be realized.
Authors
- Pengfei Sun (ORCID: https://orcid.org/0000-0002-2881-6461)
- Kejian Zhu
- Changhong Wang (ORCID: https://orcid.org/0000-0002-4201-0130)
- Tuo Li (ORCID: https://orcid.org/0000-0002-6691-7423)
- Menglong Wang (ORCID: https://orcid.org/0000-0001-9112-4700)
- Xiaofeng Zou (ORCID: https://orcid.org/0000-0003-4211-9950)
Institutions
- Peking University (CN)
- Cloud Computing Center (CN)
Publication Details
- Published
- 2024-12-27
- DOI
- https://doi.org/10.1109/eiecc64539.2024.10929573
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Shandong Province