Efficient Inverted Sequence Mapping Strategy for Neural Network Accelerator in ONoC
We propose an adaptive mapping strategy for Optical Network-on-Chip (ONoC) neural network accelerators. Under highly diverse neural network scales, this approach reduces the global average delay of ONoC processing and the transmission hop counts.
Authors
- Qiuyan Yao (ORCID: https://orcid.org/0000-0001-8753-6489)
- Jie Zhang (ORCID: https://orcid.org/0000-0002-3354-0690)
- Yijie Liang
- Chen Zhao (ORCID: https://orcid.org/0000-0003-4993-5416)
- Hui Yang (ORCID: https://orcid.org/0000-0002-3638-5526)
- Daqing Meng
- Junji Feng
Institutions
- Beijing University of Posts and Telecommunications (CN)
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11109578
- Citations
- 1
- Primary Topic
- Image Processing Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 1.14
Funders
- China Association for Science and Technology
- National Natural Science Foundation of China
- Natural Science Foundation of Beijing Municipality
- Fundamental Research Funds for the Central Universities