I/O-Efficient Computing With Integrated Photonic Iterative Processors
Using optical feedback in computing reduces latency and energy consumption during data input/output (I/O). We introduce the architecture of photonic iterative processors and demonstrate improved I/O efficiency for matrix inversion problems using silicon nitride chips.
Authors
- Minjia Chen (ORCID: https://orcid.org/0000-0001-5361-8179)
- Richard V. Penty (ORCID: https://orcid.org/0000-0003-4605-1455)
- Shuai Yang (ORCID: https://orcid.org/0000-0003-3572-516X)
- Qixiang Cheng (ORCID: https://orcid.org/0000-0001-8671-2102)
- A. Wonfor (ORCID: https://orcid.org/0000-0003-2219-7900)
- Yizhi Wang (ORCID: https://orcid.org/0000-0002-9232-7523)
- Chunhui Yao (ORCID: https://orcid.org/0000-0002-8524-0833)
Institutions
- University of Cambridge (GB)
- Bridge University (SS)
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11110541
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00