EUVIMEDEUVIMED entdecken
Open Access

Complex-valued matrix-vector multiplication using a scalable coherent photonic processor

Yiwei Xie iD, Xiyuan Ke iD, Shihan Hong, Yuxin Sun iD, Lijia Song iD, Huan Li iD, Pan Wang iD, Daoxin Dai iD

Science Advances · 04.04.2025 · 11 (14)

DOI: 10.1126/sciadv.ads7475 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 04.04.2025. Verfasst von Yiwei Xie und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Extreme Photonics and Instrumentation, Zhejiang Key Laboratory of Optoelectronic Information Technology, College of Optical S…. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Matrix-vector multiplication is a fundamental operation in modern signal processing and artificial intelligence. Developing a chip-scale photonic matrix-vector multiplication processor (MVMP) offers the potential for notably enhanced computing speed and energy efficiency beyond microelectronics. Here, we propose and demonstrate a 16-channel programmable on-chip coherent photonic processor capable of performing complex-valued matrix-vector multiplication at a computing speed of 1.28 tera-operations per second (TOPS). Low phase error Mach-Zehnder interferometers mesh and ultralow-loss broadened photonic waveguide delay lines are firstly combined for optical computing, enabling the encoding of amplitude and phase information, along with high-speed coherent detection. The proposed MVMP demonstrates high flexibility in implementing various functions, including arbitrary matrix transformation, parallel image processing, and handwritten digital recognition. Our work demonstrates the MVMP’s advantages in scalability and function flexibility, enabled by the low-loss and low phase error designs, making a substantial advancement in high-speed and large-scale photonic computing technologies.

Autor:innen und Institutionen

  • State Key Laboratory of Extreme Photonics and Instrumentation, Zhejiang Key Laboratory of Optoelectronic Information Technology, College of Optical Science and Engineering, Zhejiang University, Hangzhou 310058, China.
  • Jiaxing Key Laboratory of Photonic Sensing and Intelligent Imaging, Intelligent Optics and Photonics Research Center, Zhejiang University, Jiaxing 314000, China.
  • Ningbo Research Institute, Zhejiang University, Ningbo 315100, China.

ORCID-Profile: Yiwei Xie, Xiyuan Ke, Yuxin Sun, Lijia Song, Huan Li, Pan Wang, Daoxin Dai

Zitieren

APA

Xie, Y., Ke, X., Hong, S., Sun, Y., Song, L., Li, H., Wang, P., & Dai, D. (2025). Complex-valued matrix-vector multiplication using a scalable coherent photonic processor. Science Advances, 11(14). https://doi.org/10.1126/sciadv.ads7475

Vancouver

Xie Y, Ke X, Hong S, Sun Y, Song L, Li H, et al. Complex-valued matrix-vector multiplication using a scalable coherent photonic processor. Science Advances. 2025;11(14). doi:10.1126/sciadv.ads7475

BibTeX
@article{Xie2025,
  author = {Xie, Yiwei and Ke, Xiyuan and Hong, Shihan and Sun, Yuxin and Song, Lijia and Li, Huan and Wang, Pan and Dai, Daoxin},
  title = {Complex-valued matrix-vector multiplication using a scalable coherent photonic processor},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {14},
  doi = {10.1126/sciadv.ads7475}
}
Kostenlos starten →