EUVIMEDEUVIMED entdecken
Crossref

Scalable high-order integrated photonic tensor processor via frequency-domain modulation

Yue Wu, Liangjun Lu, Yu Li, Jianping Chen, Linjie Zhou

Optica · 20.06.2026 · 13 (6) · 998

DOI: 10.1364/optica.579208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optica, online erschienen am 21.05.2026. Verfasst von Yue Wu und 4 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Rising-Star Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rising computational demands of deep learning—particularly for high-order tensor operations—have driven the need for novel hardware accelerators. While integrated photonics presents a promising platform, the matrix scale of existing schemes is often constrained by the physical number of on-chip components. Here, we propose and experimentally demonstrate a scalable high-order integrated photonic tensor processor (HIPTP) that decouples the computational dimensionality from physical device count by leveraging a two-dimensional array combined with electrical frequency-domain modulation. The design employs a scalable array of cascaded Mach–Zehnder interferometers (MZIs) and photodetectors (PDs), enabling third- and fourth-order tensor multiplication by encoding data onto distinct microwave frequencies. A 4×4 HIPTP chip was fabricated and characterized, exhibiting high consistency across core components, which facilitates the extension toward larger-scale on-chip systems. To validate its computational capabilities, three computational modes were verified under varying frequency counts, and an inference accuracy of 97.5% was achieved on the German traffic sign recognition benchmark (GTSRB). Our work presents a promising pathway toward ultra-large-scale photonic computing for advanced AI models and frequency-aware signal processing scenarios.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Rising-Star Program

Zitieren

APA

Wu, Y., Lu, L., Li, Y., Chen, J., & Zhou, L. (2026). Scalable high-order integrated photonic tensor processor via frequency-domain modulation. Optica, 13(6), 998. https://doi.org/10.1364/optica.579208

Vancouver

Wu Y, Lu L, Li Y, Chen J, Zhou L. Scalable high-order integrated photonic tensor processor via frequency-domain modulation. Optica. 2026;13(6):998. doi:10.1364/optica.579208

BibTeX
@article{Wu2026,
  author = {Wu, Yue and Lu, Liangjun and Li, Yu and Chen, Jianping and Zhou, Linjie},
  title = {Scalable high-order integrated photonic tensor processor via frequency-domain modulation},
  journal = {Optica},
  year = {2026},
  volume = {13},
  number = {6},
  pages = {998},
  doi = {10.1364/optica.579208}
}
Kostenlos starten →