Ultrafast reconfigurable topological-modulators-based photonic processing accelerator

The rise of artificial intelligence has triggered exponential growth in data volume, demanding rapid and efficient processing. High-speed, energy-efficient, and parallel-scalable computing hardware is thus increasingly critical. We demonstrate a wafer-scale non-volatile photonic computing chip using topological modulators. Leveraging the GHz-speed electro-optic response and nonvolatility of ferroelectric lead zirconate titanate (PZT) thin films via topological photonic confinement, our chip enables 1,000× accelerated reconfiguration, near-zero static-power operation, and a computational density of 266 trillion operations per second per square millimeter (TOPS/mm²). A 16-channel wavelength-space multiplexed chip delivers 1.92 TOPS throughput with 95.64% digit-recognition accuracy and 94.5% precision for solving time-varying partial differential equations. Additionally, the chip supports functional reconfiguration for high bandwidth density optical I/O. This work establishes ferroelectric topological photonics for efficient high-speed photonic tensor processing. This work demonstrates a non-volatile photonic computing chip based on topological modulators on a PZT platform. The chip achieves 110 GHz bandwidth, 266 TOPS/mm² compute density, and near-zero static power. A 16-channel chip delivers 1.92 TOPS throughput with over 94.5% accuracy for digit recognition and PDE solving.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2026-07-23
DOI
https://doi.org/10.1038/s41467-026-75993-8
Primary Topic
Neural Networks and Reservoir Computing
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Ultrafast reconfigurable topological-modulators-based photonic processing accelerator

Ya-Hui Zhu, X Wang, Yikai Su, P D Zhang et al.
Nature Communications
Neural Networks and Reservoir Computing
article

Ultrafast reconfigurable topological-modulators-based photonic processing accelerator

Ya-Hui Zhu, X Wang, Yikai Su, P D Zhang, Jungan Wang, Bin Li, Xi Zhang, Jingchi Li, Yuqi Chen, Xiong Ni, Yan Jiang, Min Sun, Mingrui Yuan, W Zhou, Qingqing Han, Yong Zhang, Feng Qiu, Chen Yang
article en

Abstract

The rise of artificial intelligence has triggered exponential growth in data volume, demanding rapid and efficient processing. High-speed, energy-efficient, and parallel-scalable computing hardware is thus increasingly critical. We demonstrate a wafer-scale non-volatile photonic computing chip using topological modulators. Leveraging the GHz-speed electro-optic response and nonvolatility of ferroelectric lead zirconate titanate (PZT) thin films via topological photonic confinement, our chip enables 1,000× accelerated reconfiguration, near-zero static-power operation, and a computational density of 266 trillion operations per second per square millimeter (TOPS/mm²). A 16-channel wavelength-space multiplexed chip delivers 1.92 TOPS throughput with 95.64% digit-recognition accuracy and 94.5% precision for solving time-varying partial differential equations. Additionally, the chip supports functional reconfiguration for high bandwidth density optical I/O. This work establishes ferroelectric topological photonics for efficient high-speed photonic tensor processing. This work demonstrates a non-volatile photonic computing chip based on topological modulators on a PZT platform. The chip achieves 110 GHz bandwidth, 266 TOPS/mm² compute density, and near-zero static power. A 16-channel chip delivers 1.92 TOPS throughput with over 94.5% accuracy for digit recognition and PDE solving.

Nature Communications
Zhejiang Sci-Tech University (CN), Shanghai Jiao Tong University (CN), Hangzhou Academy of Agricultural Sciences (CN), Lanzhou University (CN)
National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality
Affordable and clean energy
Openalex Percentile: Top 7%
Neural Networks and Reservoir Computing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.