- Special Issue
- Special issue on optical interconnect and integrated photonic chip technologies for hyper-scale computing systems
- 2 Article (s)
High-density MDM-WDM silicon photonic transmitter chiplet based on MRMs and dual-mode GC for 4 × 56 Gbps 3D co-packaged optical interconnects|On the Cover
Xinyi Wang, Jiangbing Du, Weihong Shen, Ke Xu, and Zuyuan He
In this Letter, a four-channel silicon photonic mode-division-multiplexing (MDM) and wavelength-division multiplexing (WDM) transmitter chiplet is proposed over a 1.65 mm2 footprint, utilizing add-drop micro-ring modulators to simultaneously achieve electro-optic modulation and two-wavelength multiplexing. A dual-mode grating coupler with a side-distributed Bragg reflector for equalized two-mode coupling is realized with high chip-to-fiber coupling efficiency, so as to support the MDM optical fiber interface. A high data rate of up to 4 × 56 Gbps signaling is experimentally demonstrated, featuring applications like 200G quad small form-factor pluggable (QSFP) transceivers and indicating significant potential for high-density and large-capacity 3D co-packaged optical interconnects through flip-chip-based electronic-photonic packaging. In this Letter, a four-channel silicon photonic mode-division-multiplexing (MDM) and wavelength-division multiplexing (WDM) transmitter chiplet is proposed over a 1.65 mm2 footprint, utilizing add-drop micro-ring modulators to simultaneously achieve electro-optic modulation and two-wavelength multiplexing. A dual-mode grating coupler with a side-distributed Bragg reflector for equalized two-mode coupling is realized with high chip-to-fiber coupling efficiency, so as to support the MDM optical fiber interface. A high data rate of up to 4 × 56 Gbps signaling is experimentally demonstrated, featuring applications like 200G quad small form-factor pluggable (QSFP) transceivers and indicating significant potential for high-density and large-capacity 3D co-packaged optical interconnects through flip-chip-based electronic-photonic packaging.
Chinese Optics Letters
- Publication Date: Dec. 31, 2024
- Vol. 22, Issue 12, 120001 (2024)
Compact high-robustness diffractive neural network chip for water-immersed optical inference
Haitao Luan, Long Chen, Yibo Dong, Min Gu, and Qiming Zhang
Research in the ocean places high demands on chips’ robustness, speed, and energy consumption. Diffractive neural networks (DNNs) enable direct optical image processing at light speed, with great potential for underwater applications. Here, we experimentally demonstrate a compact DNN chip capable of operating directly in both water and air by multi-objective training and initial training value optimization. The two layers of DNNs are integrated on the two surfaces of a quartz plate, respectively. The chip achieved high accuracies above 90% in recognition tasks for handwritten digits and fashion products. The architecture and material ensure the chip’s high stability for long-term underwater use. Research in the ocean places high demands on chips’ robustness, speed, and energy consumption. Diffractive neural networks (DNNs) enable direct optical image processing at light speed, with great potential for underwater applications. Here, we experimentally demonstrate a compact DNN chip capable of operating directly in both water and air by multi-objective training and initial training value optimization. The two layers of DNNs are integrated on the two surfaces of a quartz plate, respectively. The chip achieved high accuracies above 90% in recognition tasks for handwritten digits and fashion products. The architecture and material ensure the chip’s high stability for long-term underwater use.
Chinese Optics Letters
- Publication Date: Dec. 24, 2024
- Vol. 22, Issue 12, 120002 (2024)
- <
- 1
- >
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20