In-memory photonic dot-product engine with electrically programmable weight banks

• Verfasst von: Zhou, Wen [VerfasserIn]
• Verfasst von: Dong, Bowei [VerfasserIn]
• Verfasst von: Farmakidis, Nikolaos [VerfasserIn]
• Verfasst von: Li, Xuan [VerfasserIn]
• Verfasst von: Youngblood, Nathan [VerfasserIn]
• Verfasst von: Huang, Kairan [VerfasserIn]
• Verfasst von: He, Yuhan [VerfasserIn]
• Verfasst von: Wright, C. David [VerfasserIn]
• Verfasst von: Pernice, Wolfram [VerfasserIn]
• Verfasst von: Bhaskaran, Harish [VerfasserIn]
• Titel: In-memory photonic dot-product engine with electrically programmable weight banks
• Verf.angabe: Wen Zhou, Bowei Dong, Nikolaos Farmakidis, Xuan Li, Nathan Youngblood, Kairan Huang, Yuhan He, C. David Wright, Wolfram H.P. Pernice, Harish Bhaskaran
• E-Jahr: 2023
• Jahr: 20 May 2023
• Umfang: 10 S.
• Fussnoten: Gesehen am 02.08.2023
• Titel Quelle: Enthalten in: Nature Communications
• Ort Quelle: [London] : Nature Publishing Group UK, 2010
• Jahr Quelle: 2023
• Band/Heft Quelle: 14(2023), Artikel-ID 2887, Seite 1-10
• ISSN Quelle: 2041-1723
• DOI: doi:10.1038/s41467-023-38473-x
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Optical materials and structures
• Sach-SW: Optoelectronic devices and components
• K10plus-PPN: 1854152467

Abstract

Electronically reprogrammable photonic circuits based on phase-change chalcogenides present an avenue to resolve the von-Neumann bottleneck; however, implementation of such hybrid photonic-electronic processing has not achieved computational success. Here, we achieve this milestone by demonstrating an in-memory photonic-electronic dot-product engine, one that decouples electronic programming of phase-change materials (PCMs) and photonic computation. Specifically, we develop non-volatile electronically reprogrammable PCM memory cells with a record-high 4-bit weight encoding, the lowest energy consumption per unit modulation depth (1.7 nJ/dB) for Erase operation (crystallization), and a high switching contrast (158.5%) using non-resonant silicon-on-insulator waveguide microheater devices. This enables us to perform parallel multiplications for image processing with a superior contrast-to-noise ratio (≥87.36) that leads to an enhanced computing accuracy (standard deviation σ ≤ 0.007). An in-memory hybrid computing system is developed in hardware for convolutional processing for recognizing images from the MNIST database with inferencing accuracies of 86% and 87%.