Buchumschlag

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

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Wen (VerfasserIn) , Dong, Bowei (VerfasserIn) , Farmakidis, Nikolaos (VerfasserIn) , Li, Xuan (VerfasserIn) , Youngblood, Nathan (VerfasserIn) , Huang, Kairan (VerfasserIn) , He, Yuhan (VerfasserIn) , Wright, C. David (VerfasserIn) , Pernice, Wolfram (VerfasserIn) , Bhaskaran, Harish (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 20 May 2023
In: Nature Communications
Year: 2023, Jahrgang: 14, Pages: 1-10
ISSN:2041-1723
DOI:10.1038/s41467-023-38473-x
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s41467-023-38473-x
Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s41467-023-38473-x
Volltext
Verfasserangaben:Wen Zhou, Bowei Dong, Nikolaos Farmakidis, Xuan Li, Nathan Youngblood, Kairan Huang, Yuhan He, C. David Wright, Wolfram H.P. Pernice, Harish Bhaskaran
Beschreibung
Zusammenfassung: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%.
Beschreibung:Gesehen am 02.08.2023
Beschreibung:Online Resource
ISSN:2041-1723
DOI:10.1038/s41467-023-38473-x

Ähnliche Einträge