In-memory photonic dot-product engine with electrically programmable weight banks
dc.contributor.author | Zhou, W | |
dc.contributor.author | Dong, B | |
dc.contributor.author | Farmakidis, N | |
dc.contributor.author | Li, X | |
dc.contributor.author | Youngblood, N | |
dc.contributor.author | Huang, K | |
dc.contributor.author | He, Y | |
dc.contributor.author | David Wright, C | |
dc.contributor.author | Pernice, WHP | |
dc.contributor.author | Bhaskaran, H | |
dc.date.accessioned | 2023-05-23T08:00:25Z | |
dc.date.issued | 2023-05-20 | |
dc.date.updated | 2023-05-22T15:29:34Z | |
dc.description.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%. | en_GB |
dc.description.sponsorship | European Union Horizon 2020 | en_GB |
dc.description.sponsorship | UKRI | en_GB |
dc.identifier.citation | Vol. 14(1), article 2887 | en_GB |
dc.identifier.doi | https://doi.org/10.1038/s41467-023-38473-x | |
dc.identifier.grantnumber | 780848 | en_GB |
dc.identifier.grantnumber | 101017237 | en_GB |
dc.identifier.grantnumber | EP/T023899/1 | en_GB |
dc.identifier.grantnumber | EP/R001677/1 | en_GB |
dc.identifier.grantnumber | EP/W022931/1 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/133216 | |
dc.language.iso | en | en_GB |
dc.publisher | Nature Research | en_GB |
dc.rights | © The Author(s) 2023. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. | en_GB |
dc.title | In-memory photonic dot-product engine with electrically programmable weight banks | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2023-05-23T08:00:25Z | |
exeter.article-number | 2887 | |
dc.description | This is the final version. Available on open access from Nature Research via the DOI in this record | en_GB |
dc.description | Data availability: The data that support the findings of this study are available from the corresponding author upon request. | en_GB |
dc.description | Code availability: The code used in the present work is available from the authors upon request. | en_GB |
dc.identifier.eissn | 2041-1723 | |
dc.identifier.journal | Nature Communications | en_GB |
dc.relation.ispartof | Nature Communications, 14(1) | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en_GB |
dcterms.dateAccepted | 2023-05-03 | |
rioxxterms.version | VoR | en_GB |
rioxxterms.licenseref.startdate | 2023-05-20 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2023-05-23T07:56:28Z | |
refterms.versionFCD | VoR | |
refterms.dateFOA | 2023-05-23T08:00:27Z | |
refterms.panel | B | en_GB |
refterms.dateFirstOnline | 2023-05-20 |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's licence is described as © The Author(s) 2023. Open Access. This article is licensed under a Creative Commons
Attribution 4.0 International License, which permits use, sharing,
adaptation, distribution and reproduction in any medium or format, as
long as you give appropriate credit to the original author(s) and the
source, provide a link to the Creative Commons license, and indicate if
changes were made. The images or other third party material in this
article are included in the article’s Creative Commons license, unless
indicated otherwise in a credit line to the material. If material is not
included in the article’s Creative Commons license and your intended
use is not permitted by statutory regulation or exceeds the permitted
use, you will need to obtain permission directly from the copyright
holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.