Cargando…

In-memory computing on a photonic platform

Collocated data processing and storage are the norm in biological computing systems such as the mammalian brain. As our ability to create better hardware improves, new computational paradigms are being explored beyond von Neumann architectures. Integrated photonic circuits are an attractive solution...

Descripción completa

Detalles Bibliográficos
Autores principales: Ríos, Carlos, Youngblood, Nathan, Cheng, Zengguang, Le Gallo, Manuel, Pernice, Wolfram H. P., Wright, C. David, Sebastian, Abu, Bhaskaran, Harish
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Association for the Advancement of Science 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6377270/
https://www.ncbi.nlm.nih.gov/pubmed/30793028
http://dx.doi.org/10.1126/sciadv.aau5759
_version_ 1783395715228106752
author Ríos, Carlos
Youngblood, Nathan
Cheng, Zengguang
Le Gallo, Manuel
Pernice, Wolfram H. P.
Wright, C. David
Sebastian, Abu
Bhaskaran, Harish
author_facet Ríos, Carlos
Youngblood, Nathan
Cheng, Zengguang
Le Gallo, Manuel
Pernice, Wolfram H. P.
Wright, C. David
Sebastian, Abu
Bhaskaran, Harish
author_sort Ríos, Carlos
collection PubMed
description Collocated data processing and storage are the norm in biological computing systems such as the mammalian brain. As our ability to create better hardware improves, new computational paradigms are being explored beyond von Neumann architectures. Integrated photonic circuits are an attractive solution for on-chip computing which can leverage the increased speed and bandwidth potential of the optical domain, and importantly, remove the need for electro-optical conversions. Here we show that we can combine integrated optics with collocated data storage and processing to enable all-photonic in-memory computations. By employing nonvolatile photonic elements based on the phase-change material, Ge(2)Sb(2)Te(5), we achieve direct scalar and matrix-vector multiplication, featuring a novel single-shot Write/Erase and a drift-free process. The output pulse, carrying the information of the light-matter interaction, is the result of the computation. Our all-optical approach is novel, easy to fabricate and operate, and sets the stage for development of entirely photonic computers.
format Online
Article
Text
id pubmed-6377270
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher American Association for the Advancement of Science
record_format MEDLINE/PubMed
spelling pubmed-63772702019-02-21 In-memory computing on a photonic platform Ríos, Carlos Youngblood, Nathan Cheng, Zengguang Le Gallo, Manuel Pernice, Wolfram H. P. Wright, C. David Sebastian, Abu Bhaskaran, Harish Sci Adv Research Articles Collocated data processing and storage are the norm in biological computing systems such as the mammalian brain. As our ability to create better hardware improves, new computational paradigms are being explored beyond von Neumann architectures. Integrated photonic circuits are an attractive solution for on-chip computing which can leverage the increased speed and bandwidth potential of the optical domain, and importantly, remove the need for electro-optical conversions. Here we show that we can combine integrated optics with collocated data storage and processing to enable all-photonic in-memory computations. By employing nonvolatile photonic elements based on the phase-change material, Ge(2)Sb(2)Te(5), we achieve direct scalar and matrix-vector multiplication, featuring a novel single-shot Write/Erase and a drift-free process. The output pulse, carrying the information of the light-matter interaction, is the result of the computation. Our all-optical approach is novel, easy to fabricate and operate, and sets the stage for development of entirely photonic computers. American Association for the Advancement of Science 2019-02-15 /pmc/articles/PMC6377270/ /pubmed/30793028 http://dx.doi.org/10.1126/sciadv.aau5759 Text en Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY). http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Articles
Ríos, Carlos
Youngblood, Nathan
Cheng, Zengguang
Le Gallo, Manuel
Pernice, Wolfram H. P.
Wright, C. David
Sebastian, Abu
Bhaskaran, Harish
In-memory computing on a photonic platform
title In-memory computing on a photonic platform
title_full In-memory computing on a photonic platform
title_fullStr In-memory computing on a photonic platform
title_full_unstemmed In-memory computing on a photonic platform
title_short In-memory computing on a photonic platform
title_sort in-memory computing on a photonic platform
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6377270/
https://www.ncbi.nlm.nih.gov/pubmed/30793028
http://dx.doi.org/10.1126/sciadv.aau5759
work_keys_str_mv AT rioscarlos inmemorycomputingonaphotonicplatform
AT youngbloodnathan inmemorycomputingonaphotonicplatform
AT chengzengguang inmemorycomputingonaphotonicplatform
AT legallomanuel inmemorycomputingonaphotonicplatform
AT pernicewolframhp inmemorycomputingonaphotonicplatform
AT wrightcdavid inmemorycomputingonaphotonicplatform
AT sebastianabu inmemorycomputingonaphotonicplatform
AT bhaskaranharish inmemorycomputingonaphotonicplatform