Reconfigurable large-scale optoelectronic reservoir computing on programmable silicon photonic processor

Reconfigurable large-scale optoelectronic reservoir computing on programmable silicon photonic processor | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Reconfigurable large-scale optoelectronic reservoir computing on programmable silicon photonic processor Ziwei Li, Tang DengFei, Fangchen Hu, Shiyue Hua, Shanshan Yu, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6733095/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The ever-growing demand for artificial intelligence (AI) acceleration has motivated research on novel photonic neuromorphic computation architectures, aiming for breakthroughs in computation speed and energy efficiency. Reservoir computing (RC), a hardware-friendly and training-efficient paradigm, has emerged as a compelling candidate. However, existing photonic RC systems, whether in time-multiplexed single-node implementations or passive parallel interconnections, suffer from fixed reservoir connections, which significantly constrain their adaptability and computational versatility across tasks. Here, we propose a reconfigurable optoelectronic RC system featuring a multi-physical node architecture, constructed on a large-scale programmable silicon photonic arithmetic computing engine. By integrating 64 physical nodes with tunable interconnect topology and connection density, the system allows flexible configuration of the reservoir layer tailored to specific computational demands. We further present a scalable deep RC architecture that expand the model complexity to over 600 reservoir neurons. Operating at up to 1 GHz with a per-cycle latency of 3 ns, the platform achieves a throughput of 8.19 TOPS and demonstrates robust performance across diverse tasks. Experimental validation confirms state-of-the-art performance including modulation-format identification with 99.8% accuracy over severely distorted optical channels, nonlinear equalization yielding a 0.61dB improvement in signal-quality factor compared with conventional digital post-equalization, and benchmark hand-written digit image classification of 96.7% accuracy. This work offers a scalable and reconfigurable solution for high-speed, task-adaptive neuromorphic computing, paving the way for practical deployment of photonic intelligence systems. Physical sciences/Optics and photonics/Applied optics/Integrated optics Physical sciences/Optics and photonics/Applied optics/Optoelectronic devices and components Full Text Additional Declarations There is no conflict of interest Supplementary Files SupplementaryInformation.pdf Supplemental Material Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6733095","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":496513419,"identity":"7a064cd5-ef9f-4ec6-b37d-8e3799a03477","order_by":0,"name":"Ziwei Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAv0lEQVRIiWNgGAWjYBACPmYg8cGGgbEBxOMhRgsbUAvjjDSStAAxMw9pWtjZn0nbJByW7Z/dwPjgbRuDvDkRDkuTzkk4bDzjzgFmw7ltDIY7GwhrOXY798fhxIYbCWzSvG0MCQYHCGphbLttkXA4cf6NBPbfRGphZrvNANSyAWgLM5Fa2Nh/9iSkG2+8kdgsOeechOEGQlr4+Y8/NviRYC0770bywQ9vymzkCdqCBMBRI0G8+lEwCkbBKBgFuAEAGfM7WxcTYTMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-7631-989X","institution":"Ziwei Li, Associate Professor, Fudan University","correspondingAuthor":true,"prefix":"","firstName":"Ziwei","middleName":"","lastName":"Li","suffix":""},{"id":496513420,"identity":"8788864f-dd78-4594-a00f-8806c17f99f6","order_by":1,"name":"Tang DengFei","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Tang","middleName":"","lastName":"DengFei","suffix":""},{"id":496513421,"identity":"78f7d211-3a79-44e9-8a54-298d98ac82b8","order_by":2,"name":"Fangchen Hu","email":"","orcid":"https://orcid.org/0009-0007-1328-1082","institution":"Zhangjiang Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Fangchen","middleName":"","lastName":"Hu","suffix":""},{"id":496513422,"identity":"69c90780-b4b8-45c8-a12a-d9aff0902c09","order_by":3,"name":"Shiyue Hua","email":"","orcid":"","institution":"Xizhi Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Shiyue","middleName":"","lastName":"Hua","suffix":""},{"id":496513423,"identity":"d61d14ca-56ec-49d7-a5ba-293ceb5c4040","order_by":4,"name":"Shanshan Yu","email":"","orcid":"","institution":"Xizhi Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Shanshan","middleName":"","lastName":"Yu","suffix":""},{"id":496513424,"identity":"3b5b49f0-5dc8-40d1-b173-4740aebc89bd","order_by":5,"name":"Zhiteng Luo","email":"","orcid":"","institution":"Fudan university","correspondingAuthor":false,"prefix":"","firstName":"Zhiteng","middleName":"","lastName":"Luo","suffix":""},{"id":496513425,"identity":"0adc7f45-a1d7-4110-a402-05a7e61d239e","order_by":6,"name":"Zhanhong Zhou","email":"","orcid":"","institution":"Fudan university","correspondingAuthor":false,"prefix":"","firstName":"Zhanhong","middleName":"","lastName":"Zhou","suffix":""},{"id":496513426,"identity":"62bbf80b-3dd1-4239-8dd2-cee91f657b87","order_by":7,"name":"Junwen Zhang","email":"","orcid":"https://orcid.org/0000-0001-8041-1608","institution":"Fudan Univeristy","correspondingAuthor":false,"prefix":"","firstName":"Junwen","middleName":"","lastName":"Zhang","suffix":""},{"id":496513427,"identity":"f8764660-09ca-4df5-b02f-543c0a0bac70","order_by":8,"name":"Jianyang Shi","email":"","orcid":"https://orcid.org/0000-0002-5478-3704","institution":"Fudan Univeristy","correspondingAuthor":false,"prefix":"","firstName":"Jianyang","middleName":"","lastName":"Shi","suffix":""},{"id":496513428,"identity":"aa7dea3f-8dfa-498c-98d4-1a591b541e8a","order_by":9,"name":"Wei Chu","email":"","orcid":"https://orcid.org/0000-0002-6621-8403","institution":"Zhangjiang Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Chu","suffix":""},{"id":496513429,"identity":"8766eee3-569e-4379-9d8b-ebe83b4dc328","order_by":10,"name":"Haiwen Cai","email":"","orcid":"","institution":"Shanghai Institute of Optics and Fine Mechanics","correspondingAuthor":false,"prefix":"","firstName":"Haiwen","middleName":"","lastName":"Cai","suffix":""},{"id":496513430,"identity":"d7860034-d620-4101-be29-1ec29caa86e4","order_by":11,"name":"Nan Chi","email":"","orcid":"https://orcid.org/0000-0003-4966-3844","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Nan","middleName":"","lastName":"Chi","suffix":""},{"id":496513431,"identity":"04085fe4-a049-4ada-ac7d-f2f0f0d7c892","order_by":12,"name":"Haibin Zhao","email":"","orcid":"https://orcid.org/0000-0003-1304-6609","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Haibin","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2025-05-23 13:00:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6733095/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6733095/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89551979,"identity":"9783c185-6e0c-480c-b527-8a89145b4e98","added_by":"auto","created_at":"2025-08-21 08:38:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1355154,"visible":true,"origin":"","legend":"Article File","description":"","filename":"MainManuscriptOERC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6733095/v1_covered_fd1da314-428a-404c-b239-c9507b29d4c3.pdf"},{"id":88758225,"identity":"d54b7c2e-6f82-4e81-af51-aab33590abaa","added_by":"auto","created_at":"2025-08-11 07:33:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":894975,"visible":true,"origin":"","legend":"Supplemental Material","description":"","filename":"SupplementaryInformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6733095/v1/17a31458ff70117befd168e5.pdf"}],"financialInterests":"There is no conflict of interest","formattedTitle":"Reconfigurable large-scale optoelectronic reservoir computing on programmable silicon photonic processor","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6733095/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6733095/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The ever-growing demand for artificial intelligence (AI) acceleration has motivated research on novel photonic neuromorphic computation architectures, aiming for breakthroughs in computation speed and energy efficiency. Reservoir computing (RC), a hardware-friendly and training-efficient paradigm, has emerged as a compelling candidate. However, existing photonic RC systems, whether in time-multiplexed single-node implementations or passive parallel interconnections, suffer from fixed reservoir connections, which significantly constrain their adaptability and computational versatility across tasks. Here, we propose a reconfigurable optoelectronic RC system featuring a multi-physical node architecture, constructed on a large-scale programmable silicon photonic arithmetic computing engine. By integrating 64 physical nodes with tunable interconnect topology and connection density, the system allows flexible configuration of the reservoir layer tailored to specific computational demands. We further present a scalable deep RC architecture that expand the model complexity to over 600 reservoir neurons. Operating at up to 1 GHz with a per-cycle latency of 3 ns, the platform achieves a throughput of 8.19 TOPS and demonstrates robust performance across diverse tasks. Experimental validation confirms state-of-the-art performance including modulation-format identification with 99.8% accuracy over severely distorted optical channels, nonlinear equalization yielding a 0.61dB improvement in signal-quality factor compared with conventional digital post-equalization, and benchmark hand-written digit image classification of 96.7% accuracy. This work offers a scalable and reconfigurable solution for high-speed, task-adaptive neuromorphic computing, paving the way for practical deployment of photonic intelligence systems.","manuscriptTitle":"Reconfigurable large-scale optoelectronic reservoir computing on programmable silicon photonic processor","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-11 07:33:22","doi":"10.21203/rs.3.rs-6733095/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7f65b008-8ba4-4ba3-84c6-cd894f77b05c","owner":[],"postedDate":"August 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52739065,"name":"Physical sciences/Optics and photonics/Applied optics/Integrated optics"},{"id":52739066,"name":"Physical sciences/Optics and photonics/Applied optics/Optoelectronic devices and components"}],"tags":[],"updatedAt":"2025-08-21T08:30:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-11 07:33:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6733095","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6733095","identity":"rs-6733095","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}