42 TOPS/mm2 Photonic Convolutional Processor Empowered by a Soliton Comb and a Microdisk Resonator Array

42 TOPS/mm2 Photonic Convolutional Processor Empowered by a Soliton Comb and a Microdisk Resonator Array | 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 42 TOPS/mm2 Photonic Convolutional Processor Empowered by a Soliton Comb and a Microdisk Resonator Array Jianping Yao, Shanshan Cheng, Yiran Guan, Chenye Qin, Zheng Dai, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8984623/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Photonic convolutional accelerators can effectively mitigate the speed bottleneck of traditional electronic processors by harnessing the intrinsic high speed and parallelism of photonics, significantly boosting the computing speed while reducing energy consumption. However, the degraded wavelength stability and poor miniaturization of bulky free-running light sources, together with the limited scalability of chip-scale convolutional cores, constrain the computing density and operational stability of conventional photonic processors. To address these challenges, we propose and demonstrate a photonic convolutional processor incorporating a compact soliton microcomb and a silicon integrated field programmable disk mesh (FPDM). The microcomb integrates a high-Q multimode Fabry-Perot resonator and a pump laser diode with self-injection locking for stabilization, enabling the generation of an ultra-stable soliton comb with a low phase noise of -126 dBc/Hz@10 kHz offset frequency and a small intensity fluctuation of less than 0.44% per hour. The FPDA has thirty-two tunable microdisks and sixteen optical I/O ports, supporting two 4-by-4 or eight 2-by-2 programmable convolution kernels for high-speed and parallel convolution processing. Moreover, featuring high scalability, reconfigurability, and support for signed operations, our photonic convolutional core achieves a record-breaking computing density of 42 TOPS/mm² and can theoretically scale up to 84 TOPS/mm². These advancements substantially enhance the scalability and adaptability of optical deep learning accelerators, paving the way for next-generation fully integrated photonic AI hardware. Physical sciences/Optics and photonics/Applied optics/Microwave photonics Physical sciences/Optics and photonics/Applied optics/Optoelectronic devices and components Full Text Additional Declarations There is no conflict of interest Supplementary Files SupplementaryNoteR1.pdf Supplementary Note Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: revise 21 Apr, 2026 Review # 3 received at journal 05 Apr, 2026 Review # 1 received at journal 17 Mar, 2026 Review # 2 received at journal 16 Mar, 2026 Reviewer # 3 agreed at journal 16 Mar, 2026 Reviewer # 2 agreed at journal 12 Mar, 2026 Reviewer # 1 agreed at journal 12 Mar, 2026 Reviewers invited by journal 12 Mar, 2026 Submission checks completed at journal 11 Mar, 2026 Editor assigned by journal 27 Feb, 2026 First submitted to journal 27 Feb, 2026 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-8984623","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":604895458,"identity":"4172de13-85ae-4212-a2f6-028e8e1607a8","order_by":0,"name":"Jianping Yao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYBACxgYQWUG6ljMMDDxspFnVRooW5tk9hh8+zjssZy/f/EziB4OdPGEL5pwxlpy57bAxDxubmWQPQ7JhA0EtM3IMpHm3HU7sYWMwu8HDcICRGC3Gv3nngLSwf7v5h+GAPTFazKR5G0BaeMxuA21JJKxlzrEyyxnH0o15juWU/5YxSE4mqMVwdvPmGx9qrOXYm49vNnxTYWdLWMsMDgMkrgFOhQggL8H+gAhlo2AUjIJRMKIBAMvWOhq00DZ5AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-6877-7057","institution":"University of Ottawa","correspondingAuthor":true,"prefix":"","firstName":"Jianping","middleName":"","lastName":"Yao","suffix":""},{"id":604895459,"identity":"41f80a05-49b0-4dfa-aa1d-0684ab064ac6","order_by":1,"name":"Shanshan Cheng","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shanshan","middleName":"","lastName":"Cheng","suffix":""},{"id":604895460,"identity":"82e2b1eb-c030-4665-90c3-d9968dfc4393","order_by":2,"name":"Yiran Guan","email":"","orcid":"https://orcid.org/0009-0003-5459-5521","institution":"University of Ottawa","correspondingAuthor":false,"prefix":"","firstName":"Yiran","middleName":"","lastName":"Guan","suffix":""},{"id":604895461,"identity":"4dd47b20-956c-4310-a54d-062945099843","order_by":3,"name":"Chenye Qin","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Chenye","middleName":"","lastName":"Qin","suffix":""},{"id":604895462,"identity":"f03146cf-9671-471d-81b7-dfaceb5f8ee4","order_by":4,"name":"Zheng Dai","email":"","orcid":"","institution":"University of Ottawa","correspondingAuthor":false,"prefix":"","firstName":"Zheng","middleName":"","lastName":"Dai","suffix":""},{"id":604895463,"identity":"e55b9521-64fd-4e59-9fa6-ed0bc6aa1600","order_by":5,"name":"Kunpeng Jia","email":"","orcid":"https://orcid.org/0000-0003-0038-406X","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Kunpeng","middleName":"","lastName":"Jia","suffix":""},{"id":604895464,"identity":"0ecf68f5-6c2f-4ddf-8629-e0925c9c7bc2","order_by":6,"name":"Wei Liang","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Liang","suffix":""},{"id":604895465,"identity":"825eaa73-f2ea-4329-95e4-97b550658310","order_by":7,"name":"Shining Zhu","email":"","orcid":"https://orcid.org/0000-0002-3472-6497","institution":"National Laboratory of Solid State Microstructures and School of Physics, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Shining","middleName":"","lastName":"Zhu","suffix":""},{"id":604895466,"identity":"56d20aff-c14f-47f6-bdbe-1d313bc0f2c6","order_by":8,"name":"Zhenda Xie","email":"","orcid":"https://orcid.org/0000-0003-2060-3063","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Zhenda","middleName":"","lastName":"Xie","suffix":""}],"badges":[],"createdAt":"2026-02-27 07:20:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8984623/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8984623/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104783017,"identity":"59647424-bc7e-43be-8e90-cfbe07ef2f50","added_by":"auto","created_at":"2026-03-17 07:58:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2455761,"visible":true,"origin":"","legend":"Article File","description":"","filename":"LSA20252716R1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8984623/v1_covered_a6643299-acad-4ae2-8f1b-61efcaa4e3e3.pdf"},{"id":104711275,"identity":"b63d605a-32a1-4901-90c0-7316894f3127","added_by":"auto","created_at":"2026-03-16 10:22:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1324776,"visible":true,"origin":"","legend":"Supplementary Note","description":"","filename":"SupplementaryNoteR1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8984623/v1/f8d900c3fa2e3dd014e07be1.pdf"}],"financialInterests":"There is no conflict of interest","formattedTitle":"42 TOPS/mm2 Photonic Convolutional Processor Empowered by a Soliton Comb and a Microdisk Resonator Array","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"light-science-and-applications","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"lsa","sideBox":"Learn more about [Light: Science \u0026 Applications](http://www.nature.com/lsa/)","snPcode":"41377","submissionUrl":"https://mts-lsa.nature.com/","title":"Light: Science \u0026 Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8984623/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8984623/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Photonic convolutional accelerators can effectively mitigate the speed bottleneck of traditional electronic processors by harnessing the intrinsic high speed and parallelism of photonics, significantly boosting the computing speed while reducing energy consumption. However, the degraded wavelength stability and poor miniaturization of bulky free-running light sources, together with the limited scalability of chip-scale convolutional cores, constrain the computing density and operational stability of conventional photonic processors. To address these challenges, we propose and demonstrate a photonic convolutional processor incorporating a compact soliton microcomb and a silicon integrated field programmable disk mesh (FPDM). The microcomb integrates a high-Q multimode Fabry-Perot resonator and a pump laser diode with self-injection locking for stabilization, enabling the generation of an ultra-stable soliton comb with a low phase noise of -126 dBc/Hz@10 kHz offset frequency and a small intensity fluctuation of less than 0.44% per hour. The FPDA has thirty-two tunable microdisks and sixteen optical I/O ports, supporting two 4-by-4 or eight 2-by-2 programmable convolution kernels for high-speed and parallel convolution processing. Moreover, featuring high scalability, reconfigurability, and support for signed operations, our photonic convolutional core achieves a record-breaking computing density of 42 TOPS/mm² and can theoretically scale up to 84 TOPS/mm². These advancements substantially enhance the scalability and adaptability of optical deep learning accelerators, paving the way for next-generation fully integrated photonic AI hardware.","manuscriptTitle":"42 TOPS/mm2 Photonic Convolutional Processor Empowered by a Soliton Comb and a Microdisk Resonator Array","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-16 10:22:09","doi":"10.21203/rs.3.rs-8984623/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"revise","date":"2026-04-21T15:31:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"This content is not available.","date":"2026-04-05T20:40:41+00:00","index":3,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2026-03-18T02:49:57+00:00","index":1,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2026-03-17T00:50:08+00:00","index":2,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2026-03-16T19:09:36+00:00","index":3,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2026-03-13T02:15:20+00:00","index":2,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2026-03-13T01:45:24+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewersInvited","content":"","date":"2026-03-12T07:48:26+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-11T15:27:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-27T07:15:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Light: Science \u0026 Applications","date":"2026-02-27T07:15:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"light-science-and-applications","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"lsa","sideBox":"Learn more about [Light: Science \u0026 Applications](http://www.nature.com/lsa/)","snPcode":"41377","submissionUrl":"https://mts-lsa.nature.com/","title":"Light: Science \u0026 Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cd76367e-9d98-45cd-b5b8-bb3131613427","owner":[],"postedDate":"March 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64372377,"name":"Physical sciences/Optics and photonics/Applied optics/Microwave photonics"},{"id":64372378,"name":"Physical sciences/Optics and photonics/Applied optics/Optoelectronic devices and components"}],"tags":[],"updatedAt":"2026-05-06T02:40:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-16 10:22:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8984623","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8984623","identity":"rs-8984623","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}