{"id":"https://openalex.org/W4417284309","doi":"https://doi.org/10.1109/tcsi.2025.3636104","title":"FPGA-Based Adjoint Method Accelerator for Rapid Optical Inverse Design","display_name":"FPGA-Based Adjoint Method Accelerator for Rapid Optical Inverse Design","publication_year":2025,"publication_date":"2025-12-12","ids":{"openalex":"https://openalex.org/W4417284309","doi":"https://doi.org/10.1109/tcsi.2025.3636104"},"language":null,"primary_location":{"id":"doi:10.1109/tcsi.2025.3636104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3636104","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems I: Regular Papers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050941002","display_name":"Lianyou Lai","orcid":"https://orcid.org/0009-0005-2825-9983"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianyou Lai","raw_affiliation_strings":["School of Ocean Information Engineering, Jimei University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0005-2825-9983","affiliations":[{"raw_affiliation_string":"School of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiheng Ni","orcid":"https://orcid.org/0009-0008-0966-3309"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Ni","raw_affiliation_strings":["School of Ocean Information Engineering, Jimei University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0008-0966-3309","affiliations":[{"raw_affiliation_string":"School of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013631588","display_name":"Miaoxiang Yu","orcid":"https://orcid.org/0000-0002-4382-9009"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoxiang Yu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-4382-9009","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026897196","display_name":"Zhenyu Xu","orcid":"https://orcid.org/0000-0002-3635-2409"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenyu Xu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-3635-2409","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102717169","display_name":"Weijian Xu","orcid":"https://orcid.org/0009-0009-5306-4247"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijian Xu","raw_affiliation_strings":["School of Ocean Information Engineering, Jimei University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0009-5306-4247","affiliations":[{"raw_affiliation_string":"School of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33525147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":"5","first_page":"3399","last_page":"3409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10299","display_name":"Photonic and Optical Devices","score":0.15780000388622284,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10299","display_name":"Photonic and Optical Devices","score":0.15780000388622284,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11517","display_name":"Advanced optical system design","score":0.13050000369548798,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.11500000208616257,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6898999810218811},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.6107000112533569},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5548999905586243},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5460000038146973},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4546999931335449},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.4056999981403351},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.40380001068115234},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901999711990356},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6898999810218811},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5548999905586243},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.414900004863739},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.40380001068115234},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C34972735","wikidata":"https://www.wikidata.org/wiki/Q2920267","display_name":"Engineering design process","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C48262172","wikidata":"https://www.wikidata.org/wiki/Q16908765","display_name":"Design process","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C138852830","wikidata":"https://www.wikidata.org/wiki/Q2292993","display_name":"Design methods","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C526435321","wikidata":"https://www.wikidata.org/wiki/Q1303814","display_name":"Processor design","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C55396564","wikidata":"https://www.wikidata.org/wiki/Q3084971","display_name":"Process design","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C22174128","wikidata":"https://www.wikidata.org/wiki/Q175869","display_name":"Microcode","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2025.3636104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3636104","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5013252794","display_name":null,"funder_award_id":"2023J01810","funder_id":"https://openalex.org/F4320323190","funder_display_name":"Fujian Provincial Department of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320323190","display_name":"Fujian Provincial Department of Science and Technology","ror":"https://ror.org/00rgzpv08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W145066576","https://openalex.org/W799069928","https://openalex.org/W1582934392","https://openalex.org/W1967134278","https://openalex.org/W2017318390","https://openalex.org/W2124994383","https://openalex.org/W2135942920","https://openalex.org/W2142063750","https://openalex.org/W2472433972","https://openalex.org/W2784648660","https://openalex.org/W2791343747","https://openalex.org/W2794979247","https://openalex.org/W2899691047","https://openalex.org/W2964287029","https://openalex.org/W2989413035","https://openalex.org/W3008967825","https://openalex.org/W3012414209","https://openalex.org/W3040346568","https://openalex.org/W3092323705","https://openalex.org/W3096729571","https://openalex.org/W3109834426","https://openalex.org/W3119560502","https://openalex.org/W3128157635","https://openalex.org/W3145837924","https://openalex.org/W3152573847","https://openalex.org/W3216539721","https://openalex.org/W3216584063","https://openalex.org/W4214653918","https://openalex.org/W4283729146","https://openalex.org/W4309229379","https://openalex.org/W4318602628","https://openalex.org/W4321192207","https://openalex.org/W4378516656","https://openalex.org/W4388855690","https://openalex.org/W4399384975"],"related_works":[],"abstract_inverted_index":{"Inverse":[0],"design":[1,31,108,136,157],"is":[2,16,93,112,168],"an":[3,17,115],"emerging":[4],"theory":[5],"in":[6,24,36,150,155,170],"material,":[7],"photonics,":[8],"and":[9,40,50,59,100,106,120,125,177],"other":[10],"fields.":[11],"The":[12,27,91,110,138],"Adjoint":[13],"Method":[14],"(AM)":[15],"efficient":[18,105],"gradient-based":[19],"optimization":[20,28,49],"strategy":[21],"commonly":[22],"used":[23],"inverse":[25,30,89,135],"design.":[26,90],"of":[29,84,134,152,183],"frameworks":[32],"faces":[33],"fundamental":[34],"challenges":[35],"achieving":[37],"computational":[38],"efficiency":[39],"scalability.":[41],"While":[42],"previous":[43],"approaches":[44],"have":[45],"explored":[46],"both":[47],"algorithmic":[48],"hardware":[51],"acceleration,":[52],"the":[53,82,85,123,143,161,173,178,184,189],"inherent":[54],"trade-offs":[55],"between":[56],"memory":[57,180],"consumption":[58],"processing":[60],"throughput":[61,192],"continue":[62],"to":[63,80,95,160,172],"limit":[64],"performance":[65,83,130,149],"at":[66],"scale.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,121],"propose":[72],"a":[73,132],"high-speed":[74],"field-programmable":[75],"gate":[76],"array":[77],"(FPGA)-based":[78],"accelerator":[79,92,111,146],"enhance":[81,101],"AM":[86],"for":[87,194],"fast":[88],"designed":[94],"significantly":[96],"reduce":[97],"computation":[98],"time":[99],"scalability,":[102],"enabling":[103],"more":[104],"rapid":[107],"iterations.":[109],"implemented":[113],"on":[114,131],"AMD":[116],"Alveo":[117],"U280":[118],"FPGA,":[119],"compared":[122,159],"FPGA":[124,145],"graphic":[126],"process":[127],"unit":[128],"(GPU)":[129],"series":[133],"tasks.":[137,196],"experimental":[139],"results":[140],"demonstrate":[141],"that":[142],"proposed":[144],"offers":[147],"superior":[148],"terms":[151],"speed,":[153],"especially":[154],"smaller":[156],"sizes":[158],"NVIDIA":[162],"A100":[163],"GPU.":[164],"This":[165],"significant":[166],"improvement":[167],"due,":[169],"part,":[171],"fully":[174],"pipelined":[175],"architecture":[176],"low":[179],"bandwidth":[181],"requirement":[182],"accelerator,":[185],"which":[186],"efficiently":[187],"handles":[188],"enormous":[190],"data":[191],"required":[193],"these":[195]},"counts_by_year":[],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2025-12-12T00:00:00"}