{"id":"https://openalex.org/W3092611151","doi":"https://doi.org/10.1109/dac18072.2020.9218581","title":"FTDL: A Tailored FPGA-Overlay for Deep Learning with High Scalability","display_name":"FTDL: A Tailored FPGA-Overlay for Deep Learning with High Scalability","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3092611151","doi":"https://doi.org/10.1109/dac18072.2020.9218581","mag":"3092611151"},"language":"en","primary_location":{"id":"doi:10.1109/dac18072.2020.9218581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027887058","display_name":"Runbin Shi","orcid":"https://orcid.org/0000-0003-4901-5476"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Runbin Shi","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114500402","display_name":"Yuhao Ding","orcid":"https://orcid.org/0009-0009-4819-9251"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuhao Ding","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904614","display_name":"Xuechao Wei","orcid":"https://orcid.org/0000-0002-0996-2260"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechao Wei","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032688465","display_name":"He Li","orcid":"https://orcid.org/0000-0003-3993-7928"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"He Li","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338895","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0001-7948-4236"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Stevens Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020581824","display_name":"Hayden Kwok\u2010Hay So","orcid":"https://orcid.org/0000-0002-6514-0237"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hayden K.-H. So","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.992900013923645,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9926999807357788,"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/scalability","display_name":"Scalability","score":0.7919642925262451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7883723974227905},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7748485207557678},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.6899269819259644},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5829958319664001},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5423297882080078},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5280345678329468},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4482201337814331},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.43467313051223755},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3936674892902374},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.37179726362228394},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3679753243923187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24193444848060608},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1165948212146759}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7919642925262451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883723974227905},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7748485207557678},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.6899269819259644},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5829958319664001},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5423297882080078},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5280345678329468},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4482201337814331},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.43467313051223755},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3936674892902374},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37179726362228394},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3679753243923187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24193444848060608},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1165948212146759}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18072.2020.9218581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18072.2020.9218581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 57th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1972821547","https://openalex.org/W2466675884","https://openalex.org/W2583383421","https://openalex.org/W2584311934","https://openalex.org/W2625954420","https://openalex.org/W2727238169","https://openalex.org/W2729080111","https://openalex.org/W2737762472","https://openalex.org/W2756829667","https://openalex.org/W2761085955","https://openalex.org/W2761262947","https://openalex.org/W2785662229","https://openalex.org/W2795915628","https://openalex.org/W2946610455","https://openalex.org/W2946620527","https://openalex.org/W2964333985","https://openalex.org/W2983964638","https://openalex.org/W3043571714","https://openalex.org/W4233035441","https://openalex.org/W6753380695","https://openalex.org/W6769454693"],"related_works":["https://openalex.org/W595346907","https://openalex.org/W153296825","https://openalex.org/W598989511","https://openalex.org/W2375779923","https://openalex.org/W2041986468","https://openalex.org/W1967800214","https://openalex.org/W2055675609","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506"],"abstract_inverted_index":{"Fast":[0],"inference":[1,83],"is":[2,41],"of":[3,10,48,58,79,98,125],"paramount":[4],"value":[5],"to":[6,27,131],"a":[7,18,122],"wide":[8],"range":[9],"deep":[11,24],"learning":[12,25],"applications.":[13],"This":[14],"work":[15],"presents":[16],"FTDL,":[17],"highly-scalable":[19],"FPGA":[20],"overlay":[21,40,86],"framework":[22,71],"for":[23,44],"applications,":[26],"address":[28],"the":[29,45,59,85,140],"architecture":[30],"and":[31,65,76,87,103,109,114,135],"hardware":[32,92,104],"mismatch":[33],"faced":[34],"by":[35],"traditional":[36],"efforts.":[37],"The":[38],"FTDL":[39,106],"specifically":[42],"optimized":[43],"tiled":[46],"structure":[47],"FPGAs,":[49],"thereby":[50],"achieving":[51],"post-place-and-route":[52],"operating":[53,101,120],"frequencies":[54],"exceeding":[55],"88":[56],"%":[57,91],"theoretical":[60],"maximum":[61],"across":[62],"different":[63],"devices":[64],"design":[66],"scales.":[67],"A":[68],"flexible":[69],"compilation":[70],"efficiently":[72],"schedules":[73],"matrix":[74],"multiply":[75],"convolution":[77],"operations":[78],"large":[80],"neural":[81],"network":[82],"on":[84,94,116],"achieved":[88],"over":[89],"80":[90],"efficiency":[93,124],"average.":[95],"Taking":[96],"advantage":[97],"both":[99],"high":[100],"frequency":[102],"efficiency,":[105],"achieves":[107],"402.6":[108],"151.2":[110],"FPS":[111],"with":[112],"GoogLeNet":[113],"ResNet50":[115],"ImageNet,":[117],"respectively,":[118],"while":[119],"at":[121],"power":[123],"27.6":[126],"GOPS/W,":[127],"making":[128],"it":[129],"up":[130],"7.7\u00d7":[132],"higher":[133],"performance":[134],"1.9\u00d7":[136],"more":[137],"power-efficient":[138],"than":[139],"state-of-the-art.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}