{"id":"https://openalex.org/W2963741033","doi":"https://doi.org/10.1145/3337821.3337846","title":"An Efficient Design Flow for Accelerating Complicated-connected CNNs on a Multi-FPGA Platform","display_name":"An Efficient Design Flow for Accelerating Complicated-connected CNNs on a Multi-FPGA Platform","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963741033","doi":"https://doi.org/10.1145/3337821.3337846","mag":"2963741033"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","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/A5102857675","display_name":"De\u2010Guang Wang","orcid":"https://orcid.org/0000-0003-0357-0183"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deguang Wang","raw_affiliation_strings":["National University of Defense Technology, College of Computer, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, College of Computer, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["National University of Defense Technology, College of Computer, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, College of Computer, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["National University of Defense Technology, College of Computer, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, College of Computer, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyuan Zhang","raw_affiliation_strings":["National University of Defense Technology, College of Computer, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, College of Computer, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8727678060531616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8377420902252197},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6961348652839661},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5684639811515808},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.5659454464912415},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.47725698351860046},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4483349919319153},{"id":"https://openalex.org/keywords/design-flow","display_name":"Design flow","score":0.44393303990364075},{"id":"https://openalex.org/keywords/fpga-prototype","display_name":"FPGA prototype","score":0.4345177710056305},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43014922738075256},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3616167902946472},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35760849714279175},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.35329508781433105},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35280126333236694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2636275291442871},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15459612011909485}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8727678060531616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377420902252197},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6961348652839661},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5684639811515808},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.5659454464912415},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.47725698351860046},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4483349919319153},{"id":"https://openalex.org/C37135326","wikidata":"https://www.wikidata.org/wiki/Q931942","display_name":"Design flow","level":2,"score":0.44393303990364075},{"id":"https://openalex.org/C203864433","wikidata":"https://www.wikidata.org/wiki/Q5426992","display_name":"FPGA prototype","level":3,"score":0.4345177710056305},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43014922738075256},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3616167902946472},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35760849714279175},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35329508781433105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35280126333236694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2636275291442871},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15459612011909485},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3337821.3337846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8799999952316284,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2163605009","https://openalex.org/W2193413348","https://openalex.org/W2276486856","https://openalex.org/W2285660444","https://openalex.org/W2294282016","https://openalex.org/W2334211951","https://openalex.org/W2475840367","https://openalex.org/W2504108613","https://openalex.org/W2603836393","https://openalex.org/W2789246071","https://openalex.org/W2808917878","https://openalex.org/W2810861508","https://openalex.org/W2890068895","https://openalex.org/W2895195713","https://openalex.org/W2899771611","https://openalex.org/W2950656546","https://openalex.org/W2963446712","https://openalex.org/W6725739302"],"related_works":["https://openalex.org/W2037960874","https://openalex.org/W1973069902","https://openalex.org/W2269990635","https://openalex.org/W4234221021","https://openalex.org/W1567432572","https://openalex.org/W2119904701","https://openalex.org/W2535403365","https://openalex.org/W2159184138","https://openalex.org/W4365793791","https://openalex.org/W4295935044"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4,25,30,83,90,108],"achieved":[5,31,91],"impressive":[6],"performance":[7,33],"on":[8,152,185],"various":[9],"computer":[10],"vision":[11],"tasks.":[12],"To":[13],"facilitate":[14],"better":[15],"performance,":[16],"some":[17],"complicated-connected":[18,105,150],"CNN":[19,106,133],"models":[20,107,187],"(e.g.,":[21],"GoogLeNet":[22],"and":[23,29,40,46,62,72,89,94,125,162,204,209,223,229],"DenseNet)":[24],"recently":[26],"been":[27,84],"proposed,":[28],"state-of-the-art":[32],"in":[34,56,104,136],"the":[35,60,69,98,110,123,147,190],"fields":[36],"of":[37,65,75,101,114,149,200,219],"image":[38],"classification":[39],"segmentation.":[41],"However,":[42,97],"CNNs":[43,88,151],"are":[44,119],"computation-":[45],"memory-intensive.":[47],"Thus,":[48],"it":[49],"is":[50,175],"significant":[51],"to":[52,58,68,86,121,145,177,202,207,221,226],"develop":[53],"hardware":[54,112],"accelerators":[55,82],"order":[57],"accelerate":[59,146],"inference":[61,148],"training":[63],"processes":[64],"CNNs.":[66],"Due":[67],"high-performance,":[70],"reconfigurable":[71],"energy-efficient":[73],"nature":[74],"Field-Programmable":[76],"Gate":[77],"Arrays":[78],"(FPGAs),":[79],"many":[80],"FPGA-based":[81],"proposed":[85,176,191],"implement":[87],"higher":[92],"throughput":[93,198],"energy":[95,216],"efficiency.":[96],"large":[99],"number":[100],"parameters":[102],"involved":[103],"exceeded":[109],"limited":[111],"resources":[113],"single":[115],"FPGA":[116],"board,":[117],"which":[118],"unable":[120],"meet":[122],"memory":[124],"computation":[126],"resource":[127],"demands":[128],"associated":[129],"with":[130,171],"mapping":[131,159],"entire":[132],"models.":[134],"Accordingly,":[135],"this":[137],"paper,":[138],"we":[139],"propose":[140],"a":[141,153,168,197],"complete":[142],"design":[143,163,181,194],"flow":[144],"multi-FPGA":[154,169,192],"platform,":[155],"including":[156],"DAG":[157],"abstraction,":[158],"scheme":[160],"generation":[161],"space":[164],"exploration.":[165],"In":[166],"addition,":[167],"system":[170,193],"flexible":[172],"inter-FPGA":[173],"communications":[174],"efficiently":[178],"support":[179],"our":[180],"flow.":[182],"Experimental":[183],"results":[184],"representative":[186],"illustrate":[188],"that":[189],"can":[195],"achieve":[196],"acceleration":[199],"up":[201,220],"145.2\u00d7":[203],"2.5\u00d7":[205],"compared":[206,225],"CPU":[208,228],"GPU":[210,230],"solutions,":[211],"as":[212,214],"well":[213],"an":[215],"efficiency":[217],"improvement":[218],"139.1\u00d7":[222],"4.8\u00d7":[224],"multi-core":[227],"solutions.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}