{"id":"https://openalex.org/W2962953210","doi":"https://doi.org/10.1145/3358192","title":"Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference","display_name":"Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference","publication_year":2019,"publication_date":"2019-10-08","ids":{"openalex":"https://openalex.org/W2962953210","doi":"https://doi.org/10.1145/3358192","mag":"2962953210"},"language":"en","primary_location":{"id":"doi:10.1145/3358192","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358192","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358192","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3358192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019027088","display_name":"Weiwen Jiang","orcid":"https://orcid.org/0000-0002-9004-487X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwen Jiang","raw_affiliation_strings":["East China Normal University, University of Pittsburgh, University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, University of Pittsburgh, University of Notre Dame","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077381252","display_name":"Edwin H.\u2010M. Sha","orcid":"https://orcid.org/0000-0001-5605-5631"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Edwin H.-M. Sha","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381558","display_name":"Xinyi Zhang","orcid":"https://orcid.org/0000-0002-9307-1654"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698152","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-0646-440X"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005358696","display_name":"Qingfeng Zhuge","orcid":"https://orcid.org/0000-0002-1107-3470"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Zhuge","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000141831","display_name":"Yiyu Shi","orcid":"https://orcid.org/0000-0002-6788-9823"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyu Shi","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066534595","display_name":"Jingtong Hu","orcid":"https://orcid.org/0000-0003-4029-4034"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingtong Hu","raw_affiliation_strings":["University of Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8559,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.96955165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"18","issue":"5s","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8188732266426086},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8185211420059204},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6384166479110718},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6370146870613098},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6265870332717896},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48280107975006104},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4720414876937866},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.46887803077697754},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4414484202861786},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.427106648683548},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.41859662532806396},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.394443541765213},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35491153597831726},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3437688946723938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15516534447669983},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12993913888931274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188732266426086},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8185211420059204},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6384166479110718},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6370146870613098},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6265870332717896},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48280107975006104},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4720414876937866},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.46887803077697754},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4414484202861786},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.427106648683548},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.41859662532806396},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.394443541765213},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35491153597831726},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3437688946723938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15516534447669983},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12993913888931274},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3358192","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358192","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358192","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1907.08985","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.08985","pdf_url":"https://arxiv.org/pdf/1907.08985","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3358192","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358192","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358192","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2047720370","display_name":null,"funder_award_id":"61472052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5283847649","display_name":null,"funder_award_id":"CCF-1820537","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5744410496","display_name":null,"funder_award_id":"CCF-1820537","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962953210.pdf","grobid_xml":"https://content.openalex.org/works/W2962953210.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2076285066","https://openalex.org/W2094756095","https://openalex.org/W2163605009","https://openalex.org/W2294282016","https://openalex.org/W2466675884","https://openalex.org/W2474119684","https://openalex.org/W2475840367","https://openalex.org/W2513568085","https://openalex.org/W2518660313","https://openalex.org/W2564533549","https://openalex.org/W2584311934","https://openalex.org/W2599379624","https://openalex.org/W2606722458","https://openalex.org/W2613718673","https://openalex.org/W2624745627","https://openalex.org/W2742947407","https://openalex.org/W2783681199","https://openalex.org/W2796625795","https://openalex.org/W2798956872","https://openalex.org/W2799912737","https://openalex.org/W2883929540","https://openalex.org/W2884001105","https://openalex.org/W2886457641","https://openalex.org/W2889354425","https://openalex.org/W2890068895","https://openalex.org/W2892446824","https://openalex.org/W2895195713","https://openalex.org/W2899915146","https://openalex.org/W2911884654","https://openalex.org/W2915364523","https://openalex.org/W2916975147","https://openalex.org/W2944864513","https://openalex.org/W2944950984","https://openalex.org/W2945306514","https://openalex.org/W2949357998","https://openalex.org/W2953212265","https://openalex.org/W2953328899","https://openalex.org/W2957020430","https://openalex.org/W2963037989","https://openalex.org/W2963547613","https://openalex.org/W2963948425","https://openalex.org/W2997828269","https://openalex.org/W3016142271","https://openalex.org/W3098269293","https://openalex.org/W3147600416","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W2532502681","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Real-time":[0],"Deep":[1],"Neural":[2,167],"Network":[3,168],"(DNN)":[4],"inference":[5,44],"with":[6,45,83,228],"low-latency":[7],"requirement":[8],"has":[9],"become":[10],"increasingly":[11],"important":[12],"for":[13,42,117],"numerous":[14],"applications":[15],"in":[16,40],"both":[17,35],"cloud":[18],"computing":[19,25],"(e.g.,":[20,26],"Apple\u2019s":[21],"Siri)":[22],"and":[23,38,125,134],"edge":[24],"Google/Waymo\u2019s":[27],"driverless":[28],"car).":[29],"FPGA-based":[30],"DNN":[31,119],"accelerators":[32],"have":[33],"demonstrated":[34],"superior":[36],"flexibility":[37],"performance;":[39],"addition,":[41],"real-time":[43],"low":[46],"batch":[47],"size,":[48],"FPGA":[49,222],"is":[50,65,242],"expected":[51],"to":[52,79,121,138,173,183,198,213,236],"achieve":[53,232],"further":[54,256],"performance":[55,59],"improvement.":[56],"However,":[57],"the":[58,62,68,84,106,110,127,131,135,139,185,201,237,245,251],"gain":[60],"from":[61,104,210],"single-FPGA":[63,91,239],"design":[64,107,196],"obstructed":[66],"by":[67,207],"limited":[69],"on-chip":[70],"resource.":[71],"In":[72,93,161],"this":[73,162],"paper,":[74,163],"we":[75,97,148,164,192],"employ":[76],"multiple":[77],"FPGAs":[78,230,248],"cooperatively":[80],"run":[81],"DNNs":[82],"objective":[85],"of":[86,112,142,159,187,247],"achieving":[87,105],"super-linear":[88],"speed-up":[89],"against":[90],"design.":[92,240],"implementing":[94],"such":[95],"systems,":[96],"found":[98],"two":[99],"barriers":[100],"that":[101,226],"hinder":[102],"us":[103],"goal:":[108],"(1)":[109],"lack":[111],"a":[113,150,171,194],"clear":[114],"partition":[115,189],"scheme":[116],"each":[118],"layer":[120],"fully":[122],"exploit":[123],"parallelism,":[124],"(2)":[126],"insufficient":[128],"bandwidth":[129,206],"between":[130],"off-chip":[132],"memory":[133,205,211],"accelerator":[136],"due":[137],"growing":[140],"size":[141],"DNNs.":[143,160],"To":[144],"tackle":[145],"these":[146],"issues,":[147],"propose":[149],"general":[151],"framework,":[152],"\u201cSuper-LIP\u201d,":[153],"which":[154],"can":[155,231,254],"support":[156,184],"different":[157],"kinds":[158],"take":[165],"Convolutional":[166],"(CNN)":[169],"as":[170,244],"vehicle":[172],"illustrate":[174],"Super-LIP.":[175],"We":[176,216],"first":[177],"formulate":[178],"an":[179],"accurate":[180],"system-level":[181],"model":[182],"exploration":[186],"best":[188],"schemes.":[190],"Then,":[191],"develop":[193],"novel":[195],"methodology":[197],"effectively":[199],"alleviate":[200],"heavy":[202],"loads":[203],"on":[204,220],"moving":[208],"traffic":[209],"bus":[212],"inter-FPGA":[214],"links.":[215],"implement":[217],"Super-LIP":[218,227],"based":[219],"ZCU102":[221],"boards.":[223],"Results":[224],"demonstrate":[225],"2":[229],"3.48\u00d7":[233],"speedup,":[234],"compared":[235],"state-of-the-art":[238],"What":[241],"more,":[243],"number":[246],"scales":[249],"up,":[250],"system":[252],"latency":[253],"be":[255],"reduced":[257],"while":[258],"maintaining":[259],"high":[260],"energy":[261],"efficiency.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2019-07-30T00:00:00"}