{"id":"https://openalex.org/W3025152414","doi":"https://doi.org/10.1109/tcad.2020.2994256","title":"CNN-on-AWS: Efficient Allocation of Multikernel Applications on Multi-FPGA Platforms","display_name":"CNN-on-AWS: Efficient Allocation of Multikernel Applications on Multi-FPGA Platforms","publication_year":2020,"publication_date":"2020-05-12","ids":{"openalex":"https://openalex.org/W3025152414","doi":"https://doi.org/10.1109/tcad.2020.2994256","mag":"3025152414"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2020.2994256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.2994256","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/345016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059220833","display_name":"Junnan Shan","orcid":"https://orcid.org/0000-0001-9405-8825"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Junnan Shan","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030646218","display_name":"Mihai T. Lazarescu","orcid":"https://orcid.org/0000-0003-0884-5158"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mihai T. Lazarescu","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031451250","display_name":"Jordi Cortadella","orcid":"https://orcid.org/0000-0001-8114-250X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Cortadella","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050365912","display_name":"Luciano Lavagno","orcid":"https://orcid.org/0000-0002-9762-6522"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luciano Lavagno","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036528695","display_name":"Mario R. Casu","orcid":"https://orcid.org/0000-0002-1026-0178"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario R. Casu","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059220833"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":1.2755,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.82395279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"40","issue":"2","first_page":"301","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7826942205429077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734261751174927},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6910569071769714},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6799962520599365},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6503924131393433},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4924522340297699},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4811609983444214},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.479827880859375},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4602230191230774},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33950912952423096},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2730412185192108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13031607866287231},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10585916042327881}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7826942205429077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734261751174927},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6910569071769714},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6799962520599365},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6503924131393433},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4924522340297699},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4811609983444214},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.479827880859375},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4602230191230774},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33950912952423096},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2730412185192108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13031607866287231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10585916042327881},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2020.2994256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.2994256","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/345016","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/345016","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/345016","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/345016","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G2629925963","display_name":null,"funder_award_id":"H2020-ICT-671632","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4683214174","display_name":null,"funder_award_id":"2017 SGR 786","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2094756095","https://openalex.org/W2163605009","https://openalex.org/W2165100134","https://openalex.org/W2171048418","https://openalex.org/W2194775991","https://openalex.org/W2466675884","https://openalex.org/W2475840367","https://openalex.org/W2518660313","https://openalex.org/W2606722458","https://openalex.org/W2895195713","https://openalex.org/W2899915146","https://openalex.org/W2900757645","https://openalex.org/W2916975147","https://openalex.org/W2944950984","https://openalex.org/W2945306514","https://openalex.org/W2946068432","https://openalex.org/W2962835968","https://openalex.org/W2962953210","https://openalex.org/W2962970995","https://openalex.org/W3121413886","https://openalex.org/W4235344346","https://openalex.org/W6684191040","https://openalex.org/W6726142829","https://openalex.org/W6762306914"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2186864281","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2074043759","https://openalex.org/W4255427455","https://openalex.org/W3042736233","https://openalex.org/W2082487009","https://openalex.org/W2373535795","https://openalex.org/W1966025497"],"abstract_inverted_index":{"Multi-FPGA":[0],"platforms,":[1],"like":[2,14],"Amazon":[3],"AWS":[4],"F1,":[5],"can":[6,109,190,212],"run":[7,229],"in":[8,63,89,104],"the":[9,44,51,54,64,74,93,99,102,106,122,142,164,196,223,230],"cloud":[10],"multikernel":[11],"pipelined":[12],"applications,":[13],"convolutional":[15],"neural":[16],"networks":[17],"(CNNs),":[18],"with":[19],"excellent":[20],"performance":[21,94],"and":[22,66,82,98,154,199],"lower":[23],"energy":[24],"consumption":[25],"than":[26,195,222],"CPUs":[27],"or":[28,71],"GPUs.":[29],"We":[30,77],"propose":[31],"a":[32,84,118,168,181,233],"method":[33,184,211],"to":[34,42,69,121,134,151,161,187],"efficiently":[35],"map":[36],"these":[37],"applications":[38],"on":[39,141],"multi-FPGA":[40],"platforms":[41],"maximize":[43],"application":[45],"throughput.":[46],"Our":[47],"methodology":[48],"finds,":[49],"for":[50,232],"given":[52],"resources,":[53],"optimal":[55,165],"number":[56],"of":[57,60,95,101,125],"parallel":[58],"instances":[59],"each":[61,96,126],"kernel":[62,139],"pipeline":[65],"their":[67],"allocation":[68],"one":[70],"more":[72,193],"among":[73],"available":[75],"FPGAs.":[76],"obtain":[78],"this":[79],"by":[80],"formulating":[81],"solving":[83],"mixed-integer,":[85],"nonlinear":[86,170],"optimization":[87],"problem,":[88],"which":[90,105],"we":[91,179,228],"model":[92],"component":[97],"duration":[100],"phases":[103],"accelerated":[107],"computation":[108,140],"be":[110,191],"split":[111],"into,":[112],"namely:":[113],"1)":[114],"data":[115,129,145,156],"transfer":[116,130,146,157],"from":[117,131,147,158],"host":[119],"CPU":[120],"DDR":[123,133,160],"memory":[124,150],"FPGA;":[127,143],"2)":[128],"FPGA":[132,135,148,152,159],"on-chip":[136,149],"memory;":[137],"3)":[138],"4)":[144],"DDR;":[153],"5)":[155],"host.":[162],"Finding":[163],"solution":[166],"using":[167],"mixed-integer":[169],"programming":[171],"(MINLP)":[172],"solver":[173,198],"is":[174],"often":[175],"highly":[176],"inefficient.":[177],"Hence,":[178],"provide":[180],"fast":[182],"heuristic":[183,210],"that":[185],"according":[186],"our":[188,209],"experiments":[189],"much":[192,219],"efficient":[194],"MINLP":[197,224],"finds":[200],"comparable":[201],"results.":[202],"For":[203],"larger":[204],"problems":[205],"(more":[206],"CNN":[207],"layers),":[208],"quickly":[213],"find":[214],"(several":[215],"thousand":[216],"times":[217],"faster)":[218],"better":[220],"solutions":[221],"solver,":[225],"even":[226],"if":[227],"latter":[231],"very":[234],"long":[235],"time.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
