{"id":"https://openalex.org/W2766347095","doi":"https://doi.org/10.1109/hpec.2017.8091025","title":"Application of convolutional neural networks on Intel\u00ae Xeon\u00ae processor with integrated FPGA","display_name":"Application of convolutional neural networks on Intel\u00ae Xeon\u00ae processor with integrated FPGA","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2766347095","doi":"https://doi.org/10.1109/hpec.2017.8091025","mag":"2766347095"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2017.8091025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-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/A5055662480","display_name":"Philip Colangelo","orcid":null},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philip Colangelo","raw_affiliation_strings":["Intel Corporation, San Jose, USA","University of Massachusetts Lowell, Lowell, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, San Jose, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080301343","display_name":"Enno Luebbers","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enno Luebbers","raw_affiliation_strings":["Intel Corporation, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, San Jose, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074836221","display_name":"Randy Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randy Huang","raw_affiliation_strings":["Intel Corporation, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, San Jose, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062664944","display_name":"Martin Margala","orcid":"https://orcid.org/0000-0002-0034-0369"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Margala","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013923723","display_name":"Kevin Nealis","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Nealis","raw_affiliation_strings":["Intel Corporation, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, San Jose, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055662480"],"corresponding_institution_ids":["https://openalex.org/I133738476","https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.9102,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84085763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"7"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9969000220298767,"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/T10320","display_name":"Neural Networks and Applications","score":0.9958000183105469,"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":0.8240171670913696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8180841207504272},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.8015161752700806},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7315821647644043},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6209745407104492},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.6117428541183472},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5183716416358948},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4610952138900757},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4300985038280487},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3940281271934509},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3449944853782654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22598960995674133}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8240171670913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8180841207504272},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.8015161752700806},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7315821647644043},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6209745407104492},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.6117428541183472},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5183716416358948},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4610952138900757},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4300985038280487},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3940281271934509},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3449944853782654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22598960995674133}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2017.8091025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1841592590","https://openalex.org/W1902934009","https://openalex.org/W2108598243","https://openalex.org/W2294282016","https://openalex.org/W2337344472","https://openalex.org/W2395566064","https://openalex.org/W2431931973","https://openalex.org/W2529546376","https://openalex.org/W2565125333","https://openalex.org/W2583383421","https://openalex.org/W2949117887","https://openalex.org/W2950094539","https://openalex.org/W2962835968","https://openalex.org/W2963114950","https://openalex.org/W2963374099","https://openalex.org/W3102169921","https://openalex.org/W6637373629","https://openalex.org/W6639703010","https://openalex.org/W6676297131"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W2467043670","https://openalex.org/W4252450863","https://openalex.org/W2022867993","https://openalex.org/W2051078434","https://openalex.org/W2085105049","https://openalex.org/W3203561460","https://openalex.org/W3009624197","https://openalex.org/W4251138667","https://openalex.org/W2682544458"],"abstract_inverted_index":{"Intel\u00ae's":[0],"Xeon\u00ae":[1],"processor":[2,183,225],"with":[3,21,126],"integrated":[4],"FPGA":[5,29,215,227],"is":[6],"a":[7,17,57,65,129,161,211],"new":[8,206],"research":[9],"platform":[10,43,207],"that":[11,68,132,178,208,219],"provides":[12,128],"all":[13],"the":[14,22,31,46,81,87,101,107,136,143,147,155,168,171,180,214,223,232],"capabilities":[15],"of":[16,25,50,80,103,201,213],"Broadwell":[18,181],"Xeon":[19,182,224],"Processor":[20],"added":[23],"functionality":[24],"an":[26,39],"Arria":[27,185],"10":[28,186],"in":[30,112,150,167],"same":[32],"package.":[33],"In":[34],"this":[35,42,205],"paper,":[36],"we":[37,153,188,229],"present":[38],"implementation":[40],"on":[41,236],"to":[44,55,77,91,114,142,160],"showcase":[45],"abilities":[47],"and":[48,72,157,184,226,239],"effectiveness":[49],"utilizing":[51],"both":[52,222],"hardware":[53],"architectures":[54],"accelerate":[56],"convolutional":[58],"based":[59],"neural":[60],"network":[61,66],"(CNN).":[62],"We":[63],"choose":[64],"topology":[67],"uses":[69],"binary":[70,96,163],"weights":[71],"low":[73,172],"precision":[74],"activation":[75],"data":[76,159],"take":[78],"advantage":[79],"available":[82],"customizable":[83],"fabric":[84],"provided":[85],"by":[86,105,220,234,240],"FPGA.":[88,169],"Further,":[89],"compared":[90],"standard":[92],"multiply":[93],"accumulate":[94],"CNN's,":[95],"weighted":[97],"networks":[98],"(BWN)":[99],"reduce":[100],"amount":[102],"computation":[104,149],"eliminating":[106],"need":[108],"for":[109,138],"multiplication":[110],"resulting":[111],"little":[113],"no":[115],"classification":[116],"accuracy":[117],"degradation.":[118],"Coupling":[119],"Intel's":[120],"Open":[121],"Programmable":[122],"Acceleration":[123],"Engine":[124],"(OPAE)":[125],"Caffe":[127],"robust":[130],"framework":[131],"was":[133],"used":[134],"as":[135],"foundation":[137],"our":[139,151],"application.":[140],"Due":[141],"convolution":[144,164],"primitives":[145],"taking":[146],"most":[148],"network,":[152],"offload":[154],"feature":[156],"weight":[158],"customized":[162],"accelerator":[165],"loaded":[166],"Employing":[170],"latency":[173],"Quick":[174],"Path":[175],"Interconnect":[176],"(QPI)":[177],"bridges":[179],"FPGA,":[187],"can":[189,230],"carry":[190],"out":[191],"fine-grained":[192],"offloads":[193],"while":[194],"avoiding":[195],"bandwidth":[196],"bottlenecks.":[197],"An":[198],"initial":[199],"proof":[200],"concept":[202],"design":[203],"showcasing":[204],"utilizes":[209],"only":[210],"portion":[212],"core":[216],"logic":[217],"exemplifies":[218],"using":[221],"together":[228],"improve":[231],"throughput":[233],"2\u00d7":[235],"some":[237],"layers":[238],"1.3\u00d7":[241],"overall.":[242]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}