{"id":"https://openalex.org/W3106981120","doi":"https://doi.org/10.1109/mm.2020.3039835","title":"Distributed Deep Learning With GPU-FPGA Heterogeneous Computing","display_name":"Distributed Deep Learning With GPU-FPGA Heterogeneous Computing","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W3106981120","doi":"https://doi.org/10.1109/mm.2020.3039835","mag":"3106981120"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2020.3039835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2020.3039835","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-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/A5019594872","display_name":"Kenji Tanaka","orcid":"https://orcid.org/0000-0003-4438-5830"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Tanaka","raw_affiliation_strings":["NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077656627","display_name":"Yuki Arikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Arikawa","raw_affiliation_strings":["NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025262666","display_name":"Tsuyoshi Ito","orcid":"https://orcid.org/0000-0001-6193-2408"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuyoshi Ito","raw_affiliation_strings":["NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036198872","display_name":"Kazutaka Morita","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazutaka Morita","raw_affiliation_strings":["NTT Software Innovation Center, NTT Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center, NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003486165","display_name":"Naru Nemoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naru Nemoto","raw_affiliation_strings":["NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087051382","display_name":"Kazuhiko Terada","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiko Terada","raw_affiliation_strings":["NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027440605","display_name":"Junji Teramoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junji Teramoto","raw_affiliation_strings":["NTT Software Innovation Center, NTT Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center, NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037700663","display_name":"Takeshi Sakamoto","orcid":"https://orcid.org/0000-0001-6312-2249"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Sakamoto","raw_affiliation_strings":["NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5019594872"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51095651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"41","issue":"1","first_page":"15","last_page":"22"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994999766349792,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8874727487564087},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8347164392471313},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7105037569999695},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.640807032585144},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5475276112556458},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49773672223091125},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4698076844215393},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4262534976005554},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42448121309280396},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.41575825214385986},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3907850384712219},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3317676782608032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21660259366035461},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1095658540725708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8874727487564087},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8347164392471313},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7105037569999695},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.640807032585144},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5475276112556458},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49773672223091125},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4698076844215393},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4262534976005554},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42448121309280396},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.41575825214385986},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3907850384712219},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3317676782608032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21660259366035461},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1095658540725708},{"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:10.1109/mm.2020.3039835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2020.3039835","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2057332538","https://openalex.org/W2557283755","https://openalex.org/W2755567635","https://openalex.org/W2796649226","https://openalex.org/W2901541570","https://openalex.org/W2915943718","https://openalex.org/W2931075014","https://openalex.org/W2972087877","https://openalex.org/W4301239768","https://openalex.org/W6748645090","https://openalex.org/W6750448596","https://openalex.org/W6759814442"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2081416538"],"abstract_inverted_index":{"In":[0],"distributed":[1,49,126],"deep":[2],"learning":[3],"(DL),":[4],"collective":[5],"communication":[6,112],"algorithms,":[7],"such":[8],"as":[9],"Allreduce,":[10],"used":[11],"to":[12,60,101,134],"share":[13],"training":[14,88,124],"results":[15],"between":[16],"graphical":[17],"processing":[18],"units":[19],"(GPUs)":[20],"are":[21],"an":[22],"inevitable":[23],"bottleneck.":[24],"We":[25,67],"hypothesize":[26],"that":[27],"a":[28,37,69,74],"cache":[29],"access":[30],"latency":[31,99],"occurred":[32],"at":[33,63],"every":[34],"Allreduce":[35,85,98],"is":[36,58,132],"significant":[38],"bottleneck":[39],"in":[40,73,125,139],"the":[41,64,95,111],"current":[42],"computational":[43],"systems":[44],"with":[45,128],"high-bandwidth":[46],"interconnects":[47],"for":[48,123],"DL.":[50],"To":[51],"reduce":[52],"this":[53,80],"frequency":[54],"of":[55,94,110],"latency,":[56],"it":[57],"important":[59],"aggregate":[61],"data":[62,70],"network":[65],"interfaces.":[66],"implement":[68],"aggregation":[71],"circuit":[72],"field-programmable":[75],"gate":[76],"array":[77],"(FPGA).":[78],"Using":[79],"FPGA,":[81],"we":[82],"proposed":[83],"novel":[84],"architecture":[86],"and":[87,114,130],"strategy":[89],"without":[90,136],"accuracy":[91],"degradation.":[92],"Results":[93],"measurement":[96],"show":[97],"reduction":[100],"1/4.":[102],"Our":[103],"system":[104],"can":[105],"also":[106],"conceal":[107],"about":[108],"90%":[109],"overhead":[113],"improve":[115],"scalability":[116],"by":[117],"20%.":[118],"The":[119],"end-to-end":[120],"time":[121],"consumed":[122],"DL":[127],"ResNet-50":[129],"ImageNet":[131],"reduced":[133],"87.3%":[135],"any":[137],"degradation":[138],"validation":[140],"accuracy.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}