{"id":"https://openalex.org/W2555706138","doi":"https://doi.org/10.1109/tpds.2016.2626289","title":"Parallel Deep Neural Network Training for Big Data on Blue Gene/Q","display_name":"Parallel Deep Neural Network Training for Big Data on Blue Gene/Q","publication_year":2016,"publication_date":"2016-11-08","ids":{"openalex":"https://openalex.org/W2555706138","doi":"https://doi.org/10.1109/tpds.2016.2626289","mag":"2555706138"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2626289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2626289","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5108479300","display_name":"I\u2010Hsin Chung","orcid":"https://orcid.org/0000-0003-4555-9257"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"I-Hsin Chung","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062279572","display_name":"John A. Gunnels","orcid":"https://orcid.org/0000-0001-5110-190X"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Gunnels","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079327044","display_name":"Vernon Austel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vernon Austel","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023754994","display_name":"Upendra Chauhari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Upendra Chauhari","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY","IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, Yorktown Heights, NY#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5108479300"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":4.0081,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96091429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"28","issue":"6","first_page":"1703","last_page":"1714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T10320","display_name":"Neural Networks and Applications","score":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.8871821761131287},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6363407373428345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5476741194725037},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48874545097351074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46125471591949463},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45325759053230286},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4516918659210205},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44815927743911743},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.4289205074310303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3650204539299011},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3431609272956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8871821761131287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6363407373428345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476741194725037},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48874545097351074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46125471591949463},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45325759053230286},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4516918659210205},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44815927743911743},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.4289205074310303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3650204539299011},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3431609272956848},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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":1,"locations":[{"id":"doi:10.1109/tpds.2016.2626289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2626289","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W196761320","https://openalex.org/W217970951","https://openalex.org/W1533861849","https://openalex.org/W1846810180","https://openalex.org/W1969685872","https://openalex.org/W1991083751","https://openalex.org/W1998691837","https://openalex.org/W2006903949","https://openalex.org/W2034297532","https://openalex.org/W2058641082","https://openalex.org/W2076794394","https://openalex.org/W2080035108","https://openalex.org/W2097428361","https://openalex.org/W2102017903","https://openalex.org/W2109722477","https://openalex.org/W2114016253","https://openalex.org/W2120920992","https://openalex.org/W2130984546","https://openalex.org/W2131230754","https://openalex.org/W2136922672","https://openalex.org/W2155117693","https://openalex.org/W2160815625","https://openalex.org/W2166706236","https://openalex.org/W2168231600","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2606027310","https://openalex.org/W2951282416","https://openalex.org/W2963340809","https://openalex.org/W4298114557","https://openalex.org/W6601785968","https://openalex.org/W6608133726","https://openalex.org/W6608710415","https://openalex.org/W6631943919","https://openalex.org/W6674634876","https://openalex.org/W6676367512","https://openalex.org/W6679733791","https://openalex.org/W6684249991","https://openalex.org/W6684859321","https://openalex.org/W6697318756","https://openalex.org/W6711962127","https://openalex.org/W6713280142","https://openalex.org/W6843760115"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W4315865067","https://openalex.org/W3208304128","https://openalex.org/W4390846322"],"abstract_inverted_index":{"Deep":[0,109],"Neural":[1,110],"Networks":[2],"(DNNs)":[3],"have":[4],"recently":[5],"been":[6,46],"shown":[7],"to":[8,43,55,66,106,140,193,204],"significantly":[9],"outperform":[10],"existing":[11],"machine":[12],"learning":[13],"techniques":[14],"in":[15,26,50,199,213],"several":[16],"pattern":[17],"recognition":[18],"tasks.":[19],"DNNs":[20,44],"are":[21,177],"the":[22,47,57,60,77,94,114,127,186],"state-of-the-art":[23],"models":[24],"used":[25],"image":[27],"recognition,":[28],"object":[29],"detection,":[30],"classification":[31],"and":[32,34,36,52,83,174],"tracking,":[33],"speech":[35,182],"language":[37],"processing":[38],"applications.":[39],"The":[40,166],"biggest":[41],"drawback":[42],"has":[45],"enormous":[48],"cost":[49,95],"computation":[51],"time":[53,71],"taken":[54],"train":[56,205],"parameters":[58],"of":[59,79,93,96,146,164,210],"networks-often":[61],"a":[62,143,214],"tenfold":[63],"increase":[64],"relative":[65],"conventional":[67],"technologies.":[68],"Such":[69,134],"training":[70,125,211],"costs":[72],"can":[73],"be":[74],"mitigated":[75],"by":[76],"application":[78],"parallel":[80],"computing":[81],"algorithms":[82,87],"architectures.":[84],"However,":[85],"these":[86],"often":[88],"run":[89],"into":[90],"difficulties":[91],"because":[92],"inter-processor":[97,154],"communication":[98,155],"bottlenecks.":[99],"In":[100],"this":[101,162],"paper,":[102],"we":[103,122],"describe":[104],"how":[105,169],"enable":[107],"Parallel":[108],"Network":[111],"Training":[112],"on":[113,180,188],"IBM":[115],"Blue":[116],"Gene/Q":[117],"(BG/Q)":[118],"computer":[119],"system.":[120],"Specifically,":[121],"explore":[123],"DNN":[124],"using":[126,208],"data-parallel":[128],"Hessian-free":[129],"2nd":[130],"order":[131],"optimization":[132],"algorithm.":[133,165],"an":[135,158],"algorithm":[136],"is":[137,157],"particularly":[138],"well-suited":[139],"parallelization":[141],"across":[142],"large":[144],"set":[145],"loosely":[147],"coupled":[148],"processors.":[149],"BG/Q,":[150],"with":[151,196],"its":[152],"excellent":[153],"characteristics,":[156],"ideal":[159],"match":[160],"for":[161],"type":[163],"paper":[167],"discusses":[168],"issues":[170],"regarding":[171],"programming":[172],"model":[173],"data-dependent":[175],"imbalances":[176],"addressed.":[178],"Results":[179],"large-scale":[181],"tasks":[183],"show":[184],"that":[185],"performance":[187],"BG/Q":[189],"scales":[190],"linearly":[191],"up":[192],"4,096":[194],"processes":[195],"no":[197],"loss":[198],"accuracy.":[200],"This":[201],"allows":[202],"us":[203],"neural":[206],"networks":[207],"billions":[209],"examples":[212],"few":[215],"hours.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}