{"id":"https://openalex.org/W2964688222","doi":"https://doi.org/10.1109/ipdpsw.2019.00160","title":"Towards Native Execution of Deep Learning on a Leadership-Class HPC System","display_name":"Towards Native Execution of Deep Learning on a Leadership-Class HPC System","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2964688222","doi":"https://doi.org/10.1109/ipdpsw.2019.00160","mag":"2964688222"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2019.00160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2019.00160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1550753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073529385","display_name":"Srikanth B. Yoginath","orcid":"https://orcid.org/0000-0001-8423-6050"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srikanth Yoginath","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013085686","display_name":"Maksudul Alam","orcid":"https://orcid.org/0000-0002-4941-463X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maksudul Alam","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028188095","display_name":"Arvind Ramanathan","orcid":"https://orcid.org/0000-0002-1622-5488"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Ramanathan","raw_affiliation_strings":["Oak Ridge National Laboratory, Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032222900","display_name":"Debsindhu Bhowmik","orcid":"https://orcid.org/0000-0001-7770-9091"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debsindhu Bhowmik","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002880262","display_name":"Nouamane Laanait","orcid":"https://orcid.org/0000-0001-7100-4250"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nouamane Laanait","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046010392","display_name":"Kalyan S. Perumalla","orcid":"https://orcid.org/0000-0002-7458-0832"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kalyan S. Perumalla","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5073529385"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.8219,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.6898375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"116","issue":null,"first_page":"941","last_page":"950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials 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":0.9945999979972839,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9833999872207642,"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":0.8618459701538086},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7037999629974365},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.697577953338623},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6860747337341309},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5583935379981995},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5281322598457336},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47596949338912964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4691202938556671},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.45112696290016174},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.4202975034713745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32164642214775085},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14539560675621033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618459701538086},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7037999629974365},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.697577953338623},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6860747337341309},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5583935379981995},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5281322598457336},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47596949338912964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4691202938556671},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.45112696290016174},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4202975034713745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32164642214775085},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14539560675621033},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdpsw.2019.00160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2019.00160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1550753","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1550753","pdf_url":"https://www.osti.gov/servlets/purl/1550753","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1550753","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1550753","pdf_url":"https://www.osti.gov/servlets/purl/1550753","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964688222.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1978159078","https://openalex.org/W1983881002","https://openalex.org/W2069845974","https://openalex.org/W2108598243","https://openalex.org/W2181347294","https://openalex.org/W2194775991","https://openalex.org/W2304682230","https://openalex.org/W2467604901","https://openalex.org/W2512387141","https://openalex.org/W2597705344","https://openalex.org/W2622263826","https://openalex.org/W2759465730","https://openalex.org/W2884711234","https://openalex.org/W2888206291","https://openalex.org/W2900824371","https://openalex.org/W2905478662","https://openalex.org/W2915159619","https://openalex.org/W2953302413","https://openalex.org/W2962780982","https://openalex.org/W6646429642","https://openalex.org/W6685777803","https://openalex.org/W6698022300","https://openalex.org/W6739622702","https://openalex.org/W6744711479","https://openalex.org/W6753209298","https://openalex.org/W6756488470"],"related_works":["https://openalex.org/W2003935582","https://openalex.org/W2950520577","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W2468095077","https://openalex.org/W2593878938","https://openalex.org/W305742777","https://openalex.org/W29548032","https://openalex.org/W1229628"],"abstract_inverted_index":{"Large":[0],"parallel":[1,7,64,75,134,175],"machines":[2],"generally":[3],"offer":[4],"the":[5,19,28,63,78,122,130,171],"best":[6],"performance":[8,37,168],"with":[9,18,73],"\"native":[10],"execution\"":[11],"that":[12],"is":[13,139,164],"achieved":[14,72],"using":[15,107,121],"codes":[16],"developed":[17],"optimized":[20],"compilers,":[21],"communication":[22],"libraries,":[23],"and":[24,35,67,83,115,119,185],"runtimes":[25],"offered":[26],"on":[27,45,89,102],"machines.":[29],"In":[30,77,127],"this":[31],"paper,":[32],"we":[33,58,86],"report":[34],"analyze":[36],"results":[38,97,169],"from":[39,100,112],"native":[40,74],"execution":[41,101,178],"of":[42,62,70,129,133,150,181,193],"deep":[43,151,157,176],"learning":[44,71,152,177,182],"a":[46,60,156],"leadership-class":[47],"high-performance":[48],"computing":[49],"(HPC)":[50],"system.":[51],"Using":[52],"our":[53],"new":[54],"code":[55],"called":[56,160],"DeepEx,":[57],"present":[59],"study":[61],"speed":[65,135,162,183],"up":[66,103,141],"convergence":[68,148],"rates":[69,149],"execution.":[76],"trade-off":[79],"between":[80],"computational":[81],"parallelism":[82,91],"synchronized":[84],"convergence,":[85],"first":[87],"focus":[88],"maximizing":[90],"while":[92],"still":[93],"obtaining":[94],"convergence.":[95],"Scaling":[96],"are":[98],"reported":[99],"to":[104,142,173,187],"15,000":[105],"GPUs":[106],"two":[108],"scientific":[109],"data":[110,125],"sets":[111],"atom":[113],"microscopy":[114],"protein":[116],"folding":[117],"applications,":[118],"also":[120,165],"popular":[123],"ImageNet":[124],"set.":[126],"terms":[128,180],"traditional":[131],"measure":[132],"up,":[136,184],"excellent":[137],"scaling":[138],"observed":[140],"12,000":[143],"GPUs.":[144],"Additionally,":[145],"accounting":[146],"for":[147,190],"accuracy":[153],"or":[154],"error,":[155],"learning-specific":[158],"metric":[159],"\"learning":[161],"up\"":[163],"tracked.":[166],"The":[167],"indicate":[170],"need":[172],"evaluate":[174],"in":[179],"point":[186],"additional":[188],"directions":[189],"improved":[191],"exploitation":[192],"high-end":[194],"HPC":[195],"systems.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}