{"id":"https://openalex.org/W2964483310","doi":"https://doi.org/10.1109/ipdpsw.2019.00092","title":"TensorFlow Doing HPC","display_name":"TensorFlow Doing HPC","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2964483310","doi":"https://doi.org/10.1109/ipdpsw.2019.00092","mag":"2964483310"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2019.00092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2019.00092","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.04364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Steven W. D. Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Steven W. D. Chien","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stefano Markidis","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Stefano Markidis","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vyacheslav Olshevsky","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Vyacheslav Olshevsky","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaroslav Bulatov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120668","display_name":"Creative Commons","ror":"https://ror.org/02ed4cj64","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210120668"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaroslav Bulatov","raw_affiliation_strings":["South Park Commons, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"South Park Commons, San Francisco, USA","institution_ids":["https://openalex.org/I4210120668"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Erwin Laure","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erwin Laure","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jeffrey Vetter","orcid":null},"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":"Jeffrey Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":2.4604,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88857726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"509","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6679999828338623},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.603600025177002},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5424000024795532},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.529699981212616},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42750000953674316},{"id":"https://openalex.org/keywords/fourier-domain","display_name":"Fourier domain","score":0.4235000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807699978351593},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6679999828338623},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C3019555358","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Fourier domain","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2720000147819519}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdpsw.2019.00092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2019.00092","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:arXiv.org:1903.04364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.04364","pdf_url":"https://arxiv.org/pdf/1903.04364","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.04364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.04364","pdf_url":"https://arxiv.org/pdf/1903.04364","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W1952970633","https://openalex.org/W2087440962","https://openalex.org/W2109241917","https://openalex.org/W2121893797","https://openalex.org/W2155893237","https://openalex.org/W2462018851","https://openalex.org/W2580688187","https://openalex.org/W2606722458","https://openalex.org/W2621550233","https://openalex.org/W2745734086","https://openalex.org/W2791673912","https://openalex.org/W2886189612","https://openalex.org/W2951947775","https://openalex.org/W6684859321","https://openalex.org/W6713134421","https://openalex.org/W6744677319"],"related_works":[],"abstract_inverted_index":{"TensorFlow":[0,18,31,66,112,121,136,186],"is":[1],"a":[2,38],"popular":[3],"emerging":[4,191],"open-source":[5],"programming":[6,195],"framework":[7,196],"supporting":[8,34],"the":[9,35,48,109,163,172],"execution":[10],"of":[11,37,42,111,126,143,165,190],"distributed":[12],"applications":[13,178],"on":[14,72,102,132,147],"heterogeneous":[15,198],"hardware.":[16],"While":[17],"has":[19,187],"been":[20,62],"initially":[21],"designed":[22],"for":[23,113,197],"developing":[24,114],"Machine":[25],"Learning":[26],"(ML)":[27],"applications,":[28],"in":[29,171],"fact":[30],"aims":[32],"at":[33],"development":[36],"much":[39],"broader":[40],"range":[41],"application":[43],"kinds":[44],"that":[45,120,185],"are":[46],"outside":[47],"ML":[49],"domain":[50],"and":[51,93,107,130,157,176],"can":[52,122],"possibly":[53],"include":[54],"HPC":[55,70,83,115,194],"applications.":[56,116],"However,":[57],"very":[58],"few":[59],"experiments":[60],"have":[61],"conducted":[63],"to":[64,169],"evaluate":[65,108],"performance":[67,101,128,159,182],"when":[68,161],"running":[69],"workloads":[71],"supercomputers.":[73,133,199],"This":[74],"work":[75],"addresses":[76],"this":[77],"lack":[78],"by":[79],"designing":[80],"four":[81,170],"traditional":[82],"benchmark":[84],"applications:":[85],"STREAM,":[86],"matrix-matrix":[87,173],"multiply,":[88,174],"Conjugate":[89],"Gradient":[90],"(CG)":[91],"solver":[92],"Fast":[94],"Fourier":[95],"Transform":[96],"(FFT).":[97],"We":[98,151],"analyze":[99],"their":[100],"two":[103,168],"supercomputers":[104],"with":[105],"accelerators":[106,131],"potential":[110,189],"Our":[117],"tests":[118],"show":[119],"fully":[123],"take":[124],"advantage":[125],"high":[127,188],"networks":[129],"Running":[134],"our":[135,148,181],"STREAM":[137],"benchmark,":[138],"we":[139],"obtain":[140],"over":[141],"50%":[142],"theoretical":[144],"communication":[145],"bandwidth":[146],"testing":[149],"platform.":[150],"find":[152],"an":[153],"approximately":[154],"2\u00d7,":[155],"1.7\u00d7":[156],"1.8\u00d7":[158],"improvement":[160],"increasing":[162],"number":[164],"GPUs":[166],"from":[167],"CG":[175],"FFT":[177],"respectively.":[179],"All":[180],"results":[183],"demonstrate":[184],"also":[192],"as":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2019-08-13T00:00:00"}