{"id":"https://openalex.org/W4308404500","doi":"https://doi.org/10.1007/s10586-022-03798-7","title":"A container-based workflow for distributed training of deep learning algorithms in HPC clusters","display_name":"A container-based workflow for distributed training of deep learning algorithms in HPC clusters","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308404500","doi":"https://doi.org/10.1007/s10586-022-03798-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10586-022-03798-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10586-022-03798-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10586-022-03798-7.pdf","source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cluster Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10586-022-03798-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044029293","display_name":"Jos\u00e9 Gonz\u00e1lez-Abad","orcid":"https://orcid.org/0000-0002-0764-3872"},"institutions":[{"id":"https://openalex.org/I13134134","display_name":"Universidad de Cantabria","ror":"https://ror.org/046ffzj20","country_code":"ES","type":"education","lineage":["https://openalex.org/I13134134"]},{"id":"https://openalex.org/I4210152024","display_name":"Instituto de F\u00edsica de Cantabria","ror":"https://ror.org/040kx1j83","country_code":"ES","type":"facility","lineage":["https://openalex.org/I13134134","https://openalex.org/I134820265","https://openalex.org/I4210152024"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Jose Gonz\u00e1lez-Abad","raw_affiliation_strings":["Instituto de F\u00edsica de Cantabria (IFCA), CSIC-Universidad de Cantabria, Santander, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0764-3872","affiliations":[{"raw_affiliation_string":"Instituto de F\u00edsica de Cantabria (IFCA), CSIC-Universidad de Cantabria, Santander, Spain","institution_ids":["https://openalex.org/I13134134","https://openalex.org/I4210152024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072424728","display_name":"\u00c1lvaro L\u00f3pez Garc\u00eda","orcid":"https://orcid.org/0000-0002-0013-4602"},"institutions":[{"id":"https://openalex.org/I13134134","display_name":"Universidad de Cantabria","ror":"https://ror.org/046ffzj20","country_code":"ES","type":"education","lineage":["https://openalex.org/I13134134"]},{"id":"https://openalex.org/I4210152024","display_name":"Instituto de F\u00edsica de Cantabria","ror":"https://ror.org/040kx1j83","country_code":"ES","type":"facility","lineage":["https://openalex.org/I13134134","https://openalex.org/I134820265","https://openalex.org/I4210152024"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro L\u00f3pez Garc\u00eda","raw_affiliation_strings":["Instituto de F\u00edsica de Cantabria (IFCA), CSIC-Universidad de Cantabria, Santander, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0013-4602","affiliations":[{"raw_affiliation_string":"Instituto de F\u00edsica de Cantabria (IFCA), CSIC-Universidad de Cantabria, Santander, Spain","institution_ids":["https://openalex.org/I13134134","https://openalex.org/I4210152024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103105872","display_name":"\u0412. \u041a\u043e\u0437\u043b\u043e\u0432","orcid":"https://orcid.org/0000-0002-8770-3619"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Valentin Y. Kozlov","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Steinbuch Centre for Computing (SCC), Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8770-3619","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Steinbuch Centre for Computing (SCC), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044029293"],"corresponding_institution_ids":["https://openalex.org/I13134134","https://openalex.org/I4210152024"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":5.7291,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95761125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"5","first_page":"2815","last_page":"2834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/workflow","display_name":"Workflow","score":0.9040517210960388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8937119245529175},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7912865877151489},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.6244916915893555},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5136904120445251},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5005025863647461},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4759659171104431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41559910774230957},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18677332997322083}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9040517210960388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8937119245529175},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7912865877151489},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.6244916915893555},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5136904120445251},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5005025863647461},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4759659171104431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41559910774230957},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18677332997322083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s10586-022-03798-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10586-022-03798-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10586-022-03798-7.pdf","source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cluster Computing","raw_type":"journal-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000152890","is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000152890","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cluster Computing, 26 (5), 2815\u20132834","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000152892","is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000152892","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"info:eu-repo/semantics/book"},{"id":"pmh:oai:digital.csic.es:10261/283443","is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/283443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"art\u00edculo"},{"id":"doi:10.5445/ir/1000152890","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000152890","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5445/ir/1000152892","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000152892","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"report"}],"best_oa_location":{"id":"doi:10.1007/s10586-022-03798-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10586-022-03798-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10586-022-03798-7.pdf","source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cluster Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3182399474","display_name":null,"funder_award_id":"MDM-2017-0765","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3353681303","display_name":"Designing and Enabling E-infrastructures for intensive Processing in a Hybrid DataCloud","funder_award_id":"777435","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320331771","display_name":"European Centre for Medium-Range Weather Forecasts","ror":"https://ror.org/014w0fd65"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":"https://ror.org/003x0zc53"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308404500.pdf","grobid_xml":"https://content.openalex.org/works/W4308404500.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W25727798","https://openalex.org/W1596936080","https://openalex.org/W1825216778","https://openalex.org/W2033787161","https://openalex.org/W2057332538","https://openalex.org/W2070557589","https://openalex.org/W2075174112","https://openalex.org/W2097117768","https://openalex.org/W2121745948","https://openalex.org/W2125621954","https://openalex.org/W2194775991","https://openalex.org/W2257617748","https://openalex.org/W2402800985","https://openalex.org/W2511876377","https://openalex.org/W2604521289","https://openalex.org/W2612836460","https://openalex.org/W2613409207","https://openalex.org/W2735218636","https://openalex.org/W2767770039","https://openalex.org/W2767963221","https://openalex.org/W2768885587","https://openalex.org/W2777476837","https://openalex.org/W2781302587","https://openalex.org/W2798737969","https://openalex.org/W2893189831","https://openalex.org/W2900615125","https://openalex.org/W2903356587","https://openalex.org/W2910096450","https://openalex.org/W2912122742","https://openalex.org/W2921498552","https://openalex.org/W2946476686","https://openalex.org/W2963446712","https://openalex.org/W2974527409","https://openalex.org/W2981977644","https://openalex.org/W2993735428","https://openalex.org/W2998827957","https://openalex.org/W2999056749","https://openalex.org/W2999282239","https://openalex.org/W3005244836","https://openalex.org/W3006548806","https://openalex.org/W3020999790","https://openalex.org/W3035574324","https://openalex.org/W3035892425","https://openalex.org/W3044232223","https://openalex.org/W3097933316","https://openalex.org/W3098597768","https://openalex.org/W3102637439","https://openalex.org/W3104422888","https://openalex.org/W3104674222","https://openalex.org/W3177828909","https://openalex.org/W4294351759","https://openalex.org/W4301239768","https://openalex.org/W6899342355"],"related_works":["https://openalex.org/W2367301169","https://openalex.org/W3181407718","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1852113167","https://openalex.org/W1493858311","https://openalex.org/W1824242903","https://openalex.org/W2155470929","https://openalex.org/W2394465510","https://openalex.org/W2111125783"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"learning":[2,113,179],"has":[3],"been":[4],"postulated":[5],"as":[6,131,137],"a":[7,39,103,122,196],"solution":[8],"for":[9,107,139],"numerous":[10],"problems":[11],"in":[12,38,115,214],"different":[13,82,87,227],"branches":[14],"of":[15,21,52,62,67,111,124,142,172,176,189,199,218],"science.":[16],"Given":[17],"the":[18,43,65,92,108,140,143,159,169,173,177,190,209,215,219],"resource-intensive":[19],"nature":[20,75],"these":[22,68],"models,":[23],"they":[24],"often":[25],"need":[26,151],"to":[27,49,72,157,184,226],"be":[28],"executed":[29],"on":[30,129,135,164],"specialized":[31],"hardware":[32],"such":[33],"graphical":[34],"processing":[35],"units":[36],"(GPUs)":[37],"distributed":[40,109,216],"manner.":[41],"In":[42,80,98],"academic":[44],"field,":[45],"researchers":[46,120,156,194],"get":[47],"access":[48],"this":[50,99],"kind":[51,61],"resources":[53],"through":[54],"High":[55],"Performance":[56],"Computing":[57],"(HPC)":[58],"clusters.":[59,228],"This":[60],"infrastructures":[63],"make":[64],"training":[66,110,174,217],"models":[69,114,144,220],"difficult":[70],"due":[71,183],"their":[73,201],"multi-user":[74],"and":[76,105,134,186,221],"limited":[77],"user":[78],"permission.":[79],"addition,":[81],"HPC":[83,116],"clusters":[84,117],"may":[85],"possess":[86],"peculiarities":[88],"that":[89,208,222],"can":[90],"entangle":[91],"research":[93],"cycle":[94],"(e.g.,":[95],"libraries":[96],"dependencies).":[97],"paper":[100],"we":[101],"develop":[102],"workflow":[104,161,210],"methodology":[106],"deep":[112,178],"which":[118],"provides":[119,193],"with":[121,195],"series":[123],"novel":[125],"advantages.":[126],"It":[127],"relies":[128],"udocker":[130,148],"containerization":[132,185],"tool":[133],"Horovod":[136,167],"library":[138],"distribution":[141,171],"across":[145],"multiple":[146],"GPUs.":[147],"does":[149],"not":[150],"any":[152,165],"special":[153],"permission,":[154],"allowing":[155],"run":[158],"entire":[160],"without":[162],"relying":[163],"administrator.":[166],"ensures":[168],"efficient":[170],"independently":[175],"framework":[180],"used.":[181],"Additionally,":[182],"specific":[187],"features":[188],"workflow,":[191],"it":[192,223],"cluster-agnostic":[197],"way":[198],"running":[200],"models.":[202],"The":[203],"experiments":[204],"carried":[205],"out":[206],"show":[207],"offers":[211],"good":[212],"scalability":[213],"easily":[224],"adapts":[225]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}