{"id":"https://openalex.org/W3038118166","doi":"https://doi.org/10.1145/3369583.3392678","title":"Towards HPC I/O Performance Prediction through Large-scale Log Analysis","display_name":"Towards HPC I/O Performance Prediction through Large-scale Log Analysis","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3038118166","doi":"https://doi.org/10.1145/3369583.3392678","mag":"3038118166"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3369583.3392678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":"https://sdm.lbl.gov/oapapers/hpdc20-kim.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102708750","display_name":"Sunggon Kim","orcid":"https://orcid.org/0000-0002-2295-3385"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunggon Kim","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068293431","display_name":"Alex Sim","orcid":"https://orcid.org/0000-0002-6295-1982"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Sim","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043129695","display_name":"Kesheng Wu","orcid":"https://orcid.org/0000-0002-6907-3393"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kesheng Wu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062233562","display_name":"Suren Byna","orcid":"https://orcid.org/0000-0003-3048-3448"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suren Byna","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076633496","display_name":"Yongseok Son","orcid":"https://orcid.org/0000-0003-4512-0121"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongseok Son","raw_affiliation_strings":["Chung-Ang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059863","display_name":"Hyeonsang Eom","orcid":"https://orcid.org/0000-0002-1902-6767"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonsang Eom","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.251,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.999807,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"88"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.991,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.991,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9855,"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":0.9648,"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/provisioning","display_name":"Provisioning","score":0.6227499},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance Prediction","score":0.6046344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336129},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7816252},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.6227499},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.6046344},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.55213225},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45795855},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.44877988},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4337533},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2945432},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22632071},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.16646108},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3369583.3392678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/71f87255","pdf_url":"https://sdm.lbl.gov/oapapers/hpdc20-kim.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":["California Digital Library"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/71f87255","pdf_url":"https://sdm.lbl.gov/oapapers/hpdc20-kim.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":["California Digital Library"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.65,"display_name":"Decent work and economic growth"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":34,"referenced_works":["https://openalex.org/W1488264517","https://openalex.org/W1583700199","https://openalex.org/W1596936080","https://openalex.org/W162515996","https://openalex.org/W2010628428","https://openalex.org/W203122272","https://openalex.org/W2095727900","https://openalex.org/W2101234009","https://openalex.org/W2107530312","https://openalex.org/W2108691459","https://openalex.org/W2115890460","https://openalex.org/W2130695501","https://openalex.org/W2136245133","https://openalex.org/W2140136927","https://openalex.org/W2157777898","https://openalex.org/W2163605009","https://openalex.org/W2253710306","https://openalex.org/W2309679942","https://openalex.org/W2342249984","https://openalex.org/W2402144811","https://openalex.org/W2559796885","https://openalex.org/W2566279479","https://openalex.org/W2566699981","https://openalex.org/W2631751282","https://openalex.org/W273955616","https://openalex.org/W2805496990","https://openalex.org/W2899477092","https://openalex.org/W2901824939","https://openalex.org/W2902431547","https://openalex.org/W2954028704","https://openalex.org/W317957491","https://openalex.org/W4206038948","https://openalex.org/W4231299715","https://openalex.org/W95608104"],"related_works":["https://openalex.org/W44553394","https://openalex.org/W4400094300","https://openalex.org/W4386869550","https://openalex.org/W4319941049","https://openalex.org/W3208959265","https://openalex.org/W3047653192","https://openalex.org/W2418418119","https://openalex.org/W2384867379","https://openalex.org/W2329539859","https://openalex.org/W2075436644"],"abstract_inverted_index":{"Large-scale":[0],"high":[1],"performance":[2,52,68,72,109,165],"computing":[3],"(HPC)":[4],"systems":[5],"typically":[6],"consist":[7],"of":[8,11,22,33,50,54,106,121,175],"many":[9],"thousands":[10,21],"CPUs":[12],"and":[13,44,63,92,125,143],"storage":[14],"units,":[15],"while":[16],"used":[17],"by":[18],"hundreds":[19],"to":[20,75,115,168],"users":[23,34],"at":[24,185],"the":[25,51,70,78,84,93,104,107,133,138,146,151,163,173,176,180],"same":[26],"time.":[27],"Applications":[28],"from":[29,118,137,182],"these":[30,67],"large":[31],"numbers":[32],"have":[35],"diverse":[36],"characteristics,":[37,69],"such":[38],"as":[39],"varying":[40],"compute,":[41],"communication,":[42],"memory,":[43],"I/O":[45,71,79,85,94,108,164],"intensiveness.":[46],"A":[47],"good":[48],"understanding":[49],"characteristics":[53],"each":[55],"user":[56],"application":[57],"is":[58,73,82,87],"important":[59],"for":[60,150],"job":[61],"scheduling":[62],"resource":[64],"provisioning.":[65],"Among":[66],"difficult":[74],"predict":[76,162],"because":[77],"system":[80,86,123],"software":[81],"complex,":[83],"shared":[88],"among":[89],"all":[90],"users,":[91],"operations":[95],"also":[96],"heavily":[97],"rely":[98],"on":[99,110],"networking":[100],"systems.":[101],"To":[102],"improve":[103],"prediction":[105,152,170],"HPC":[111],"systems,":[112],"we":[113],"propose":[114],"integrate":[116],"information":[117],"a":[119,127],"number":[120],"different":[122],"logs":[124,181],"develop":[126],"regression-based":[128],"approach":[129],"that":[130,157],"dynamically":[131],"selects":[132],"most":[134,139],"relevant":[135],"features":[136],"recent":[140],"log":[141],"entries,":[142],"automatically":[144],"select":[145],"best":[147],"regression":[148],"algorithm":[149],"task.":[153],"Evaluation":[154],"results":[155],"show":[156],"our":[158],"proposed":[159],"scheme":[160],"can":[161],"with":[166],"up":[167],"84%":[169],"accuracy":[171],"in":[172],"case":[174],"I/O-intensive":[177],"applications":[178],"using":[179],"CORI":[183],"supercomputer":[184],"NERSC.":[186]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3038118166","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2024-12-12T16:32:43.105964","created_date":"2020-07-02"}