{"id":"https://openalex.org/W4318603806","doi":"https://doi.org/10.1109/pmbs56514.2022.00016","title":"OMPICollTune: Autotuning MPI Collectives by Incremental Online Learning","display_name":"OMPICollTune: Autotuning MPI Collectives by Incremental Online Learning","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4318603806","doi":"https://doi.org/10.1109/pmbs56514.2022.00016"},"language":"en","primary_location":{"id":"doi:10.1109/pmbs56514.2022.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs56514.2022.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5020893403","display_name":"Sascha Hunold","orcid":"https://orcid.org/0000-0002-5280-3855"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sascha Hunold","raw_affiliation_strings":["TU Wien,Faculty of Informatics,Vienna,Austria","Faculty of Informatics, TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Faculty of Informatics,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Faculty of Informatics, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103137827","display_name":"Sebastian Steiner","orcid":"https://orcid.org/0000-0001-9582-427X"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Steiner","raw_affiliation_strings":["TU Wien,Faculty of Informatics,Vienna,Austria","Faculty of Informatics, TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Faculty of Informatics,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Faculty of Informatics, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":3.7056,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.95033251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9941999912261963,"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"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9941999912261963,"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/T12288","display_name":"Optimization and Search Problems","score":0.9940000176429749,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9926000237464905,"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/computer-science","display_name":"Computer science","score":0.8752660155296326},{"id":"https://openalex.org/keywords/tuner","display_name":"Tuner","score":0.7127904891967773},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6903177499771118},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6475927829742432},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5445842742919922},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.42225590348243713},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3368796408176422},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33454039692878723},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33227381110191345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27539265155792236},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1593092381954193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8752660155296326},{"id":"https://openalex.org/C9819579","wikidata":"https://www.wikidata.org/wiki/Q1544018","display_name":"Tuner","level":3,"score":0.7127904891967773},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6903177499771118},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6475927829742432},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5445842742919922},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.42225590348243713},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3368796408176422},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33454039692878723},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33227381110191345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27539265155792236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1593092381954193},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pmbs56514.2022.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pmbs56514.2022.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W12500326","https://openalex.org/W1991732708","https://openalex.org/W2295598076","https://openalex.org/W2335421672","https://openalex.org/W2613264550","https://openalex.org/W2784285104","https://openalex.org/W2898873842","https://openalex.org/W3060868468","https://openalex.org/W3097718020","https://openalex.org/W4221068112","https://openalex.org/W4238128135","https://openalex.org/W4312268627","https://openalex.org/W6637837102"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W2098482419","https://openalex.org/W4254638342","https://openalex.org/W2054468904"],"abstract_inverted_index":{"Collective":[0],"communication":[1],"operations,":[2],"such":[3,214],"as":[4],"Broadcast":[5],"or":[6],"Reduce,":[7],"are":[8,194,209],"fundamental":[9],"cornerstones":[10],"in":[11,56,66,76,227],"many":[12],"high-performance":[13],"applications.":[14],"Most":[15],"collective":[16,149,188],"operations":[17],"can":[18,69,240],"be":[19,70],"implemented":[20],"using":[21,231],"different":[22,89,104],"algorithms,":[23],"each":[24],"of":[25,91,103,125,135,156,163,222,245],"which":[26],"has":[27,53],"advantages":[28],"and":[29,127],"disadvantages.":[30],"For":[31],"that":[32,41,59,179,215,237],"reason,":[33],"MPI":[34,67,97,109,113,148,158],"libraries":[35,68],"typically":[36],"implement":[37],"a":[38,77,87,118,161,176,186,219,228],"selection":[39,63,95,138],"logic":[40,64],"attempts":[42],"to":[43,144,174,197],"make":[44],"good":[45],"algorithmic":[46],"choices":[47],"for":[48,96,160,185,205],"specific":[49],"problem":[50],"instances.":[51],"It":[52],"been":[54],"shown":[55],"the":[57,60,74,82,93,101,108,123,128,132,136,141,154,166,170,199,203,212,232,243],"literature":[58],"hard-coded":[61],"algorithm":[62,94,143,184,208],"found":[65],"improved":[71],"by":[72,211],"tuning":[73],"collectives":[75],"separate,":[78],"offline":[79],"micro-benchmarking":[80],"run.In":[81],"present":[83],"paper,":[84],"we":[85],"go":[86],"fundamentally":[88],"way":[90],"improving":[92],"collectives.":[98],"We":[99,225],"integrate":[100],"probing":[102],"algorithms":[105,217],"directly":[106],"into":[107],"library.":[110],"Whenever":[111],"an":[112,146,182,207],"application":[114,235],"is":[115,172],"started":[116],"with":[117],"given":[119,187],"process":[120],"configuration,":[121],"i.e.,":[122],"number":[124],"nodes":[126],"processes":[129],"per":[130],"node,":[131],"tuner,":[133,213],"instead":[134],"default":[137],"logic,":[139],"finds":[140],"next":[142],"complete":[145],"issued":[147],"call.":[150],"The":[151],"tuner":[152,171],"records":[153],"runtime":[155],"this":[157],"call":[159],"subset":[162],"processes.":[164],"With":[165],"recorded":[167,191],"performance":[168,177,192,200,244],"data,":[169],"able":[173],"build":[175],"model":[178],"allows":[180],"selecting":[181,206],"efficient":[183],"problem.":[189],"Subsequently":[190],"results":[193],"then":[195],"used":[196],"update":[198],"model,":[201],"where":[202],"probabilities":[204],"adapted":[210],"slow":[216],"get":[218],"smaller":[220],"chance":[221],"being":[223],"selected.":[224],"show":[226],"case":[229],"study,":[230],"ECP":[233],"proxy":[234],"miniAMR,":[236],"our":[238],"approach":[239],"effectively":[241],"tune":[242],"Allreduce.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}