{"id":"https://openalex.org/W2505455397","doi":"https://doi.org/10.1145/2934661","title":"Identifying the Root Causes of Wait States in Large-Scale Parallel Applications","display_name":"Identifying the Root Causes of Wait States in Large-Scale Parallel Applications","publication_year":2016,"publication_date":"2016-07-20","ids":{"openalex":"https://openalex.org/W2505455397","doi":"https://doi.org/10.1145/2934661","mag":"2505455397"},"language":"en","primary_location":{"id":"doi:10.1145/2934661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2934661","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1305834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008218695","display_name":"David B\u00f6hme","orcid":"https://orcid.org/0000-0002-4159-1519"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David B\u00f6hme","raw_affiliation_strings":["Lawrence Livermore National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002367144","display_name":"Markus Geimer","orcid":"https://orcid.org/0000-0002-5575-8287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus Geimer","raw_affiliation_strings":["J\u00fclich Supercomputing Centre, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048050068","display_name":"Lukas Arnold","orcid":"https://orcid.org/0000-0002-5939-8995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Arnold","raw_affiliation_strings":["J\u00fclich Supercomputing Centre, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032519700","display_name":"Felix Voigtlaender","orcid":"https://orcid.org/0000-0002-5061-2756"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Voigtlaender","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018089961","display_name":"Felix Wolf","orcid":"https://orcid.org/0000-0001-6595-3599"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Wolf","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008218695"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":2.8819,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.90547309,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"2","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9994999766349792,"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/scalability","display_name":"Scalability","score":0.7858427166938782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7669399976730347},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.6945258975028992},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.6251420378684998},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.595880925655365},{"id":"https://openalex.org/keywords/microprocessor","display_name":"Microprocessor","score":0.5697579383850098},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5307307839393616},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5157163739204407},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48171669244766235},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4794932007789612},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4590318500995636},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.42774102091789246},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.4105871021747589},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3614259660243988},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2008841633796692},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.1601533591747284},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.128800630569458},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11756402254104614}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7858427166938782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669399976730347},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.6945258975028992},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.6251420378684998},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.595880925655365},{"id":"https://openalex.org/C2780728072","wikidata":"https://www.wikidata.org/wiki/Q5297","display_name":"Microprocessor","level":2,"score":0.5697579383850098},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5307307839393616},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5157163739204407},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48171669244766235},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4794932007789612},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4590318500995636},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.42774102091789246},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.4105871021747589},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3614259660243988},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2008841633796692},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.1601533591747284},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.128800630569458},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11756402254104614},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2934661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2934661","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1305834","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1305834","pdf_url":"https://www.osti.gov/servlets/purl/1305834","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},{"id":"pmh:oai:edoc.ku.de:29920","is_oa":false,"landing_page_url":"https://edoc.ku.de/id/eprint/29920/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400143","display_name":"Publication Server of the Catholic University Eichst\u00e4tt-Ingolstadt (Catholic University of Eichst\u00e4tt-Ingolstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I199417121","host_organization_name":"Catholic University of Eichst\u00e4tt-Ingolstadt","host_organization_lineage":["https://openalex.org/I199417121"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:95829","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/95829/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1305834","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1305834","pdf_url":"https://www.osti.gov/servlets/purl/1305834","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":[{"display_name":"Decent work and economic growth","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1169089040","display_name":null,"funder_award_id":"GSC 111","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1615501055","display_name":null,"funder_award_id":"GSC 111","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6441358257","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8374966015","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G991281326","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320308614","display_name":"University Corporation for Atmospheric Research","ror":"https://ror.org/04zhhyn23"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2505455397.pdf","grobid_xml":"https://content.openalex.org/works/W2505455397.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W9763237","https://openalex.org/W1483660941","https://openalex.org/W1500982531","https://openalex.org/W1554008840","https://openalex.org/W1655895913","https://openalex.org/W1835267339","https://openalex.org/W1948591071","https://openalex.org/W1983303351","https://openalex.org/W2002877301","https://openalex.org/W2019137846","https://openalex.org/W2024135699","https://openalex.org/W2034774580","https://openalex.org/W2055706457","https://openalex.org/W2074172828","https://openalex.org/W2076991560","https://openalex.org/W2101778912","https://openalex.org/W2103559542","https://openalex.org/W2109074901","https://openalex.org/W2117203365","https://openalex.org/W2142535572","https://openalex.org/W2144038733","https://openalex.org/W2148429254","https://openalex.org/W2152419477","https://openalex.org/W2152875769","https://openalex.org/W2156850758","https://openalex.org/W2157108859","https://openalex.org/W2161398072","https://openalex.org/W2171181746","https://openalex.org/W2341553120","https://openalex.org/W2406624004","https://openalex.org/W2793320394","https://openalex.org/W4244834437","https://openalex.org/W4248073216"],"related_works":["https://openalex.org/W2030594396","https://openalex.org/W2535098331","https://openalex.org/W2202104725","https://openalex.org/W4255366506","https://openalex.org/W2056250485","https://openalex.org/W4280640835","https://openalex.org/W2885334669","https://openalex.org/W2111856191","https://openalex.org/W4230518569","https://openalex.org/W4295855176"],"abstract_inverted_index":{"Driven":[0],"by":[1,7,92],"growing":[2],"application":[3],"requirements":[4],"and":[5,76,107,128,135],"accelerated":[6],"current":[8],"trends":[9],"in":[10,111,124],"microprocessor":[11],"design,":[12],"the":[13,39,52,82,133,140],"number":[14],"of":[15,38,44,81,85,113,149,151],"processor":[16],"cores":[17],"on":[18,89],"modern":[19],"supercomputers":[20],"is":[21],"increasing":[22],"from":[23,35],"generation":[24],"to":[25,73,116],"generation.":[26],"However,":[27],"load":[28],"or":[29],"communication":[30,60],"imbalance":[31],"prevents":[32],"many":[33],"codes":[34],"taking":[36],"advantage":[37],"available":[40],"parallelism,":[41],"as":[42],"delays":[43],"single":[45],"processes":[46,134],"may":[47,64],"spread":[48],"wait":[49,62,105],"states":[50,63,106],"across":[51],"entire":[53],"machine.":[54],"Moreover,":[55],"when":[56],"employing":[57],"complex":[58],"point-to-point":[59],"patterns,":[61],"propagate":[65],"along":[66],"far-reaching":[67],"cause-effect":[68],"chains":[69],"that":[70,77,102],"are":[71],"hard":[72],"track":[74],"manually":[75],"complicate":[78],"an":[79,86],"assessment":[80],"actual":[83],"costs":[84,110],"imbalance.":[87],"Building":[88],"earlier":[90],"work":[91],"Meira,":[93],"Jr.,":[94],"et":[95],"al.,":[96],"we":[97,130],"present":[98],"a":[99],"scalable":[100],"approach":[101],"identifies":[103],"program":[104],"attributes":[108],"their":[109,117],"terms":[112],"resource":[114],"waste":[115],"original":[118],"cause.":[119],"By":[120],"replaying":[121],"event":[122],"traces":[123],"parallel":[125],"both":[126],"forward":[127],"backward,":[129],"can":[131],"identify":[132],"call":[136],"paths":[137],"responsible":[138],"for":[139,145],"most":[141],"severe":[142],"imbalances,":[143],"even":[144],"runs":[146],"with":[147],"hundreds":[148],"thousands":[150],"processes.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}
