{"id":"https://openalex.org/W2061156357","doi":"https://doi.org/10.1109/tpds.2014.2314100","title":"Diagnosis of Performance Faults in LargeScale MPI Applications via Probabilistic Progress-Dependence Inference","display_name":"Diagnosis of Performance Faults in LargeScale MPI Applications via Probabilistic Progress-Dependence Inference","publication_year":2014,"publication_date":"2014-04-21","ids":{"openalex":"https://openalex.org/W2061156357","doi":"https://doi.org/10.1109/tpds.2014.2314100","mag":"2061156357"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2314100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2314100","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1769172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033868370","display_name":"Ignacio Laguna","orcid":"https://orcid.org/0000-0002-9374-4433"},"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":false,"raw_author_name":"Ignacio Laguna","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA 94550","Lawrence Livermore National Laboratory , Livermore, CA 94550"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory , Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006598908","display_name":"Dong H. Ahn","orcid":"https://orcid.org/0000-0001-6722-0532"},"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":false,"raw_author_name":"Dong H. Ahn","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA 94550","Lawrence Livermore National Laboratory , Livermore, CA 94550"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory , Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058719424","display_name":"Bronis R. de Supinski","orcid":"https://orcid.org/0000-0002-0339-1006"},"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":false,"raw_author_name":"Bronis R. de Supinski","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA 94550","Lawrence Livermore National Laboratory , Livermore, CA 94550"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory , Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310442","display_name":"Saurabh Bagchi","orcid":"https://orcid.org/0000-0002-4239-5632"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Bagchi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, 465 Northwestern Avenue, West Lafayette, IN 47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, 465 Northwestern Avenue, West Lafayette, IN 47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007709486","display_name":"Todd Gamblin","orcid":"https://orcid.org/0000-0002-7857-2805"},"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":false,"raw_author_name":"Todd Gamblin","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA 94550","Lawrence Livermore National Laboratory , Livermore, CA 94550"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory , Livermore, CA 94550","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0992,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83472818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"26","issue":"5","first_page":"1280","last_page":"1289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.913661539554596},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7241691946983337},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6935827732086182},{"id":"https://openalex.org/keywords/program-slicing","display_name":"Program slicing","score":0.6673521995544434},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.6223748326301575},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6119629740715027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5599793791770935},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.545099139213562},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.5376741886138916},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5365360379219055},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.5016360282897949},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.46994760632514954},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4651181995868683},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42768147587776184},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38548243045806885},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2453821301460266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11753475666046143},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0938245952129364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.913661539554596},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7241691946983337},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6935827732086182},{"id":"https://openalex.org/C91071405","wikidata":"https://www.wikidata.org/wiki/Q1413145","display_name":"Program slicing","level":3,"score":0.6673521995544434},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.6223748326301575},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6119629740715027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5599793791770935},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.545099139213562},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5376741886138916},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5365360379219055},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.5016360282897949},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.46994760632514954},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4651181995868683},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42768147587776184},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38548243045806885},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2453821301460266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11753475666046143},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0938245952129364},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpds.2014.2314100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2314100","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1769172","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1769172","pdf_url":null,"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:pure.qub.ac.uk/portal:publications/08ce1cd2-4fcb-4f4e-9732-32f5cb8eca37","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/08ce1cd2-4fcb-4f4e-9732-32f5cb8eca37","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Laguna , I , Ahn , D H , De Supinski , B R , Bagchi , S &amp; Gamblin , T 2015 , ' Diagnosis of Performance Faults in LargeScale MPI Applications via Probabilistic Progress-Dependence Inference ' , IEEE Transactions on Parallel and Distributed Systems , vol. 26 , no. 5 , 6803050 , pp. 1280-1289 . https://doi.org/10.1109/TPDS.2014.2314100","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1769172","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1769172","pdf_url":null,"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":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G342851973","display_name":null,"funder_award_id":"CNS-0916337","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8157651756","display_name":null,"funder_award_id":"DEAC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1967324265","https://openalex.org/W2024166759","https://openalex.org/W2036048726","https://openalex.org/W2055767681","https://openalex.org/W2056400780","https://openalex.org/W2073949144","https://openalex.org/W2075092012","https://openalex.org/W2079055089","https://openalex.org/W2105079569","https://openalex.org/W2112121929","https://openalex.org/W2115408363","https://openalex.org/W2120542024","https://openalex.org/W2122282651","https://openalex.org/W2123728588","https://openalex.org/W2124515646","https://openalex.org/W2125359382","https://openalex.org/W2131613942","https://openalex.org/W2132148774","https://openalex.org/W2134633067","https://openalex.org/W2140476198","https://openalex.org/W2144344516","https://openalex.org/W2149897682","https://openalex.org/W2157593310","https://openalex.org/W2160097679","https://openalex.org/W2161694060","https://openalex.org/W2161957670","https://openalex.org/W2293624369","https://openalex.org/W3145311561","https://openalex.org/W3147759568","https://openalex.org/W4232616607","https://openalex.org/W6656719657","https://openalex.org/W6678505535","https://openalex.org/W6684031922"],"related_works":["https://openalex.org/W2011854888","https://openalex.org/W4226031072","https://openalex.org/W2076425886","https://openalex.org/W3027921940","https://openalex.org/W2078882461","https://openalex.org/W2105166025","https://openalex.org/W2360072927","https://openalex.org/W138282132","https://openalex.org/W2888556190","https://openalex.org/W2387633336"],"abstract_inverted_index":{"Debugging":[0],"large-scale":[1],"parallel":[2,29,44,198],"applications":[3],"is":[4],"challenging.":[5],"Most":[6],"existing":[7],"techniques":[8],"provide":[9],"little":[10],"information":[11],"about":[12],"failure":[13,49,83],"root":[14,149],"causes.":[15],"Further,":[16],"most":[17],"debuggers":[18],"significantly":[19],"slow":[20],"down":[21],"program":[22,45],"execution,":[23],"and":[24,74,184],"run":[25],"sluggishly":[26],"with":[27,66,126],"massively":[28],"applications.":[30],"This":[31],"paper":[32],"presents":[33],"a":[34,43,48,87,99,152,156,192],"novel":[35,88],"technique":[36,61,125,146,176],"that":[37,90,104,144,186],"scalably":[38],"infers":[39,91,116],"the":[40,54,71,77,82,119,133,137,148],"tasks":[41,97,166],"in":[42,56,155,180],"on":[46,195],"which":[47,57,81,160],"occurred,":[50],"as":[51,53],"well":[52],"code":[55,78,134],"it":[58],"originated.":[59],"Our":[60],"combines":[62],"scalable":[63],"runtime":[64],"analysis":[65,68,188],"static":[67,127],"to":[69,75,111],"determine":[70],"least-progressed":[72,120],"task(s)":[73],"identify":[76],"lines":[79],"at":[80,164],"arose.":[84],"We":[85,122,169],"present":[86],"algorithm":[89,115],"probabilistically":[92],"progress":[93],"dependence":[94],"among":[95],"MPI":[96],"using":[98],"globally":[100],"constructed":[101],"Markov":[102],"model":[103],"represents":[105],"tasks'":[106],"control-flow":[107],"behavior.":[108],"In":[109],"comparison":[110],"previous":[112],"work,":[113],"our":[114,145,175,187],"more":[117],"precisely":[118],"task.":[121],"combine":[123],"this":[124],"backward":[128],"slicing":[129],"analysis,":[130],"further":[131],"isolating":[132],"responsible":[135],"for":[136],"current":[138],"state.":[139],"A":[140],"blind":[141],"study":[142],"demonstrates":[143],"isolates":[147],"cause":[150],"of":[151,174,197],"concurrency":[153],"bug":[154],"molecular":[157],"dynamics":[158],"simulation,":[159],"only":[161],"manifests":[162],"itself":[163],"7,996":[165],"or":[167],"more.":[168],"extensively":[170],"evaluate":[171],"fault":[172,178],"coverage":[173],"via":[177],"injections":[179],"10":[181],"HPC":[182],"benchmarks":[183],"show":[185],"takes":[189],"less":[190],"than":[191],"few":[193],"seconds":[194],"thousands":[196],"tasks.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
