{"id":"https://openalex.org/W2904341006","doi":"https://doi.org/10.1109/ftxs.2018.00008","title":"Analyzing the Impact of System Reliability Events on Applications in the Titan Supercomputer","display_name":"Analyzing the Impact of System Reliability Events on Applications in the Titan Supercomputer","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2904341006","doi":"https://doi.org/10.1109/ftxs.2018.00008","mag":"2904341006"},"language":"en","primary_location":{"id":"doi:10.1109/ftxs.2018.00008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 8th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1486940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067111830","display_name":"Rizwan A. Ashraf","orcid":"https://orcid.org/0000-0003-4477-0042"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rizwan A. Ashraf","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Engelmann","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067111830"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":2.0555,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90876239,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9984999895095825,"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":0.9983999729156494,"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/supercomputer","display_name":"Supercomputer","score":0.8391348123550415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7950648069381714},{"id":"https://openalex.org/keywords/serviceability","display_name":"Serviceability (structure)","score":0.6500790119171143},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.6271953582763672},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5651677250862122},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.43570056557655334},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.40490835905075073},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40122607350349426}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8391348123550415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950648069381714},{"id":"https://openalex.org/C110245778","wikidata":"https://www.wikidata.org/wiki/Q2169658","display_name":"Serviceability (structure)","level":2,"score":0.6500790119171143},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.6271953582763672},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5651677250862122},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.43570056557655334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.40490835905075073},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40122607350349426},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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":[{"id":"doi:10.1109/ftxs.2018.00008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 8th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1486940","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1486940","pdf_url":"https://www.osti.gov/servlets/purl/1486940","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}],"best_oa_location":{"id":"pmh:oai:osti.gov:1486940","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1486940","pdf_url":"https://www.osti.gov/servlets/purl/1486940","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":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2042897603","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4694431782","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G6129992089","display_name":null,"funder_award_id":"DE-AC05-","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G6488227018","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6864165199","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7114708214","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8813984943","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8943143067","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904341006.pdf","grobid_xml":"https://content.openalex.org/works/W2904341006.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1553890549","https://openalex.org/W1978082708","https://openalex.org/W1987117298","https://openalex.org/W1998221613","https://openalex.org/W2025024269","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2136797898","https://openalex.org/W2510192911","https://openalex.org/W2743531752","https://openalex.org/W2767346922","https://openalex.org/W2808242862","https://openalex.org/W2883087177","https://openalex.org/W2883779746","https://openalex.org/W2899199289","https://openalex.org/W6756361114"],"related_works":["https://openalex.org/W2408545863","https://openalex.org/W643179351","https://openalex.org/W2370611442","https://openalex.org/W4234058849","https://openalex.org/W3151946113","https://openalex.org/W2097451945","https://openalex.org/W2740469715","https://openalex.org/W2905265805","https://openalex.org/W75531337","https://openalex.org/W2166828374"],"abstract_inverted_index":{"Extreme-scale":[0],"computing":[1],"systems":[2],"employ":[3],"Reliability,":[4],"Availability":[5],"and":[6,10,32,70,85,164],"Serviceability":[7],"(RAS)":[8],"mechanisms":[9],"infrastructure":[11],"to":[12,37,116,176],"log":[13],"events":[14,44,81,92,100,128],"from":[15],"multiple":[16,120],"system":[17,67,113,141,157,163,177],"components.":[18],"In":[19,147],"this":[20],"paper,":[21],"we":[22,75,110],"analyze":[23],"RAS":[24,43,80,127],"logs":[25],"in":[26,35],"conjunction":[27],"with":[28,95],"the":[29,39,52,77,152,171],"application":[30,46,83,131,144],"placement":[31],"scheduling":[33],"database,":[34],"order":[36],"understand":[38],"impact":[40,78,130],"of":[41,54,79,173,183],"common":[42],"on":[45,51,60,82],"performance.":[47],"This":[48],"study":[49],"conducted":[50],"records":[53],"about":[55],"2":[56],"million":[57],"applications":[58,119],"executed":[59],"Titan":[61],"supercomputer":[62],"provides":[63],"important":[64],"insights":[65],"for":[66,179],"users,":[68],"operators":[69],"computer":[71],"science":[72],"researchers.":[73],"Specifically,":[74],"investigate":[76],"performance":[84,145],"its":[86],"variability":[87],"by":[88],"comparing":[89],"cases":[90,97],"where":[91,98],"are":[93,101],"recorded":[94],"corresponding":[96],"no":[99],"recorded.":[102],"Such":[103],"a":[104],"statistical":[105],"investigation":[106,150],"is":[107],"possible":[108],"since":[109],"observed":[111],"that":[112,125,139],"users":[114,178],"tend":[115],"execute":[117],"their":[118],"times.":[121],"Our":[122,168],"analysis":[123],"reveals":[124],"most":[126],"do":[129],"performance,":[132],"although":[133],"not":[134],"always.":[135],"We":[136],"also":[137],"find":[138],"different":[140],"components":[142],"affect":[143],"differently.":[146],"particular,":[148],"our":[149],"includes":[151],"following":[153],"components:":[154],"parallel":[155],"file":[156],"processor,":[158],"memory,":[159],"graphics":[160],"processing":[161],"units,":[162],"user":[165],"software":[166],"issues.":[167],"work":[169],"establishes":[170],"importance":[172],"providing":[174],"feedback":[175],"increasing":[180],"operational":[181],"efficiency":[182],"extreme-scale":[184],"systems.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}