{"id":"https://openalex.org/W2093741299","doi":"https://doi.org/10.1142/s0129626414420031","title":"Online Monitoring Systems for Performance Fault Detection","display_name":"Online Monitoring Systems for Performance Fault Detection","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2093741299","doi":"https://doi.org/10.1142/s0129626414420031","mag":"2093741299"},"language":"en","primary_location":{"id":"doi:10.1142/s0129626414420031","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414420031","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"},"type":"article","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/A5075909942","display_name":"Roberto Gioiosa","orcid":"https://orcid.org/0000-0001-9430-2656"},"institutions":[{"id":"https://openalex.org/I1325736334","display_name":"Battelle","ror":"https://ror.org/01h5tnr73","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1325736334"]},{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Gioiosa","raw_affiliation_strings":["Advanced Computation, Mathematics and Data Division, Pacific Northwest National Laboratory, 902, Battelle blvd, 99352 Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computation, Mathematics and Data Division, Pacific Northwest National Laboratory, 902, Battelle blvd, 99352 Richland, WA, USA","institution_ids":["https://openalex.org/I1325736334","https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048219922","display_name":"G\u00f6k\u00e7en Kestor","orcid":"https://orcid.org/0000-0002-9105-5634"},"institutions":[{"id":"https://openalex.org/I1325736334","display_name":"Battelle","ror":"https://ror.org/01h5tnr73","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1325736334"]},{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokcen Kestor","raw_affiliation_strings":["Advanced Computation, Mathematics and Data Division, Pacific Northwest National Laboratory, 902, Battelle blvd, 99352 Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computation, Mathematics and Data Division, Pacific Northwest National Laboratory, 902, Battelle blvd, 99352 Richland, WA, USA","institution_ids":["https://openalex.org/I1325736334","https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064935199","display_name":"Darren J. Kerbyson","orcid":null},"institutions":[{"id":"https://openalex.org/I1325736334","display_name":"Battelle","ror":"https://ror.org/01h5tnr73","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1325736334"]},{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darren J. Kerbyson","raw_affiliation_strings":["Advanced Computation, Mathematics and Data Division, Pacific Northwest National Laboratory, 902, Battelle blvd, 99352 Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computation, Mathematics and Data Division, Pacific Northwest National Laboratory, 902, Battelle blvd, 99352 Richland, WA, USA","institution_ids":["https://openalex.org/I1325736334","https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80487805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"24","issue":"04","first_page":"1442003","last_page":"1442003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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":0.9980999827384949,"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":0.8579968214035034},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6968066096305847},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6028692126274109},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5364732146263123},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.521722674369812},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5049422383308411},{"id":"https://openalex.org/keywords/linux-kernel","display_name":"Linux kernel","score":0.4675627648830414},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.446275532245636},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.40085312724113464},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22885406017303467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579968214035034},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6968066096305847},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6028692126274109},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5364732146263123},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.521722674369812},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5049422383308411},{"id":"https://openalex.org/C553261973","wikidata":"https://www.wikidata.org/wiki/Q14579","display_name":"Linux kernel","level":2,"score":0.4675627648830414},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.446275532245636},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.40085312724113464},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22885406017303467},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0129626414420031","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129626414420031","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1495954130","https://openalex.org/W1533140796","https://openalex.org/W1543047378","https://openalex.org/W1973923004","https://openalex.org/W1977661221","https://openalex.org/W1995308043","https://openalex.org/W2057234250","https://openalex.org/W2068975988","https://openalex.org/W2070525241","https://openalex.org/W2074172828","https://openalex.org/W2075286371","https://openalex.org/W2079577430","https://openalex.org/W2090409324","https://openalex.org/W2093097249","https://openalex.org/W2101778912","https://openalex.org/W2130604611","https://openalex.org/W2136434791","https://openalex.org/W2143884002","https://openalex.org/W2154467933","https://openalex.org/W2155598399"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2480201319","https://openalex.org/W2387706296","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W362492756","https://openalex.org/W2113594494"],"abstract_inverted_index":{"To":[0,128],"achieve":[1,129],"the":[2,27,38,98,106,117,123,126,135,179,183],"exaFLOPS":[3],"performance":[4,61,75,95,154,201],"within":[5],"a":[6,54,70,111,142,170],"contained":[7],"power":[8,213],"budget,":[9],"next":[10],"generation":[11,72],"supercomputers":[12],"will":[13,57],"feature":[14],"hundreds":[15],"of":[16,18,33,40,53,69,73,88,110,119,125,138,182],"millions":[17],"components":[19,35],"operating":[20],"at":[21,30,151,162],"low-":[22],"and":[23,76,91,108,122,157,211],"near-threshold":[24],"voltage.":[25],"As":[26],"probability":[28],"that":[29,50,65,79,92,114,178],"least":[31],"one":[32],"these":[34],"fails":[36],"during":[37,85,97],"execution":[39],"an":[41],"application":[42,56,99,209],"approaches":[43],"certainty,":[44],"it":[45],"seems":[46],"unrealistic":[47],"to":[48,198],"expect":[49],"any":[51],"run":[52],"scientific":[55],"not":[58],"experience":[59],"some":[60],"faults.":[62],"We":[63,164],"believe":[64],"there":[66],"is":[67,149,186],"need":[68],"new":[71],"light-weight":[74],"debugging":[77],"tools":[78],"can":[80,93,195],"be":[81,196],"used":[82,197],"online":[83],"even":[84],"production":[86],"runs":[87],"parallel":[89],"applications":[90,121],"identify":[94,200],"anomalies":[96],"execution.":[100],"In":[101],"this":[102],"work":[103],"we":[104,140,176,190],"propose":[105,141],"design":[107],"implementation":[109],"monitoring":[112,148,167,184],"system":[113,168,185,194],"continuously":[115],"inspects":[116],"evolution":[118],"running":[120],"health":[124],"system.":[127],"minimum":[130],"runtime":[131,180],"overhead":[132,181],"while":[133,153],"maintaining":[134],"desired":[136],"level":[137],"flexibility,":[139],"decoupled":[143],"approach":[144],"in":[145,203],"which":[146],"accurate":[147],"performed":[150,161],"kernel-level":[152],"anomaly":[155],"disambiguation":[156],"corrective":[158],"actions":[159],"are":[160],"user-level.":[163],"evaluate":[165],"our":[166,193],"on":[169],"128-core":[171],"AMD":[172],"Interlagos":[173],"system:":[174],"First,":[175],"show":[177,191],"negligible":[187],"(0-2%).":[188],"Then":[189],"how":[192],"precisely":[199],"faults":[202],"three":[204],"different":[205],"scenarios:":[206],"OS":[207],"noise,":[208],"co-scheduling":[210],"dynamic":[212],"capping.":[214]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
