{"id":"https://openalex.org/W2028846878","doi":"https://doi.org/10.1145/2751504.2751506","title":"A Principled Approach to HPC Event Monitoring","display_name":"A Principled Approach to HPC Event Monitoring","publication_year":2015,"publication_date":"2015-06-08","ids":{"openalex":"https://openalex.org/W2028846878","doi":"https://doi.org/10.1145/2751504.2751506","mag":"2028846878"},"language":"en","primary_location":{"id":"doi:10.1145/2751504.2751506","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751504.2751506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Fault Tolerance for HPC at eXtreme Scale","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/A5071471063","display_name":"Alireza Goudarzi","orcid":"https://orcid.org/0000-0003-2944-2681"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Goudarzi","raw_affiliation_strings":["University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084153776","display_name":"Dorian Arnold","orcid":"https://orcid.org/0000-0002-9425-1884"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorian Arnold","raw_affiliation_strings":["University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103204365","display_name":"Darko Stefanovi\u0107","orcid":"https://orcid.org/0000-0002-5619-3599"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darko Stefanovic","raw_affiliation_strings":["University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020783484","display_name":"Kurt Brian Ferreira","orcid":"https://orcid.org/0000-0001-5607-5691"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt B. Ferreira","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019879490","display_name":"Guy Feldman","orcid":"https://orcid.org/0000-0002-2784-927X"},"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":"Guy Feldman","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5295,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57513984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"10"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9965999722480774,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7875561714172363},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6263864636421204},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5036529898643494},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4644909203052521},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.46335485577583313},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.44440606236457825},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41648396849632263},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3995617628097534},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3749373257160187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32938331365585327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875561714172363},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6263864636421204},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5036529898643494},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4644909203052521},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.46335485577583313},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.44440606236457825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41648396849632263},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3995617628097534},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3749373257160187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32938331365585327},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751504.2751506","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751504.2751506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Fault Tolerance for HPC at eXtreme Scale","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W130470821","https://openalex.org/W1506806321","https://openalex.org/W1558516248","https://openalex.org/W1995875735","https://openalex.org/W2053691501","https://openalex.org/W2095157729","https://openalex.org/W2107263349","https://openalex.org/W2128825142","https://openalex.org/W2136159049","https://openalex.org/W2143220335","https://openalex.org/W2148508494","https://openalex.org/W2155063211","https://openalex.org/W2158907675","https://openalex.org/W2160821994","https://openalex.org/W2323834113","https://openalex.org/W2978725006","https://openalex.org/W4300463303","https://openalex.org/W6678568454","https://openalex.org/W6839976737"],"related_works":["https://openalex.org/W2579148721","https://openalex.org/W4387893611","https://openalex.org/W2347335694","https://openalex.org/W2091056927","https://openalex.org/W2067407580","https://openalex.org/W4317486777","https://openalex.org/W4389669152","https://openalex.org/W2038514069","https://openalex.org/W1967233468","https://openalex.org/W2009181529"],"abstract_inverted_index":{"As":[0],"high-performance":[1],"computing":[2],"(HPC)":[3],"systems":[4],"become":[5,86],"larger":[6],"and":[7,28,31,34,67,75,84,97,127,161,223],"more":[8,48],"complex,":[9],"fault":[10,82,91],"tolerance":[11,92],"becomes":[12,37],"a":[13],"greater":[14],"concern.":[15],"At":[16],"the":[17,20,43,58,117,145,186],"same":[18],"time,":[19],"data":[21,120,232],"volume":[22],"collected":[23],"to":[24,51,57,130,143,169,171,178],"help":[25],"in":[26,102,134,185],"understanding":[27,80],"mitigating":[29],"hardware":[30],"software":[32],"faults":[33],"failures":[35],"also":[36],"prohibitively":[38],"large.":[39],"We":[40],"argue":[41],"that":[42,72,189],"HPC":[44,103,135,150,179,192,230],"community":[45],"must":[46],"adopt":[47],"systematic":[49],"approaches":[50],"system":[52],"event":[53,73,95,114,136,180,193,221,231],"logging":[54],"as":[55],"opposed":[56],"current,":[59],"ad":[60,195],"hoc,":[61],"strategies":[62],"based":[63,200],"on":[64,201],"practitioner":[65],"intuition":[66],"experience.":[68],"Specifically,":[69],"we":[70,105,124,139,154,164],"show":[71],"correlation":[74,96],"prediction":[76,98,213],"can":[77,85,176,190,204,227],"increase":[78],"our":[79],"of":[81,89,149,219,235],"behavior":[83],"critical":[87],"components":[88],"effective":[90],"strategies.":[93],"While":[94],"have":[99],"been":[100],"used":[101],"contexts,":[104],"offer":[106],"new":[107],"insights":[108,188],"about":[109],"their":[110],"potential":[111],"capabilities.":[112],"Using":[113],"logs":[115],"from":[116],"computer":[118],"failure":[119,151,159,212,220],"repository":[121],"(cfdr)":[122],"(1)":[123],"use":[125,140,165],"cross":[126],"partial":[128],"correlations":[129,133,197,203],"observe":[131],"conditional":[132],"data;":[137,152],"(2)":[138],"information":[141],"theory":[142],"understand":[144,170],"fundamental":[146],"predictive":[147],"power":[148],"(3)":[153],"study":[155],"neural":[156],"networks":[157],"for":[158],"prediction;":[160],"(4)":[162],"finally,":[163],"principal":[166,224],"component":[167,225],"analysis":[168,226],"what":[172],"extent":[173],"dimensionality":[174],"reduction":[175],"apply":[177],"data.":[181],"This":[182],"work":[183],"results":[184],"following":[187],"inform":[191],"monitoring:":[194],"hoc":[196],"or":[198,207],"ones":[199],"direct":[202],"be":[205],"deficient":[206],"even":[208],"misleading;":[209],"highly":[210],"accurate":[211],"may":[214],"only":[215],"require":[216],"small":[217],"windows":[218],"history;":[222],"significantly":[228],"reduce":[229],"without":[233],"loss":[234],"relevant":[236],"information.":[237]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}