{"id":"https://openalex.org/W3115176797","doi":"https://doi.org/10.1109/hpec43674.2020.9286239","title":"Hybrid Approach to HPC Cluster Telemetry and Hardware Log Analytics","display_name":"Hybrid Approach to HPC Cluster Telemetry and Hardware Log Analytics","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3115176797","doi":"https://doi.org/10.1109/hpec43674.2020.9286239","mag":"3115176797"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-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/A5080601320","display_name":"Justin Thaler","orcid":"https://orcid.org/0009-0009-2234-6225"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Justin Thaler","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082901516","display_name":"Woong Shin","orcid":"https://orcid.org/0000-0001-7207-7814"},"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":"Woong Shin","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110732557","display_name":"Steven Roberts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Roberts","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109487673","display_name":"James H. Rogers","orcid":null},"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":"James H. Rogers","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025264793","display_name":"Todd Rosedahl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Todd Rosedahl","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080601320"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4625,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68221491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9983999729156494,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9916999936103821,"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":0.780157208442688},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6070743799209595},{"id":"https://openalex.org/keywords/telemetry","display_name":"Telemetry","score":0.4738926291465759},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.44114676117897034},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43194475769996643},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.41965538263320923},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3849591016769409},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2693503797054291},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.26379716396331787},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1099335253238678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780157208442688},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6070743799209595},{"id":"https://openalex.org/C183121708","wikidata":"https://www.wikidata.org/wiki/Q209867","display_name":"Telemetry","level":2,"score":0.4738926291465759},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.44114676117897034},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43194475769996643},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.41965538263320923},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3849591016769409},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2693503797054291},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26379716396331787},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1099335253238678},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1493211444","https://openalex.org/W2052205184","https://openalex.org/W2899199289","https://openalex.org/W2926415742","https://openalex.org/W2960249967","https://openalex.org/W4300080488"],"related_works":["https://openalex.org/W2070863773","https://openalex.org/W4212896802","https://openalex.org/W2056771637","https://openalex.org/W748047311","https://openalex.org/W2359918844","https://openalex.org/W4298110012","https://openalex.org/W2519661158","https://openalex.org/W4388599231","https://openalex.org/W2058226360","https://openalex.org/W1971349181"],"abstract_inverted_index":{"The":[0,110],"number":[1],"of":[2,34,43,98,135,161],"computer":[3],"processing":[4],"nodes":[5,163],"and":[6,16,36,46,65,75,101,133,147,154],"processor":[7],"cores":[8],"in":[9,24,138,149,151],"cluster":[10,73,106],"systems":[11],"is":[12,148],"growing":[13],"rapidly.":[14],"Discovering,":[15],"reacting":[17],"to,":[18],"a":[19,25,88],"hardware":[20],"or":[21,58],"environmental":[22],"issue":[23],"timely":[26],"manner":[27],"enables":[28],"proper":[29],"fault":[30],"isolation,":[31],"improves":[32,37],"quality":[33],"service,":[35],"system":[38,108,160],"up-time.":[39],"In":[40],"the":[41,103,127,158],"case":[42],"performance":[44],"impacts":[45],"node":[47],"outages,":[48],"RAS":[49,99],"policies":[50],"can":[51,68],"direct":[52],"actions":[53],"such":[54],"as":[55,79,81,123],"job":[56,83],"quiescence":[57],"migration.":[59],"Additionally,":[60],"power":[61],"consumption,":[62],"thermal":[63],"information,":[64],"utilization":[66],"metrics":[67],"be":[69],"used":[70],"to":[71,130],"provide":[72],"energy":[74],"cooling":[76],"efficiency":[77],"improvements":[78],"well":[80],"optimized":[82],"placement.":[84],"This":[85,142],"paper":[86],"describes":[87],"highly":[89],"scalable":[90],"telemetry":[91,137],"architecture":[92,111],"that":[93],"allows":[94],"event":[95],"aggregation,":[96],"application":[97],"policies,":[100,119],"provides":[102],"ability":[104],"for":[105],"control":[107],"feedback.":[109],"advances":[112],"existing":[113],"approaches":[114],"by":[115],"including":[116,157],"both":[117,152],"programmable":[118],"which":[120],"are":[121],"applied":[122],"events":[124],"stream":[125],"through":[126],"hierarchical":[128],"network":[129],"persistence":[131],"storage,":[132],"treatment":[134],"sensor":[136],"an":[139],"extensible":[140],"framework.":[141],"implementation":[143],"has":[144],"proven":[145],"robust":[146],"use":[150],"cloud":[153],"HPC":[155],"environments":[156],"Summit":[159],"4,608":[162],"at":[164],"Oak":[165],"Ridge":[166],"National":[167],"Laboratory":[168],"[5].":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-01-11T23:08:45.486102","created_date":"2025-10-10T00:00:00"}
