{"id":"https://openalex.org/W2743531752","doi":"https://doi.org/10.1109/tdsc.2017.2737537","title":"Resiliency of HPC Interconnects: A Case Study of Interconnect Failures and Recovery in Blue Waters","display_name":"Resiliency of HPC Interconnects: A Case Study of Interconnect Failures and Recovery in Blue Waters","publication_year":2017,"publication_date":"2017-08-09","ids":{"openalex":"https://openalex.org/W2743531752","doi":"https://doi.org/10.1109/tdsc.2017.2737537","mag":"2743531752"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdsc.2017.2737537","pdf_url":null,"source":{"id":"https://openalex.org/S133795288","display_name":"IEEE Transactions on Dependable and Secure Computing","issn_l":"1545-5971","issn":["1545-5971","1941-0018","2160-9209"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016778130","display_name":"Saurabh Jha","orcid":"https://orcid.org/0000-0003-0926-0776"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Jha","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015185649","display_name":"Valerio Formicola","orcid":"https://orcid.org/0000-0003-1166-4729"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valerio Formicola","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021964790","display_name":"Catello Di Martino","orcid":"https://orcid.org/0000-0003-4460-516X"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catello Di Martino","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020870714","display_name":"Mark W. Dalton","orcid":"https://orcid.org/0000-0002-8943-9655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Dalton","raw_affiliation_strings":["Cray Inc., Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Cray Inc., Seattle, WA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110595734","display_name":"William Kramer","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William T. Kramer","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043860236","display_name":"Zbigniew Kalbarczyk","orcid":"https://orcid.org/0009-0002-6040-6865"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zbigniew Kalbarczyk","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067802693","display_name":"Ravishankar K. Iyer","orcid":"https://orcid.org/0000-0003-2245-3038"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravishankar K. Iyer","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.686,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.872218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":89},"biblio":{"volume":"15","issue":"6","first_page":"915","last_page":"930"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998,"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":0.9996,"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":0.9957,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8802011},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.833098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821516},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4271223},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3516687},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.31944948},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2616643}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdsc.2017.2737537","pdf_url":null,"source":{"id":"https://openalex.org/S133795288","display_name":"IEEE Transactions on Dependable and Secure Computing","issn_l":"1545-5971","issn":["1545-5971","1941-0018","2160-9209"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":43,"referenced_works":["https://openalex.org/W1501077214","https://openalex.org/W1552325196","https://openalex.org/W1553890549","https://openalex.org/W1558516248","https://openalex.org/W1581232847","https://openalex.org/W1818681200","https://openalex.org/W1987117298","https://openalex.org/W1992580876","https://openalex.org/W2001495258","https://openalex.org/W200983080","https://openalex.org/W2010805714","https://openalex.org/W2025024269","https://openalex.org/W2026048928","https://openalex.org/W2036641664","https://openalex.org/W2045129218","https://openalex.org/W2049459394","https://openalex.org/W2065742943","https://openalex.org/W2072637364","https://openalex.org/W2079577430","https://openalex.org/W2081612620","https://openalex.org/W2093736609","https://openalex.org/W2098279176","https://openalex.org/W2105524676","https://openalex.org/W2107263349","https://openalex.org/W2129307244","https://openalex.org/W2142812297","https://openalex.org/W2143220335","https://openalex.org/W2154323564","https://openalex.org/W2155204206","https://openalex.org/W2155713541","https://openalex.org/W2158700277","https://openalex.org/W2171878649","https://openalex.org/W2287381992","https://openalex.org/W2557174605","https://openalex.org/W2607321658","https://openalex.org/W2950142238","https://openalex.org/W4210992409","https://openalex.org/W4237492115","https://openalex.org/W4248409180","https://openalex.org/W4248489181","https://openalex.org/W4255095948","https://openalex.org/W4256158364","https://openalex.org/W4295172975"],"related_works":["https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2765823764","https://openalex.org/W2523801036","https://openalex.org/W2384867379","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2151092287","https://openalex.org/W2079244304"],"abstract_inverted_index":{"Availability":[0],"of":[1,17,43,56,65,108,135,150,157],"the":[2,14,35,38,49,62,66,70,85,115,132],"interconnection":[3],"network":[4,32,73],"in":[5,113],"high-performance":[6],"computing":[7],"(HPC)":[8],"systems":[9,45],"is":[10],"fundamental":[11],"to":[12,30,52,104],"sustaining":[13],"continuous":[15],"execution":[16,55,134],"applications":[18,118],"at":[19,84],"scale.":[20],"When":[21],"failures":[22,53,100,109,140,154],"occur,":[23],"interconnect":[24,68,99],"recovery":[25,63,102,125,136],"mechanisms":[26],"orchestrate":[27],"complex":[28],"operations":[29],"recover":[31],"connectivity":[33],"between":[34],"nodes.":[36],"As":[37],"scale":[39],"and":[40,101,110,117,130,152],"design":[41],"complexity":[42],"HPC":[44],"increase,":[46],"so":[47],"does":[48],"system's":[50],"susceptibility":[51],"during":[54,119,142],"interconnect-recovery":[57],"procedures.":[58],"This":[59],"study":[60],"characterizes":[61],"procedures":[64,103,126],"Gemini":[67,72],"network,":[69],"largest":[71],"built":[74],"by":[75],"Cray,":[76],"on":[77],"Blue":[78],"Waters,":[79],"a":[80,94],"13.3":[81],"petaflop":[82],"supercomputer":[83],"National":[86],"Center":[87],"for":[88],"Supercomputing":[89],"Applications":[90],"(NCSA).":[91],"We":[92],"propose":[93],"propagation":[95,112],"model":[96],"that":[97,124,131],"captures":[98],"help":[105],"understand":[106],"types":[107],"their":[111],"both":[114],"system":[116],"recovery.":[120],"The":[121],"measurements":[122],"show":[123],"occur":[127,141],"very":[128],"frequently":[129],"unsuccessful":[133],"procedures,":[137],"when":[138],"additional":[139],"recovery,":[143],"causes":[144],"system-wide":[145],"outages":[146],"(SWOs,":[147],"28":[148],"out":[149],"101)":[151],"application":[153],"(3.4":[155],"percent":[156],"all":[158],"running":[159],"applications).":[160]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2743531752","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2024-12-09T06:52:23.122016","created_date":"2017-08-17"}