{"id":"https://openalex.org/W2520478933","doi":"https://doi.org/10.1109/hpcsim.2016.7568304","title":"Panels: Panel session I: Resiliency in extreme scale high performance computing systems and applications","display_name":"Panels: Panel session I: Resiliency in extreme scale high performance computing systems and applications","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2520478933","doi":"https://doi.org/10.1109/hpcsim.2016.7568304","mag":"2520478933"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2016.7568304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing &amp; Simulation (HPCS)","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/A5013084939","display_name":"Vassil Alexandrov","orcid":"https://orcid.org/0000-0002-4889-1207"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Vassil Alexandrov","raw_affiliation_strings":["Barcelona Supercomputer Center, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputer Center, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064121950","display_name":"Thomas Ropars","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Ropars","raw_affiliation_strings":["Universite Grenoble Alpes, France"],"affiliations":[{"raw_affiliation_string":"Universite Grenoble Alpes, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006324486","display_name":"Lorenzo Strigini","orcid":"https://orcid.org/0000-0002-4246-2866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Strigini","raw_affiliation_strings":["City University London, U.K"],"affiliations":[{"raw_affiliation_string":"City University London, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013084939"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10958923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9871000051498413,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9871000051498413,"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":0.977400004863739,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9702000021934509,"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":0.7435119152069092},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.7076294422149658},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5827285051345825},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5720042586326599},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5311072468757629},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.520569384098053},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4835655391216278},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4357474446296692},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3216616213321686},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22682827711105347},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1545705497264862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435119152069092},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7076294422149658},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5827285051345825},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5720042586326599},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5311072468757629},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.520569384098053},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4835655391216278},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4357474446296692},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3216616213321686},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22682827711105347},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1545705497264862},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2016.7568304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W3119814709","https://openalex.org/W2384867379","https://openalex.org/W2018477250","https://openalex.org/W1508895727","https://openalex.org/W4241418540","https://openalex.org/W2725786787","https://openalex.org/W2353986702"],"abstract_inverted_index":{"Recent":[0],"experiences":[1],"in":[2,151,185],"extreme":[3,92,189],"scale":[4,93,190],"high":[5,119],"performance":[6],"computing":[7],"systems":[8,192],"and":[9,51,53,62,72,89,104,148,155,173,193],"applications":[10],"indicate":[11],"that":[12,138,176],"failure":[13,120],"rates":[14,121],"continue":[15,66],"to":[16,67,78,87,99,117,180],"be":[17,76,96,178],"on":[18],"the":[19,123,165,186],"rise,":[20,68],"at":[21],"times":[22],"exponentially.":[23],"The":[24,28,83],"reasons":[25],"are":[26,115,142],"multi-faceted.":[27],"probability":[29],"of":[30,101,164,188],"errors":[31,141],"not":[32],"only":[33],"grows":[34],"with":[35,40,126],"system":[36],"size,":[37],"but":[38],"also":[39],"increasing":[41,59],"architectural":[42],"vulnerabilities":[43],"caused":[44],"by":[45,54],"employing":[46],"accelerators,":[47],"such":[48,112,127,132],"as":[49,113,133],"FPGAs":[50],"GPUs,":[52],"shrinking":[55],"nanometer":[56],"technologies.":[57],"Ever":[58],"component":[60],"counts":[61],"software":[63],"complexities":[64],"will":[65,75,161,177],"while":[69],"application":[70,157],"correctness":[71],"execution":[73],"efficiency":[74],"expected":[77],"become":[79],"even":[80,145],"more":[81],"critical.":[82],"gains":[84],"made":[85],"due":[86,98],"today's":[88],"future":[90],"generation":[91],"designs":[94],"can":[95],"diminished":[97],"lack":[100],"fault":[102,109],"tolerance":[103,110],"resiliency":[105,130],"adequate":[106],"solutions.":[107],"Reactive":[108],"technologies,":[111,131],"checkpointing/restarting,":[114],"unable":[116],"handle":[118],"given":[122,137],"overheads":[124],"associated":[125],"approaches.":[128],"Proactive":[129],"migration,":[134],"cannot":[135],"cope":[136],"random":[139],"soft":[140],"unpredictable,":[143],"may":[144],"remain":[146],"undetected":[147],"thus":[149],"resulting":[150],"silent":[152],"data":[153],"corruption":[154],"incorrect":[156],"output.":[158],"This":[159],"panel":[160],"address":[162],"some":[163],"resilience":[166],"foundations,":[167],"enabling":[168],"infrastructure":[169],"for":[170],"resilience,":[171],"exiting":[172],"projected":[174],"solutions":[175],"required":[179],"meet":[181],"this":[182],"key":[183],"challenge":[184],"era":[187],"HPC":[191],"applications.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
