{"id":"https://openalex.org/W4388581252","doi":"https://doi.org/10.1145/3624062.3624134","title":"Experiences Detecting Defective Hardware in Exascale Supercomputers","display_name":"Experiences Detecting Defective Hardware in Exascale Supercomputers","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581252","doi":"https://doi.org/10.1145/3624062.3624134"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624134","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624134","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624134","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067897656","display_name":"Nick Hagerty","orcid":"https://orcid.org/0000-0003-3001-4414"},"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":"Nick Hagerty","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3001-4414","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509283","display_name":"Jordan Webb","orcid":"https://orcid.org/0000-0003-3887-7601"},"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":"Jordan Webb","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3887-7601","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035259771","display_name":"Ver\u00f3nica Melesse Vergara","orcid":"https://orcid.org/0000-0002-4333-4145"},"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":"Veronica Melesse Vergara","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4333-4145","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113044581","display_name":"Matt Ezell","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":"Matt Ezell","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4149-0638","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.4173,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58834951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"619","last_page":"626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9980999827384949,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9980999827384949,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10558","display_name":"Advancements in Semiconductor Devices and Circuit Design","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7171821594238281},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.6964300870895386},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5239051580429077},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38136738538742065},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3511248528957367},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33899587392807007},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.24138879776000977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171821594238281},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.6964300870895386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5239051580429077},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38136738538742065},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3511248528957367},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33899587392807007},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.24138879776000977}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3624062.3624134","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624134","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624134","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2224160","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2224160","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3624062.3624134","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624134","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624134","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G121915436","display_name":null,"funder_award_id":"DEAC05- 00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3759531448","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581252.pdf","grobid_xml":"https://content.openalex.org/works/W4388581252.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1528697349","https://openalex.org/W3201073812"],"related_works":["https://openalex.org/W3174642189","https://openalex.org/W2295013321","https://openalex.org/W4388103229","https://openalex.org/W2418291489","https://openalex.org/W2068121105","https://openalex.org/W3010946599","https://openalex.org/W3096519538","https://openalex.org/W4388662129","https://openalex.org/W2744747300","https://openalex.org/W4241166160"],"abstract_inverted_index":{"In":[0,54,95],"May":[1],"2022,":[2],"the":[3,8,20,66,78,118,121,131,134,138,142,163,172,175,189,200],"newest":[4],"supercomputer":[5],"to":[6,124,129],"top":[7],"TOP":[9],"500":[10],"list":[11],"was":[12],"Frontier":[13,56,91],"at":[14],"Oak":[15],"Ridge":[16],"National":[17],"Laboratory,":[18],"demonstrating":[19],"capability":[21],"of":[22,37,69,74,84,150],"computing":[23,38],"more":[24,41,58,168],"than":[25,42,59,169],"1.1":[26],"quintillion":[27],"(1018)":[28],"floating-point":[29],"calculations":[30],"every":[31],"second.":[32],"Driving":[33],"this":[34,64,96],"ground-breaking":[35],"rate":[36],"is":[39],"Frontier\u2019s":[40,109],"37,000":[43],"graphics":[44],"processing":[45,51],"units":[46,52],"(GPUs)":[47],"and":[48,100,145,194],"9,408":[49,110],"central":[50],"(CPUs).":[53],"total,":[55],"contains":[57],"60":[60],"million":[61],"parts.":[62],"At":[63],"scale,":[65],"smallest":[67],"margin":[68],"error":[70],"may":[71],"generate":[72],"hundreds":[73],"hardware":[75,183],"errors":[76,81],"across":[77],"system.":[79],"These":[80],"are":[82,114],"capable":[83],"directly":[85],"hindering":[86],"world-class":[87],"science":[88],"performed":[89],"on":[90,199],"if":[92],"not":[93],"found.":[94],"work,":[97],"we":[98,160],"describe":[99],"evaluate":[101],"two":[102,115],"strategies":[103,116],"for":[104],"finding":[105],"hardware-level":[106],"faults":[107],"in":[108,141,185],"compute":[111,127],"nodes.":[112],"There":[113],"developed:":[117],"first":[119,143,164,202],"uses":[120],"Slurm":[122],"scheduler":[123],"scavenge":[125],"available":[126],"time":[128],"run":[130],"node":[132,197],"screen,":[133],"second":[135,176],"builds":[136],"upon":[137],"lessons":[139,190],"learned":[140,191],"strategy":[144,166],"enforces":[146],"a":[147,157,196],"weekly":[148],"screen":[149,198],"each":[151],"node.":[152],"Using":[153],"June":[154],"2023":[155],"as":[156,174],"case":[158],"study,":[159],"find":[161],"that":[162],"scheduling":[165,177],"consumed":[167],"ten":[170],"times":[171],"resources":[173],"strategy,":[178],"but":[179],"successfully":[180],"detected":[181],"five":[182],"defects":[184],"Frontier.":[186],"We":[187],"summarize":[188],"while":[192],"developing":[193],"running":[195],"world\u2019s":[201],"exascale":[203],"supercomputer.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
