{"id":"https://openalex.org/W1966243865","doi":"https://doi.org/10.1145/2807591.2807666","title":"Reliability lessons learned from GPU experience with the Titan supercomputer at Oak Ridge leadership computing facility","display_name":"Reliability lessons learned from GPU experience with the Titan supercomputer at Oak Ridge leadership computing facility","publication_year":2015,"publication_date":"2015-10-27","ids":{"openalex":"https://openalex.org/W1966243865","doi":"https://doi.org/10.1145/2807591.2807666","mag":"1966243865"},"language":"en","primary_location":{"id":"doi:10.1145/2807591.2807666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2807591.2807666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1248768","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074406596","display_name":"Devesh Tiwari","orcid":"https://orcid.org/0000-0002-7253-2458"},"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":true,"raw_author_name":"Devesh Tiwari","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/A5064269047","display_name":"Saurabh Gupta","orcid":"https://orcid.org/0000-0002-5984-852X"},"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":"Saurabh Gupta","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/A5087277680","display_name":"George Gallarno","orcid":null},"institutions":[{"id":"https://openalex.org/I102015815","display_name":"Christian Brothers University","ror":"https://ror.org/03andr831","country_code":"US","type":"education","lineage":["https://openalex.org/I102015815"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Gallarno","raw_affiliation_strings":["Christian Brothers University"],"affiliations":[{"raw_affiliation_string":"Christian Brothers University","institution_ids":["https://openalex.org/I102015815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048985153","display_name":"Jim Rogers","orcid":"https://orcid.org/0000-0001-8196-4503"},"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":"Jim 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/A5058796463","display_name":"Don Maxwell","orcid":"https://orcid.org/0000-0002-3794-5687"},"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":"Don Maxwell","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074406596"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":10.9506,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.98708213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.47049999237060547,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.47049999237060547,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.17649999260902405,"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":0.11800000071525574,"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/supercomputer","display_name":"Supercomputer","score":0.9330955743789673},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.9200137853622437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7679562568664551},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6957812905311584},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6105722784996033},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.53020179271698},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5184899568557739},{"id":"https://openalex.org/keywords/oak-ridge-national-laboratory","display_name":"Oak Ridge National Laboratory","score":0.5101852416992188},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5057861804962158},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.42889177799224854},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41911059617996216},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3414027988910675},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31293177604675293},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.08461400866508484}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.9330955743789673},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.9200137853622437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679562568664551},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6957812905311584},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6105722784996033},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.53020179271698},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5184899568557739},{"id":"https://openalex.org/C2775907726","wikidata":"https://www.wikidata.org/wiki/Q714439","display_name":"Oak Ridge National Laboratory","level":2,"score":0.5101852416992188},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5057861804962158},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.42889177799224854},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41911059617996216},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3414027988910675},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31293177604675293},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.08461400866508484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","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":2,"locations":[{"id":"doi:10.1145/2807591.2807666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2807591.2807666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1248768","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1248768","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":"pmh:oai:osti.gov:1248768","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1248768","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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1578105119","https://openalex.org/W1998221613","https://openalex.org/W1999900893","https://openalex.org/W2018212274","https://openalex.org/W2021595237","https://openalex.org/W2025024269","https://openalex.org/W2027716782","https://openalex.org/W2031533321","https://openalex.org/W2039631162","https://openalex.org/W2091212189","https://openalex.org/W2093962471","https://openalex.org/W2094127360","https://openalex.org/W2095157729","https://openalex.org/W2103759606","https://openalex.org/W2107263349","https://openalex.org/W2108157916","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2142812297","https://openalex.org/W2143220335","https://openalex.org/W2144569590","https://openalex.org/W2146351362","https://openalex.org/W2151204271","https://openalex.org/W2152211247","https://openalex.org/W2158907675","https://openalex.org/W2160821994","https://openalex.org/W2161234420","https://openalex.org/W2163059351","https://openalex.org/W3003432522","https://openalex.org/W3004493283"],"related_works":["https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W1969233021","https://openalex.org/W2167646277","https://openalex.org/W2063573318","https://openalex.org/W2388314963","https://openalex.org/W3158047141","https://openalex.org/W1656096860","https://openalex.org/W2027443981","https://openalex.org/W2375309128"],"abstract_inverted_index":{"The":[0,19],"high":[1],"computational":[2,34],"capability":[3],"of":[4,45,71,100,103],"graphics":[5],"processing":[6],"units":[7],"(GPUs)":[8],"is":[9,50],"enabling":[10],"and":[11,41,74,80],"driving":[12],"the":[13,85,89,98,126],"scientific":[14,39],"discovery":[15],"process":[16,99],"at":[17,63,105],"large-scale.":[18,64],"world's":[20],"second":[21],"fastest":[22],"supercomputer":[23,91],"for":[24],"open":[25],"science,":[26],"Titan,":[27],"has":[28],"more":[29],"than":[30],"18,000":[31],"GPUs":[32,57,87,104,124],"that":[33],"scientists":[35],"use":[36],"to":[37,111,122],"perform":[38],"simulations":[40],"data":[42],"analysis.":[43],"Understanding":[44],"GPU":[46,72,118],"reliability":[47],"characteristics,":[48],"however,":[49],"still":[51],"in":[52,97,125],"its":[53],"nascent":[54],"stage":[55],"since":[56],"have":[58,116],"only":[59],"recently":[60],"been":[61],"deployed":[62],"This":[65],"paper":[66],"presents":[67],"a":[68],"detailed":[69],"study":[70],"errors":[73],"their":[75],"impact":[76],"on":[77,88],"system":[78],"operations":[79],"applications,":[81],"describing":[82],"experiences":[83,108],"with":[84],"18,688":[86],"Titan":[90],"as":[92,94],"well":[93],"lessons":[95],"learned":[96],"efficient":[101],"operation":[102],"scale.":[106],"These":[107],"are":[109],"helpful":[110],"HPC":[112],"sites":[113],"which":[114],"already":[115],"large-scale":[117],"clusters":[119],"or":[120],"plan":[121],"deploy":[123],"future.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
