{"id":"https://openalex.org/W4399282312","doi":"https://doi.org/10.1145/3650200.3656615","title":"Understanding GPU Memory Corruption at Extreme Scale: The Summit Case Study","display_name":"Understanding GPU Memory Corruption at Extreme Scale: The Summit Case Study","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399282312","doi":"https://doi.org/10.1145/3650200.3656615"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656615","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656615","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656615","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","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/10.1145/3650200.3656615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026185056","display_name":"Vladyslav Oles","orcid":"https://orcid.org/0000-0001-8872-7463"},"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":"Vladyslav Oles","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-8872-7463","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084469065","display_name":"Anna Schmedding","orcid":"https://orcid.org/0000-0003-3392-6574"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Schmedding","raw_affiliation_strings":["William & Mary, USA"],"raw_orcid":"https://orcid.org/0000-0003-3392-6574","affiliations":[{"raw_affiliation_string":"William & Mary, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062363588","display_name":"George Ostrouchov","orcid":"https://orcid.org/0000-0002-2043-6026"},"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":"George Ostrouchov","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-2043-6026","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"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, USA"],"raw_orcid":"https://orcid.org/0000-0001-7207-7814","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017102040","display_name":"Evgenia Smirni","orcid":"https://orcid.org/0000-0001-8754-581X"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evgenia Smirni","raw_affiliation_strings":["William & Mary, USA"],"raw_orcid":"https://orcid.org/0000-0001-8754-581X","affiliations":[{"raw_affiliation_string":"William & Mary, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"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":"Christian Engelmann","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0003-4365-6416","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9984999895095825,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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":[{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.8142930269241333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7908143997192383},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6972752809524536},{"id":"https://openalex.org/keywords/summit","display_name":"Summit","score":0.6035370826721191},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5817036628723145},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5813281536102295},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5369868278503418},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4783996343612671},{"id":"https://openalex.org/keywords/language-change","display_name":"Language change","score":0.4719516336917877},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4711773991584778},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4438930153846741},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41395068168640137},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3068760633468628}],"concepts":[{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.8142930269241333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908143997192383},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6972752809524536},{"id":"https://openalex.org/C2778848561","wikidata":"https://www.wikidata.org/wiki/Q207326","display_name":"Summit","level":2,"score":0.6035370826721191},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5817036628723145},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5813281536102295},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5369868278503418},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4783996343612671},{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.4719516336917877},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4711773991584778},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4438930153846741},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41395068168640137},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3068760633468628},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C100970517","wikidata":"https://www.wikidata.org/wiki/Q52107","display_name":"Physical geography","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3650200.3656615","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656615","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656615","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2378092","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2378092","pdf_url":"https://www.osti.gov/servlets/purl/2378092","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:10.1145/3650200.3656615","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656615","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656615","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[{"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/G1652287392","display_name":null,"funder_award_id":"IS-2130681","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G2949170702","display_name":"EAGER: Epidemic Spread Modeling Using Hard Data","funder_award_id":"2130681","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/G5472348745","display_name":null,"funder_award_id":"IIS-1838022","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G6495930337","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G6864165199","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G7995982022","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/G8471942486","display_name":"BIGDATA: IA: Collaborative Research: Protecting Yourself from Wildfire Smoke: Big Data-Driven Adaptive Air Quality Prediction Methodologies","funder_award_id":"1838022","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W613690151","https://openalex.org/W944143979","https://openalex.org/W1559781097","https://openalex.org/W1966243865","https://openalex.org/W1985372952","https://openalex.org/W1999900893","https://openalex.org/W2009063162","https://openalex.org/W2027716782","https://openalex.org/W2037586880","https://openalex.org/W2094127360","https://openalex.org/W2157116240","https://openalex.org/W2318507312","https://openalex.org/W2612733213","https://openalex.org/W2760030941","https://openalex.org/W2770542984","https://openalex.org/W2883087177","https://openalex.org/W2965512201","https://openalex.org/W2984602844","https://openalex.org/W2998041822","https://openalex.org/W3004383742","https://openalex.org/W3007396174","https://openalex.org/W3012032150","https://openalex.org/W3026947705","https://openalex.org/W3112402894","https://openalex.org/W3129927603","https://openalex.org/W3147894994","https://openalex.org/W3162763762","https://openalex.org/W3187552919","https://openalex.org/W3187862527","https://openalex.org/W3206212707","https://openalex.org/W3209605437","https://openalex.org/W3215220453","https://openalex.org/W4230727657","https://openalex.org/W4248895726","https://openalex.org/W4253391807","https://openalex.org/W4283378767","https://openalex.org/W4283689961","https://openalex.org/W4299959846","https://openalex.org/W4360831854"],"related_works":["https://openalex.org/W4241376597","https://openalex.org/W1982074779","https://openalex.org/W3203904831","https://openalex.org/W4230129158","https://openalex.org/W630050097","https://openalex.org/W4246070377","https://openalex.org/W1996312672","https://openalex.org/W2280577319","https://openalex.org/W3137434606","https://openalex.org/W4372263373"],"abstract_inverted_index":{"GPU":[0],"memory":[1],"corruption":[2],"and":[3,29,54,64,76],"in":[4,59],"particular":[5],"double-bit":[6],"errors":[7],"(DBEs)":[8],"remain":[9],"one":[10],"of":[11,16,34,69],"the":[12,42,50,67],"least":[13],"understood":[14],"aspects":[15],"HPC":[17,70],"system":[18],"reliability.":[19],"Albeit":[20],"rare,":[21],"their":[22,55],"occurrences":[23],"always":[24],"lead":[25],"to":[26,48],"job":[27],"termination":[28],"can":[30],"potentially":[31],"cost":[32],"thousands":[33],"node-hours,":[35],"either":[36],"from":[37,44],"wasted":[38],"computations":[39],"or":[40],"as":[41],"overhead":[43],"regular":[45],"checkpointing":[46],"needed":[47],"minimize":[49],"losses.":[51],"As":[52],"supercomputers":[53],"components":[56],"simultaneously":[57],"grow":[58],"scale,":[60],"density,":[61],"failure":[62],"rates,":[63],"environmental":[65],"footprint,":[66],"efficiency":[68],"operations":[71],"becomes":[72],"both":[73],"an":[74],"imperative":[75],"a":[77],"challenge.":[78]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}