{"id":"https://openalex.org/W4416199156","doi":"https://doi.org/10.1145/3712285.3759821","title":"Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs","display_name":"Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416199156","doi":"https://doi.org/10.1145/3712285.3759821"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759821","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759821","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062104583","display_name":"Shengkun Cui","orcid":"https://orcid.org/0009-0003-8074-8712"},"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":true,"raw_author_name":"Shengkun Cui","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0009-0003-8074-8712","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036886711","display_name":"Archit Patke","orcid":"https://orcid.org/0009-0006-7878-8856"},"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":"Archit Patke","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0009-0006-7878-8856","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038003572","display_name":"Thai-Hung Nguyen","orcid":"https://orcid.org/0000-0003-0883-8011"},"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":"Hung Nguyen","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0003-0883-8011","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102526353","display_name":"Aditya Ranjan","orcid":"https://orcid.org/0009-0003-3564-2249"},"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":"Aditya Ranjan","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0009-0003-3564-2249","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziheng Chen","orcid":"https://orcid.org/0009-0006-2335-8656"},"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":"Ziheng Chen","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0009-0006-2335-8656","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011948693","display_name":"Phuong Cao","orcid":"https://orcid.org/0000-0001-6028-0583"},"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":"Phuong Cao","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0001-6028-0583","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074942058","display_name":"Gregory H. Bauer","orcid":"https://orcid.org/0000-0001-7247-0915"},"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":"Gregory Bauer","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0001-7247-0915","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062604151","display_name":"Brett Bode","orcid":"https://orcid.org/0000-0002-4202-1024"},"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":"Brett Bode","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0002-4202-1024","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","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/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Catello Di Martino","raw_affiliation_strings":["Nokia Bell Labs, Sao Paulo, Brazil"],"raw_orcid":"https://orcid.org/0009-0004-9151-6594","affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Sao Paulo, Brazil","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016778130","display_name":"Saurabh Jha","orcid":"https://orcid.org/0000-0003-0926-0776"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Jha","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0003-0926-0776","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043854372","display_name":"Chandra Narayanaswami","orcid":"https://orcid.org/0000-0002-4242-5352"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandra Narayanaswami","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0002-4242-5352","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042350438","display_name":"Daby Sow","orcid":"https://orcid.org/0000-0003-2227-5243"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daby Sow","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0003-2227-5243","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"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 T. Kalbarczyk","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0009-0002-6040-6865","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","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 Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0003-2245-3038","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5062104583"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30036694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1145","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.4189000129699707,"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"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.4189000129699707,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.4117000102996826,"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":0.08150000125169754,"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/resilience","display_name":"Resilience (materials science)","score":0.6711999773979187},{"id":"https://openalex.org/keywords/psychological-resilience","display_name":"Psychological resilience","score":0.578499972820282},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.36169999837875366},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3005000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331999778747559},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.6711999773979187},{"id":"https://openalex.org/C137176749","wikidata":"https://www.wikidata.org/wiki/Q4105337","display_name":"Psychological resilience","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3712285.3759821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759821","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:arXiv.org:2503.11901","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11901","pdf_url":"https://arxiv.org/pdf/2503.11901","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759821","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3138142384","display_name":null,"funder_award_id":"2029049,2319190,2430244,2530738,2320345,2005572,2138259,2138286,2138307,2137603,2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1578105119","https://openalex.org/W1583519197","https://openalex.org/W1596936080","https://openalex.org/W1963880259","https://openalex.org/W1966243865","https://openalex.org/W1999900893","https://openalex.org/W2025024269","https://openalex.org/W2027716782","https://openalex.org/W2100997884","https://openalex.org/W2146351362","https://openalex.org/W2150981663","https://openalex.org/W2161537327","https://openalex.org/W2318507312","https://openalex.org/W2400561398","https://openalex.org/W2767346922","https://openalex.org/W2770542984","https://openalex.org/W2805459376","https://openalex.org/W2895690683","https://openalex.org/W2901848761","https://openalex.org/W2998208529","https://openalex.org/W3004697822","https://openalex.org/W3013374519","https://openalex.org/W3129298663","https://openalex.org/W3129927603","https://openalex.org/W4206384029","https://openalex.org/W4244241786","https://openalex.org/W4283689961","https://openalex.org/W4286220308","https://openalex.org/W4312356560","https://openalex.org/W4360831854","https://openalex.org/W4385469644","https://openalex.org/W4387868960","https://openalex.org/W4389491852","https://openalex.org/W4399282312","https://openalex.org/W4399757647","https://openalex.org/W4404133430","https://openalex.org/W4409131852","https://openalex.org/W4409248832","https://openalex.org/W4411800338","https://openalex.org/W4413059236"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"characterizes":[2],"GPU":[3,35,38,46,53,65,86,99,131,147],"resilience":[4,48,88],"in":[5,109],"Delta,":[6],"a":[7],"large-scale":[8],"AI":[9],"system":[10],"that":[11,138],"consists":[12],"of":[13,23,30,116,130,141],"1,056":[14],"A100":[15,52,90,103],"and":[16,104,124,136],"H100":[17,45,70,81,105],"GPUs,":[18],"with":[19,55,92],"over":[20,89],"1,300":[21],"petaflops":[22],"peak":[24],"throughput.":[25],"We":[26,126],"used":[27],"2.5":[28],"years":[29],"operational":[31],"data":[32],"(11.7":[33],"million":[34],"hours)":[36],"on":[37,69,101,134],"errors.":[39],"Our":[40],"major":[41],"findings":[42],"include:":[43],"(i)":[44],"memory":[47,61,66,78],"is":[49,143],"worse":[50],"than":[51],"memory,":[54],"3.2x":[56],"lower":[57],"per-GPU":[58],"MTBE":[59],"for":[60],"errors,":[62],"(ii)":[63],"The":[64],"error-recovery":[67],"mechanisms":[68,119],"GPUs":[71,82,91,106],"are":[72],"insufficient":[73],"to":[74,94,113,145],"handle":[75,146],"the":[76,114,121,128],"increased":[77],"capacity,":[79],"(iii)":[80],"demonstrate":[83],"significantly":[84],"improved":[85],"hardware":[87,96],"respect":[93],"critical":[95],"components,":[97],"(iv)":[98],"errors":[100],"both":[102],"frequently":[107],"result":[108],"job":[110],"failures":[111],"due":[112],"lack":[115],"robust":[117],"recovery":[118],"at":[120],"application":[122],"level,":[123],"(v)":[125],"project":[127],"impact":[129],"node":[132],"availability":[133],"larger-scales":[135],"find":[137],"significant":[139],"overprovisioning":[140],"5%":[142],"necessary":[144],"failures.":[148]},"counts_by_year":[],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-11-12T00:00:00"}
