{"id":"https://openalex.org/W4381612905","doi":"https://doi.org/10.1145/3579370.3594777","title":"Predicting GPU Failures With High Precision Under Deep Learning Workloads","display_name":"Predicting GPU Failures With High Precision Under Deep Learning Workloads","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4381612905","doi":"https://doi.org/10.1145/3579370.3594777"},"language":"en","primary_location":{"id":"doi:10.1145/3579370.3594777","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579370.3594777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Systems and Storage","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/A5060516265","display_name":"Heting Liu","orcid":"https://orcid.org/0000-0002-0321-347X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Heting Liu","raw_affiliation_strings":["ByteDance Inc., San Jose, United States of America"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103043568","display_name":"Zhichao Li","orcid":"https://orcid.org/0000-0001-7388-7341"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhichao Li","raw_affiliation_strings":["ByteDance Inc., Seattle, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759092","display_name":"Cheng Tan","orcid":"https://orcid.org/0000-0002-1420-5125"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Tan","raw_affiliation_strings":["Northeastern University, Boston, United States of America"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090398573","display_name":"Rongqiu Yang","orcid":"https://orcid.org/0009-0009-2360-4791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongqiu Yang","raw_affiliation_strings":["ByteDance Inc., Beijing, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029367295","display_name":"Guohong Cao","orcid":"https://orcid.org/0000-0003-2115-7165"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guohong Cao","raw_affiliation_strings":["Pennsylvania State University, State College, United States of America"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, State College, United States of America","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090569171","display_name":"Zherui Liu","orcid":"https://orcid.org/0009-0002-4910-6095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zherui Liu","raw_affiliation_strings":["ByteDance Inc., Beijing, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054205326","display_name":"Chuanxiong Guo","orcid":"https://orcid.org/0000-0002-0730-8468"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuanxiong Guo","raw_affiliation_strings":["Bytedance, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Bytedance, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5060516265"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7988,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72829215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9830999970436096,"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":0.8450474739074707},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6769202947616577},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.6768410205841064},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6228209733963013},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.6095355153083801},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5821106433868408},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5645807981491089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45581358671188354},{"id":"https://openalex.org/keywords/damages","display_name":"Damages","score":0.43784815073013306},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39774787425994873},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.15971890091896057},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14952856302261353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450474739074707},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6769202947616577},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.6768410205841064},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6228209733963013},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.6095355153083801},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5821106433868408},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5645807981491089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45581358671188354},{"id":"https://openalex.org/C2777381055","wikidata":"https://www.wikidata.org/wiki/Q308922","display_name":"Damages","level":2,"score":0.43784815073013306},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39774787425994873},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.15971890091896057},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14952856302261353},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579370.3594777","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579370.3594777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Systems and Storage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1980264541","https://openalex.org/W1985554184","https://openalex.org/W1999900893","https://openalex.org/W2091085232","https://openalex.org/W2107263349","https://openalex.org/W2118676041","https://openalex.org/W2135293965","https://openalex.org/W2158907675","https://openalex.org/W2221879666","https://openalex.org/W2509298940","https://openalex.org/W2743678626","https://openalex.org/W2767321582","https://openalex.org/W2794693252","https://openalex.org/W2808242862","https://openalex.org/W2966284335","https://openalex.org/W3025035827","https://openalex.org/W4234178886","https://openalex.org/W4234592442","https://openalex.org/W4245744969","https://openalex.org/W4252832591","https://openalex.org/W4253240889"],"related_works":["https://openalex.org/W2075046026","https://openalex.org/W2008492897","https://openalex.org/W2142485291","https://openalex.org/W2191246539","https://openalex.org/W2319727539","https://openalex.org/W2952476118","https://openalex.org/W2009127573","https://openalex.org/W189420351","https://openalex.org/W2806179752","https://openalex.org/W127524933"],"abstract_inverted_index":{"Graphics":[0],"processing":[1,10],"units":[2],"(GPUs)":[3],"are":[4,21],"the":[5,50],"de":[6],"facto":[7],"standard":[8],"for":[9],"deep":[11],"learning":[12,58],"(DL)":[13],"tasks.":[14],"In":[15,45],"large-scale":[16],"GPU":[17,19,30,54],"clusters,":[18],"failures":[20,31,55],"inevitable":[22],"and":[23,38],"may":[24],"cause":[25],"severe":[26],"consequences.":[27],"For":[28],"example,":[29],"disrupt":[32],"distributed":[33],"training,":[34],"crash":[35],"inference":[36],"services,":[37],"result":[39],"in":[40],"service":[41],"level":[42],"agreement":[43],"violations.":[44],"this":[46],"paper,":[47],"we":[48],"study":[49],"problem":[51],"of":[52],"predicting":[53],"using":[56],"machine":[57],"(ML)":[59],"models":[60],"to":[61],"mitigate":[62],"their":[63],"damages.":[64]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}