{"id":"https://openalex.org/W4414199006","doi":"https://doi.org/10.1109/dac63849.2025.11132417","title":"MemSeer: Leverage Memory Failure Distinctions and Multi-Grained Prediction in Ultra-Scale Heterogeneous X86/ARM Clusters","display_name":"MemSeer: Leverage Memory Failure Distinctions and Multi-Grained Prediction in Ultra-Scale Heterogeneous X86/ARM Clusters","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414199006","doi":"https://doi.org/10.1109/dac63849.2025.11132417"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085577563","display_name":"Yunfei Gu","orcid":"https://orcid.org/0000-0002-9181-8996"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Gu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746009","display_name":"Yixuan Liu","orcid":"https://orcid.org/0000-0002-5290-2415"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020647435","display_name":"Xinyuan Wu","orcid":"https://orcid.org/0009-0002-7291-3813"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101710035","display_name":"Bo Shao","orcid":"https://orcid.org/0000-0003-2376-177X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Shao","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783501","display_name":"Chentao Wu","orcid":"https://orcid.org/0000-0002-6882-3754"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chentao Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626061","display_name":"Shiyi Li","orcid":"https://orcid.org/0000-0001-8206-6916"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyi Li","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101372398","display_name":"Jieru Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieru Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428370","display_name":"Jie Li","orcid":"https://orcid.org/0009-0006-8674-1775"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102763431","display_name":"Kunlin Yang","orcid":"https://orcid.org/0000-0002-8752-8347"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunlin Yang","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021835539","display_name":"Wengui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengui Zhang","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065674816","display_name":"Feilong Lin","orcid":"https://orcid.org/0000-0003-2887-2882"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Lin","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9580000042915344,"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":0.9580000042915344,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9370999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9294000267982483,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/leverage","display_name":"Leverage (statistics)","score":0.6608999967575073},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6347000002861023},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.40779998898506165},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.35910001397132874},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.34060001373291016},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.28790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222999930381775},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6347000002861023},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.2678999900817871}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1559781097","https://openalex.org/W1600744878","https://openalex.org/W1990697197","https://openalex.org/W1998791759","https://openalex.org/W2027476456","https://openalex.org/W2108021109","https://openalex.org/W2118637853","https://openalex.org/W2234482445","https://openalex.org/W2295598076","https://openalex.org/W2751591301","https://openalex.org/W2772956929","https://openalex.org/W2773498542","https://openalex.org/W2792281126","https://openalex.org/W2908177913","https://openalex.org/W2989171707","https://openalex.org/W2999222310","https://openalex.org/W2999606367","https://openalex.org/W3003432522","https://openalex.org/W3004493283","https://openalex.org/W3009207130","https://openalex.org/W3086126534","https://openalex.org/W3093988908","https://openalex.org/W3132629440","https://openalex.org/W3167937798","https://openalex.org/W3205272658","https://openalex.org/W4200335215","https://openalex.org/W4230282358","https://openalex.org/W4285361475","https://openalex.org/W4287849472","https://openalex.org/W4308083853","https://openalex.org/W4313451571","https://openalex.org/W4318147164","https://openalex.org/W4321636490","https://openalex.org/W4385688947","https://openalex.org/W4399554754"],"related_works":[],"abstract_inverted_index":{"In":[0],"high-performance":[1],"ultra-scale":[2],"cloud":[3],"computing,":[4],"heterogeneous":[5,68,86],"clusters":[6],"consisting":[7],"of":[8,42,59,100],"x86":[9],"and":[10,21,51,94,130],"ARM":[11],"architecture":[12],"platforms":[13,65],"have":[14],"become":[15],"increasingly":[16],"common":[17],"to":[18,48,108,128],"boost":[19],"performance":[20],"energy":[22],"efficiency.":[23],"Ensuring":[24],"high":[25],"availability":[26],"in":[27,66,116,120,133],"these":[28],"environments":[29],"is":[30],"crucial":[31],"for":[32,84],"meeting":[33],"service-level":[34],"agreements.":[35],"However,":[36],"DRAM":[37],"failures,":[38],"a":[39,78],"primary":[40],"cause":[41],"server":[43],"downtimes,":[44],"present":[45],"significant":[46],"challenges":[47],"reliability,":[49],"availability,":[50],"serviceability.":[52],"This":[53],"paper":[54],"provides":[55],"an":[56,73,98],"in-depth":[57],"analysis":[58],"memory":[60,80,118],"failure":[61,81],"characteristics":[62],"across":[63,103],"cross-architecture":[64],"large-scale":[67],"clusters.":[69,87],"We":[70],"introduce":[71],"MemSeer,":[72],"AIOps-integrated":[74],"tool":[75],"that":[76],"utilizes":[77],"multi-grained":[79],"prediction":[82],"approach":[83],"x86/ARM":[85],"MemSeer":[88],"improves":[89],"the":[90],"F1-score":[91],"by":[92,97,126],"17.3%":[93],"increases":[95],"recall":[96],"average":[99],"$27":[101],"\\%$":[102],"different":[104],"lead":[105],"times":[106],"compared":[107],"state-of-the-art":[109],"methods.":[110],"These":[111],"advancements":[112],"show":[113],"great":[114],"promise":[115],"reducing":[117],"failures":[119],"cluster":[121],"environments,":[122],"decreasing":[123],"VM":[124],"interruptions":[125],"up":[127],"42.7%":[129],"averaging":[131],"24.2%":[132],"real-world":[134],"implementations.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
