{"id":"https://openalex.org/W4414592239","doi":"https://doi.org/10.1145/3767333","title":"Looking Back to Move Forward: Unveiling the Mysteries of HBM Errors to Predict Future Failures","display_name":"Looking Back to Move Forward: Unveiling the Mysteries of HBM Errors to Predict Future Failures","publication_year":2025,"publication_date":"2025-09-12","ids":{"openalex":"https://openalex.org/W4414592239","doi":"https://doi.org/10.1145/3767333"},"language":"en","primary_location":{"id":"doi:10.1145/3767333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3767333","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-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/A5080701169","display_name":"Shuyue Zhou","orcid":"https://orcid.org/0000-0002-2355-3738"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyue Zhou","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-2355-3738","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036096704","display_name":"X. Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbin Hu","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0007-6042-8323","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406125","display_name":"Ronglong Wu","orcid":"https://orcid.org/0009-0001-9008-5401"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronglong Wu","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-9008-5401","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091164788","display_name":"Jiahao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Lu","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0003-3790-6519","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015815028","display_name":"Zhirong Shen","orcid":"https://orcid.org/0000-0003-2673-5868"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirong Shen","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0003-2673-5868","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113938138","display_name":"Zikang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zikang Xu","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0002-7346-5418","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397991","display_name":"Yue Yu","orcid":"https://orcid.org/0000-0002-9865-2212"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yu","raw_affiliation_strings":["Peng Cheng Laboratory","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9865-2212","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002074598","display_name":"Yuze Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuze Jiang","raw_affiliation_strings":["Department of Statistics, University of Michigan","Department of Statistics, University of Michigan, Ann Arbor, United States"],"raw_orcid":"https://orcid.org/0009-0002-5602-3677","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Statistics, University of Michigan, Ann Arbor, United States","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101740783","display_name":"Jiwu Shu","orcid":"https://orcid.org/0000-0002-7362-2789"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwu Shu","raw_affiliation_strings":["Tsinghua University, Xiamen University","Tsinghua University, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-7362-2789","affiliations":[{"raw_affiliation_string":"Tsinghua University, Xiamen University","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I191208505"]},{"raw_affiliation_string":"Tsinghua University, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101929692","display_name":"Kunlin Yang","orcid":"https://orcid.org/0000-0002-9179-7363"},"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"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Kunlin Yang","raw_affiliation_strings":["Huawei Technologies Co Ltd","Huawei Technologies Co Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9179-7363","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Huawei Technologies Co Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feilong Lin","orcid":"https://orcid.org/0009-0003-7988-109X"},"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"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Feilong Lin","raw_affiliation_strings":["Huawei Technologies Co Ltd","Huawei Technologies Co Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-7988-109X","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Huawei Technologies Co Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395351","display_name":"Yiming Zhang","orcid":"https://orcid.org/0000-0001-6450-8485"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":["School of Informatics, Xiamen University","School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-6450-8485","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27719263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9976999759674072,"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/T10472","display_name":"Semiconductor materials and devices","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.8884999752044678},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5608999729156494},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5192999839782715},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4487000107765198},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.42329999804496765},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4106999933719635}],"concepts":[{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.8884999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539999723434448},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5608999729156494},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C154474529","wikidata":"https://www.wikidata.org/wiki/Q1658917","display_name":"Soft error","level":2,"score":0.27129998803138733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3767333","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2209249849","display_name":null,"funder_award_id":"2024YFB4505201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8202640126","display_name":null,"funder_award_id":"No. U22B2023, No. 62441220 and No. 624B2120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1976494130","https://openalex.org/W1990320020","https://openalex.org/W2094976743","https://openalex.org/W2114668191","https://openalex.org/W2142812297","https://openalex.org/W2233147800","https://openalex.org/W2734941459","https://openalex.org/W2751343396","https://openalex.org/W2911964244","https://openalex.org/W2926767350","https://openalex.org/W2997591727","https://openalex.org/W2999600391","https://openalex.org/W3003432522","https://openalex.org/W3004493283","https://openalex.org/W3112402894","https://openalex.org/W3125828735","https://openalex.org/W3182912591","https://openalex.org/W4230714643","https://openalex.org/W4232973962","https://openalex.org/W4234178886","https://openalex.org/W4234493895","https://openalex.org/W4238404680","https://openalex.org/W4312117005","https://openalex.org/W4402040240"],"related_works":[],"abstract_inverted_index":{"High-bandwidth":[0],"memory":[1,13,26],"(HBM)":[2],"is":[3],"regarded":[4],"as":[5],"a":[6,88,138],"promising":[7],"technology":[8],"for":[9,125,130,143],"fundamentally":[10],"overcoming":[11],"the":[12,25,47,61,101,167],"wall.":[14],"It":[15],"stacks":[16],"up":[17],"multiple":[18],"DRAM":[19,126],"dies":[20],"vertically":[21],"to":[22,160],"dramatically":[23],"improve":[24],"access":[27],"bandwidth.":[28],"However,":[29],"this":[30,57],"architecture":[31],"also":[32,51],"comes":[33],"with":[34],"more":[35],"severe":[36],"reliability":[37],"issues,":[38],"since":[39],"HBM":[40,66,102,144],"not":[41],"only":[42],"inherits":[43],"error":[44,54,73,93,105,127],"patterns":[45,106],"of":[46,85,90,112,169],"conventional":[48,108],"DRAM,":[49,109],"but":[50],"introduces":[52],"new":[53],"causes.":[55],"In":[56],"article,":[58],"we":[59,98],"conduct":[60],"first":[62],"systematical":[63],"study":[64],"on":[65,146],"errors,":[67],"which":[68,120,149],"cover":[69],"over":[70,82],"460":[71],"million":[72],"events":[74],"collected":[75],"from":[76,107,156],"19":[77],"data":[78],"centers":[79],"and":[80,95,117,134,153],"span":[81],"two":[83],"years":[84],"deployment":[86],"under":[87],"variety":[89],"services.":[91],"Through":[92],"analyses":[94],"methodology":[96],"validations,":[97],"confirm":[99],"that":[100],"exhibits":[103],"different":[104],"in":[110],"terms":[111],"spatial":[113],"locality,":[114],"temporal":[115],"correlation,":[116],"sensor":[118,154],"metrics":[119],"make":[121],"empirical":[122],"prediction":[123,128,141,171],"models":[124],"ineffective":[129],"HBM.":[131],"We":[132],"design":[133],"implement":[135],"Calchas":[136],",":[137],"hierarchical":[139,173],"failure":[140,170],"framework":[142],"based":[145],"our":[147],"findings,":[148],"integrate":[150],"spatial,":[151],"temporal,":[152],"information":[155],"various":[157],"device":[158],"levels":[159],"predict":[161],"upcoming":[162],"failures.":[163],"The":[164],"results":[165],"demonstrate":[166],"feasibility":[168],"across":[172],"levels.":[174]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
