{"id":"https://openalex.org/W7133568313","doi":"https://doi.org/10.1109/hpca68181.2026.11408474","title":"Predicting DRAM Failures at Scale: A Two-Stage Approach for Heterogeneous Systems","display_name":"Predicting DRAM Failures at Scale: A Two-Stage Approach for Heterogeneous Systems","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133568313","doi":"https://doi.org/10.1109/hpca68181.2026.11408474"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5128064881","display_name":"Chenglin Wang","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":true,"raw_author_name":"Chenglin Wang","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128044138","display_name":"Shouxin Wang","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":"Shouxin Wang","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125984819","display_name":"Zhirong Shen","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":"Zhirong Shen","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771172","display_name":"Lu Tang","orcid":"https://orcid.org/0000-0002-2682-6578"},"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":"Lu Tang","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","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":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","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":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128106855","display_name":"Min zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhou","raw_affiliation_strings":["Huawei"],"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128067102","display_name":"Jialiang Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialiang Yu","raw_affiliation_strings":["Huawei"],"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128071770","display_name":"Yiming Zhang","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":"Yiming Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5128064881"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55848628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.19949999451637268,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.19949999451637268,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.133200004696846,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.12039999663829803,"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/dram","display_name":"Dram","score":0.48739999532699585},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.3887999951839447},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3407999873161316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5932000279426575},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.44699999690055847},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27309998869895935},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.24279999732971191}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.7208906412124634,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G3690359744","display_name":null,"funder_award_id":"92373114,U22B2023,624B2120,62302410","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1559781097","https://openalex.org/W2065171379","https://openalex.org/W2090877534","https://openalex.org/W2094976743","https://openalex.org/W2101234009","https://openalex.org/W2295598076","https://openalex.org/W2546811911","https://openalex.org/W2664249172","https://openalex.org/W2752311492","https://openalex.org/W2772956929","https://openalex.org/W2908177913","https://openalex.org/W2989171707","https://openalex.org/W2999600391","https://openalex.org/W3003432522","https://openalex.org/W3004493283","https://openalex.org/W3023512926","https://openalex.org/W3093988908","https://openalex.org/W3112402894","https://openalex.org/W3132629440","https://openalex.org/W3167937798","https://openalex.org/W3205272658","https://openalex.org/W4200335215","https://openalex.org/W4248895726","https://openalex.org/W4285361475","https://openalex.org/W4287849472","https://openalex.org/W4313451571","https://openalex.org/W4318147164","https://openalex.org/W4321636490","https://openalex.org/W4360831854","https://openalex.org/W4383888947","https://openalex.org/W4385688947","https://openalex.org/W4389163020","https://openalex.org/W4400762160","https://openalex.org/W4409248466","https://openalex.org/W4410637911","https://openalex.org/W4412876836","https://openalex.org/W4414199006"],"related_works":[],"abstract_inverted_index":{"Memory":[0],"failures":[1],"in":[2,32],"large-scale":[3,57,192],"production":[4,59],"environments":[5],"pose":[6],"critical":[7],"threats":[8],"to":[9,103,109,136],"system":[10],"reliability":[11],"and":[12,25,68,76,86,106,123,132,140,157,172,199],"service":[13],"availability.":[14],"While":[15],"existing":[16,164],"studies":[17],"have":[18],"conducted":[19],"in-depth":[20],"analyses":[21],"of":[22,28,50,152,174,184,195],"the":[23,170,182,190],"temporal":[24,69,101],"spatial":[26,67],"correlations":[27],"memory":[29,196,205],"errors,":[30],"differences":[31],"characteristics":[33],"across":[34,71,177],"architectures":[35,75],"remain":[36],"largely":[37],"unexplored.":[38],"To":[39,181],"uncover":[40,82],"these":[41],"overlooked":[42],"correlations,":[43],"this":[44],"paper":[45],"conducts":[46],"an":[47],"extensive":[48],"analysis":[49,70,194],"over":[51,61],"130,000":[52],"DDR4":[53],"DIMMs":[54],"collected":[55],"from":[56],"heterogeneous":[58],"clusters":[60],"a":[62,88],"nine-month":[63],"period.":[64],"Through":[65],"systematic":[66],"two":[72],"Intel":[73,155,160],"x86":[74],"four":[77],"major":[78],"DRAM":[79],"vendors,":[80],"we":[81],"five":[83],"new":[84,201],"findings":[85],"propose":[87],"novel":[89],"twostage":[90],"training":[91],"strategy.":[92],"This":[93,166],"strategy":[94],"addresses":[95],"sample":[96],"quality":[97],"issues":[98],"by":[99],"applying":[100],"weighting":[102],"positive":[104],"samples":[105],"adaptive":[107,133],"reweighting":[108],"negative":[110],"samples.":[111],"It":[112],"also":[113],"incorporates":[114],"comprehensive":[115],"multi-dimensional":[116],"feature":[117],"engineering,":[118],"covering":[119],"static,":[120],"spatial,":[121],"temporal,":[122],"micro-level":[124],"characteristics.":[125],"Finally,":[126],"it":[127],"integrates":[128],"dual-driven":[129],"sampling":[130],"strategies":[131],"prediction":[134,138,207],"timing":[135],"balance":[137],"accuracy":[139],"operational":[141],"efficiency.":[142],"Extensive":[143],"evaluation":[144],"shows":[145],"that":[146],"our":[147,175,185,187],"CatBoost-based":[148],"model":[149],"achieves":[150],"F1-scores":[151],"49.9%":[153],"on":[154,159],"x86v5":[156],"57.6%":[158],"x86v6,":[161],"substantially":[162],"outperforming":[163],"methods.":[165],"cross-architecture":[167,193],"validation":[168],"demonstrates":[169],"robustness":[171],"generalization":[173],"approach":[176],"different":[178],"hardware":[179],"platforms.":[180],"best":[183],"knowledge,":[186],"work":[188],"presents":[189],"first":[191],"error":[197],"patterns":[198],"provides":[200],"insights":[202],"for":[203],"production-scale":[204],"failure":[206],"systems.":[208]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-05T00:00:00"}