{"id":"https://openalex.org/W2664249172","doi":"https://doi.org/10.1145/3086157.3086164","title":"Understanding the Spatial Characteristics of DRAM Errors in HPC Clusters","display_name":"Understanding the Spatial Characteristics of DRAM Errors in HPC Clusters","publication_year":2017,"publication_date":"2017-06-23","ids":{"openalex":"https://openalex.org/W2664249172","doi":"https://doi.org/10.1145/3086157.3086164","mag":"2664249172"},"language":"en","primary_location":{"id":"doi:10.1145/3086157.3086164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3086157.3086164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3086157.3086164?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Workshop on Fault-Tolerance for HPC at Extreme Scale","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3086157.3086164?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025321482","display_name":"Ayush Patwari","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ayush Patwari","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033868370","display_name":"Ignacio Laguna","orcid":"https://orcid.org/0000-0002-9374-4433"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Laguna","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047310442","display_name":"Saurabh Bagchi","orcid":"https://orcid.org/0000-0002-4239-5632"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Bagchi","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025321482"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.0948,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80621072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9980000257492065,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9980000257492065,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9973000288009644,"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/dram","display_name":"Dram","score":0.9388830065727234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183551788330078},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6892057061195374},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5815537571907043},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5664003491401672},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5380563139915466},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.24981150031089783},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15048909187316895},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12556192278862},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.0891181230545044}],"concepts":[{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.9388830065727234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183551788330078},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6892057061195374},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5815537571907043},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5664003491401672},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5380563139915466},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.24981150031089783},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15048909187316895},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12556192278862},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0891181230545044},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3086157.3086164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3086157.3086164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3086157.3086164?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Workshop on Fault-Tolerance for HPC at Extreme Scale","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3086157.3086164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3086157.3086164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3086157.3086164?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Workshop on Fault-Tolerance for HPC at Extreme Scale","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3355367070","display_name":null,"funder_award_id":"DEAC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G4784552025","display_name":null,"funder_award_id":"DEAC52-07NA27344","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5685548091","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G8157651756","display_name":null,"funder_award_id":"DEAC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8374966015","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G991281326","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2664249172.pdf","grobid_xml":"https://content.openalex.org/works/W2664249172.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1578105119","https://openalex.org/W1978082708","https://openalex.org/W2040379684","https://openalex.org/W2094127360","https://openalex.org/W2101221989","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2501379806","https://openalex.org/W3003432522","https://openalex.org/W3004493283","https://openalex.org/W4229701516","https://openalex.org/W6660789703"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3120961607","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2227905990","https://openalex.org/W3148568549","https://openalex.org/W2765823764","https://openalex.org/W2794038527","https://openalex.org/W2151092287"],"abstract_inverted_index":{"Understanding":[0,52],"DRAM":[1,46,56,82],"errors":[2,47,57,83,102,121],"in":[3,87,105],"high-performance":[4],"computing":[5],"(HPC)":[6],"clusters":[7],"is":[8,62],"paramount":[9],"to":[10,120,130],"address":[11],"future":[12],"HPC":[13,91],"resilience":[14],"challenges.":[15],"While":[16],"there":[17],"have":[18,38],"been":[19],"studies":[20,37],"on":[21,28,84],"this":[22,74],"topic,":[23],"previous":[24],"work":[25],"has":[26],"focused":[27],"on-node":[29],"and":[30,70],"single-rack":[31],"characteristics":[32],"of":[33,45,55,81,101],"errors;":[34],"conversely,":[35],"few":[36],"presented":[39],"insights":[40],"into":[41],"the":[42,78],"spatial":[43,53,79,106],"behavior":[44],"across":[48],"an":[49,59],"entire":[50,60],"cluster.":[51,92],"peculiarities":[54],"through":[58],"cluster":[61,65],"crucial":[63],"for":[64,108],"temperature":[66],"management,":[67],"job":[68],"allocation,":[69],"failure":[71],"prediction.":[72],"In":[73],"paper,":[75],"we":[76],"study":[77],"nature":[80],"data":[85],"gathered":[86],"a":[88,132],"large":[89],"production":[90],"Our":[93],"analysis":[94],"shows":[95],"that":[96,112],"nodes":[97],"with":[98],"high":[99],"degree":[100],"are":[103,116],"grouped":[104],"regions":[107,115,137,141],"time":[109],"periods,":[110],"suggesting":[111],"these":[113],"\"susceptible\"":[114],"collectively":[117],"more":[118],"vulnerable":[119],"than":[122],"other":[123],"regions.":[124],"We":[125],"then":[126],"use":[127],"our":[128],"observations":[129],"build":[131],"predictor,":[133],"which":[134],"identifies":[135],"such":[136],"given":[138],"prior":[139],"neighboring":[140],"patterns.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
