{"id":"https://openalex.org/W4283378767","doi":"https://doi.org/10.1145/3502181.3531465","title":"Understanding Memory Failures on a Petascale Arm System","display_name":"Understanding Memory Failures on a Petascale Arm System","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283378767","doi":"https://doi.org/10.1145/3502181.3531465"},"language":"en","primary_location":{"id":"doi:10.1145/3502181.3531465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502181.3531465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/2003151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020783484","display_name":"Kurt Brian Ferreira","orcid":"https://orcid.org/0000-0001-5607-5691"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt B. Ferreira","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018865548","display_name":"Scott Levy","orcid":"https://orcid.org/0000-0002-2232-3201"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Levy","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049677807","display_name":"Joshua Hemmert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Hemmert","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052855971","display_name":"Kevin Pedretti","orcid":"https://orcid.org/0000-0002-1261-0178"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Pedretti","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104735"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998999834060669,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9976000189781189,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.8184115886688232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888731956481934},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5383509397506714},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5359450578689575},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4878130257129669},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.48698362708091736},{"id":"https://openalex.org/keywords/rack","display_name":"Rack","score":0.48268747329711914},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.43722760677337646},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.4336308240890503},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.41402286291122437},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22605717182159424},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.11031210422515869},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09484291076660156}],"concepts":[{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.8184115886688232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888731956481934},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5383509397506714},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5359450578689575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4878130257129669},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.48698362708091736},{"id":"https://openalex.org/C2776843527","wikidata":"https://www.wikidata.org/wiki/Q1351382","display_name":"Rack","level":2,"score":0.48268747329711914},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.43722760677337646},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.4336308240890503},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.41402286291122437},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22605717182159424},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11031210422515869},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09484291076660156},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3502181.3531465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502181.3531465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2003151","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2003151","pdf_url":"https://www.osti.gov/servlets/purl/2003151","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2003151","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2003151","pdf_url":"https://www.osti.gov/servlets/purl/2003151","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2209453243","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2214935549","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G4903105778","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4947178736","display_name":null,"funder_award_id":"-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5211897158","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G5339743583","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G8279418378","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283378767.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1558516248","https://openalex.org/W1559781097","https://openalex.org/W1578105119","https://openalex.org/W1966243865","https://openalex.org/W1998221613","https://openalex.org/W1999900893","https://openalex.org/W2000042664","https://openalex.org/W2009063162","https://openalex.org/W2040379684","https://openalex.org/W2060573894","https://openalex.org/W2094127360","https://openalex.org/W2101221989","https://openalex.org/W2113273853","https://openalex.org/W2114462749","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2136797898","https://openalex.org/W2143220335","https://openalex.org/W2158907675","https://openalex.org/W2318507312","https://openalex.org/W2524688414","https://openalex.org/W2664249172","https://openalex.org/W2751243270","https://openalex.org/W2767346922","https://openalex.org/W2782944865","https://openalex.org/W2903241786","https://openalex.org/W2913716454","https://openalex.org/W3129378740","https://openalex.org/W3129927603","https://openalex.org/W4238228080","https://openalex.org/W4393819972"],"related_works":["https://openalex.org/W1970451660","https://openalex.org/W2085974832","https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W4206324154","https://openalex.org/W1978931242","https://openalex.org/W2154629969"],"abstract_inverted_index":{"New":[0],"and":[1,8,82,127,161,185,203,219,225,240,288],"novel":[2],"HPC":[3,43,88,129,150,292],"platforms":[4,280],"provide":[5,15,272],"interesting":[6,119],"challenges":[7],"opportunities.":[9],"Analysis":[10],"of":[11,19,62,93,138,238,252,269],"these":[12],"systems":[13,30,130],"can":[14,172],"a":[16,91,249],"better":[17],"understanding":[18],"both":[20,123],"the":[21,73,80,107,124,136,154,183,217,236,257,289],"specific":[22],"platform":[23,126],"being":[24],"studied":[25],"as":[26,28],"well":[27],"large-scale":[29,57,149,264,291],"in":[31,42,60,110,131,145,261,281,286,294],"general.":[32,132,295],"Arm":[33,125,285],"is":[34,49],"one":[35],"such":[36],"architecture":[37],"that":[38,191],"has":[39,83],"been":[40,84],"explored":[41],"for":[44,55,90,170],"several":[45,118,262],"years,":[46],"however":[47],"little":[48],"still":[50],"known":[51],"about":[52],"its":[53],"viability":[54],"supporting":[56],"production":[58,87,111],"workloads":[59],"terms":[61],"system":[63,67,78,108,184,220],"reliability.":[64],"The":[65,267],"Astra":[66,105],"at":[68],"Sandia":[69],"National":[70],"Laboratories":[71],"was":[72,109],"first":[74],"public":[75],"peta-FLOPS":[76],"Arm-based":[77],"on":[79,163,182,216,242],"Top500":[81],"successfully":[85],"running":[86,112],"applications":[89],"couple":[92],"years.":[94],"In":[95],"this":[96,147,270],"paper,":[97],"we":[98,134,178,234,247],"analyze":[99],"memory":[100,192],"failure":[101],"data":[102],"collected":[103],"from":[104],"while":[106],"unclassified":[113],"applications.":[114],"This":[115],"analysis":[116,271],"revealed":[117],"contributions":[120],"related":[121],"to":[122,128,142,174,188,275],"First,":[133],"outline":[135],"number":[137],"components":[139],"replaced":[140],"due":[141],"reliability":[143,265],"issues":[144],"standing-up":[146,277],"first-of-its-kind,":[148],"system.":[151],"We":[152],"show":[153,186,235],"distribution":[155],"differences":[156],"between":[157],"correctable":[158,244],"DRAM":[159,180,200,243],"faults":[160,171,181,193,230],"errors":[162],"Astra,":[164],"showing":[165],"that,":[166],"not":[167,208],"properly":[168],"accounting":[169],"lead":[173],"erroneous":[175],"conclusions.":[176],"Additionally,":[177],"characterize":[179],"contrary":[187],"existing":[189],"work":[190],"are":[194,207],"uniformly":[195],"distributed":[196],"across":[197,210],"CPU":[198],"socket,":[199],"column,":[201],"bank":[202],"rack":[204],"region,":[205],"but":[206],"uniform":[209],"node,":[211],"DIMM":[212,214,226],"rank,":[213],"slot":[215],"motherboard,":[218],"rack:":[221],"some":[222],"racks,":[223],"ranks":[224],"slots":[227],"experience":[228],"more":[229],"than":[231],"others.":[232],"Similarly,":[233],"impact":[237],"temperature":[239],"power":[241],"errors.":[245],"Finally,":[246],"make":[248],"detailed":[250],"comparison":[251],"results":[253,268],"presented":[254],"here":[255],"with":[256],"positional":[258],"affects":[259],"found":[260],"previous":[263],"studies.":[266],"valuable":[273],"guidance":[274],"organizations":[276,283],"first-in-":[278],"class":[279],"HPC,":[282,287],"using":[284],"entire":[290],"community":[293]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
