{"id":"https://openalex.org/W2089344916","doi":"https://doi.org/10.1145/2063384.2063445","title":"System implications of memory reliability in exascale computing","display_name":"System implications of memory reliability in exascale computing","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2089344916","doi":"https://doi.org/10.1145/2063384.2063445","mag":"2089344916"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1143850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100359799","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-9346-6050"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452006","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0002-6093-6623"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of Notre Dame and Hewlett-Packard Labs","University of Notre Dame and Hewlett-Packard Labs#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame and Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837","https://openalex.org/I107639228"]},{"raw_affiliation_string":"University of Notre Dame and Hewlett-Packard Labs#TAB#","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112511467","display_name":"Mingyu Hsieh","orcid":"https://orcid.org/0000-0001-9621-4254"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]},{"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":"Ming-Yu Hsieh","raw_affiliation_strings":["Sandia National Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Labs","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034067036","display_name":"Naveen Muralimanohar","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naveen Muralimanohar","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012725183","display_name":"Chad Kersey","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chad D. Kersey","raw_affiliation_strings":["Georgia Institute of Technology","[Georgia Institute of Technology.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026229568","display_name":"Jay Brockman","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay B. Brockman","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011812189","display_name":"Arun Rodrigues","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":"Arun F. Rodrigues","raw_affiliation_strings":["Sandia National Labs","Sandia National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Labs","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050207942","display_name":"Norman P. Jouppi","orcid":"https://orcid.org/0000-0003-1765-1929"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norman P. Jouppi","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.895,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.95618557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9997000098228455,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8317151069641113},{"id":"https://openalex.org/keywords/bch-code","display_name":"BCH code","score":0.7824774980545044},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6454656720161438},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5775842666625977},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5532606244087219},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.5452393293380737},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5126925706863403},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4792509078979492},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3907144367694855},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.3519224524497986},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3210950493812561},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3133223056793213},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2718151807785034},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.19640517234802246},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07039022445678711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317151069641113},{"id":"https://openalex.org/C42276685","wikidata":"https://www.wikidata.org/wiki/Q795705","display_name":"BCH code","level":3,"score":0.7824774980545044},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6454656720161438},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5775842666625977},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5532606244087219},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.5452393293380737},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5126925706863403},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4792509078979492},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3907144367694855},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3519224524497986},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3210950493812561},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3133223056793213},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2718151807785034},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.19640517234802246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07039022445678711},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2063384.2063445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1143850","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1143850","pdf_url":null,"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:1143850","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1143850","pdf_url":null,"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":[{"score":0.800000011920929,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G4577376950","display_name":null,"funder_award_id":"DE - SC0005026","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1515422725","https://openalex.org/W1533071485","https://openalex.org/W1558516248","https://openalex.org/W1601753226","https://openalex.org/W1998886257","https://openalex.org/W2007444174","https://openalex.org/W2009063162","https://openalex.org/W2010585077","https://openalex.org/W2033656974","https://openalex.org/W2057218453","https://openalex.org/W2060824022","https://openalex.org/W2079668820","https://openalex.org/W2096800126","https://openalex.org/W2103498248","https://openalex.org/W2104129492","https://openalex.org/W2104741809","https://openalex.org/W2108981656","https://openalex.org/W2110942501","https://openalex.org/W2111509329","https://openalex.org/W2125640880","https://openalex.org/W2133046454","https://openalex.org/W2133834148","https://openalex.org/W2134633067","https://openalex.org/W2135496605","https://openalex.org/W2138661001","https://openalex.org/W2143436626","https://openalex.org/W2145021036","https://openalex.org/W2151917022","https://openalex.org/W2155462575","https://openalex.org/W2157348261","https://openalex.org/W2162457113","https://openalex.org/W2164188348","https://openalex.org/W2169875292","https://openalex.org/W2170310381","https://openalex.org/W2170382128","https://openalex.org/W2537224236","https://openalex.org/W2585550685","https://openalex.org/W2602894751","https://openalex.org/W4230841325","https://openalex.org/W4239813889","https://openalex.org/W4244381167","https://openalex.org/W6635987275"],"related_works":["https://openalex.org/W4318068934","https://openalex.org/W3172524400","https://openalex.org/W2290952066","https://openalex.org/W1723747798","https://openalex.org/W2997651281","https://openalex.org/W2121197955","https://openalex.org/W2313229959","https://openalex.org/W2354450728","https://openalex.org/W4320480730","https://openalex.org/W2056528600"],"abstract_inverted_index":{"Resiliency":[0],"will":[1],"be":[2],"one":[3],"of":[4,18,34,69,82],"the":[5,19,61,66,80],"toughest":[6],"challenges":[7],"in":[8,28,57,90,116,130],"future":[9,29,95],"exascale":[10,30,96],"systems.":[11,31,97,153],"Memory":[12],"errors":[13],"contribute":[14],"more":[15],"than":[16,149],"40%":[17],"total":[20],"hardware-related":[21],"failures":[22],"and":[23,39,75,88],"are":[24,41,50],"projected":[25],"to":[26,45,64,127],"increase":[27],"The":[32],"use":[33,128],"error":[35],"correction":[36],"codes":[37],"(ECC)":[38],"checkpointing":[40,56,93],"two":[42],"effective":[43],"approaches":[44],"fault":[46],"tolerance.":[47],"While":[48],"there":[49],"numerous":[51],"studies":[52],"on":[53,71,94],"ECC":[54,84],"or":[55],"isolation,":[58],"this":[59],"is":[60,105,139],"first":[62],"paper":[63],"investigate":[65],"combined":[67],"effect":[68],"both":[70],"overall":[72],"system":[73,117,147],"performance":[74],"power.":[76],"Specifically,":[77],"we":[78],"study":[79],"impact":[81],"various":[83],"schemes":[85],"(SECDED,":[86],"BCH,":[87],"chipkill)":[89],"conjunction":[91],"with":[92,134],"Our":[98,141],"simulation":[99],"results":[100],"show":[101],"that":[102],"while":[103],"chipkill":[104,138],"13%":[106],"better":[107,146],"for":[108,121],"computation-intensive":[109],"applications,":[110],"BCH":[111,129],"has":[112],"a":[113],"28%":[114],"advantage":[115],"energy-delay":[118],"product":[119],"(EDP)":[120],"memory-intensive":[122],"applications.":[123],"We":[124],"also":[125],"propose":[126],"tagged":[131,151],"memory":[132,152],"systems":[133],"commodity":[135],"DRAMs":[136],"where":[137],"impractical.":[140],"proposed":[142],"architecture":[143],"achieves":[144],"2.3x":[145],"EDP":[148],"state-of-the-art":[150]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
