{"id":"https://openalex.org/W1970958679","doi":"https://doi.org/10.1145/1970386.1970387","title":"Hybrid checkpointing using emerging nonvolatile memories for future exascale systems","display_name":"Hybrid checkpointing using emerging nonvolatile memories for future exascale systems","publication_year":2011,"publication_date":"2011-06-21","ids":{"openalex":"https://openalex.org/W1970958679","doi":"https://doi.org/10.1145/1970386.1970387","mag":"1970958679"},"language":"en","primary_location":{"id":"doi:10.1145/1970386.1970387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1970386.1970387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1970386.1970387","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1970386.1970387","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101973148","display_name":"Xiangyu Dong","orcid":"https://orcid.org/0009-0004-8380-5265"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Dong","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"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":"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0173,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98330623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"2","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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":0.8942084312438965},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8203219175338745},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7354941368103027},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.6881574392318726},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5713051557540894},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.486771821975708},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47246384620666504},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.4537610411643982},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4396848678588867},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.43605396151542664},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4196878969669342},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.41114896535873413},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36786019802093506},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2846226096153259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8942084312438965},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8203219175338745},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7354941368103027},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.6881574392318726},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5713051557540894},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.486771821975708},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47246384620666504},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.4537610411643982},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4396848678588867},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.43605396151542664},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4196878969669342},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.41114896535873413},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36786019802093506},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2846226096153259},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1970386.1970387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1970386.1970387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1970386.1970387","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.3092","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.3092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/people/naveen_muralimanohar/taco11.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-133627","is_oa":false,"landing_page_url":"http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000291726100001","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/1970386.1970387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1970386.1970387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1970386.1970387","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4290372162","display_name":null,"funder_award_id":"7.03E+26","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5325503655","display_name":"CSR--EHS:  Collaborative Research:  Hybrid Timing Analysis via Multi-Mode Execution","funder_award_id":"0720659","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5530168811","display_name":"HoDoo:  Holistic Design of On-chip Interconnects","funder_award_id":"0702617","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6901979050","display_name":"ADAMS: Architecture and Design Automation for 3D Multi-core Systems","funder_award_id":"0903432","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8117051612","display_name":"CSR: Medium: Collaborative Research: Providing Predictable Timing for Task Migration in Embedded Multi-Core Environments (TiME-ME)","funder_award_id":"0905365","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1970958679.pdf","grobid_xml":"https://content.openalex.org/works/W1970958679.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W307918303","https://openalex.org/W1482022028","https://openalex.org/W1498586823","https://openalex.org/W1971952282","https://openalex.org/W1980672506","https://openalex.org/W1987131925","https://openalex.org/W1987608073","https://openalex.org/W1997021720","https://openalex.org/W2001495258","https://openalex.org/W2028646030","https://openalex.org/W2033656974","https://openalex.org/W2069367007","https://openalex.org/W2096020561","https://openalex.org/W2096800126","https://openalex.org/W2100346277","https://openalex.org/W2100970777","https://openalex.org/W2102469268","https://openalex.org/W2104129492","https://openalex.org/W2113512876","https://openalex.org/W2116011221","https://openalex.org/W2118582701","https://openalex.org/W2124632665","https://openalex.org/W2125169487","https://openalex.org/W2125488852","https://openalex.org/W2126394324","https://openalex.org/W2127795402","https://openalex.org/W2131053137","https://openalex.org/W2133046454","https://openalex.org/W2135393827","https://openalex.org/W2158272436","https://openalex.org/W2160814308","https://openalex.org/W2164590718","https://openalex.org/W2167238665","https://openalex.org/W2171938442","https://openalex.org/W2296772319","https://openalex.org/W2539921360","https://openalex.org/W2603146559","https://openalex.org/W3150685302","https://openalex.org/W4230669310","https://openalex.org/W6645373946"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W3007424606","https://openalex.org/W3129378740","https://openalex.org/W2607572736","https://openalex.org/W2266027327","https://openalex.org/W2249929881","https://openalex.org/W2278366184","https://openalex.org/W1486544172"],"abstract_inverted_index":{"The":[0],"scalability":[1],"of":[2,27,67,82,91,120,134],"future":[3,56],"Massively":[4],"Parallel":[5],"Processing":[6],"(MPP)":[7],"systems":[8,34],"is":[9],"being":[10],"severely":[11],"challenged":[12],"by":[13,166],"high":[14],"failure":[15,94,97],"rates.":[16],"Current":[17],"centralized":[18],"Hard":[19],"Disk":[20],"Drive":[21],"(HDD)":[22],"checkpointing":[23,51,85,105,127,138,157,170],"results":[24],"in":[25],"overhead":[26,165,184],"25%":[28],"or":[29],"more":[30,36],"at":[31,144],"petascale.":[32],"Since":[33],"become":[35],"vulnerable":[37],"as":[38,78,125],"the":[39,55,68,83,118,135,154,159,164,175],"node":[40],"count":[41],"keeps":[42],"increasing,":[43],"novel":[44],"techniques":[45,123],"that":[46],"enable":[47],"fast":[48,84],"and":[49,96,128,147],"frequent":[50],"are":[52,139],"critical":[53],"to":[54,141,148,158],"exascale":[57,188],"system":[58],"implementation.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,99,173],"first":[64],"introduce":[65],"one":[66],"emerging":[69],"nonvolatile":[70],"memory":[71],"technologies,":[72],"Phase-Change":[73],"Random":[74],"Access":[75],"Memory":[76],"(PCRAM),":[77],"a":[79,88,101,111,150,168,186],"proper":[80],"candidate":[81],"device.":[86],"After":[87],"thorough":[89],"analysis":[90],"MPP":[92],"systems,":[93],"rates":[95],"sources,":[98],"propose":[100],"PCRAM-based":[102,136],"hybrid":[103,137,169],"local/global":[104],"mechanism":[106],"which":[107],"not":[108],"only":[109,178],"provides":[110],"faster":[112],"checkpoint":[113],"storage,":[114],"but":[115],"also":[116],"boosts":[117],"effectiveness":[119],"other":[121],"orthogonal":[122],"such":[124],"incremental":[126],"background":[129],"checkpointing.":[130],"Three":[131],"variant":[132],"implementations":[133],"designed":[140],"be":[142],"adopted":[143],"different":[145],"stages":[146],"offer":[149],"smooth":[151],"transition":[152],"from":[153],"conventional":[155],"in-disk":[156],"instant":[160],"in-memory":[161],"approach.":[162],"Analyzing":[163],"using":[167],"performance":[171,183],"model,":[172],"show":[174],"proposed":[176],"approach":[177],"incurs":[179],"less":[180],"than":[181],"3%":[182],"on":[185],"projected":[187],"system.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}