{"id":"https://openalex.org/W2772676150","doi":"https://doi.org/10.1109/tpds.2017.2781257","title":"An Efficient In-Memory Checkpoint Method and its Practice on Fault-Tolerant HPL","display_name":"An Efficient In-Memory Checkpoint Method and its Practice on Fault-Tolerant HPL","publication_year":2017,"publication_date":"2017-12-08","ids":{"openalex":"https://openalex.org/W2772676150","doi":"https://doi.org/10.1109/tpds.2017.2781257","mag":"2772676150"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2017.2781257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2781257","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5011572497","display_name":"Xiongchao Tang","orcid":"https://orcid.org/0000-0002-1692-3964"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongchao Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1692-3964","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063948705","display_name":"Bowen Yu","orcid":"https://orcid.org/0000-0001-5537-8244"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Yu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087894632","display_name":"Keqin Li","orcid":"https://orcid.org/0000-0001-5224-4048"},"institutions":[{"id":"https://openalex.org/I157455823","display_name":"SUNY New Paltz","ror":"https://ror.org/03j3dv688","country_code":"US","type":"education","lineage":["https://openalex.org/I157455823"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keqin Li","raw_affiliation_strings":["Department of Computer Science, State University of New York, New Paltz, NY"],"raw_orcid":"https://orcid.org/0000-0001-5224-4048","affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY","institution_ids":["https://openalex.org/I157455823"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2621,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83411619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"29","issue":"4","first_page":"758","last_page":"771"},"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8465590476989746},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5635883808135986},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5093117952346802},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4868432879447937},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48315662145614624},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.47246360778808594},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4184502065181732},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3390433192253113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465590476989746},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5635883808135986},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5093117952346802},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4868432879447937},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48315662145614624},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.47246360778808594},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4184502065181732},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3390433192253113},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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":1,"locations":[{"id":"doi:10.1109/tpds.2017.2781257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2781257","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G1220216664","display_name":null,"funder_award_id":"2017YFB1003103","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1403752315","display_name":"\u4e91\u8ba1\u7b97\u73af\u5883\u4e0b\u9762\u5411\u590d\u6742\u5de5\u7a0b\u5e94\u7528\u7684\u8d44\u6e90\u7ba1\u7406\u8c03\u5ea6\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61232008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8403825466","display_name":null,"funder_award_id":"61722208","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"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320330357","display_name":"Tsinghua Initiative Scientific Research Program","ror":null},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1496108277","https://openalex.org/W1532689837","https://openalex.org/W1576341769","https://openalex.org/W1939822385","https://openalex.org/W1980321276","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1986009243","https://openalex.org/W1993660990","https://openalex.org/W1995746640","https://openalex.org/W1998221613","https://openalex.org/W2000739449","https://openalex.org/W2024966997","https://openalex.org/W2031260715","https://openalex.org/W2037523067","https://openalex.org/W2055835320","https://openalex.org/W2063924830","https://openalex.org/W2074787299","https://openalex.org/W2083613288","https://openalex.org/W2096504919","https://openalex.org/W2104129492","https://openalex.org/W2116115793","https://openalex.org/W2128511938","https://openalex.org/W2128854702","https://openalex.org/W2133046454","https://openalex.org/W2133287150","https://openalex.org/W2142812297","https://openalex.org/W2145670264","https://openalex.org/W2147504831","https://openalex.org/W2155204206","https://openalex.org/W2160123909","https://openalex.org/W2161416813","https://openalex.org/W2161551433","https://openalex.org/W2163295644","https://openalex.org/W2165022815","https://openalex.org/W2189348454","https://openalex.org/W2296772319","https://openalex.org/W2327901940","https://openalex.org/W2440916949","https://openalex.org/W2532113261","https://openalex.org/W2581192167","https://openalex.org/W4242361160","https://openalex.org/W4248578633","https://openalex.org/W6682581173","https://openalex.org/W6687348328"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2011430815","https://openalex.org/W4321606653","https://openalex.org/W2064720525","https://openalex.org/W4401278057","https://openalex.org/W2111125783"],"abstract_inverted_index":{"Fault":[0],"tolerance":[1],"is":[2],"increasingly":[3],"important":[4,133],"in":[5],"high-performance":[6],"computing":[7],"due":[8],"to":[9,29,61,67,131,183],"the":[10,31,102,113,176,179,184,191,199],"substantial":[11],"growth":[12],"of":[13,34,65,105,175,178],"system":[14,18],"scale":[15],"and":[16,145,156,198],"decreasing":[17],"reliability.":[19],"In-memory/diskless":[20],"checkpoint":[21,37,44,57,93,108,187],"has":[22],"gained":[23],"extensive":[24],"attention":[25],"as":[26],"a":[27,90,143],"solution":[28],"avoid":[30],"IO":[32],"bottleneck":[33],"traditional":[35],"disk-based":[36],"methods.":[38],"However,":[39],"applications":[40,118],"using":[41],"previous":[42,55,106],"in-memory":[43,56,81,92,107,186],"suffer":[45],"from":[46],"little":[47],"available":[48,114,192],"memory":[49,115,193],"space.":[50],"To":[51,123],"provide":[52],"high":[53],"reliability,":[54],"methods":[58],"either":[59],"need":[60],"keep":[62],"two":[63,160],"copies":[64],"checkpoints":[66,73,82],"tolerate":[68],"failures":[69],"while":[70],"updating":[71],"old":[72],"or":[74],"trade":[75],"performance":[76,177,200],"for":[77,117],"space":[78,116],"by":[79,119,195,201],"flushing":[80],"into":[83],"disk.":[84],"In":[85],"this":[86,151],"paper,":[87],"we":[88,127],"propose":[89],"novel":[91],"method,":[94,126,153,188],"called":[95,154],"self-checkpoint,":[96],"which":[97],"can":[98],"not":[99],"only":[100],"achieve":[101],"same":[103],"reliability":[104],"methods,":[109],"but":[110],"also":[111],"increase":[112],"almost":[120],"50":[121],"percent.":[122,203],"validate":[124,157],"our":[125],"apply":[128],"self-checkpoint":[129],"method":[130],"an":[132],"problem:":[134],"High-Performance":[135],"Linpack":[136],"(HPL)":[137],"with":[138,165],"fault":[139,146],"tolerance.":[140],"We":[141],"implement":[142],"scalable":[144],"tolerant":[147],"HPL":[148],"based":[149],"on":[150,159],"new":[152],"SKT-HPL,":[155],"it":[158,189],"large-scale":[161],"systems.":[162],"Experimental":[163],"results":[164],"24,576":[166],"processes":[167],"show":[168],"that":[169],"SKT-HPL":[170],"achieves":[171],"over":[172],"95":[173],"percent":[174,197],"original":[180],"HPL.":[181],"Compared":[182],"state-of-the-art":[185],"improves":[190],"size":[194],"47":[196],"5":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
