{"id":"https://openalex.org/W2069891156","doi":"https://doi.org/10.1145/1075395.1075402","title":"User-level checkpoint and recovery for LAM/MPI","display_name":"User-level checkpoint and recovery for LAM/MPI","publication_year":2005,"publication_date":"2005-07-01","ids":{"openalex":"https://openalex.org/W2069891156","doi":"https://doi.org/10.1145/1075395.1075402","mag":"2069891156"},"language":"en","primary_location":{"id":"doi:10.1145/1075395.1075402","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1075395.1075402","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"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 SIGOPS Operating Systems Review","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/A5016596981","display_name":"Youhui Zhang","orcid":"https://orcid.org/0000-0003-2333-3580"},"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":"Youhui Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108189987","display_name":"Dongsheng Wong","orcid":null},"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":"Dongsheng Wong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","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":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.9736,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92184262,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"39","issue":"3","first_page":"72","last_page":"81"},"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9006335735321045},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7692738771438599},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6640700697898865},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6173470616340637},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6027792692184448},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5722036361694336},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5324351191520691},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.5309887528419495},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4787815809249878},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.454832524061203},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4432259500026703},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4207618236541748},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.360450804233551},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3334712088108063},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3020099997520447},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.14031335711479187},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12997126579284668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9006335735321045},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7692738771438599},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6640700697898865},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6173470616340637},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6027792692184448},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5722036361694336},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5324351191520691},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.5309887528419495},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4787815809249878},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.454832524061203},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4432259500026703},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4207618236541748},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.360450804233551},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3334712088108063},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3020099997520447},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.14031335711479187},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12997126579284668},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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":1,"locations":[{"id":"doi:10.1145/1075395.1075402","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1075395.1075402","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"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 SIGOPS Operating Systems Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W34870269","https://openalex.org/W1482022028","https://openalex.org/W1484530169","https://openalex.org/W1510543252","https://openalex.org/W1524357507","https://openalex.org/W1573548168","https://openalex.org/W1589918049","https://openalex.org/W1641327695","https://openalex.org/W1862835629","https://openalex.org/W1997021720","https://openalex.org/W2043787842","https://openalex.org/W2045879521","https://openalex.org/W2081612620","https://openalex.org/W2100970777","https://openalex.org/W2116006827","https://openalex.org/W2903691225","https://openalex.org/W4242589337","https://openalex.org/W4285719527","https://openalex.org/W4298399544","https://openalex.org/W6628864681","https://openalex.org/W6635487442"],"related_works":["https://openalex.org/W1902983110","https://openalex.org/W2124048060","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2116006827","https://openalex.org/W2081612620","https://openalex.org/W2361929291","https://openalex.org/W2086666199","https://openalex.org/W1997862718","https://openalex.org/W1934112916"],"abstract_inverted_index":{"As":[0],"high-performance":[1],"clusters":[2],"continue":[3],"to":[4,33,45],"grow":[5],"in":[6],"size":[7],"and":[8,14,28,62,74],"popularity,":[9],"issues":[10],"of":[11,39,55,94],"fault":[12],"tolerance":[13],"reliability":[15],"are":[16],"becoming":[17],"limiting":[18],"factors":[19],"on":[20,69],"application":[21],"scalability.":[22],"We":[23],"integrated":[24],"one":[25],"user-level":[26],"checkpointing":[27,61],"rollback":[29],"recovery":[30],"(CRR)":[31],"library":[32],"LAM/MPI,":[34,56],"a":[35],"high":[36],"performance":[37,86],"implementation":[38,54],"the":[40,51,79,91],"Message":[41],"Passing":[42],"Interface":[43],"(MPI),":[44],"improve":[46],"its":[47],"availability.":[48],"Compared":[49],"with":[50],"current":[52],"CRR":[53,92],"our":[57,95],"work":[58],"supports":[59],"file":[60],"own":[63],"higher":[64],"portability,":[65],"which":[66],"can":[67],"run":[68],"more":[70],"platforms":[71],"including":[72],"IA32":[73],"IA64":[75],"Linux.":[76],"In":[77],"addition,":[78],"test":[80],"shows":[81],"that":[82],"less":[83],"than":[84],"15%":[85],"overhead":[87],"is":[88],"introduced":[89],"by":[90],"mechanism":[93],"implementation.":[96]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
