{"id":"https://openalex.org/W2144108682","doi":"https://doi.org/10.1145/2600212.2600219","title":"Transparent checkpoint-restart over infiniband","display_name":"Transparent checkpoint-restart over infiniband","publication_year":2014,"publication_date":"2014-06-20","ids":{"openalex":"https://openalex.org/W2144108682","doi":"https://doi.org/10.1145/2600212.2600219","mag":"2144108682"},"language":"en","primary_location":{"id":"doi:10.1145/2600212.2600219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600212.2600219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international symposium on High-performance parallel and distributed computing","raw_type":"proceedings-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/A5073564468","display_name":"Jiajun Cao","orcid":"https://orcid.org/0009-0000-8797-2491"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiajun Cao","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029150876","display_name":"Gregory Kerr","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Kerr","raw_affiliation_strings":["Northeastern Universiy, Boston, MA, USA","Northeastern Universiy, Boston, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Northeastern Universiy, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Northeastern Universiy, Boston, MA, USA#TAB#","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087915276","display_name":"Kapil Arya","orcid":"https://orcid.org/0000-0003-1844-2117"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kapil Arya","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070983794","display_name":"Gene Cooperman","orcid":"https://orcid.org/0000-0003-2175-3848"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gene Cooperman","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073564468"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":3.9569,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94322585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"24"},"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":0.9994999766349792,"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":0.9993000030517578,"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/infiniband","display_name":"InfiniBand","score":0.9567010402679443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8866525888442993},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7039558291435242},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5944032073020935},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5743765830993652},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.5736783742904663},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.47516223788261414},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4690811038017273},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.44426289200782776},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4150567650794983}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9567010402679443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8866525888442993},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7039558291435242},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5944032073020935},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5743765830993652},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.5736783742904663},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.47516223788261414},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4690811038017273},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.44426289200782776},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4150567650794983},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2600212.2600219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600212.2600219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international symposium on High-performance parallel and distributed computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.431.1259","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.431.1259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ccs.neu.edu/home/gene/papers/hpdc14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.748.7197","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.748.7197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1312.3938.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W179815580","https://openalex.org/W1527076549","https://openalex.org/W1527754331","https://openalex.org/W1777978235","https://openalex.org/W1965091139","https://openalex.org/W1997021720","https://openalex.org/W2034881140","https://openalex.org/W2045879521","https://openalex.org/W2102650110","https://openalex.org/W2108208207","https://openalex.org/W2109217687","https://openalex.org/W2115367411","https://openalex.org/W2116115793","https://openalex.org/W2116283852","https://openalex.org/W2117508157","https://openalex.org/W2118926411","https://openalex.org/W2139244298","https://openalex.org/W2155662278","https://openalex.org/W2165205049","https://openalex.org/W2170454619","https://openalex.org/W2527113028","https://openalex.org/W6607433595","https://openalex.org/W6607501997"],"related_works":["https://openalex.org/W2116532831","https://openalex.org/W4245850706","https://openalex.org/W2097115404","https://openalex.org/W2089098642","https://openalex.org/W2147959273","https://openalex.org/W1978254186","https://openalex.org/W1968781019","https://openalex.org/W2744668842","https://openalex.org/W4234905039","https://openalex.org/W2724554809"],"abstract_inverted_index":{"Transparently":[0],"saving":[1],"the":[2,5,38,48,54,73,134,138,150],"state":[3],"of":[4,10,22,57,82,137],"InfiniBand":[6],"network":[7,49],"as":[8],"part":[9],"distributed":[11],"checkpointing":[12,110],"has":[13,25],"been":[14],"a":[15,23,76],"long-standing":[16],"challenge":[17],"for":[18,75],"researchers.":[19],"The":[20,65,80,122],"lack":[21],"solution":[24],"forced":[26],"typical":[27],"MPI":[28,92,112],"implementations":[29],"to":[30,91,94,142,152,157],"include":[31],"custom":[32],"checkpoint-restart":[33,60],"services":[34],"that":[35,61],"\"tear":[36],"down\"":[37],"network,":[39],"checkpoint":[40,131],"each":[41],"node":[42],"in":[43,100],"isolation,":[44],"and":[45,93,128],"then":[46],"re-connect":[47],"again.":[50],"This":[51],"work":[52],"presents":[53],"first":[55],"example":[56],"transparent,":[58],"system-initiated":[59],"directly":[62],"supports":[63],"InfiniBand.":[64],"new":[66],"approach":[67,84],"simplifies":[68],"current":[69],"practice":[70],"by":[71,87,109],"avoiding":[72],"need":[74],"privileged":[77],"kernel":[78],"module.":[79],"generality":[81],"this":[83],"is":[85,107,140],"demonstrated":[86],"applying":[88],"it":[89],"both":[90],"Berkeley":[95],"UPC":[96],"(Unified":[97],"Parallel":[98],"C),":[99],"its":[101],"native":[102],"mode":[103],"(without":[104],"MPI).":[105],"Scalability":[106],"shown":[108,141],"2,048":[111],"processes":[113],"across":[114],"128":[115],"nodes":[116],"(with":[117],"16":[118],"cores":[119],"per":[120],"node).":[121],"run-time":[123],"overhead":[124],"varies":[125],"between":[126],"0.8%":[127],"1.7%.":[129],"While":[130],"times":[132],"dominate,":[133],"network-only":[135],"portion":[136],"implementation":[139],"require":[143],"less":[144],"than":[145],"100":[146],"milliseconds":[147],"(not":[148],"including":[149],"time":[151],"locally":[153],"write":[154],"application":[155],"memory":[156],"stable":[158],"storage).":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}