{"id":"https://openalex.org/W1965091139","doi":"https://doi.org/10.1145/1551609.1551619","title":"Interconnect agnostic checkpoint/restart in open MPI","display_name":"Interconnect agnostic checkpoint/restart in open MPI","publication_year":2009,"publication_date":"2009-06-09","ids":{"openalex":"https://openalex.org/W1965091139","doi":"https://doi.org/10.1145/1551609.1551619","mag":"1965091139"},"language":"en","primary_location":{"id":"doi:10.1145/1551609.1551619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1551609.1551619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM international symposium on High performance 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/A5076123370","display_name":"Joshua Hursey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joshua Hursey","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013020019","display_name":"Timothy I. Mattox","orcid":"https://orcid.org/0000-0001-5265-4848"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy I. Mattox","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074260102","display_name":"Andrew Lumsdaine","orcid":"https://orcid.org/0000-0002-9153-6622"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Lumsdaine","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076123370"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":9.0535,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.97989176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"58"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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":0.9977999925613403,"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/infiniband","display_name":"InfiniBand","score":0.940638542175293},{"id":"https://openalex.org/keywords/myrinet","display_name":"Myrinet","score":0.9011827707290649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8622647523880005},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6205706596374512},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5429534316062927},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5136082172393799},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5019221305847168},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.47639361023902893},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.4653763175010681},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4622810184955597},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.44782838225364685},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41944336891174316},{"id":"https://openalex.org/keywords/ethernet","display_name":"Ethernet","score":0.4147060215473175},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4041045904159546},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38455820083618164},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.32948213815689087}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.940638542175293},{"id":"https://openalex.org/C2780601250","wikidata":"https://www.wikidata.org/wiki/Q1863181","display_name":"Myrinet","level":3,"score":0.9011827707290649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622647523880005},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6205706596374512},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5429534316062927},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5136082172393799},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5019221305847168},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.47639361023902893},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.4653763175010681},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4622810184955597},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.44782838225364685},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41944336891174316},{"id":"https://openalex.org/C172173386","wikidata":"https://www.wikidata.org/wiki/Q79984","display_name":"Ethernet","level":2,"score":0.4147060215473175},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4041045904159546},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38455820083618164},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32948213815689087}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1551609.1551619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1551609.1551619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM international symposium on High performance distributed computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.177.5837","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.177.5837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.osl.iu.edu/publications/prints/2009/hursey%3Ahpdc09%3AInterconnect-Agnostic-CR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W134816542","https://openalex.org/W346518175","https://openalex.org/W1527754331","https://openalex.org/W1537929875","https://openalex.org/W1825216778","https://openalex.org/W1997021720","https://openalex.org/W2019680442","https://openalex.org/W2037730929","https://openalex.org/W2045879521","https://openalex.org/W2046309377","https://openalex.org/W2067021722","https://openalex.org/W2077452259","https://openalex.org/W2095487435","https://openalex.org/W2098123240","https://openalex.org/W2100970777","https://openalex.org/W2108208207","https://openalex.org/W2114035455","https://openalex.org/W2118697699","https://openalex.org/W2126071114","https://openalex.org/W2131053137","https://openalex.org/W2133201251","https://openalex.org/W2135310158","https://openalex.org/W2155662278","https://openalex.org/W2170454619","https://openalex.org/W2171268876","https://openalex.org/W2171453084","https://openalex.org/W2260133378","https://openalex.org/W2610607207","https://openalex.org/W2611176464","https://openalex.org/W4232281662","https://openalex.org/W4233549502","https://openalex.org/W4242589337","https://openalex.org/W4285719527","https://openalex.org/W6600210833","https://openalex.org/W6631987640"],"related_works":["https://openalex.org/W1519171198","https://openalex.org/W2119634093","https://openalex.org/W1970720081","https://openalex.org/W2099337421","https://openalex.org/W2751263050","https://openalex.org/W2366325093","https://openalex.org/W2498758832","https://openalex.org/W2161210471","https://openalex.org/W2133825528","https://openalex.org/W2154020360"],"abstract_inverted_index":{"Long":[0],"running":[1],"High":[2],"Performance":[3],"Computing":[4],"(HPC)":[5],"applications":[6],"at":[7],"scale":[8],"must":[9],"be":[10,91,100,113],"able":[11],"to":[12,19,39,47,60,90,99,144,146,157,168],"tolerate":[13],"inevitable":[14],"faults":[15],"if":[16],"they":[17],"are":[18],"harness":[20],"current":[21],"and":[22,109,112,123],"future":[23],"HPC":[24,40,142,189],"systems.":[25],"Message":[26],"Passing":[27],"Interface":[28],"(MPI)":[29],"level":[30],"transparent":[31],"checkpoint/restart":[32,80,89,136],"fault":[33],"tolerance":[34],"is":[35],"an":[36,97,163],"appealing":[37],"option":[38,57],"application":[41,98,143],"developers":[42],"that":[43,54,83],"do":[44],"not":[45],"wish":[46],"restructure":[48],"their":[49],"code.":[50],"Historically,":[51],"MPI":[52,86],"implementations":[53],"provided":[55],"this":[56,186],"have":[58],"struggled":[59],"provide":[61],"a":[62,75,116,169,173],"full":[63],"range":[64],"of":[65,88,105,119,176,185],"interconnect":[66,92,132,154],"support,":[67],"especially":[68],"shared":[69,110,124],"memory":[70,125],"support.":[71],"This":[72,94],"paper":[73],"presents":[74],"new":[76],"approach":[77,95,187],"for":[78],"implementing":[79],"coordination":[81,137],"algorithms":[82],"allows":[84,96],"the":[85,130,135,141,149,182],"implementation":[87],"agnostic.":[93],"checkpointed":[101],"on":[102,162,188],"one":[103],"set":[104,118,175],"interconnects":[106,120],"(e.g.,":[107,121],"InfiniBand":[108],"memory)":[111],"restarted":[114],"with":[115,172],"different":[117,170,174],"Myrinet":[122],"or":[126,166],"Ethernet).":[127],"By":[128],"separating":[129],"network":[131],"details":[133],"from":[134],"algorithm":[138],"we":[139],"allow":[140],"respond":[145],"changes":[147],"in":[148],"cluster":[150],"environment":[151],"such":[152],"as":[153],"unavailability":[155],"due":[156],"switch":[158],"failure,":[159],"re-load":[160],"balance":[161],"existing":[164],"machine,":[165],"migrate":[167],"machine":[171],"interconnects.":[177],"We":[178],"present":[179],"results":[180],"characterizing":[181],"performance":[183],"impact":[184],"applications.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
