{"id":"https://openalex.org/W2122452466","doi":"https://doi.org/10.1109/hipc.2010.5713195","title":"Fault-tolerant communication runtime support for data-centric programming models","display_name":"Fault-tolerant communication runtime support for data-centric programming models","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2122452466","doi":"https://doi.org/10.1109/hipc.2010.5713195","mag":"2122452466"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2010.5713195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2010.5713195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009322871","display_name":"Abhinav Vishnu","orcid":"https://orcid.org/0000-0002-0593-4780"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Vishnu","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA","Pacific Northwest National Laboratory; Richland WA 99352"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory; Richland WA 99352","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huub Van Dam","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huub Van Dam","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA","Pacific Northwest National Laboratory; Richland WA 99352"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory; Richland WA 99352","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034688782","display_name":"Wibe A. de Jong","orcid":"https://orcid.org/0000-0002-7114-8315"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wibe De Jong","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA","Pacific Northwest National Laboratory; Richland WA 99352"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory; Richland WA 99352","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050531633","display_name":"Pavan Balaji","orcid":"https://orcid.org/0000-0002-9785-4461"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan Balaji","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL, Argonne","Mathematics and Computer Science Division. Argonne National Laboratory , Argonne, IL 60439"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL, Argonne","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division. Argonne National Laboratory , Argonne, IL 60439","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Song","raw_affiliation_strings":["Department of Computer Science, Virginia Polytechnic Institute, Blacksburg, VA","Department of Computer Science, Virginia Polytechnic Institute, Blacksburg, VA 24060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Polytechnic Institute, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Polytechnic Institute, Blacksburg, VA 24060","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"i","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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/T10772","display_name":"Distributed systems and fault tolerance","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/partitioned-global-address-space","display_name":"Partitioned global address space","score":0.943213939666748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7953765392303467},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6800113916397095},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5969366431236267},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5157328248023987},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.499922513961792},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.49691298604011536},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4700205326080322},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.44439899921417236},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.4443942904472351},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43096688389778137},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4162943959236145},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38844969868659973},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34101971983909607},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1762164831161499},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1516089141368866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10228577256202698}],"concepts":[{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.943213939666748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953765392303467},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6800113916397095},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5969366431236267},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5157328248023987},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.499922513961792},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.49691298604011536},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4700205326080322},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.44439899921417236},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.4443942904472351},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43096688389778137},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4162943959236145},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38844969868659973},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34101971983909607},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1762164831161499},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1516089141368866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10228577256202698},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hipc.2010.5713195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2010.5713195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.306.4161","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.306.4161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scape.cs.vt.edu/wp-content/uploads/2012/08/hipc10_song_scape.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1576341769","https://openalex.org/W1594956651","https://openalex.org/W1595141187","https://openalex.org/W1641327695","https://openalex.org/W1861151562","https://openalex.org/W1980670496","https://openalex.org/W2008505510","https://openalex.org/W2011979817","https://openalex.org/W2041591938","https://openalex.org/W2045579177","https://openalex.org/W2069079195","https://openalex.org/W2080230387","https://openalex.org/W2081612620","https://openalex.org/W2082490936","https://openalex.org/W2082659044","https://openalex.org/W2090409324","https://openalex.org/W2094526959","https://openalex.org/W2102459212","https://openalex.org/W2105039796","https://openalex.org/W2108208207","https://openalex.org/W2109065830","https://openalex.org/W2109982223","https://openalex.org/W2113559580","https://openalex.org/W2114728910","https://openalex.org/W2135342109","https://openalex.org/W2138907145","https://openalex.org/W2149083310","https://openalex.org/W2151255837","https://openalex.org/W2153635026","https://openalex.org/W2160123909","https://openalex.org/W2160895517","https://openalex.org/W2170500888","https://openalex.org/W4239022315","https://openalex.org/W6636635267","https://openalex.org/W6676906424","https://openalex.org/W6683390773"],"related_works":["https://openalex.org/W2166185777","https://openalex.org/W3004875591","https://openalex.org/W2494227547","https://openalex.org/W2143665235","https://openalex.org/W2561033805","https://openalex.org/W3032127535","https://openalex.org/W1593064209","https://openalex.org/W4318604915","https://openalex.org/W2094133266","https://openalex.org/W2111309158"],"abstract_inverted_index":{"The":[0,74,153],"largest":[1],"supercomputers":[2],"in":[3,77],"the":[4,43,50,67,81,95,189],"world":[5],"today":[6],"consist":[7],"of":[8,10,12,83,156,203],"hundreds":[9],"thousands":[11],"processing":[13],"cores":[14],"and":[15,85,137,148,162,172,175,198],"many":[16],"more":[17],"other":[18,51],"hardware":[19,24],"components.":[20],"At":[21],"such":[22,65],"scales,":[23],"faults":[25],"are":[26,37],"a":[27,108,128,139,157,200],"commonplace,":[28],"necessitating":[29],"fault-resilient":[30,35,158],"software":[31],"systems.":[32,183],"While":[33],"different":[34],"models":[36,64,79],"available,":[38],"most":[39],"focus":[40],"on":[41],"allowing":[42,98],"computational":[44],"processes":[45],"to":[46,100,195],"survive":[47],"faults.":[48],"On":[49],"hand,":[52],"we":[53,126],"have":[54],"recently":[55],"started":[56],"investigating":[57],"fault":[58,133,165,204],"resilience":[59,134],"techniques":[60],"for":[61,179,206],"data-centric":[62,78,132],"programming":[63],"as":[66],"partitioned":[68],"global":[69],"address":[70],"space":[71],"(PGAS)":[72],"models.":[73,208],"primary":[75],"difference":[76],"is":[80,92,110,121],"decoupling":[82],"computation":[84],"data":[86,90,114,120],"locality.":[87],"That":[88],"is,":[89],"placement":[91],"decoupled":[93],"from":[94,113],"executing":[96],"processes,":[97],"us":[99],"view":[101],"process":[102,109,159],"failure":[103,115,173],"(a":[104,116],"physical":[105,117],"node":[106,118],"hosting":[107,119],"dead)":[111],"separately":[112],"dead).":[122],"In":[123],"this":[124],"paper,":[125],"take":[127],"first":[129],"step":[130],"toward":[131],"by":[135],"designing":[136],"implementing":[138],"fault-resilient,":[140],"one-sided":[141,180],"communication":[142,150,170,181],"runtime":[143,182],"framework":[144,154,190,202],"using":[145],"Global":[146],"Arrays":[147],"its":[149],"system,":[151],"ARMCI.":[152],"consists":[155],"manager;":[160],"low-overhead":[161],"network-assisted":[163],"remote-node":[164],"detection":[166],"module;":[167],"non-data-moving":[168],"collective":[169],"primitives;":[171],"semantics":[174],"err":[176],"or":[177],"codes":[178],"Our":[184],"performance":[185],"evaluation":[186],"indicates":[187],"that":[188],"incurs":[191],"little":[192],"overhead":[193],"compared":[194],"state-of-the-art":[196],"designs":[197],"provides":[199],"fundamental":[201],"resiliency":[205],"PGAS":[207]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
