{"id":"https://openalex.org/W2056583598","doi":"https://doi.org/10.1145/2600212.2600224","title":"Fault tolerance for remote memory access programming models","display_name":"Fault tolerance for remote memory access programming models","publication_year":2014,"publication_date":"2014-06-20","ids":{"openalex":"https://openalex.org/W2056583598","doi":"https://doi.org/10.1145/2600212.2600224","mag":"2056583598"},"language":"en","primary_location":{"id":"doi:10.1145/2600212.2600224","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600212.2600224","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":"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/A5056549312","display_name":"Maciej Besta","orcid":"https://orcid.org/0000-0002-6550-7916"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maciej Besta","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"48"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.993399977684021,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9915000200271606,"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":0.8457216024398804},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7887451648712158},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7400383949279785},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.6389463543891907},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6285590529441833},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6131096482276917},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.6050029993057251},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4797302782535553},{"id":"https://openalex.org/keywords/memory-protection","display_name":"Memory protection","score":0.4439643621444702},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4424101710319519},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.43420684337615967},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39437931776046753},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3296085298061371},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3200491964817047},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23177790641784668},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2312929332256317},{"id":"https://openalex.org/keywords/extended-memory","display_name":"Extended memory","score":0.2160995602607727},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.17458194494247437},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0899457037448883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457216024398804},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7887451648712158},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7400383949279785},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.6389463543891907},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6285590529441833},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6131096482276917},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.6050029993057251},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4797302782535553},{"id":"https://openalex.org/C18131444","wikidata":"https://www.wikidata.org/wiki/Q163585","display_name":"Memory protection","level":5,"score":0.4439643621444702},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4424101710319519},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.43420684337615967},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39437931776046753},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3296085298061371},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3200491964817047},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23177790641784668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2312929332256317},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.2160995602607727},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.17458194494247437},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0899457037448883},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2600212.2600224","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600212.2600224","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:10.1.1.646.3147","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.3147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://htor.inf.ethz.ch/publications/img/besta-hoefler-ftrma.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":38,"referenced_works":["https://openalex.org/W98893444","https://openalex.org/W153168184","https://openalex.org/W1575350781","https://openalex.org/W1973501242","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1991421378","https://openalex.org/W1993143336","https://openalex.org/W2004381122","https://openalex.org/W2023324599","https://openalex.org/W2050991960","https://openalex.org/W2077546582","https://openalex.org/W2091085450","https://openalex.org/W2100970777","https://openalex.org/W2101699635","https://openalex.org/W2103579240","https://openalex.org/W2105039796","https://openalex.org/W2112121929","https://openalex.org/W2120384642","https://openalex.org/W2123713800","https://openalex.org/W2125776594","https://openalex.org/W2126565923","https://openalex.org/W2129418947","https://openalex.org/W2131053137","https://openalex.org/W2133046454","https://openalex.org/W2147853062","https://openalex.org/W2148575324","https://openalex.org/W2156935376","https://openalex.org/W2160779498","https://openalex.org/W2164507994","https://openalex.org/W2165022815","https://openalex.org/W2169164058","https://openalex.org/W2171938442","https://openalex.org/W2207785195","https://openalex.org/W2296772319","https://openalex.org/W3102191699","https://openalex.org/W3137220996","https://openalex.org/W3143778233"],"related_works":["https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W2368477821","https://openalex.org/W1584308544","https://openalex.org/W2069613115","https://openalex.org/W3147391527","https://openalex.org/W2055367414"],"abstract_inverted_index":{"Remote":[0],"Memory":[1],"Access":[2],"(RMA)":[3],"is":[4,39],"an":[5],"emerging":[6,157],"mechanism":[7],"for":[8,21,33,55,60,92,146],"programming":[9,159],"high-performance":[10],"computers":[11],"and":[12,24,35,65,89,135,148,156],"datacenters.":[13],"However,":[14],"little":[15],"work":[16],"exists":[17],"on":[18],"resilience":[19,43,144],"schemes":[20],"RMA-based":[22],"applications":[23],"systems.":[25],"In":[26],"this":[27,70],"paper":[28],"we":[29],"analyze":[30],"fault":[31,58,154],"tolerance":[32,59,155],"RMA":[34,147,158],"show":[36],"that":[37,77,132],"it":[38],"fundamentally":[40],"different":[41],"from":[42],"mechanisms":[44,76,145],"targeting":[45],"the":[46,111],"message":[47],"passing":[48],"(MP)":[49],"model.":[50],"We":[51,68],"design":[52],"a":[53,90,150],"model":[54,71,130],"reasoning":[56],"about":[57],"RMA,":[61],"addressing":[62],"both":[63],"flat":[64],"hierarchical":[66],"hardware.":[67],"use":[69],"to":[72],"construct":[73],"several":[74],"highly-scalable":[75,143],"provide":[78,137],"efficient":[79],"low-overhead":[80],"in-memory":[81,133],"checkpointing,":[82],"transparent":[83,93],"logging":[84,136],"of":[85,95,105,110,114,120],"remote":[86],"memory":[87,106],"accesses,":[88],"scheme":[91,123],"recovery":[94],"failed":[96],"processes.":[97],"Our":[98,128],"protocols":[99],"take":[100],"into":[101],"account":[102],"diminishing":[103],"amounts":[104],"per":[107],"core,":[108],"one":[109],"major":[112],"features":[113],"future":[115],"exascale":[116],"machines.":[117],"The":[118],"implementation":[119],"our":[121],"fault-tolerance":[122],"entails":[124],"negligible":[125],"additional":[126],"overheads.":[127],"reliability":[129],"shows":[131],"checkpointing":[134],"high":[138],"resilience.":[139],"This":[140],"study":[141],"enables":[142],"fills":[149],"research":[151],"gap":[152],"between":[153],"models.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
