{"id":"https://openalex.org/W2028561190","doi":"https://doi.org/10.1145/2465813.2465819","title":"Replication for send-deterministic MPI HPC applications","display_name":"Replication for send-deterministic MPI HPC applications","publication_year":2013,"publication_date":"2013-06-18","ids":{"openalex":"https://openalex.org/W2028561190","doi":"https://doi.org/10.1145/2465813.2465819","mag":"2028561190"},"language":"en","primary_location":{"id":"doi:10.1145/2465813.2465819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2465813.2465819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01121949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031212846","display_name":"Arnaud Lefray","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Arnaud Lefray","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Algorithms and Software Architectures for Distributed and HPC Platforms"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Algorithms and Software Architectures for Distributed and HPC Platforms","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064121950","display_name":"Thomas Ropars","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Ropars","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111458171","display_name":"Andr\u00e9 Schiper","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Schiper","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7545,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75300749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"40"},"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8870165348052979},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.6630151271820068},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6154817342758179},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6142326593399048},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5634136199951172},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5598085522651672},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5428221225738525},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5339428782463074},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5142573714256287},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4874032139778137},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34388506412506104},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28413158655166626},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13206887245178223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8870165348052979},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6630151271820068},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6154817342758179},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6142326593399048},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5634136199951172},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5598085522651672},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5428221225738525},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5339428782463074},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5142573714256287},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4874032139778137},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34388506412506104},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28413158655166626},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13206887245178223},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2465813.2465819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2465813.2465819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01121949v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01121949","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3rd Workshop on Fault-Tolerance for HPC at Extreme Scale (FTXS), 2013, New-York City, United States. &#x27E8;10.1145/2465813.2465819&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:infoscience.epfl.ch:189833","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/189833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01121949v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01121949","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3rd Workshop on Fault-Tolerance for HPC at Extreme Scale (FTXS), 2013, New-York City, United States. &#x27E8;10.1145/2465813.2465819&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W192062974","https://openalex.org/W1973501242","https://openalex.org/W1977323337","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1993660990","https://openalex.org/W2045611838","https://openalex.org/W2063377848","https://openalex.org/W2063924830","https://openalex.org/W2077546582","https://openalex.org/W2088552220","https://openalex.org/W2102924960","https://openalex.org/W2112161048","https://openalex.org/W2129820467","https://openalex.org/W2150798641","https://openalex.org/W2159427602","https://openalex.org/W2160779498","https://openalex.org/W2164590718","https://openalex.org/W2165009364","https://openalex.org/W3137220996"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2082659044","https://openalex.org/W2811255748"],"abstract_inverted_index":{"Replication":[0],"has":[1],"recently":[2],"gained":[3],"attention":[4],"in":[5],"the":[6,30,38,70,88,101],"context":[7],"of":[8,40,51,76,100],"fault":[9],"tolerance":[10],"for":[11],"large":[12],"scale":[13],"MPI":[14,23,58,71,90,102],"HPC":[15,59,118],"applications.":[16],"Existing":[17],"implementations":[18],"try":[19,47],"to":[20,26,48,56,66,87],"cover":[21],"all":[22,105],"codes":[24],"and":[25,107,120],"be":[27],"independent":[28],"from":[29],"underlying":[31],"library.":[32,72],"In":[33],"this":[34],"paper,":[35],"we":[36,46,64],"evaluate":[37],"advantages":[39],"adopting":[41],"a":[42,52,84],"different":[43],"approach.":[44],"First,":[45],"take":[49],"advantage":[50,75],"communication":[53],"property":[54],"common":[55],"many":[57],"application,":[60],"namely":[61],"send-determinism.":[62],"Second,":[63],"choose":[65],"implement":[67],"replication":[68],"inside":[69],"The":[73],"main":[74,98],"our":[77,92],"approach":[78],"is":[79],"simplicity.":[80],"While":[81],"being":[82],"only":[83],"small":[85],"patch":[86],"Open":[89],"library,":[91],"solution":[93],"called":[94],"SDR-MPI":[95,110],"supports":[96],"most":[97],"features":[99],"standard":[103],"including":[104],"collectives":[106],"group":[108],"operations.":[109],"additionally":[111],"achieves":[112],"good":[113],"performance:":[114],"Experiments":[115],"run":[116],"with":[117],"benchmarks":[119],"applications":[121],"show":[122],"that":[123],"its":[124],"overhead":[125],"remains":[126],"below":[127],"5%.":[128]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
