{"id":"https://openalex.org/W2120384642","doi":"https://doi.org/10.1145/2312005.2312029","title":"High-performance RMA-based broadcast on the intel SCC","display_name":"High-performance RMA-based broadcast on the intel SCC","publication_year":2012,"publication_date":"2012-06-25","ids":{"openalex":"https://openalex.org/W2120384642","doi":"https://doi.org/10.1145/2312005.2312029","mag":"2120384642"},"language":"en","primary_location":{"id":"doi:10.1145/2312005.2312029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2312005.2312029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-fourth annual ACM symposium on Parallelism in algorithms and architectures","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://inria.hal.science/hal-01121943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046020902","display_name":"Darko Petrovi\u0107","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":"Darko Petrovi\u0107","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054711276","display_name":"Omid Shahmirzadi","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":"Omid Shahmirzadi","raw_affiliation_strings":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"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":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, 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":["EPFL, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":3.5147,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92882337,"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":"121","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.8679735660552979},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7065057158470154},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5954571962356567},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5859317779541016},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.5613124966621399},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.49628597497940063},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4955192804336548},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4912242293357849},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.48112693428993225},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4358811378479004},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41666334867477417},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4134112596511841},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3221626877784729},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.23050591349601746},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17108529806137085},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.12112647294998169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8679735660552979},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7065057158470154},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5954571962356567},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5859317779541016},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.5613124966621399},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.49628597497940063},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4955192804336548},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4912242293357849},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.48112693428993225},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4358811378479004},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41666334867477417},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4134112596511841},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3221626877784729},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.23050591349601746},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17108529806137085},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.12112647294998169},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/2312005.2312029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2312005.2312029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-fourth annual ACM symposium on Parallelism in algorithms and architectures","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.361.529","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.361.529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/176499/files/ocbcast-techreport.pdf?version=2","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.5768","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.5768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01121943v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01121943","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA2012), 2012, Pittsburgh, United States. ⟨10.1145/2312005.2312029⟩","raw_type":"Conference papers"},{"id":"pmh:oai:infoscience.epfl.ch:176499","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/176499","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"},{"id":"pmh:oai:infoscience.tind.io:176499","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/79761","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01121943v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01121943","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA2012), 2012, Pittsburgh, United States. ⟨10.1145/2312005.2312029⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W48937496","https://openalex.org/W246536198","https://openalex.org/W1560897251","https://openalex.org/W1591363587","https://openalex.org/W1825216778","https://openalex.org/W1964057018","https://openalex.org/W1974420955","https://openalex.org/W1984788566","https://openalex.org/W2004022056","https://openalex.org/W2019629740","https://openalex.org/W2035720033","https://openalex.org/W2065742943","https://openalex.org/W2102061396","https://openalex.org/W2111580991","https://openalex.org/W2114052846","https://openalex.org/W2131613942","https://openalex.org/W2131940306","https://openalex.org/W2133557963","https://openalex.org/W2142548635","https://openalex.org/W2148564531","https://openalex.org/W2151194859","https://openalex.org/W2164945803","https://openalex.org/W2168075869","https://openalex.org/W2404301698","https://openalex.org/W4246788062","https://openalex.org/W4285719527","https://openalex.org/W6713478309"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2116006827","https://openalex.org/W2361929291","https://openalex.org/W2086666199","https://openalex.org/W1997862718","https://openalex.org/W1511717675","https://openalex.org/W2185992486","https://openalex.org/W2146057962"],"abstract_inverted_index":{"Many-core":[0],"chips":[1],"with":[2],"more":[3],"than":[4],"1000":[5],"cores":[6],"are":[7,195,212],"expected":[8],"by":[9,79,124,151,168],"the":[10,13,29,36,56,97,106,121,141,147,152,173,177,189,206],"end":[11],"of":[12,28,49,73,81,96,179,186,218,221],"decade.":[14],"To":[15],"overcome":[16],"scalability":[17],"issues":[18],"related":[19],"to":[20,34,58,93,99,119,140,205,214],"cache":[21],"coherence":[22],"at":[23,169],"such":[24,84],"a":[25,47,50,113,128,198],"scale,":[26],"one":[27],"main":[30],"research":[31],"directions":[32],"is":[33,46,76],"leverage":[35],"message-passing":[37,51,74,223],"programming":[38],"model.":[39],"The":[40],"Intel":[41],"Single-Chip":[42],"Cloud":[43],"Computer":[44],"(SCC)":[45],"prototype":[48],"many-core":[52,224],"chip.":[53],"It":[54],"offers":[55],"ability":[57],"move":[59],"data":[60],"between":[61],"on-chip":[62,125],"Message":[63],"Passing":[64],"Buffers":[65],"(MPB)":[66],"using":[67],"Remote":[68],"Memory":[69],"Access":[70],"(RMA).":[71],"Performance":[72],"applications":[75],"directly":[77],"affected":[78],"efficiency":[80],"collective":[82,210],"operations,":[83],"as":[85],"broadcast.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90,131],"study":[91],"how":[92],"make":[94],"use":[95],"MPBs":[98],"implement":[100],"an":[101,133],"efficient":[102],"broadcast":[103,143,192],"algorithm":[104,117,139],"for":[105,146],"SCC.":[107,148],"We":[108],"propose":[109],"OC-Bcast":[110,158,182],"(On-Chip":[111],"Broadcast),":[112],"pipelined":[114],"k-ary":[115],"tree":[116],"tailored":[118],"exploit":[120],"parallelism":[122],"provided":[123],"RMA.":[126],"Using":[127],"LogP-based":[129],"model,":[130,153],"present":[132],"analytical":[134,174],"evaluation":[135,175],"that":[136,157,208],"compares":[137],"our":[138,180],"state-of-the-art":[142],"algorithms":[144],"implemented":[145],"As":[149],"predicted":[150],"experimental":[154],"results":[155],"show":[156],"attains":[159],"almost":[160],"three":[161],"times":[162],"better":[163],"throughput,":[164],"and":[165],"improves":[166],"latency":[167],"least":[170],"27\\%.":[171],"Furthermore,":[172],"highlights":[176],"benefits":[178],"approach:":[181],"takes":[183],"direct":[184],"advantage":[185,217],"RMA,":[187],"unlike":[188],"other":[190],"considered":[191],"algorithms,":[193],"which":[194],"based":[196],"on":[197],"higher-level":[199],"send/receive":[200],"interface.":[201],"This":[202],"leads":[203],"us":[204],"conclusion":[207],"RMA-based":[209],"operations":[211],"needed":[213],"take":[215],"full":[216],"hardware":[219],"features":[220],"future":[222],"architectures.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}