{"id":"https://openalex.org/W2889463335","doi":"https://doi.org/10.1109/tpds.2018.2867222","title":"Exploiting Hardware Multicast and GPUDirect RDMA for Efficient Broadcast","display_name":"Exploiting Hardware Multicast and GPUDirect RDMA for Efficient Broadcast","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889463335","doi":"https://doi.org/10.1109/tpds.2018.2867222","mag":"2889463335"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2867222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2867222","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5076405830","display_name":"Ching-Hsiang Chu","orcid":"https://orcid.org/0000-0002-6752-3135"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Hsiang Chu","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-6752-3135","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067748041","display_name":"Xiaoyi Lu","orcid":"https://orcid.org/0000-0001-7581-8905"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Lu","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-7581-8905","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004330728","display_name":"Ammar Ahmad Awan","orcid":"https://orcid.org/0000-0002-6272-3760"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ammar A. Awan","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-6272-3760","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-1200-2754","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022589297","display_name":"Bracy H. Elton","orcid":"https://orcid.org/0000-0001-6449-1310"},"institutions":[{"id":"https://openalex.org/I4210104289","display_name":"Engility (United States)","ror":"https://ror.org/01h2d3422","country_code":"US","type":"company","lineage":["https://openalex.org/I4210104289"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bracy Elton","raw_affiliation_strings":["Engility Corporation, WPAFB, Dayton, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-6449-1310","affiliations":[{"raw_affiliation_string":"Engility Corporation, WPAFB, Dayton, OH, USA","institution_ids":["https://openalex.org/I4210104289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.7542,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.86533638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":"3","first_page":"575","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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":0.9975000023841858,"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/T11478","display_name":"Caching and Content Delivery","score":0.9970999956130981,"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":0.9119798541069031},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.8693045377731323},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.8093839883804321},{"id":"https://openalex.org/keywords/multicast","display_name":"Multicast","score":0.6632922887802124},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5964303612709045},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4531354308128357},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.45309263467788696},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4419347643852234},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41053932905197144},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4023221731185913},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3557749092578888},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27075523138046265},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24044698476791382},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08679300546646118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9119798541069031},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.8693045377731323},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.8093839883804321},{"id":"https://openalex.org/C32295351","wikidata":"https://www.wikidata.org/wiki/Q899288","display_name":"Multicast","level":2,"score":0.6632922887802124},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5964303612709045},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4531354308128357},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.45309263467788696},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4419347643852234},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41053932905197144},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4023221731185913},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3557749092578888},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27075523138046265},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24044698476791382},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08679300546646118},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2867222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2867222","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5081535240","display_name":null,"funder_award_id":"GS04T09DBC0017","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W107057451","https://openalex.org/W1576599451","https://openalex.org/W1577304665","https://openalex.org/W1637731592","https://openalex.org/W1686810756","https://openalex.org/W1777209000","https://openalex.org/W1964981582","https://openalex.org/W1969636218","https://openalex.org/W1992727573","https://openalex.org/W2024565525","https://openalex.org/W2038067847","https://openalex.org/W2110172144","https://openalex.org/W2117539524","https://openalex.org/W2126852285","https://openalex.org/W2129418947","https://openalex.org/W2131940306","https://openalex.org/W2136041296","https://openalex.org/W2151194859","https://openalex.org/W2163605009","https://openalex.org/W2167967054","https://openalex.org/W2171277573","https://openalex.org/W2194775991","https://openalex.org/W2294630901","https://openalex.org/W2294872507","https://openalex.org/W2295816259","https://openalex.org/W2329155633","https://openalex.org/W2513583054","https://openalex.org/W2535374105","https://openalex.org/W2567312658","https://openalex.org/W2567368162","https://openalex.org/W2580688187","https://openalex.org/W2581372641","https://openalex.org/W2753665345","https://openalex.org/W2953200226","https://openalex.org/W3102191699","https://openalex.org/W3105781365","https://openalex.org/W4242547806","https://openalex.org/W4246883971","https://openalex.org/W4293318097","https://openalex.org/W6637373629","https://openalex.org/W6679245683","https://openalex.org/W6684191040","https://openalex.org/W6725900697","https://openalex.org/W6765060121"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W1984788566","https://openalex.org/W4253931064","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W2139382794"],"abstract_inverted_index":{"Broadcast":[0],"is":[1,48],"a":[2,45,135,145],"widely":[3],"used":[4],"operation":[5],"in":[6,86,118],"many":[7],"streaming":[8,137],"and":[9,73,97,105,139],"deep":[10,146],"learning":[11,147],"applications":[12],"to":[13,50,67,107,114,124],"disseminate":[14],"large":[15],"amounts":[16],"of":[17,54,89,111],"data":[18],"on":[19,58],"emerging":[20],"heterogeneous":[21],"High-Performance":[22],"Computing":[23],"(HPC)":[24],"systems.":[25],"However,":[26],"traditional":[27],"broadcast":[28,56,63],"schemes":[29,57,64],"do":[30],"not":[31],"fully":[32],"utilize":[33],"hardware":[34,70],"features":[35],"for":[36,77,134,144],"Graphics":[37],"Processing":[38],"Unit":[39],"(GPU)-based":[40],"applications.":[41,98],"In":[42],"this":[43],"paper,":[44],"model-oriented":[46],"analysis":[47],"presented":[49],"identify":[51],"performance":[52],"bottlenecks":[53],"existing":[55],"GPU":[59],"clusters.":[60],"Next,":[61],"streaming-based":[62],"are":[65,84],"proposed":[66,82,128],"exploit":[68],"InfiniBand":[69],"multicast":[71],"(IB-MCAST)":[72],"NVIDIA":[74],"GPUDirect":[75],"technology":[76],"efficient":[78],"message":[79],"transmission.":[80],"The":[81,99],"designs":[83],"evaluated":[85],"the":[87,115,119,125,127],"context":[88],"using":[90],"Message":[91],"Passing":[92],"Interface":[93],"(MPI)":[94],"based":[95],"benchmarks":[96],"experimental":[100],"results":[101],"indicate":[102],"improved":[103],"scalability":[104],"up":[106],"82":[108],"percent":[109],"reduction":[110],"latency":[112],"compared":[113,123],"state-of-the-art":[116],"solutions":[117],"benchmark-level":[120],"evaluation.":[121],"Furthermore,":[122],"state-of-the-art,":[126],"design":[129],"yields":[130],"stable":[131],"higher":[132],"throughput":[133],"synthetic":[136],"workload,":[138],"1.3x":[140],"faster":[141],"training":[142],"time":[143],"framework.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}