{"id":"https://openalex.org/W4291908378","doi":"https://doi.org/10.1109/icccs55155.2022.9846190","title":"Hybrid Approach to Optimize MPI Collectives by In-network-computation and Point-to-Point Messages","display_name":"Hybrid Approach to Optimize MPI Collectives by In-network-computation and Point-to-Point Messages","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4291908378","doi":"https://doi.org/10.1109/icccs55155.2022.9846190"},"language":"en","primary_location":{"id":"doi:10.1109/icccs55155.2022.9846190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs55155.2022.9846190","pdf_url":null,"source":{"id":"https://openalex.org/S4363608130","display_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-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/A5100668208","display_name":"Shuping Chen","orcid":"https://orcid.org/0009-0003-3434-1209"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuping Chen","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology,Bejing,China","National Research Center of Parallel Computer Engineering and Technology, Bejing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology,Bejing,China","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Bejing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109376997","display_name":"Wangquan He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wangquan He","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology,Bejing,China","National Research Center of Parallel Computer Engineering and Technology, Bejing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology,Bejing,China","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Bejing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047914844","display_name":"Fengbin Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengbin Qi","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology,Bejing,China","National Research Center of Parallel Computer Engineering and Technology, Bejing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology,Bejing,China","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Bejing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343287","display_name":"Yan Zheng","orcid":"https://orcid.org/0000-0002-9754-9264"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology,Bejing,China","National Research Center of Parallel Computer Engineering and Technology, Bejing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology,Bejing,China","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Bejing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624617","display_name":"Yu Kang","orcid":"https://orcid.org/0000-0002-0999-8802"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang Yu","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology,Bejing,China","National Research Center of Parallel Computer Engineering and Technology, Bejing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology,Bejing,China","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Bejing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100668208"],"corresponding_institution_ids":["https://openalex.org/I4210131745"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08982202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":null,"first_page":"773","last_page":"783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","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/T10829","display_name":"Interconnection Networks and Systems","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8698499202728271},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6655306816101074},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.583936870098114},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5228745937347412},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5185906887054443},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4926522374153137},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4892113208770752},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4735735356807709},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4555649757385254},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4364017844200134},{"id":"https://openalex.org/keywords/software-defined-networking","display_name":"Software-defined networking","score":0.4173429012298584},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41167041659355164},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4007846415042877},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.38627681136131287},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29074329137802124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8698499202728271},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6655306816101074},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.583936870098114},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5228745937347412},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5185906887054443},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4926522374153137},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4892113208770752},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4735735356807709},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4555649757385254},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4364017844200134},{"id":"https://openalex.org/C77270119","wikidata":"https://www.wikidata.org/wiki/Q1655198","display_name":"Software-defined networking","level":2,"score":0.4173429012298584},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41167041659355164},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4007846415042877},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38627681136131287},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29074329137802124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccs55155.2022.9846190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs55155.2022.9846190","pdf_url":null,"source":{"id":"https://openalex.org/S4363608130","display_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1568736435","https://openalex.org/W1937799376","https://openalex.org/W1987117608","https://openalex.org/W2009852231","https://openalex.org/W2010519474","https://openalex.org/W2013390839","https://openalex.org/W2059300917","https://openalex.org/W2062764889","https://openalex.org/W2097982440","https://openalex.org/W2102061396","https://openalex.org/W2107406335","https://openalex.org/W2131613942","https://openalex.org/W2131993480","https://openalex.org/W2148470708","https://openalex.org/W2166097017","https://openalex.org/W2166214860","https://openalex.org/W2495682485","https://openalex.org/W2505535144","https://openalex.org/W2532546572","https://openalex.org/W2563521659","https://openalex.org/W2571237871","https://openalex.org/W2767393956","https://openalex.org/W2767461568","https://openalex.org/W2769986458","https://openalex.org/W2784240842","https://openalex.org/W2784285104","https://openalex.org/W2886520239","https://openalex.org/W2887690473","https://openalex.org/W2902551881","https://openalex.org/W2944157987","https://openalex.org/W2945882313","https://openalex.org/W2985709405","https://openalex.org/W3084537083","https://openalex.org/W3097072756","https://openalex.org/W3126246198","https://openalex.org/W3147460469","https://openalex.org/W3149292517","https://openalex.org/W4242634435","https://openalex.org/W4245836145","https://openalex.org/W4251820394","https://openalex.org/W4252163020","https://openalex.org/W4256344501"],"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/W2327638088","https://openalex.org/W2151092287"],"abstract_inverted_index":{"Using":[0],"in-network-computation":[1,134],"capabilities":[2],"of":[3,38,55,122,198,249,257,265],"the":[4,27,39,52,58,85,92,139,144,156,166,169,176,183,196,199,209,221,234,240,246,258,263],"network":[5,59,157],"devices":[6],"(also":[7],"called":[8],"hardware":[9,28,56,170,242,260],"collectives)":[10],"to":[11,46,50,63,80,101,115,129,155,160,194,227,239],"optimize":[12,130],"MPI":[13,70,82,105,131],"collectives":[14,29,132,171,228,261],"has":[15],"become":[16],"popular":[17],"in":[18,33,148,175,208,262],"high-performance":[19],"computing,":[20],"and":[21,107,120,135],"shows":[22],"significant":[23,109],"performance":[24,53,110,119,207,235],"advantages.":[25],"However,":[26],"are":[30,172],"not":[31],"flawless":[32],"practical":[34],"use":[35,143],"scenarios.":[36],"One":[37,77],"problems":[40],"is":[41,44,73,79,252],"that":[42,217,256],"it":[43,99,180],"difficult":[45],"use.":[47,123],"In":[48,244],"order":[49],"obtain":[51],"advantage":[54],"collectives,":[57],"management":[60,93,158],"software":[61,94,159],"need":[62],"create":[64,161],"dedicated":[65,162],"aggregate":[66,88,146,163],"tree":[67],"for":[68],"each":[69,149],"communicator,":[71],"which":[72],"a":[74,126,191],"complicated":[75],"task.":[76],"solution":[78],"make":[81,116],"communicators":[83,106],"sharing":[84],"global":[86],"imprecise":[87],"trees":[89,147],"created":[90],"by":[91,133,224,230],"when":[95],"initiating":[96],"networks,":[97],"but":[98],"leads":[100],"heavy":[102,266],"interference":[103],"between":[104,118],"causes":[108],"degradation.":[111],"So":[112],"we":[113,142],"have":[114],"tradeoff":[117],"ease":[121],"We":[124,189,203],"propose":[125],"hybrid":[127,200],"approach":[128,219,251],"point-to-point":[136,231],"messages.":[137],"On":[138,165],"one":[140],"hand,":[141,168],"pre-created":[145],"super-node,":[150,178],"rather":[151],"than":[152,255],"sending":[153],"requests":[154],"trees.":[164],"other":[167,187],"transferred":[173],"only":[174],"local":[177],"so":[179],"cannot":[181],"disturb":[182],"jobs":[184],"running":[185],"on":[186],"super-nodes.":[188],"provide":[190],"cost":[192],"model":[193],"evaluate":[195],"overhead":[197],"collective":[201],"algorithms.":[202],"also":[204],"test":[205],"its":[206],"new":[210],"generation":[211],"Sunway":[212],"supercomputer.":[213],"The":[214],"results":[215],"show":[216],"our":[218,250],"reduces":[220],"median":[222],"latency":[223,248],"18%~74%":[225],"compared":[226,238],"implemented":[229],"messages,":[232],"although":[233],"decrease":[236],"slightly":[237],"original":[241,259],"collectives.":[243],"addition,":[245],"tail":[247],"significantly":[253],"lower":[254],"presence":[264],"interference.":[267]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}