{"id":"https://openalex.org/W2129933264","doi":"https://doi.org/10.1109/icccn.2013.6614098","title":"Accelerating Allreduce Operation: A Switch-Based Solution","display_name":"Accelerating Allreduce Operation: A Switch-Based Solution","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2129933264","doi":"https://doi.org/10.1109/icccn.2013.6614098","mag":"2129933264"},"language":"en","primary_location":{"id":"doi:10.1109/icccn.2013.6614098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn.2013.6614098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 22nd International Conference on Computer Communication and Networks (ICCCN)","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/A5020789064","display_name":"HU Nong-da","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nongda Hu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445424","display_name":"Dawei Wang","orcid":"https://orcid.org/0000-0001-9981-3623"},"institutions":[{"id":"https://openalex.org/I1339145263","display_name":"Juniper Networks (United States)","ror":"https://ror.org/02pwct569","country_code":"US","type":"company","lineage":["https://openalex.org/I1339145263"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawei Wang","raw_affiliation_strings":["Juniper Networks, California, USA","Juniper Networks, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Juniper Networks, California, USA","institution_ids":["https://openalex.org/I1339145263"]},{"raw_affiliation_string":"Juniper Networks, CA, USA","institution_ids":["https://openalex.org/I1339145263"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029024939","display_name":"Zheng Cao","orcid":"https://orcid.org/0000-0002-1565-3683"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Cao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101472673","display_name":"Xuejun An","orcid":"https://orcid.org/0009-0005-0494-6332"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejun An","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738013","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-1953-1392"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Inst. of Comput. Technol., Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18287781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8408321142196655},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8012068271636963},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6169053912162781},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.614120364189148},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5938558578491211},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5509499907493591},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5054185390472412},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4557878077030182},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4426979124546051},{"id":"https://openalex.org/keywords/point-to-point","display_name":"Point-to-point","score":0.4407593309879303},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43258392810821533},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.42693817615509033},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4257630705833435},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4174027442932129},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.28391188383102417},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1841457486152649},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12229910492897034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8408321142196655},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8012068271636963},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6169053912162781},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.614120364189148},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5938558578491211},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5509499907493591},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5054185390472412},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4557878077030182},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4426979124546051},{"id":"https://openalex.org/C174440990","wikidata":"https://www.wikidata.org/wiki/Q681349","display_name":"Point-to-point","level":2,"score":0.4407593309879303},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43258392810821533},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.42693817615509033},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4257630705833435},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4174027442932129},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28391188383102417},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1841457486152649},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12229910492897034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccn.2013.6614098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn.2013.6614098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 22nd International Conference on Computer Communication and Networks (ICCCN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W112345847","https://openalex.org/W1483165234","https://openalex.org/W1518038022","https://openalex.org/W1562382568","https://openalex.org/W1572016165","https://openalex.org/W1591363587","https://openalex.org/W1742033587","https://openalex.org/W1825216778","https://openalex.org/W1847080476","https://openalex.org/W1972981713","https://openalex.org/W1993852360","https://openalex.org/W2018899347","https://openalex.org/W2021216254","https://openalex.org/W2057332538","https://openalex.org/W2109039688","https://openalex.org/W2115020004","https://openalex.org/W2131613942","https://openalex.org/W2137002702","https://openalex.org/W2141561793","https://openalex.org/W2143539682","https://openalex.org/W2164352834","https://openalex.org/W2164945803","https://openalex.org/W2170796499","https://openalex.org/W2330608237","https://openalex.org/W2365613379","https://openalex.org/W4302227757","https://openalex.org/W6604513283","https://openalex.org/W6630919106","https://openalex.org/W6634263594","https://openalex.org/W6638601623","https://openalex.org/W6707548318","https://openalex.org/W6728372283"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2209382646"],"abstract_inverted_index":{"Collective":[0],"operations,":[1,53,79],"such":[2],"as":[3,9],"all":[4],"reduce,":[5],"are":[6,33,73,84],"widely":[7],"treated":[8],"the":[10,55,62,66,94,125,132,147,158],"critical":[11],"limiting":[12],"factors":[13],"in":[14,18,36,121,140],"achieving":[15],"high":[16,67],"performance":[17],"massively":[19],"parallel":[20],"applications.":[21],"Conventional":[22],"host-based":[23,133],"implementations,":[24],"which":[25],"introduce":[26],"a":[27,45,99,103,136],"large":[28],"amount":[29],"of":[30,47,61,77],"point-to-point":[31,71],"communications,":[32],"less":[34,166],"efficient":[35,117],"large-scale":[37,122],"systems.":[38,123],"To":[39],"address":[40],"this":[41],"issue,":[42],"we":[43],"propose":[44],"design":[46,96],"switch":[48],"chip":[49],"to":[50,155],"accelerate":[51],"collective":[52],"especially":[54,120],"allreduce":[56,78,113,160],"operation.":[57],"The":[58,107],"major":[59],"advantage":[60],"proposed":[63,95],"solution":[64],"is":[65,115],"scalability":[68],"since":[69],"expensive":[70],"communications":[72],"avoided.":[74],"Two":[75],"kinds":[76],"namely":[80],"block-allreduce":[81],"and":[82,88,102,118],"burst-allreduce,":[83],"implemented":[85],"for":[86],"short":[87],"long":[89],"messages,":[90],"respectively.":[91],"We":[92],"evaluated":[93],"with":[97,135],"both":[98],"cycle-accurate":[100],"simulator":[101],"FPGA":[104],"prototype":[105],"system.":[106],"experimental":[108],"results":[109],"prove":[110],"that":[111],"switch-based":[112,128,159],"implementation":[114,129],"quite":[116],"scalable,":[119],"In":[124],"prototype,":[126],"our":[127],"significantly":[130],"outperforms":[131],"one,":[134],"16":[137,144],"times":[138],"improvement":[139],"MPI":[141],"time":[142],"on":[143],"nodes.":[145],"Furthermore,":[146],"simulation":[148],"shows":[149],"that,":[150],"upon":[151],"scaling":[152],"from":[153],"2":[154,168],"4096":[156],"nodes,":[157],"latency":[161],"only":[162],"increases":[163],"slightly":[164],"by":[165],"than":[167],"us.":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
