{"id":"https://openalex.org/W4411866825","doi":"https://doi.org/10.1109/jiot.2025.3584768","title":"DirectReduce: A Scalable Ring AllReduce Offloading Architecture for Torus Topologies","display_name":"DirectReduce: A Scalable Ring AllReduce Offloading Architecture for Torus Topologies","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4411866825","doi":"https://doi.org/10.1109/jiot.2025.3584768"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2025.3584768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3584768","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5078633929","display_name":"Lihuan Hui","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lihuan Hui","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0002-9923-356X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762363","display_name":"Wang Yang","orcid":"https://orcid.org/0000-0003-0774-9762"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0774-9762","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082402770","display_name":"Fan Wu","orcid":"https://orcid.org/0000-0003-3615-1217"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3615-1217","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605035","display_name":"Yanbo Wang","orcid":"https://orcid.org/0000-0002-6034-8012"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbo Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6034-8012","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035157184","display_name":"Feng Lyu","orcid":"https://orcid.org/0000-0002-2990-5415"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lyu","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2990-5415","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069049205","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0001-6717-461X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6717-461X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078633929"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":2.1733,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89161287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"12","issue":"16","first_page":"32951","last_page":"32964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10126","display_name":"Logic, programming, and type systems","score":0.9401000142097473,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.9401000142097473,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/network-topology","display_name":"Network topology","score":0.7879670858383179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642982006072998},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6329448819160461},{"id":"https://openalex.org/keywords/torus","display_name":"Torus","score":0.6237775683403015},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5329514741897583},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5255516767501831},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46123528480529785},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4598478078842163},{"id":"https://openalex.org/keywords/ring","display_name":"Ring (chemistry)","score":0.4432765543460846},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1719406247138977}],"concepts":[{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.7879670858383179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642982006072998},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6329448819160461},{"id":"https://openalex.org/C9767117","wikidata":"https://www.wikidata.org/wiki/Q12510","display_name":"Torus","level":2,"score":0.6237775683403015},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5329514741897583},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5255516767501831},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46123528480529785},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4598478078842163},{"id":"https://openalex.org/C2780378348","wikidata":"https://www.wikidata.org/wiki/Q25351438","display_name":"Ring (chemistry)","level":2,"score":0.4432765543460846},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1719406247138977},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3584768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3584768","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1491834576","display_name":null,"funder_award_id":"2023SK2020","funder_id":"https://openalex.org/F4320330214","funder_display_name":"Key Research and Development Program of Hunan Province of China"},{"id":"https://openalex.org/G1638672902","display_name":null,"funder_award_id":"62072474","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2795870502","display_name":null,"funder_award_id":"2024JJ4068","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G4016464524","display_name":null,"funder_award_id":"62320106006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4756823131","display_name":null,"funder_award_id":"1053320211421","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6863796122","display_name":null,"funder_award_id":"62372472","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320330214","display_name":"Key Research and Development Program of Hunan Province of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1572016165","https://openalex.org/W2097982440","https://openalex.org/W2131613942","https://openalex.org/W2160054705","https://openalex.org/W2407746682","https://openalex.org/W2562244919","https://openalex.org/W2767393956","https://openalex.org/W2892809916","https://openalex.org/W2899187877","https://openalex.org/W2899266172","https://openalex.org/W2905104204","https://openalex.org/W2913662728","https://openalex.org/W2946986405","https://openalex.org/W2979567330","https://openalex.org/W2981086990","https://openalex.org/W3016395792","https://openalex.org/W3091097978","https://openalex.org/W3161014634","https://openalex.org/W3161432682","https://openalex.org/W3177554119","https://openalex.org/W3190806564","https://openalex.org/W3206778761","https://openalex.org/W4238128135","https://openalex.org/W4242634435","https://openalex.org/W4282970470","https://openalex.org/W4320018413","https://openalex.org/W4327911839","https://openalex.org/W4381886086","https://openalex.org/W4383989053","https://openalex.org/W4389722097","https://openalex.org/W4390044398","https://openalex.org/W4391013613","https://openalex.org/W4391929663","https://openalex.org/W4400678983","https://openalex.org/W4400876885","https://openalex.org/W4401352466","https://openalex.org/W4401878997","https://openalex.org/W4404035432","https://openalex.org/W4404238200","https://openalex.org/W4407129061","https://openalex.org/W4407784078","https://openalex.org/W6748645090","https://openalex.org/W6756439839","https://openalex.org/W6760703128","https://openalex.org/W6776186991","https://openalex.org/W6792106764","https://openalex.org/W6794216301","https://openalex.org/W6839137647"],"related_works":["https://openalex.org/W2167530280","https://openalex.org/W3124916295","https://openalex.org/W2022411416","https://openalex.org/W2146447767","https://openalex.org/W1487790116","https://openalex.org/W3197597876","https://openalex.org/W4248544590","https://openalex.org/W4396520414","https://openalex.org/W4381247976","https://openalex.org/W2038335296"],"abstract_inverted_index":{"The":[0,68,79],"all-reduce":[1,32,65,69,100,180],"operation":[2],"is":[3,103,147],"critically":[4],"important":[5],"for":[6,113,127,132,148],"communication-intensive":[7],"workloads":[8],"emerging":[9],"at":[10],"the":[11,31,59,62,74,109,124,138,143,158,168,178,204],"convergence":[12],"of":[13,19,61,105],"High-Performance":[14],"Computing":[15],"(HPC)":[16],"and":[17,156,196],"Internet":[18],"Things":[20],"(IoT)":[21],"applications.":[22],"However,":[23],"existing":[24],"optimization":[25],"efforts":[26],"primarily":[27],"concentrate":[28],"on":[29,90,167],"offloading":[30,98],"onto":[33],"network":[34],"switches,":[35],"known":[36],"as":[37],"In-Network":[38],"Aggregation,":[39],"which":[40,141],"are":[41],"incompatible":[42],"with":[43],"switchless":[44],"torus":[45],"topologies.":[46],"Driven":[47],"by":[48,182],"our":[49],"systematic":[50],"analysis,":[51],"we":[52,93],"identified":[53],"two":[54],"key":[55],"factors":[56],"that":[57,102,174],"impact":[58],"performance":[60],"standard":[63,205],"ring":[64,99,179,188,206],"operation:":[66],"i.":[67],"computation":[70,76],"process":[71],"frequently":[72],"interrupts":[73],"GPU/CPU\u2019s":[75],"tasks;":[77],"ii.":[78],"GPU/CPU":[80],"is,":[81],"in":[82,186,192,198],"fact,":[83],"indifferent":[84],"to":[85,117,123,162,184,203],"intermediate":[86,149],"computational":[87],"results.":[88],"Based":[89],"this":[91],"insight,":[92],"propose":[94],"DirectReduce,":[95],"a":[96,187,193,199],"fully":[97],"architecture":[101],"comprised":[104],"three":[106],"components:":[107],"(i)":[108],"GateKeeper":[110],"module,":[111,140,160],"responsible":[112],"evaluating":[114],"outgoing":[115],"data":[116,145],"decide":[118],"its":[119],"progression-either":[120],"directing":[121],"it":[122,131],"Protocol":[125],"Engine":[126],"packetization":[128],"or":[129,152],"intercepting":[130],"reduction":[133,151,164],"(e.g.,":[134],"sum,":[135],"maximum);":[136],"(ii)":[137],"DataDirector":[139],"classifies":[142],"incoming":[144],"either":[146],"result":[150,154],"final":[153],"storage;":[155],"(iii)":[157],"ComputeEnhancer":[159],"designed":[161],"execute":[163],"operations":[165],"directly":[166],"SmartNIC.":[169],"Extensive":[170],"simulation":[171],"results":[172],"show":[173],"DirectReduce":[175],"can":[176],"reduce":[177],"latency":[181],"up":[183],"1.98X":[185],"(1D-torus)":[189],"topology,":[190,195],"1.97X":[191],"3D-torus":[194],"1.75X":[197],"6D-torus":[200],"topology":[201],"compared":[202],"all-reduce.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
