{"id":"https://openalex.org/W4413144476","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00016","title":"Collaborative Bandwidth-Efficient Intra-Node Allreduce","display_name":"Collaborative Bandwidth-Efficient Intra-Node Allreduce","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4413144476","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00016"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","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/A5031362631","display_name":"Amirhossein Sojoodi","orcid":"https://orcid.org/0000-0001-9877-3201"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Amirhossein Sojoodi","raw_affiliation_strings":["Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada"],"affiliations":[{"raw_affiliation_string":"Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119281787","display_name":"Ali Farazdaghi","orcid":"https://orcid.org/0009-0006-7112-5080"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ali Farazdaghi","raw_affiliation_strings":["Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada"],"affiliations":[{"raw_affiliation_string":"Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114553985","display_name":"Hamed Sharifian","orcid":"https://orcid.org/0009-0002-2275-3313"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hamed Sharifian","raw_affiliation_strings":["Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada"],"affiliations":[{"raw_affiliation_string":"Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009842811","display_name":"Ryan E. Grant","orcid":"https://orcid.org/0000-0002-0163-3892"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ryan E. Grant","raw_affiliation_strings":["Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada"],"affiliations":[{"raw_affiliation_string":"Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039854005","display_name":"Ahmad Afsahi","orcid":"https://orcid.org/0000-0002-2924-6851"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Afsahi","raw_affiliation_strings":["Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada"],"affiliations":[{"raw_affiliation_string":"Queen’s University,Department of Electrical and Computer Engineering,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031362631"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23363025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9567000269889832,"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"}},"topics":[{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9567000269889832,"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"}},{"id":"https://openalex.org/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9099000096321106,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9035000205039978,"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":0.6507152318954468},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6283804178237915},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5050259232521057},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.48880502581596375},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10417395830154419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507152318954468},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6283804178237915},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5050259232521057},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.48880502581596375},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10417395830154419},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"concept":[1],"of":[2,71],"GPU-aware":[3],"multi-path":[4,27,50],"communication":[5,28,43,51],"and":[6,33,49,58,68,80,93,125],"heterogeneous":[7,47],"computing":[8,17,20,48,69],"is":[9],"pivotal":[10],"in":[11],"enhancing":[12],"HPC":[13],"cluster":[14],"performance.":[15],"Heterogeneous":[16],"utilizes":[18,46],"various":[19,123],"units":[21],"to":[22,90,112,115,122],"boost":[23],"distributed":[24],"applications,":[25],"while":[26],"frameworks":[29],"optimize":[30],"data":[31,66],"transfer":[32,67],"reduce":[34],"latency.":[35],"This":[36],"study":[37],"proposes":[38],"a":[39,77,83],"collaborative":[40],"Allreduce":[41,104],"collective":[42],"framework":[44,101],"that":[45,99],"for":[52,106,132],"multi-GPU":[53,85],"systems.":[54],"Leveraging":[55],"GPU":[56],"parallelism":[57],"high":[59],"memory":[60],"bandwidth,":[61],"our":[62,100],"approach":[63,118],"optimizes":[64],"both":[65],"power":[70],"the":[72,133],"host":[73],"system.":[74],"We":[75],"provide":[76],"proof-of-concept":[78],"implementation":[79],"evaluation":[81],"on":[82],"single-node":[84],"system,":[86],"comparing":[87],"its":[88],"performance":[89,105],"NCCL,":[91],"UCC,":[92],"other":[94],"algorithms.":[95],"Our":[96,117],"results":[97],"show":[98],"can":[102,119],"improve":[103],"large":[107],"message":[108],"sizes":[109],"by":[110],"up":[111],"1.45x":[113],"compared":[114],"NCCL.":[116],"be":[120],"extended":[121],"topologies":[124],"systems,":[126],"with":[127],"more":[128],"extensive":[129],"evaluations":[130],"planned":[131],"future.":[134]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}