{"id":"https://openalex.org/W4414170464","doi":"https://doi.org/10.1109/iwqos65803.2025.11143446","title":"HiPIPE: Adaptive-Chunk Pipeline Scheduling for Hierarchical Collective Communication","display_name":"HiPIPE: Adaptive-Chunk Pipeline Scheduling for Hierarchical Collective Communication","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414170464","doi":"https://doi.org/10.1109/iwqos65803.2025.11143446"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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/A5114860546","display_name":"Xin Song","orcid":"https://orcid.org/0009-0001-2759-4000"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xin Song","raw_affiliation_strings":["Huawei Technologies,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044077636","display_name":"Manaf Bin-Yahya","orcid":"https://orcid.org/0000-0003-3688-1594"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Manaf Bin-Yahya","raw_affiliation_strings":["Huawei Technologies,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073778515","display_name":"Amir Shani","orcid":"https://orcid.org/0000-0002-4614-5315"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amir Shani","raw_affiliation_strings":["Huawei Technologies,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Canada","institution_ids":["https://openalex.org/I4210115038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210115038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21855984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9944000244140625,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9944000244140625,"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":0.9908000230789185,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.989799976348877,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6891000270843506},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.6643000245094299},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.49480000138282776},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/telecommunications-network","display_name":"Telecommunications network","score":0.4032999873161316},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.37279999256134033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199999928474426},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6984000205993652},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6891000270843506},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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":21,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1572016165","https://openalex.org/W2131613942","https://openalex.org/W2963956318","https://openalex.org/W3072623287","https://openalex.org/W3129488589","https://openalex.org/W3190806564","https://openalex.org/W3193985311","https://openalex.org/W4281790033","https://openalex.org/W4380874786","https://openalex.org/W4381886086","https://openalex.org/W4386709668","https://openalex.org/W4391136507","https://openalex.org/W4400680348","https://openalex.org/W4401176521","https://openalex.org/W4401176799","https://openalex.org/W4401176822","https://openalex.org/W4402896827","https://openalex.org/W4402897082","https://openalex.org/W4404955085","https://openalex.org/W4412610442"],"related_works":[],"abstract_inverted_index":{"Multi-dimensional":[0],"networks":[1],"have":[2],"become":[3],"the":[4,25,115],"standard":[5],"for":[6,70],"interconnecting":[7],"GPUs":[8],"to":[9,44,55,113,160],"support":[10],"large-scale":[11],"distributed":[12],"machine":[13],"learning":[14],"(ML)":[15],"training,":[16],"driven":[17],"by":[18],"increasing":[19],"computational":[20],"and":[21,87,98,123,144],"memory":[22],"demands.":[23],"However,":[24],"inherent":[26],"bandwidth":[27,100,156],"heterogeneity":[28],"across":[29,81,140],"network":[30,142],"dimensions":[31],"poses":[32],"a":[33,67,109],"significant":[34],"challenge":[35],"in":[36],"efficiently":[37],"scheduling":[38,80],"collective":[39,73],"operations,":[40],"such":[41],"as":[42,108],"AllReduce,":[43],"minimize":[45],"communication":[46,96,149],"time.":[47],"Existing":[48],"hierarchical":[49],"approaches":[50,139],"suffer":[51],"from":[52],"inefficiencies":[53],"due":[54],"static":[56],"or":[57],"suboptimal":[58],"pipeline":[59,121],"structures":[60],"with":[61],"uniform-sized":[62],"chunks.":[63],"We":[64],"propose":[65],"HiPIPE,":[66],"novel":[68],"solution":[69],"multi-dimensional":[71],"All-Reduce":[72],"communication,":[74],"incorporating":[75],"three":[76],"key":[77],"optimizations:":[78],"chunk":[79,85,89,105,117],"all":[82],"dimensions,":[83],"adaptive":[84],"sizing,":[86],"dynamic":[88],"number":[90],"selection.":[91],"These":[92],"techniques":[93],"collectively":[94],"enhance":[95],"efficiency":[97],"maximize":[99],"utilization.":[101],"Particularly,":[102],"we":[103],"formulate":[104],"size":[106],"optimization":[107],"linear":[110],"programming":[111],"problem":[112],"derive":[114],"optimal":[116],"sizes,":[118],"significantly":[119],"reducing":[120],"bubbles":[122],"improving":[124],"overall":[125],"performance.":[126],"Extensive":[127],"experiments":[128],"using":[129],"real-testbed":[130],"emulation":[131],"demonstrate":[132],"that":[133],"HiPIPE":[134],"consistently":[135],"outperforms":[136],"state-of-the-art":[137],"(SOTA)":[138],"diverse":[141],"topologies":[143],"configurations,":[145],"achieving":[146],"an":[147],"average":[148],"time":[150],"reduction":[151],"of":[152,158],"28.85%":[153],"while":[154],"sustaining":[155],"utilization":[157],"up":[159],"98.11%.":[161]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}