{"id":"https://openalex.org/W7124215587","doi":"https://doi.org/10.1109/icpads67057.2025.11323027","title":"Planning ECMP Paths with Minimal Overlap for Efficient Cross-Host Collective Communications","display_name":"Planning ECMP Paths with Minimal Overlap for Efficient Cross-Host Collective Communications","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124215587","doi":"https://doi.org/10.1109/icpads67057.2025.11323027"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5100646070","display_name":"Boyang Zhou","orcid":"https://orcid.org/0000-0003-0436-4293"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyang Zhou","raw_affiliation_strings":["Research Center for High Efficiency Computing Infrastructure, Zhejiang Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for High Efficiency Computing Infrastructure, Zhejiang Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013518014","display_name":"Chunming Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123002177","display_name":"Qiang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101833043","display_name":"Bin Hu","orcid":"https://orcid.org/0000-0003-4182-4180"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Hu","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.6184999942779541,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.6184999942779541,"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"}},{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.2581999897956848,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.024800000712275505,"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/randomness","display_name":"Randomness","score":0.6366999745368958},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5533999800682068},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4668999910354614},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.45239999890327454},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4429999887943268},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.4034999907016754},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3926999866962433},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.3767000138759613},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.36570000648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027999997138977},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5385000109672546},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5318999886512756},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C114809511","wikidata":"https://www.wikidata.org/wiki/Q1412924","display_name":"Flow network","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C77270119","wikidata":"https://www.wikidata.org/wiki/Q1655198","display_name":"Software-defined networking","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C67069471","wikidata":"https://www.wikidata.org/wiki/Q1140205","display_name":"IT service continuity","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46038663387298584,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W170020907","https://openalex.org/W1975303631","https://openalex.org/W2038861084","https://openalex.org/W2093030849","https://openalex.org/W2137793678","https://openalex.org/W2169246522","https://openalex.org/W2477023729","https://openalex.org/W2548640435","https://openalex.org/W2552554409","https://openalex.org/W3072623287","https://openalex.org/W3097013252","https://openalex.org/W3161886301","https://openalex.org/W4235670058","https://openalex.org/W4235732943","https://openalex.org/W4281931699","https://openalex.org/W4300550233","https://openalex.org/W4385245566","https://openalex.org/W4396680554","https://openalex.org/W4401176799","https://openalex.org/W4401176822","https://openalex.org/W4404955085","https://openalex.org/W4410950198","https://openalex.org/W4412610789","https://openalex.org/W4413757132","https://openalex.org/W4413757568","https://openalex.org/W4416429858"],"related_works":[],"abstract_inverted_index":{"In":[0,156],"data":[1],"center":[2],"networks,":[3],"cross-host":[4,40,59],"collective":[5],"communications":[6],"(CC)":[7],"for":[8,70],"LLM":[9,125],"training":[10,176],"often":[11],"suffer":[12],"from":[13],"ECMP's":[14],"hash-based":[15],"randomness":[16],"which":[17],"funnels":[18],"flows":[19],"onto":[20],"overlapping":[21],"spine-leaf":[22,89],"links,":[23],"creating":[24],"hotspots,":[25],"rank":[26],"stragglers,":[27],"and":[28,65,100,134,148],"degraded":[29],"CC":[30,44,138],"efficiency.":[31],"A":[32],"promising":[33],"yet":[34],"underexplored":[35],"approach":[36],"is":[37,68],"to":[38,61,103,145,153],"plan":[39],"paths":[41,60,86],"ahead":[42],"during":[43],"initialization.":[45],"This":[46],"leverages":[47],"host-side":[48,98],"steering,":[49,99],"exploiting":[50],"ECMP":[51],"hash":[52],"linearity":[53],"via":[54,96],"lightweight":[55],"packet-header":[56],"modification.":[57],"Assigning":[58],"minimize":[62],"link":[63,132],"overlap":[64,133],"balance":[66],"load":[67],"NP-complete":[69],"large-scale":[71],"networks.":[72],"To":[73],"address":[74],"this,":[75],"we":[76],"propose":[77],"PathPlanner,":[78],"a":[79,174],"centralized":[80],"service":[81],"that":[82,128],"heuristically":[83],"selects":[84],"near-optimal":[85],"with":[87,123],"minimal":[88],"overlaps,":[90],"generates":[91],"multiple":[92],"valid":[93],"source":[94],"ports":[95],"the":[97,113],"distributes":[101],"them":[102],"workers.":[104],"By":[105],"cycling":[106],"through":[107],"these":[108],"ports,":[109],"each":[110],"flow":[111,140],"traverses":[112],"intended":[114],"path":[115],"without":[116],"modifying":[117],"software":[118],"logics.":[119],"High-fidelity":[120],"SimAI":[121],"simulations":[122],"realistic":[124],"workloads":[126],"demonstrate":[127],"PathPlanner":[129],"significantly":[130],"reduces":[131],"straggler":[135],"effects,":[136],"cutting":[137],"primitive":[139],"completion":[141],"times":[142,150],"by":[143,151,164],"up":[144,152],"44.7":[146],"%":[147],"execution":[149],"21.35":[154],"%.":[155],"32-rank":[157],"Mixtral":[158],"training,":[159],"it":[160],"shortens":[161],"per-iteration":[162],"runtimes":[163],"1.6\u20132.1s,":[165],"yielding":[166],"estimated":[167],"cumulative":[168],"savings":[169],"of":[170],"2.65-3.52":[171],"days":[172],"over":[173],"complete":[175],"run.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}
