{"id":"https://openalex.org/W4415124464","doi":"https://doi.org/10.1109/icnp65844.2025.11192370","title":"TuCCL: Tailored and Unified Configuration Optimizations for High-Performance Collective Communication Library","display_name":"TuCCL: Tailored and Unified Configuration Optimizations for High-Performance Collective Communication Library","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4415124464","doi":"https://doi.org/10.1109/icnp65844.2025.11192370"},"language":"en","primary_location":{"id":"doi:10.1109/icnp65844.2025.11192370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnp65844.2025.11192370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","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/A5000421284","display_name":"Ziming Li","orcid":"https://orcid.org/0000-0002-3647-8140"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziming Li","raw_affiliation_strings":["Northeastern University,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093548286","display_name":"Chenyang Hei","orcid":"https://orcid.org/0000-0001-5010-1529"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Hei","raw_affiliation_strings":["Northeastern University,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083598234","display_name":"Fuliang Li","orcid":"https://orcid.org/0000-0001-9782-0053"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuliang Li","raw_affiliation_strings":["Northeastern University,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tongrui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongrui Liu","raw_affiliation_strings":["Northeastern University,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106856666","display_name":"Chengxi Gao","orcid":"https://orcid.org/0000-0003-1386-7394"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengxi Gao","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043755655","display_name":"Xiuzhu Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuzhu Sha","raw_affiliation_strings":["Northeastern University,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326915","display_name":"Xingwei Wang","orcid":"https://orcid.org/0000-0003-2856-4716"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Wang","raw_affiliation_strings":["Northeastern University,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000421284"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24514392,"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":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9383000135421753,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/sketch","display_name":"Sketch","score":0.6546000242233276},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4934999942779541},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4715000092983246},{"id":"https://openalex.org/keywords/configuration-space","display_name":"Configuration space","score":0.4293000102043152},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.38449999690055847},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.33169999718666077},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.3278000056743622},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3118000030517578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051999807357788},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5694000124931335},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C90738871","wikidata":"https://www.wikidata.org/wiki/Q41642869","display_name":"Configuration space","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C10451660","wikidata":"https://www.wikidata.org/wiki/Q5160113","display_name":"Configuration design","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnp65844.2025.11192370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnp65844.2025.11192370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2535374105","https://openalex.org/W2963096510","https://openalex.org/W3072623287","https://openalex.org/W3117684406","https://openalex.org/W3193250980","https://openalex.org/W3193985311","https://openalex.org/W3206778761","https://openalex.org/W4312060029","https://openalex.org/W4317883989","https://openalex.org/W4318541593","https://openalex.org/W4360831831","https://openalex.org/W4378895279","https://openalex.org/W4386486713","https://openalex.org/W4388010208","https://openalex.org/W4395073435","https://openalex.org/W4401175629","https://openalex.org/W4401176822"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"distributed":[1],"training":[2,123],"systems":[3,102],"face":[4],"escalating":[5],"communication":[6,18,59],"bottlenecks":[7],"as":[8],"GPU":[9],"clusters":[10],"scale":[11],"to":[12],"accommodate":[13],"large":[14],"models.":[15],"While":[16],"collective":[17],"libraries":[19],"and":[20,42,61,82,120],"automated":[21],"synthesizers":[22],"address":[23],"algorithmic":[24],"efficiency,":[25],"they":[26],"suffer":[27],"from":[28],"three":[29,65],"critical":[30],"limitations":[31],"including":[32],"labor-intensive":[33],"manual":[34],"intervention":[35],"requirement,":[36],"overreliance":[37],"on":[38,109],"predefined":[39],"input":[40],"optimization,":[41],"suboptimal":[43],"isolated":[44],"configuration":[45,89,115],"optimization.":[46],"To":[47],"solve":[48],"these":[49],"problems,":[50],"we":[51],"present":[52],"TuCCL,":[53],"a":[54],"systematic":[55],"framework":[56],"that":[57,70],"co-optimizes":[58],"algorithms":[60],"runtime":[62],"parameters":[63],"through":[64],"innovations:":[66],"Topology-Aware":[67],"Sketch":[68],"Generation":[69],"automatically":[71],"produces":[72],"high-performance":[73],"primitives,":[74],"Hierarchical":[75],"Configuration":[76,85],"Optimization":[77,86],"modeling":[78],"nonlinear":[79],"parameter-performance":[80],"relationships,":[81],"Multi-phase":[83],"Resource-Aware":[84],"enabling":[87],"joint":[88],"tuning":[90],"with":[91,103],"adaptive":[92],"search":[93,116],"space":[94],"pruning.":[95],"Evaluations":[96],"demonstrate":[97],"TuCCL\u2019s":[98],"superiority":[99],"over":[100],"state-of-the-art":[101],"1.75x\u201311.49x":[104],"bandwidth":[105],"improvements":[106],"for":[107],"AllGather/AllReduce":[108],"NVIDIA":[110],"V100/A100":[111],"clusters,":[112],"90.2%":[113],"faster":[114],"than":[117],"grid":[118],"methods,":[119],"1.22x-2.52x":[121],"end-to-end":[122],"speedups":[124],"across":[125],"diverse":[126],"model":[127],"scales.":[128]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-14T00:00:00"}
