{"id":"https://openalex.org/W7129022394","doi":"https://doi.org/10.1109/mascots67699.2025.11283230","title":"Parameterized Algorithms and Parameter Selection for Fast GPU-GPU Collective Communication","display_name":"Parameterized Algorithms and Parameter Selection for Fast GPU-GPU Collective Communication","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W7129022394","doi":"https://doi.org/10.1109/mascots67699.2025.11283230"},"language":null,"primary_location":{"id":"doi:10.1109/mascots67699.2025.11283230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots67699.2025.11283230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 33rd International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","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/A5102862237","display_name":"Peizhi Liu","orcid":"https://orcid.org/0009-0007-3446-6019"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peizhi Liu","raw_affiliation_strings":["Northwestern University Evanston,Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University Evanston,Chicago","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126162725","display_name":"Sean Rhee","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Rhee","raw_affiliation_strings":["Northwestern University Evanston,Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University Evanston,Chicago","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034029332","display_name":"Michael Wilkins","orcid":"https://orcid.org/0000-0003-0806-1599"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wilkins","raw_affiliation_strings":["Argonne National Laboratory,Lemont,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory,Lemont,United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077304920","display_name":"Peter A. Dinda","orcid":"https://orcid.org/0000-0001-5315-5987"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Dinda","raw_affiliation_strings":["Northwestern University Evanston,Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University Evanston,Chicago","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5759000182151794,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5759000182151794,"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":0.3391999900341034,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.7454000115394592},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6916000247001648},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5242999792098999},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/selection-algorithm","display_name":"Selection algorithm","score":0.4244999885559082},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.42250001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750999927520752},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7454000115394592},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6916000247001648},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5453000068664551},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.4244999885559082},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4104999899864197},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mascots67699.2025.11283230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots67699.2025.11283230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 33rd International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1558115001","https://openalex.org/W2029023406","https://openalex.org/W2042120213","https://openalex.org/W2057332538","https://openalex.org/W2102061396","https://openalex.org/W2109008148","https://openalex.org/W2131613942","https://openalex.org/W2155187164","https://openalex.org/W2161708191","https://openalex.org/W2170796499","https://openalex.org/W3047038256","https://openalex.org/W3072623287","https://openalex.org/W3217045543","https://openalex.org/W4282970470","https://openalex.org/W4386768656","https://openalex.org/W4388855519","https://openalex.org/W4394805246","https://openalex.org/W4396790354"],"related_works":[],"abstract_inverted_index":{"High-performance":[0],"collective":[1,21,54],"communication":[2],"among":[3],"GPUs":[4],"in":[5],"modern":[6],"supercomputers":[7,93],"is":[8],"crucial":[9],"for":[10,35,77],"enabling":[11],"many":[12],"applications.":[13],"Complex":[14],"hierarchical":[15],"interconnects":[16],"between":[17],"GPU":[18,53],"devices":[19],"necessitate":[20],"algorithms":[22,34,98],"that":[23,95],"can":[24,67,99],"effectively":[25],"leverage":[26],"the":[27,120],"underlying":[28],"network":[29],"topology.":[30],"We":[31],"present":[32],"parameterized":[33,97],"two":[36],"GPU-to-GPU":[37],"collectives,":[38],"Allgather":[39],"and":[40,81,90],"Allreduce,":[41],"as":[42,44],"well":[43],"an":[45],"optimized":[46],"permutation":[47],"kernel":[48],"used":[49],"to":[50,73],"further":[51],"enhance":[52],"communication.":[55],"By":[56],"employing":[57],"a":[58,103],"LogGP-based":[59],"model":[60],"calibrated":[61],"with":[62,111],"real":[63],"machine":[64],"measurements,":[65],"we":[66],"efficiently":[68],"simulate":[69],"various":[70],"parameter":[71,113],"choices":[72],"identify":[74],"optimal":[75],"settings":[76],"specific":[78],"device":[79],"allocations":[80],"message":[82],"sizes.":[83],"Our":[84],"comprehensive":[85],"evaluation":[86],"on":[87,101],"NCSA":[88],"Delta":[89],"Argonne":[91],"Polaris":[92],"demonstrates":[94],"our":[96,112],"achieve,":[100],"average,":[102],"$20":[104],"\\%$":[105,118],"speedup":[106],"over":[107],"their":[108],"non-parameterized":[109],"counterparts,":[110],"selection":[114],"process":[115],"capturing":[116],"$98":[117],"of":[119],"potential":[121],"speedup.":[122]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-17T00:00:00"}