{"id":"https://openalex.org/W3048170716","doi":"https://doi.org/10.1145/3404397.3404426","title":"Detailed Analysis and Optimization of CUDA K-means Algorithm","display_name":"Detailed Analysis and Optimization of CUDA K-means Algorithm","publication_year":2020,"publication_date":"2020-08-09","ids":{"openalex":"https://openalex.org/W3048170716","doi":"https://doi.org/10.1145/3404397.3404426","mag":"3048170716"},"language":"en","primary_location":{"id":"doi:10.1145/3404397.3404426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404397.3404426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th International Conference on Parallel Processing - ICPP","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/A5084726014","display_name":"Martin Kruli\u0161","orcid":"https://orcid.org/0000-0002-0985-8949"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Kruli\u0161","raw_affiliation_strings":["Charles University, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University, Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081106885","display_name":"Miroslav Kratochv\u00edl","orcid":"https://orcid.org/0000-0001-7356-4075"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Miroslav Kratochv\u00edl","raw_affiliation_strings":["Charles University, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University, Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21250087"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"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/T11478","display_name":"Caching and Content Delivery","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9987999796867371,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8766231536865234},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7819979190826416},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7022020816802979},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.698118269443512},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6007130146026611},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5779879093170166},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4997398853302002},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.49762609601020813},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.464944988489151},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.45479705929756165},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4418051838874817},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44064226746559143},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31155961751937866},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2985968291759491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17930054664611816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8766231536865234},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7819979190826416},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7022020816802979},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.698118269443512},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6007130146026611},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5779879093170166},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4997398853302002},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.49762609601020813},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.464944988489151},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.45479705929756165},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4418051838874817},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44064226746559143},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31155961751937866},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2985968291759491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17930054664611816},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404397.3404426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404397.3404426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th International Conference on Parallel Processing - ICPP","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":18,"referenced_works":["https://openalex.org/W191714665","https://openalex.org/W797398368","https://openalex.org/W1159302035","https://openalex.org/W1971784203","https://openalex.org/W1993835819","https://openalex.org/W2063257142","https://openalex.org/W2099205848","https://openalex.org/W2114124472","https://openalex.org/W2160039585","https://openalex.org/W2171209182","https://openalex.org/W2261553819","https://openalex.org/W2464521989","https://openalex.org/W2773394213","https://openalex.org/W2797650988","https://openalex.org/W2799523655","https://openalex.org/W2887826853","https://openalex.org/W2891639990","https://openalex.org/W2916475468"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"K-means":[0],"is":[1],"one":[2],"of":[3,16,46,50,71,80,94,114,127],"the":[4,17,47,65,69,78,95,101,137,151],"most":[5],"frequently":[6],"used":[7],"algorithms":[8],"for":[9,103],"unsupervised":[10],"clustering":[11],"data":[12,39],"analysis.":[13],"Individual":[14],"steps":[15,53,130],"k-means":[18,51],"algorithm":[19],"include":[20],"nearest":[21],"neighbor":[22],"finding,":[23],"efficient":[24],"distance":[25],"computation,":[26],"and":[27,42,108,120,131],"cluster-wise":[28],"reduction,":[29],"which":[30],"may":[31],"be":[32],"generalized":[33],"to":[34],"many":[35,57,81],"other":[36,58],"purposes":[37],"in":[38,68,155],"analysis,":[40],"visualization,":[41],"machine":[43],"learning.":[44],"Efficiency":[45],"available":[48],"implementations":[49,97,154],"computation":[52,129],"therefore":[54],"directly":[55],"affect":[56],"applications.":[59],"In":[60],"this":[61,85],"work,":[62],"we":[63,87],"examine":[64],"performance":[66,92,139],"limits":[67],"context":[70],"modern":[72],"massively":[73],"parallel":[74],"GPU":[75,96,142],"accelerators.":[76],"Despite":[77],"existence":[79],"published":[82],"papers":[83],"on":[84,111,140],"topic,":[86],"have":[88],"found":[89],"that":[90,135],"crucial":[91],"aspects":[93],"remain":[98],"unaddressed,":[99],"including":[100],"optimizations":[102,134],"memory":[104],"bandwidth,":[105],"cache":[106],"limits,":[107],"workload":[109],"dispatching":[110],"problem":[112],"instances":[113],"varying":[115],"cluster":[116],"count,":[117],"dataset":[118],"size,":[119],"dimensionality.":[121],"We":[122],"present":[123],"a":[124],"detailed":[125],"analysis":[126],"individual":[128],"propose":[132],"several":[133],"improve":[136],"overall":[138],"contemporary":[141],"architectures.":[143],"Our":[144],"open-source":[145],"prototype":[146],"exhibits":[147],"significant":[148],"speedup":[149],"over":[150],"current":[152],"state-of-the-art":[153],"virtually":[156],"all":[157],"practical":[158],"scenarios.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}