{"id":"https://openalex.org/W1979256186","doi":"https://doi.org/10.1145/1964179.1964182","title":"A new method for GPU based irregular reductions and its application to k-means clustering","display_name":"A new method for GPU based irregular reductions and its application to k-means clustering","publication_year":2011,"publication_date":"2011-03-05","ids":{"openalex":"https://openalex.org/W1979256186","doi":"https://doi.org/10.1145/1964179.1964182","mag":"1979256186"},"language":"en","primary_location":{"id":"doi:10.1145/1964179.1964182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964179.1964182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units","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/A5041755993","display_name":"Balaji Dhanasekaran","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Balaji Dhanasekaran","raw_affiliation_strings":["Advanced Micro Devices, Inc","[Advanced Micro Devices Inc.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]},{"raw_affiliation_string":"[Advanced Micro Devices Inc.]","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036463155","display_name":"Norman Rubin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Norman Rubin","raw_affiliation_strings":["Advanced Micro Devices, Inc","[Advanced Micro Devices Inc.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]},{"raw_affiliation_string":"[Advanced Micro Devices Inc.]","institution_ids":["https://openalex.org/I1311921367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311921367"],"apc_list":null,"apc_paid":null,"fwci":5.2756,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95351259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9965000152587891,"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/T11106","display_name":"Data Management and Algorithms","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8299004435539246},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.761461615562439},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7453645467758179},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7450193762779236},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7267054319381714},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.511417806148529},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5038546919822693},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.48287490010261536},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4613160789012909},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4399757385253906},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4253700375556946},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16622960567474365},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12452083826065063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10150262713432312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09676435589790344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299004435539246},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.761461615562439},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7453645467758179},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7450193762779236},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7267054319381714},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.511417806148529},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5038546919822693},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.48287490010261536},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4613160789012909},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4399757385253906},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4253700375556946},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16622960567474365},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12452083826065063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10150262713432312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09676435589790344},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1964179.1964182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964179.1964182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units","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/W57462620","https://openalex.org/W191714665","https://openalex.org/W1562066701","https://openalex.org/W1634005169","https://openalex.org/W2022846158","https://openalex.org/W2036477303","https://openalex.org/W2065392434","https://openalex.org/W2066815973","https://openalex.org/W2095595785","https://openalex.org/W2122137926","https://openalex.org/W2128022558","https://openalex.org/W2132777634","https://openalex.org/W2140434878","https://openalex.org/W2150593711","https://openalex.org/W2207292641","https://openalex.org/W3017143921","https://openalex.org/W4212848460","https://openalex.org/W6637170354"],"related_works":["https://openalex.org/W1973046741","https://openalex.org/W2983282793","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/W2080146221","https://openalex.org/W2370314112"],"abstract_inverted_index":{"A":[0,19],"frequently":[1],"used":[2,41],"method":[3],"of":[4,16,123],"clustering":[5],"is":[6,23,35,50,59,103],"a":[7,28,31,42,69,200],"technique":[8],"called":[9],"k-means":[10,13,79],"clustering.":[11],"The":[12],"algorithm":[14,71],"consists":[15],"two":[17],"steps:":[18],"map":[20,48,87,170],"step,":[21,33],"which":[22,34,46],"simple":[24],"to":[25,78,148,193],"execute":[26],"on":[27,52,61,129,136,176,199],"GPU,":[29],"and":[30,55,75,88,128,171],"reduce":[32,57,89,172],"more":[36],"problematic.":[37],"Previous":[38],"researchers":[39],"have":[40],"hybrid":[43,109,150],"approach":[44],"in":[45],"the":[47,53,56,62,82,86,108,121,149,156,160,169,177,183],"step":[49,58],"computed":[51,175],"GPU":[54,83,157,185],"performed":[60],"CPU.":[63,178,205],"In":[64,152,165],"this":[65],"work,":[66],"we":[67,154],"present":[68],"new":[70,184],"for":[72,111,132],"irregular":[73],"reductions":[74],"apply":[76],"it":[77],"such":[80],"that":[81,100,166],"executes":[84],"both":[85,168],"steps.":[90],"We":[91],"provide":[92],"experimental":[93],"comparisons":[94],"using":[95],"OpenCL.":[96],"Our":[97],"results":[98],"show":[99],"our":[101],"scheme":[102,110,186],"3.2":[104],"times":[105,118,195],"faster":[106,119,196],"than":[107,197],"k":[112,125,133],"=":[113,126,134],"10,":[114],"an":[115,137],"average":[116,130],"1.5":[117],"when":[120],"number":[122],"clusters,":[124],"100":[127],"equal":[131],"400,":[135],"ATI":[138],"Radeon\u00ae":[139],"HD":[140],"5870":[141],"(best":[142],"speedup":[143],"was":[144],"3.5":[145],"times)":[146],"compared":[147],"approach.":[151],"addition,":[153],"compare":[155],"code":[158],"with":[159,190],"standard":[161],"OpenMP":[162],"benchmark,":[163],"MineBench.":[164],"implementation,":[167],"steps":[173],"are":[174],"For":[179],"large":[180],"data":[181],"sizes,":[182],"shows":[187],"great":[188],"promise,":[189],"performance":[191],"up":[192],"35":[194],"MineBench":[198],"four":[201],"core":[202],"Intel":[203],"i7":[204]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}