{"id":"https://openalex.org/W2047728798","doi":"https://doi.org/10.1109/ipdps.2010.5470429","title":"Large-scale multi-dimensional document clustering on GPU clusters","display_name":"Large-scale multi-dimensional document clustering on GPU clusters","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2047728798","doi":"https://doi.org/10.1109/ipdps.2010.5470429","mag":"2047728798"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","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/A5101414442","display_name":"Yongpeng Zhang","orcid":"https://orcid.org/0000-0001-7955-5524"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yongpeng Zhang","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA","Dept. of Computer Science, North Carolina State University, Raleigh, NC 27695-7534"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Dept. of Computer Science, North Carolina State University, Raleigh, NC 27695-7534","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031749427","display_name":"Frank Mueller","orcid":"https://orcid.org/0000-0002-0258-0294"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Mueller","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA","Dept. of Computer Science, North Carolina State University, Raleigh, NC 27695-7534"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Dept. of Computer Science, North Carolina State University, Raleigh, NC 27695-7534","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041280931","display_name":"Xiaohui Cui","orcid":"https://orcid.org/0000-0001-6079-009X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Cui","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","Oak Ridge National Laboratory,Computational Sciences and Engineering Division,Oak Ridge,TN,37831"],"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory,Computational Sciences and Engineering Division,Oak Ridge,TN,37831","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000241304","display_name":"Thomas E. Potok","orcid":"https://orcid.org/0000-0001-6687-3435"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Potok","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","Oak Ridge National Laboratory,Computational Sciences and Engineering Division,Oak Ridge,TN,37831"],"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory,Computational Sciences and Engineering Division,Oak Ridge,TN,37831","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101414442"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":4.7345,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95414708,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9984999895095825,"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":0.9983000159263611,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.858639657497406},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7972062826156616},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6458188891410828},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6164015531539917},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5177649259567261},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4607703387737274},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.43657630681991577},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.42510777711868286},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.41189634799957275},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.34075507521629333},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33979061245918274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19385552406311035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1829652488231659},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08846494555473328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.858639657497406},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7972062826156616},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6458188891410828},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6164015531539917},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5177649259567261},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4607703387737274},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.43657630681991577},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.42510777711868286},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.41189634799957275},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.34075507521629333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33979061245918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19385552406311035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1829652488231659},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08846494555473328},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2010.5470429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.5832","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.5832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://moss.csc.ncsu.edu/~mueller/ftp/pub/mueller/papers/ipdps10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1507533931","https://openalex.org/W1530060812","https://openalex.org/W1651093245","https://openalex.org/W1978394996","https://openalex.org/W2033286692","https://openalex.org/W2036477303","https://openalex.org/W2097101478","https://openalex.org/W2098162425","https://openalex.org/W2104624750","https://openalex.org/W2122137926","https://openalex.org/W2128022558","https://openalex.org/W2129692177","https://openalex.org/W2139131532","https://openalex.org/W2141579716","https://openalex.org/W2150312211","https://openalex.org/W2165236847","https://openalex.org/W2605699756","https://openalex.org/W2733264231","https://openalex.org/W4250996537","https://openalex.org/W6674403372","https://openalex.org/W6674809819","https://openalex.org/W6678493076","https://openalex.org/W6679290893","https://openalex.org/W6680965528","https://openalex.org/W6736347439"],"related_works":["https://openalex.org/W2011430815","https://openalex.org/W4321606653","https://openalex.org/W2056717482","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W2092007952","https://openalex.org/W2548246577","https://openalex.org/W2096672917"],"abstract_inverted_index":{"Document":[0],"clustering":[1,14,39],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,31,43,69,132,182],"data":[7,167,187],"mining":[8,168],"systems.":[9],"Recently,":[10],"a":[11,75,80,110,133,143],"flocking-based":[12,118],"document":[13,119],"algorithm":[15],"has":[16],"been":[17],"proposed":[18],"to":[19,37,52,112,125,142,163,189],"solve":[20,165],"the":[21,26,44,47,53,63,70,92,96,115,158,174,183,190],"problem":[22],"through":[23],"simulation":[24],"resembling":[25],"flocking":[27],"behavior":[28],"of":[29,58,72,85,94,99,117,160,185,192],"birds":[30],"nature.":[32],"This":[33],"method":[34],"is":[35,49,61,66],"superior":[36],"other":[38],"algorithms,":[40],"including":[41],"k-means,":[42],"sense":[45],"that":[46,62],"outcome":[48],"not":[50],"sensitive":[51],"initial":[54],"state.":[55],"One":[56],"limitation":[57],"this":[59,88],"approach":[60],"algorithmic":[64],"complexity":[65],"inherently":[67],"quadratic":[68],"number":[71,84],"documents.":[73,86],"As":[74],"result,":[76],"execution":[77],"time":[78],"becomes":[79],"bottleneck":[81],"with":[82,103,146,173],"large":[83],"In":[87],"paper,":[89],"we":[90,152],"assess":[91],"benefits":[93],"exploiting":[95],"computational":[97],"power":[98],"Beowulf-like":[100],"clusters":[101,162],"equipped":[102],"contemporary":[104],"Graphics":[105],"Processing":[106],"Units":[107],"(GPUs)":[108],"as":[109],"means":[111],"significantly":[113],"reduce":[114],"runtime":[116],"clustering.":[120],"Our":[121],"framework":[122],"scales":[123],"up":[124],"over":[126],"one":[127],"million":[128],"documents":[129],"processed":[130],"simultaneously":[131],"sixteen-node":[134],"moderate":[135],"GPU":[136,161],"cluster.":[137],"Results":[138],"are":[139,180],"also":[140],"compared":[141],"four-node":[144],"cluster":[145],"higher-end":[147],"GPUs.":[148],"On":[149],"these":[150],"clusters,":[151],"observe":[153],"30X-50X":[154],"speedups,":[155],"which":[156],"demonstrate":[157],"potential":[159,176],"efficiently":[164],"massive":[166],"problems.":[169],"Such":[170],"speedups":[171],"combined":[172],"scalability":[175],"and":[177],"accelerator-based":[178],"parallelization":[179],"unique":[181],"domain":[184],"document-based":[186],"mining,":[188],"best":[191],"our":[193],"knowledge.":[194]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}