{"id":"https://openalex.org/W2095890830","doi":"https://doi.org/10.1109/ipdps.2010.5470445","title":"High performance comparison-based sorting algorithm on many-core GPUs","display_name":"High performance comparison-based sorting algorithm on many-core GPUs","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2095890830","doi":"https://doi.org/10.1109/ipdps.2010.5470445","mag":"2095890830"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470445","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":"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/A5023098180","display_name":"Xiaochun Ye","orcid":"https://orcid.org/0000-0003-4598-1685"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Ye","raw_affiliation_strings":["Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011407484","display_name":"Dongrui Fan","orcid":"https://orcid.org/0000-0001-5219-0908"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongrui Fan","raw_affiliation_strings":["Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037140449","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0003-4075-7414"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102155488","display_name":"Nan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Yuan","raw_affiliation_strings":["Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020575991","display_name":"Paolo Ienne","orcid":"https://orcid.org/0000-0002-6142-7345"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Paolo Ienne","raw_affiliation_strings":["Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","School of Computer and Communication Sciences, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer System and Architecture, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"School of Computer and Communication Sciences, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9129,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.96021565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8921893835067749},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8158294558525085},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.760447084903717},{"id":"https://openalex.org/keywords/merge-algorithm","display_name":"Merge algorithm","score":0.7427312731742859},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5309360027313232},{"id":"https://openalex.org/keywords/merge-sort","display_name":"Merge sort","score":0.5295729637145996},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.4806155562400818},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.4309839606285095},{"id":"https://openalex.org/keywords/quicksort","display_name":"Quicksort","score":0.42854470014572144},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4274812340736389},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37236836552619934},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.07861986756324768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8921893835067749},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8158294558525085},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.760447084903717},{"id":"https://openalex.org/C140086265","wikidata":"https://www.wikidata.org/wiki/Q11341754","display_name":"Merge algorithm","level":4,"score":0.7427312731742859},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5309360027313232},{"id":"https://openalex.org/C35555965","wikidata":"https://www.wikidata.org/wiki/Q189057","display_name":"Merge sort","level":4,"score":0.5295729637145996},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.4806155562400818},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.4309839606285095},{"id":"https://openalex.org/C2778937211","wikidata":"https://www.wikidata.org/wiki/Q486598","display_name":"Quicksort","level":4,"score":0.42854470014572144},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4274812340736389},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37236836552619934},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.07861986756324768},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2010.5470445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470445","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:10.1.1.168.3237","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.168.3237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lap.epfl.ch/webdav/site/lap/shared/publications/YeApr10_HighPerformanceComparisonBasedSortingAlgorithmOnManyCoreGpus_IPDPS10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1995596660","https://openalex.org/W2007519459","https://openalex.org/W2016939324","https://openalex.org/W2102420343","https://openalex.org/W2108157916","https://openalex.org/W2111435979","https://openalex.org/W2113841249","https://openalex.org/W2118558147","https://openalex.org/W2119547137","https://openalex.org/W2122817518","https://openalex.org/W2127766448","https://openalex.org/W2132587889","https://openalex.org/W2139126712","https://openalex.org/W2141389982","https://openalex.org/W2155119349","https://openalex.org/W2155503253","https://openalex.org/W2161061943","https://openalex.org/W2760911295","https://openalex.org/W3046848437","https://openalex.org/W4240180700","https://openalex.org/W6675229854","https://openalex.org/W6676153268","https://openalex.org/W6676674358","https://openalex.org/W6676774251","https://openalex.org/W6677993110","https://openalex.org/W6678107477","https://openalex.org/W6680280236","https://openalex.org/W6680874277","https://openalex.org/W6683923952"],"related_works":["https://openalex.org/W2093482277","https://openalex.org/W2575539670","https://openalex.org/W2949983223","https://openalex.org/W1986816028","https://openalex.org/W2118558147","https://openalex.org/W2085544944","https://openalex.org/W2160498963","https://openalex.org/W2011379812","https://openalex.org/W2240806428","https://openalex.org/W2778624466"],"abstract_inverted_index":{"Sorting":[0],"is":[1],"a":[2,6,16,34,39,67,89],"kernel":[3],"algorithm":[4,43,154],"for":[5,84],"wide":[7],"range":[8],"of":[9,33,60,64,108,137,160],"applications.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14,57,96],"present":[15],"new":[17],"algorithm,":[18],"GPU-Warpsort,":[19],"to":[20,53,69,91,110,121,144],"perform":[21],"comparison-based":[22,151],"parallel":[23,82],"sort":[24,36,100],"on":[25,134,155],"Graphics":[26],"Processing":[27],"Units":[28],"(GPUs).":[29],"It":[30],"mainly":[31],"consists":[32],"bitonic":[35,74],"followed":[37],"by":[38,47,102,114],"merge":[40,99],"sort.":[41],"Our":[42,126],"achieves":[44,142],"high":[45],"performance":[46,147],"efficiently":[48,101],"mapping":[49],"the":[50,61,71,86,98,123],"sorting":[51,75,153],"tasks":[52],"GPU":[54,152],"architectures.":[55],"Firstly,":[56],"take":[58],"advantage":[59],"synchronous":[62],"execution":[63],"threads":[65,87],"in":[66,73],"warp":[68,90,105],"eliminate":[70,122],"barriers":[72],"network.":[76],"We":[77],"also":[78],"provide":[79],"sufficient":[80],"homogeneous":[81],"operations":[83],"all":[85],"within":[88],"avoid":[92],"branch":[93],"divergence.":[94],"Furthermore,":[95],"implement":[97],"assigning":[103],"each":[104],"independent":[106],"pairs":[107],"sequences":[109,157],"be":[111],"merged":[112],"and":[113,140],"exploiting":[115],"totally":[116],"coalesced":[117],"global":[118],"memory":[119],"accesses":[120],"bandwidth":[124],"bottleneck.":[125],"experimental":[127],"results":[128],"indicate":[129],"that":[130],"GPU-Warpsort":[131],"works":[132],"well":[133],"different":[135],"kinds":[136],"input":[138,156],"distributions,":[139],"it":[141],"up":[143],"30%":[145],"higher":[146],"than":[148],"previous":[149],"optimized":[150],"with":[158],"millions":[159],"elements.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}