{"id":"https://openalex.org/W2620106252","doi":"https://doi.org/10.1145/3079079.3079105","title":"Fast segmented sort on GPUs","display_name":"Fast segmented sort on GPUs","publication_year":2017,"publication_date":"2017-05-31","ids":{"openalex":"https://openalex.org/W2620106252","doi":"https://doi.org/10.1145/3079079.3079105","mag":"2620106252"},"language":"en","primary_location":{"id":"doi:10.1145/3079079.3079105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3079079.3079105","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3079105&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3079105&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047871879","display_name":"Kaixi Hou","orcid":"https://orcid.org/0000-0003-3921-6709"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kaixi Hou","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["DK","NO"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["University of Copenhagen, Copenhagen, Denmark and Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark and Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367","https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050002532","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-3557-6301"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047871879"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":8.7841,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.98548889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8230615854263306},{"id":"https://openalex.org/keywords/merge-sort","display_name":"Merge sort","score":0.7995880246162415},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.7437480688095093},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7293646931648254},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4637710452079773},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4282892346382141},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3681882619857788},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.3504984676837921},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34533917903900146},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3205549716949463},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09840217232704163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230615854263306},{"id":"https://openalex.org/C35555965","wikidata":"https://www.wikidata.org/wiki/Q189057","display_name":"Merge sort","level":4,"score":0.7995880246162415},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.7437480688095093},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7293646931648254},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4637710452079773},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4282892346382141},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3681882619857788},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.3504984676837921},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34533917903900146},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3205549716949463},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09840217232704163},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3079079.3079105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3079079.3079105","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3079105&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/b93f2bb2-84a1-446f-8d44-61b1852026a8","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/b93f2bb2-84a1-446f-8d44-61b1852026a8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hou , K , Liu , W , Wang , H & Feng , W-C 2017 , Fast segmented sort on GPUs . in Proceedings of the International Conference on Supercomputing 17 . ACM edn , vol. 12 , Chicago, USA . https://doi.org/10.1145/3079079.3079105","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/b93f2bb2-84a1-446f-8d44-61b1852026a8","is_oa":false,"landing_page_url":"https://curis.ku.dk/portal/da/publications/fast-segmented-sort-on-gpus(b93f2bb2-84a1-446f-8d44-61b1852026a8).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hou , K , Liu , W , Wang , H & Feng , W-C 2017 , Fast segmented sort on GPUs . in Proceedings of the International Conference on Supercomputing 17 . ACM edn , vol. 12 , Chicago, USA . https://doi.org/10.1145/3079079.3079105","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3079079.3079105","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3079079.3079105","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3079105&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1179131320","display_name":null,"funder_award_id":"752321","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2689612763","display_name":null,"funder_award_id":"Marie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3666695478","display_name":null,"funder_award_id":"BIGDATA","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5808022030","display_name":"BIGDATA: Mid-Scale: DA: Collaborative Research: Genomes Galore - Core Techniques, Libraries, and Domain Specific Languages for High-Throughput DNA Sequencing","funder_award_id":"1247693","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6986638558","display_name":null,"funder_award_id":"IIS-1247693","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2620106252.pdf","grobid_xml":"https://content.openalex.org/works/W2620106252.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W1964704819","https://openalex.org/W1985263109","https://openalex.org/W1993399552","https://openalex.org/W1995596660","https://openalex.org/W2009654791","https://openalex.org/W2014214820","https://openalex.org/W2016279572","https://openalex.org/W2029940394","https://openalex.org/W2035080386","https://openalex.org/W2039283011","https://openalex.org/W2059966434","https://openalex.org/W2066367171","https://openalex.org/W2087977509","https://openalex.org/W2098297530","https://openalex.org/W2110975861","https://openalex.org/W2111643426","https://openalex.org/W2113622448","https://openalex.org/W2115052535","https://openalex.org/W2118558147","https://openalex.org/W2123440268","https://openalex.org/W2133732112","https://openalex.org/W2138215414","https://openalex.org/W2146223937","https://openalex.org/W2151285624","https://openalex.org/W2152290683","https://openalex.org/W2158874082","https://openalex.org/W2160406723","https://openalex.org/W2162707967","https://openalex.org/W2166955231","https://openalex.org/W2168931017","https://openalex.org/W2263483768","https://openalex.org/W2411480360","https://openalex.org/W2415973476","https://openalex.org/W2422616509","https://openalex.org/W2469975815","https://openalex.org/W2474844316","https://openalex.org/W2506072259","https://openalex.org/W2538301624","https://openalex.org/W2567317362","https://openalex.org/W2581189719","https://openalex.org/W2605251767","https://openalex.org/W2623016866","https://openalex.org/W3125710003","https://openalex.org/W6604925666","https://openalex.org/W6605973162"],"related_works":["https://openalex.org/W2765396134","https://openalex.org/W1493296159","https://openalex.org/W1480783219","https://openalex.org/W3037448952","https://openalex.org/W4300167273","https://openalex.org/W4409584514","https://openalex.org/W2190513794","https://openalex.org/W4229364780","https://openalex.org/W3116699298","https://openalex.org/W4289541648"],"abstract_inverted_index":{"Segmented":[0],"sort,":[1,7],"as":[2],"a":[3,9,15,60,80,96],"generalization":[4],"of":[5,11,23],"classical":[6],"orders":[8],"batch":[10],"independent":[12],"segments":[13],"in":[14],"whole":[16],"array.":[17],"Along":[18],"with":[19],"the":[20,69,118],"wider":[21],"adoption":[22],"manycore":[24],"processors":[25],"for":[26,63],"HPC":[27],"and":[28,75,78,89,123,128,143,147],"big":[29],"data":[30,91],"applications,":[31,138],"segmented":[32,48,111],"sort":[33,49,82,112],"plays":[34],"an":[35,46],"increasingly":[36],"important":[37],"role":[38],"than":[39],"sort.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,132],"present":[45],"adaptive":[47],"mechanism":[50,113,135],"on":[51,125,136],"GPUs.":[52,130],"Our":[53,110],"mechanisms":[54],"include":[55],"two":[56,137],"core":[57],"techniques:":[58],"(1)":[59],"differentiated":[61],"method":[62,83,100],"different":[64],"segment":[65],"lengths":[66],"to":[67,84,101],"eliminate":[68],"irregularity":[70],"caused":[71],"by":[72],"various":[73],"workloads":[74],"thread":[76],"divergence;":[77],"(2)":[79],"register-based":[81],"support":[85,102],"N-to-M":[86],"data-thread":[87],"binding":[88],"in-register":[90],"communication.":[92],"We":[93],"also":[94],"implement":[95],"shared":[97],"memory-based":[98],"merge":[99,106],"non-uniform":[103],"length":[104],"chunk":[105],"via":[107],"multiple":[108],"warps.":[109],"shows":[114],"great":[115],"improvements":[116],"over":[117,151],"methods":[119],"from":[120],"CUB,":[121],"CUSP":[122],"ModernGPU":[124],"NVIDIA":[126],"K80-Kepler":[127],"TitanX-Pascal":[129],"Furthermore,":[131],"apply":[133],"our":[134],"i.e.,":[139],"suffix":[140],"array":[141],"construction":[142],"sparse":[144],"matrix-matrix":[145],"multiplication,":[146],"obtain":[148],"obvious":[149],"gains":[150],"state-of-the-art":[152],"implementations.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}