{"id":"https://openalex.org/W4301891805","doi":"https://doi.org/10.1145/3108139","title":"GPU Multisplit","display_name":"GPU Multisplit","publication_year":2017,"publication_date":"2017-03-31","ids":{"openalex":"https://openalex.org/W4301891805","doi":"https://doi.org/10.1145/3108139"},"language":"en","primary_location":{"id":"doi:10.1145/3108139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3108139","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-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/A5025222722","display_name":"Saman Ashkiani","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saman Ashkiani","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012494631","display_name":"Andrew Davidson","orcid":"https://orcid.org/0000-0003-3784-682X"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Davidson","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103183708","display_name":"Ulrich Meyer","orcid":"https://orcid.org/0000-0002-1197-3153"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrich Meyer","raw_affiliation_strings":["Goethe-Universit\u00e4t Frankfurt am Main"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Goethe-Universit\u00e4t Frankfurt am Main","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028662746","display_name":"John D. Owens","orcid":"https://orcid.org/0000-0001-6582-8237"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John D. Owens","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025222722"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":1.1555,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.81336406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":"1","first_page":"1","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980999827384949,"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":0.8712977170944214},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.7280418872833252},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6960148215293884},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.6023930907249451},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5875047445297241},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.5235276222229004},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.49377045035362244},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48947465419769287},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.46102485060691833},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4233197569847107},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2751879096031189},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.14489391446113586},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12797698378562927},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12450295686721802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8712977170944214},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.7280418872833252},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6960148215293884},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.6023930907249451},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5875047445297241},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5235276222229004},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.49377045035362244},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48947465419769287},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.46102485060691833},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4233197569847107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2751879096031189},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.14489391446113586},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12797698378562927},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12450295686721802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3108139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3108139","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7091924582","display_name":null,"funder_award_id":"CCF-1017399 and OCI-1032859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320324281","display_name":"Center for Massive Data Algorithmics","ror":"https://ror.org/00qbzpp62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W1482680420","https://openalex.org/W1981585303","https://openalex.org/W2007742815","https://openalex.org/W2017086619","https://openalex.org/W2024794876","https://openalex.org/W2035080386","https://openalex.org/W2050182684","https://openalex.org/W2050277572","https://openalex.org/W2057112598","https://openalex.org/W2072731885","https://openalex.org/W2074982700","https://openalex.org/W2087507944","https://openalex.org/W2093012449","https://openalex.org/W2107173440","https://openalex.org/W2111194344","https://openalex.org/W2134427337","https://openalex.org/W2145455679","https://openalex.org/W2155503253","https://openalex.org/W2169528473","https://openalex.org/W2336892223","https://openalex.org/W2951135776","https://openalex.org/W3138798301","https://openalex.org/W4240899876","https://openalex.org/W4245926874","https://openalex.org/W4251164127"],"related_works":["https://openalex.org/W2809748609","https://openalex.org/W2095055219","https://openalex.org/W2482527088","https://openalex.org/W280163585","https://openalex.org/W3033694952","https://openalex.org/W2908348257","https://openalex.org/W4392178020","https://openalex.org/W2085265870","https://openalex.org/W2362374543","https://openalex.org/W2348196682"],"abstract_inverted_index":{"Multisplit":[0],"is":[1,28,57,88,141],"a":[2,26,53,128,144,184,192,200,214,242],"broadly":[3],"useful":[4],"parallel":[5,129],"primitive":[6],"that":[7,21],"permutes":[8],"its":[9],"input":[10,70,92,173],"data":[11,71,109],"into":[12,25],"contiguous":[13],"buckets":[14,79],"or":[15],"bins":[16],",":[17],"where":[18],"the":[19,31,35,112,135,230],"function":[20],"categorizes":[22],"an":[23,38,61],"element":[24],"bucket":[27,65],"provided":[29],"by":[30],"programmer.":[32],"Due":[33],"to":[34,49,58,89,147,161,175,229],"lack":[36],"of":[37,64,150,179,195,244],"efficient":[39],"multisplit":[40,51,87,136,142,209],"on":[41,73],"Graphics":[42],"Processing":[43],"Units":[44],"(GPUs),":[45],"programmers":[46],"often":[47],"choose":[48],"implement":[50],"with":[52,241],"sort.":[54,219],"One":[55],"way":[56,85],"first":[59],"generate":[60],"auxiliary":[62],"array":[63],"IDs":[66],"and":[67,98,131,157,165],"then":[68],"sort":[69,91,223,233],"based":[72],"it.":[74],"In":[75,123,220],"case":[76],"smaller":[77,81],"indexed":[78],"possess":[80],"valued":[82],"keys,":[83],"another":[84],"for":[86,134,143,199,217],"directly":[90],"data.":[93],"Both":[94],"methods":[95],"are":[96],"inefficient":[97],"require":[99],"more":[100,107],"work":[101],"than":[102],"necessary:":[103],"The":[104],"former":[105],"requires":[106],"expensive":[108],"movements":[110],"while":[111],"latter":[113],"spends":[114],"unnecessary":[115],"effort":[116],"in":[117],"sorting":[118,235],"elements":[119,174],"within":[120],"each":[121],"bucket.":[122],"this":[124],"work,":[125],"we":[126,189,206,225],"provide":[127],"model":[130],"multiple":[132],"implementations":[133],"problem.":[137],"Our":[138],"principal":[139],"focus":[140],"small":[145],"(up":[146],"256)":[148],"number":[149],"buckets.":[151],"We":[152,169],"use":[153],"warp-synchronous":[154],"programming":[155],"models":[156],"emphasize":[158],"warpwide":[159],"communications":[160],"avoid":[162],"branch":[163],"divergence":[164],"reduce":[166],"memory":[167,181],"usage.":[168],"also":[170],"hierarchically":[171],"reorder":[172],"achieve":[176,226],"better":[177],"coalescing":[178],"global":[180],"accesses.":[182],"On":[183],"GeForce":[185],"GTX":[186],"1080":[187],"GPU,":[188],"can":[190,210],"reach":[191],"peak":[193],"throughput":[194,243],"18.93Gkeys/s":[196],"(or":[197,202],"11.68Gpairs/s)":[198],"key-only":[201],"key-value)":[203],"multisplit.":[204],"Finally,":[205],"demonstrate":[207],"how":[208],"be":[211],"used":[212],"as":[213],"building":[215],"block":[216],"radix":[218],"our":[221],"multisplit-based":[222],"implementation,":[224],"comparable":[227],"performance":[228],"fastest":[231],"GPU":[232],"routines,":[234],"32-bit":[236],"keys":[237],"(and":[238,246],"key-value":[239],"pairs)":[240],"3.0Gkeys/s":[245],"2.1Gpair/s).":[247]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2022-10-06T00:00:00"}
