{"id":"https://openalex.org/W2336892223","doi":"https://doi.org/10.1145/2851141.2851169","title":"GPU multisplit","display_name":"GPU multisplit","publication_year":2016,"publication_date":"2016-02-22","ids":{"openalex":"https://openalex.org/W2336892223","doi":"https://doi.org/10.1145/2851141.2851169","mag":"2336892223"},"language":"en","primary_location":{"id":"doi:10.1145/2851141.2851169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2851141.2851169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/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"],"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102783797","display_name":"Andrew Davidson","orcid":"https://orcid.org/0009-0002-3364-0699"},"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"],"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"],"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"],"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":4.73,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95015986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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":0.8903900384902954},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8048047423362732},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7608938217163086},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.6117018461227417},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5807995200157166},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5469005107879639},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48410284519195557},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47012412548065186},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.44215258955955505},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4186702370643616},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.18613851070404053},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13898217678070068},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1310448944568634},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11061415076255798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8903900384902954},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8048047423362732},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7608938217163086},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.6117018461227417},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5807995200157166},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5469005107879639},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48410284519195557},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47012412548065186},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.44215258955955505},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4186702370643616},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.18613851070404053},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13898217678070068},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1310448944568634},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11061415076255798},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2851141.2851169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2851141.2851169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W619004858","https://openalex.org/W1532566247","https://openalex.org/W1981585303","https://openalex.org/W1982891605","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/W2118169763","https://openalex.org/W2145455679","https://openalex.org/W2148329647","https://openalex.org/W2155503253","https://openalex.org/W2161061943","https://openalex.org/W2169528473","https://openalex.org/W2207292641","https://openalex.org/W2257258878","https://openalex.org/W3138798301","https://openalex.org/W4240899876","https://openalex.org/W6631965851","https://openalex.org/W6683923952"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W280163585"],"abstract_inverted_index":{"Multisplit":[0],"is":[1,27,62,83],"a":[2,25,49,70,86,156,165],"broadly":[3],"useful":[4],"parallel":[5,71],"primitive":[6],"that":[7,20],"permutes":[8],"its":[9],"input":[10,135],"data":[11],"into":[12,24],"contiguous":[13],"buckets":[14],"or":[15],"bins,":[16],"where":[17],"the":[18,30,34,77,96,100,106],"function":[19],"categorizes":[21],"an":[22,37,146],"element":[23],"bucket":[26],"provided":[28],"by":[29],"programmer.":[31],"Due":[32],"to":[33,45,58,102,121,137],"lack":[35],"of":[36,89,99,105,112,134,141,168],"efficient":[38],"multisplit":[39,47,78,84],"on":[40],"GPUs,":[41],"programmers":[42],"often":[43],"choose":[44],"implement":[46,59],"with":[48,109],"sort.":[50],"However,":[51],"sort":[52],"does":[53],"more":[54],"work":[55,107],"than":[56],"necessary":[57],"multisplit,":[60,153],"and":[61,73,125,163],"thus":[63],"inefficient.":[64],"In":[65,91],"this":[66],"work,":[67],"we":[68,94,154],"provide":[69],"model":[72],"multiple":[74],"implementations":[75],"for":[76,85,150],"problem.":[79],"Our":[80],"principal":[81],"focus":[82],"small":[87],"number":[88],"buckets.":[90],"our":[92],"implementations,":[93],"exploit":[95],"computational":[97],"hierarchy":[98],"GPU":[101],"perform":[103],"most":[104],"locally,":[108],"minimal":[110],"usage":[111],"global":[113,142],"operations.":[114],"We":[115],"also":[116],"use":[117],"warp-synchronous":[118],"programming":[119],"models":[120],"avoid":[122],"branch":[123],"divergence":[124],"reduce":[126],"memory":[127,143],"usage,":[128],"as":[129,131],"well":[130],"hierarchical":[132],"reordering":[133],"elements":[136],"achieve":[138,164],"better":[139],"coalescing":[140],"accesses.":[144],"On":[145],"NVIDIA":[147],"K40c":[148],"GPU,":[149],"key-only":[151],"(key-value)":[152],"demonstrate":[155],"3.0-6.7x":[157],"(4.4-8.0x)":[158],"speedup":[159],"over":[160],"radix":[161],"sort,":[162],"peak":[166],"throughput":[167],"10.0":[169],"G":[170],"keys/s.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
