{"id":"https://openalex.org/W2547543723","doi":"https://doi.org/10.1145/3035918.3064043","title":"A Memory Bandwidth-Efficient Hybrid Radix Sort on GPUs","display_name":"A Memory Bandwidth-Efficient Hybrid Radix Sort on GPUs","publication_year":2017,"publication_date":"2017-05-09","ids":{"openalex":"https://openalex.org/W2547543723","doi":"https://doi.org/10.1145/3035918.3064043","mag":"2547543723"},"language":"en","primary_location":{"id":"doi:10.1145/3035918.3064043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3035918.3064043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1611.01137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Elias Stehle","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elias Stehle","raw_affiliation_strings":["Technical University of Munich (TUM), Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hans-Arno Jacobsen","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans-Arno Jacobsen","raw_affiliation_strings":["Technical University of Munich (TUM), Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.3657,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.93124227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9979000091552734,"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/sorting-algorithm","display_name":"Sorting algorithm","score":0.7771000266075134},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.7598999738693237},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.666700005531311},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/merge-sort","display_name":"Merge sort","score":0.5266000032424927},{"id":"https://openalex.org/keywords/sorting-network","display_name":"Sorting network","score":0.4675000011920929},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.39629998803138733},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468000292778015},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7871000170707703},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.7771000266075134},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.7598999738693237},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.666700005531311},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C35555965","wikidata":"https://www.wikidata.org/wiki/Q189057","display_name":"Merge sort","level":4,"score":0.5266000032424927},{"id":"https://openalex.org/C64540648","wikidata":"https://www.wikidata.org/wiki/Q646477","display_name":"Sorting network","level":4,"score":0.4675000011920929},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.39629998803138733},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C2778937211","wikidata":"https://www.wikidata.org/wiki/Q486598","display_name":"Quicksort","level":4,"score":0.3336000144481659},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3035918.3064043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3035918.3064043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1611.01137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.01137","pdf_url":"https://arxiv.org/pdf/1611.01137","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1611.01137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.01137","pdf_url":"https://arxiv.org/pdf/1611.01137","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1566552779","https://openalex.org/W1902965424","https://openalex.org/W1974796034","https://openalex.org/W1992730709","https://openalex.org/W1995596660","https://openalex.org/W2003515726","https://openalex.org/W2005818856","https://openalex.org/W2006552857","https://openalex.org/W2023236551","https://openalex.org/W2036073865","https://openalex.org/W2059966434","https://openalex.org/W2082695854","https://openalex.org/W2095890830","https://openalex.org/W2103086360","https://openalex.org/W2113622448","https://openalex.org/W2118558147","https://openalex.org/W2122817518","https://openalex.org/W2125529470","https://openalex.org/W2127766448","https://openalex.org/W2154614053","https://openalex.org/W2162707967","https://openalex.org/W2164340703","https://openalex.org/W2166955231","https://openalex.org/W2278783412","https://openalex.org/W2296407087","https://openalex.org/W2336892223","https://openalex.org/W2406955896","https://openalex.org/W2407641568","https://openalex.org/W2426048753","https://openalex.org/W6637239461","https://openalex.org/W6638907241"],"related_works":[],"abstract_inverted_index":{"Sorting":[0],"is":[1],"at":[2],"the":[3,39,54,99,108,134,166,170,190,198,203],"core":[4],"of":[5,64,101,118,146,152],"many":[6],"database":[7],"operations,":[8,30],"such":[9],"as":[10,23,79,122,124],"index":[11],"creation,":[12],"sort-merge":[13],"joins,":[14],"and":[15,217,230],"user-requested":[16],"output":[17],"sorting.":[18],"As":[19],"GPUs":[20,33],"are":[21,75],"emerging":[22],"a":[24,35,61,93,130,143,150,183,215,218,228,231],"promising":[25],"platform":[26],"to":[27,53,114,202],"accelerate":[28],"various":[29],"sorting":[31,49,62,180,186,200,222],"on":[32,50,165,176],"becomes":[34],"viable":[36],"endeavour.":[37],"Over":[38],"past":[40],"few":[41],"years,":[42],"several":[43],"improvements":[44],"have":[45],"been":[46],"proposed":[47],"for":[48,139,154,221],"GPUs,":[51],"leading":[52],"first":[55],"radix":[56,137,206],"sort":[57,115,138,207],"implementations":[58],"that":[59,96,160,188],"achieve":[60],"rate":[63],"over":[65,133],"one":[66],"billion":[67],"32-bit":[68],"keys":[69],"per":[70],"second.":[71],"Yet,":[72],"state-of-the-art":[73,135,204],"approaches":[74],"heavily":[76],"memory":[77,84,102,109],"bandwidth-bound,":[78],"they":[80],"require":[81],"substantially":[82],"more":[83],"transfers":[85,103],"than":[86,149],"their":[87],"CPU-based":[88,205],"counterparts.":[89],"Our":[90],"work":[91],"proposes":[92],"novel":[94],"approach":[95,128,181,213],"almost":[97],"halves":[98],"amount":[100],"and,":[104],"therefore,":[105],"considerably":[106],"lifts":[107],"bandwidth":[110],"limitation.":[111],"Being":[112],"able":[113],"two":[116],"gigabytes":[117],"eight-byte":[119],"records":[120],"in":[121],"little":[123],"50":[125],"milliseconds,":[126],"our":[127,177,211],"achieves":[129,214],"2.32-fold":[131],"improvement":[132,220],"GPU-based":[136],"uniform":[140,232],"distributions,":[141],"sustaining":[142],"minimum":[144],"speed-up":[145],"no":[147],"less":[148],"factor":[151],"1.66":[153],"skewed":[155,229],"distributions.":[156],"To":[157],"address":[158],"inputs":[159],"either":[161],"do":[162],"not":[163],"reside":[164],"GPU":[167,179],"or":[168],"exceed":[169],"available":[171],"device":[172],"memory,":[173],"we":[174],"build":[175],"efficient":[178],"with":[182,193,227],"pipelined":[184],"heterogeneous":[185,212],"algorithm":[187],"mitigates":[189],"overhead":[191],"associated":[192],"PCIe":[194],"data":[195],"transfers.":[196],"Comparing":[197],"end-to-end":[199],"performance":[201],"running":[208],"16":[209],"threads,":[210],"2.06-fold":[216],"1.53-fold":[219],"64":[223],"GB":[224],"key-value":[225],"pairs":[226],"distribution,":[233],"respectively.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-11-11T00:00:00"}