{"id":"https://openalex.org/W6967460604","doi":"https://doi.org/10.5281/zenodo.10996585","title":"RadiK: Scalable and Optimized GPU-Parallel Radix Top-K Selection","display_name":"RadiK: Scalable and Optimized GPU-Parallel Radix Top-K Selection","publication_year":2024,"publication_date":"2024-04-19","ids":{"openalex":"https://openalex.org/W6967460604","doi":"https://doi.org/10.5281/zenodo.10996585"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10996585","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10996585","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"type":"software","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10996585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Yifei","orcid":"https://orcid.org/0000-0002-5041-1284"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Yifei","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":"https://orcid.org/0000-0002-5041-1284","affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Bole","orcid":"https://orcid.org/0009-0004-5450-5124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Bole","raw_affiliation_strings":["Independent"],"raw_orcid":"https://orcid.org/0009-0004-5450-5124","affiliations":[{"raw_affiliation_string":"Independent","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Jiejing","orcid":"https://orcid.org/0009-0006-3341-2943"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jiejing","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":"https://orcid.org/0009-0006-3341-2943","affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei, Xuechao","orcid":"https://orcid.org/0000-0002-0996-2260"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei, Xuechao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":"https://orcid.org/0000-0002-0996-2260","affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yinghan","orcid":"https://orcid.org/0009-0002-9618-5523"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Yinghan","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":"https://orcid.org/0009-0002-9618-5523","affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chen, Yingda","orcid":"https://orcid.org/0009-0000-7358-819X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Yingda","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":"https://orcid.org/0009-0000-7358-819X","affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.9693999886512756},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8691999912261963},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5206999778747559},{"id":"https://openalex.org/keywords/radix","display_name":"Radix (gastropod)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.45410001277923584},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.43650001287460327},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4253000020980835}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9693999886512756},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8691999912261963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134999871253967},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6205000281333923},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C2779091547","wikidata":"https://www.wikidata.org/wiki/Q287565","display_name":"Radix (gastropod)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10996585","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10996585","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10996585","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10996585","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Top-k":[0],"selection,":[1],"which":[2,147],"identifies":[3],"the":[4,53,61,121,145],"largest":[5],"or":[6],"smallest":[7],"k":[8,85],"elements":[9],"from":[10],"a":[11,15,64,73,103],"data":[12],"set,":[13],"is":[14],"fundamental":[16],"operation":[17],"in":[18],"data-intensive":[19],"domains":[20],"such":[21],"as":[22],"databases":[23],"and":[24,30,49,75,97,112,127],"deep":[25],"learning,":[26],"so":[27],"its":[28,42],"scalability":[29,62],"efficiency":[31],"are":[32,46],"critical":[33],"for":[34,108,124,132],"these":[35],"high-performance":[36],"systems.":[37],"However,":[38],"previous":[39],"studies":[40],"on":[41,52,68,154],"efficient":[43],"GPU":[44],"implementation":[45],"mostly":[47],"merge-based":[48],"rely":[50],"heavily":[51],"fast":[54],"but":[55],"size-limited":[56],"on-chip":[57],"memory,":[58],"thereby":[59],"limiting":[60],"with":[63],"restricted":[65],"upper":[66],"bound":[67],"k.":[69],"This":[70],"work":[71],"introduces":[72],"scalable":[74],"optimized":[76],"GPU-parallel":[77],"radix":[78],"top-k":[79],"selection":[80],"that":[81,143],"supports":[82],"significantly":[83],"larger":[84],"values":[86],"than":[87],"existing":[88],"methods":[89],"without":[90],"compromising":[91],"efficiency,":[92],"regardless":[93],"of":[94],"input":[95,157],"length":[96],"batch":[98,133],"size.":[99],"Our":[100],"method":[101],"incorporates":[102],"novel":[104],"optimization":[105],"framework":[106],"tailored":[107],"high":[109],"memory":[110],"bandwidth":[111],"resource":[113],"utilization,":[114],"achieving":[115],"up":[116,128,150],"to":[117,129,151],"2.5x":[118],"speedup":[119,131,153],"over":[120],"prior":[122],"art":[123],"non-batch":[125],"queries":[126],"4.8x":[130],"queries.":[134],"In":[135],"addition,":[136],"we":[137],"propose":[138],"an":[139],"adaptive":[140],"scaling":[141],"technique":[142],"strengthens":[144],"robustness,":[146],"further":[148],"provides":[149],"2.7x":[152],"highly":[155],"adversarial":[156],"distributions.":[158]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}