{"id":"https://openalex.org/W2344380003","doi":"https://doi.org/10.1109/tbdata.2015.2511001","title":"GPU-Accelerated Large-Scale Distributed Sorting Coping with Device Memory Capacity","display_name":"GPU-Accelerated Large-Scale Distributed Sorting Coping with Device Memory Capacity","publication_year":2016,"publication_date":"2016-01-05","ids":{"openalex":"https://openalex.org/W2344380003","doi":"https://doi.org/10.1109/tbdata.2015.2511001","mag":"2344380003"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2015.2511001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2015.2511001","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","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/A5020297870","display_name":"Hideyuki Shamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Shamoto","raw_affiliation_strings":["Department of Computing and Mathematical Sciences, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Mathematical Sciences, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102314855","display_name":"Koichi Shirahata","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shirahata","raw_affiliation_strings":["Department of Computing and Mathematical Sciences, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Mathematical Sciences, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277099","display_name":"Aleksandr Drozd","orcid":"https://orcid.org/0000-0002-4575-7213"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aleksandr Drozd","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080099014","display_name":"Hitoshi Sato","orcid":"https://orcid.org/0000-0003-1516-8538"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Sato","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0681,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88204216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2","issue":"1","first_page":"57","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11478","display_name":"Caching and Content Delivery","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":0.9959999918937683,"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":0.8953098058700562},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7982262372970581},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6650639772415161},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6425836086273193},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6306238174438477},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5919151306152344},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5761251449584961},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5301274657249451},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.5052040219306946},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.455719918012619},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4447769522666931},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.42011603713035583},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.41123855113983154},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3288659453392029},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2770705223083496},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12339150905609131},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11359935998916626},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09630489349365234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8953098058700562},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7982262372970581},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6650639772415161},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6425836086273193},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6306238174438477},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5919151306152344},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5761251449584961},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5301274657249451},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.5052040219306946},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.455719918012619},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4447769522666931},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42011603713035583},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.41123855113983154},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3288659453392029},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2770705223083496},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12339150905609131},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11359935998916626},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09630489349365234},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2015.2511001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2015.2511001","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W1694308253","https://openalex.org/W1963960519","https://openalex.org/W1989741444","https://openalex.org/W1993172344","https://openalex.org/W2002779106","https://openalex.org/W2005818856","https://openalex.org/W2006554829","https://openalex.org/W2023236551","https://openalex.org/W2059966434","https://openalex.org/W2060451781","https://openalex.org/W2062743552","https://openalex.org/W2085248745","https://openalex.org/W2092574257","https://openalex.org/W2102420343","https://openalex.org/W2113622448","https://openalex.org/W2127766448","https://openalex.org/W2140193104","https://openalex.org/W2141389982","https://openalex.org/W2147418091","https://openalex.org/W2154614053","https://openalex.org/W2162707967","https://openalex.org/W2164131708","https://openalex.org/W2167659042","https://openalex.org/W2321517917","https://openalex.org/W4251164127","https://openalex.org/W4285719527","https://openalex.org/W6680526578","https://openalex.org/W6832800064"],"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/W1980160788","https://openalex.org/W4376647684","https://openalex.org/W1905405560","https://openalex.org/W2007942862","https://openalex.org/W2311112479"],"abstract_inverted_index":{"Splitter-based":[0],"parallel":[1],"sorting":[2,12,36,124],"algorithms":[3,37,50],"are":[4],"known":[5],"to":[6,14,25,47,63,136],"be":[7,180],"highly":[8],"efficient":[9],"for":[10,172],"distributed":[11,35],"due":[13],"their":[15,32],"low":[16],"communication":[17],"complexity.":[18],"Although":[19],"using":[20,44],"GPU":[21,45,74,187],"accelerators":[22],"could":[23],"help":[24],"reduce":[26],"the":[27,48,68,73,89,96,102,147,156,162,176],"computation":[28,61],"cost":[29],"in":[30,34,182],"general,":[31],"effectiveness":[33],"remains":[38],"unclear.":[39],"We":[40,94],"investigate":[41],"applicability":[42],"of":[43,70,98,127,168],"devices":[46],"splitter-based":[49,56],"and":[51],"extend":[52],"HykSort,":[53],"an":[54],"existing":[55],"algorithm":[57],"by":[58,161],"offloading":[59],"costly":[60],"phases":[62],"GPUs.":[64,111],"To":[65],"cope":[66],"with":[67,82,119,184],"volumes":[69],"data":[71,90],"exceeding":[72],"memory":[75],"capacity,":[76],"out-of-core":[77],"local":[78],"sort":[79],"is":[80,92,142,158],"used":[81],"small":[83],"overhead":[84],"about":[85],"7.5":[86],"percent":[87],"when":[88,123],"size":[91],"tripled.":[93],"evaluate":[95],"performance":[97,157,177],"our":[99],"implementation":[100],"on":[101,132,138],"TSUBAME2.5":[103],"supercomputer":[104],"that":[105,155],"comprises":[106],"over":[107],"4,000":[108],"NVIDIA":[109],"K20x":[110],"Weak":[112],"scaling":[113],"analysis":[114,152],"shows":[115],"389":[116],"times":[117,144],"speedup":[118],"0.25":[120],"TB/s":[121],"throughput":[122],"4":[125],"TB":[126],"64":[128],"bit":[129],"integer":[130],"values":[131],"1,024":[133],"nodes":[134],"compared":[135],"running":[137],"one":[139],"node;":[140],"this":[141],"1.40":[143],"faster":[145],"than":[146],"reference":[148],"CPU":[149],"implementation.":[150],"Detailed":[151],"however":[153],"reveals":[154],"mostly":[159],"bottlenecked":[160],"CPU-GPU":[163],"host-to-device":[164],"bandwidth.":[165],"With":[166],"orders":[167],"magnitude":[169],"improvements":[170],"announced":[171],"next":[173],"generation":[174],"GPUs,":[175],"boost":[178],"will":[179],"tremendous":[181],"accordance":[183],"other":[185],"successful":[186],"accelerations.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
