{"id":"https://openalex.org/W2585361384","doi":"https://doi.org/10.1109/bigdata.2016.7840629","title":"I/O chunking and latency hiding approach for out-of-core sorting acceleration using GPU and flash NVM","display_name":"I/O chunking and latency hiding approach for out-of-core sorting acceleration using GPU and flash NVM","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2585361384","doi":"https://doi.org/10.1109/bigdata.2016.7840629","mag":"2585361384"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/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"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Sato","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan","Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059348290","display_name":"Ryo Mizote","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":"Ryo Mizote","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"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"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan","Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103752908","display_name":"Hirotaka Ogawa","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirotaka Ogawa","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9219","issue":null,"first_page":"398","last_page":"403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11478","display_name":"Caching and Content Delivery","score":0.9965000152587891,"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":0.8512431383132935},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6858571767807007},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.48441082239151},{"id":"https://openalex.org/keywords/flash-memory","display_name":"Flash memory","score":0.4736664891242981},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4515690505504608},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.44553685188293457},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.42503461241722107},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41558152437210083},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.39076733589172363},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.335650235414505},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3334379494190216},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.31638166308403015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.06415075063705444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8512431383132935},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6858571767807007},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.48441082239151},{"id":"https://openalex.org/C2776531357","wikidata":"https://www.wikidata.org/wiki/Q174077","display_name":"Flash memory","level":2,"score":0.4736664891242981},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4515690505504608},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.44553685188293457},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.42503461241722107},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41558152437210083},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.39076733589172363},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.335650235414505},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3334379494190216},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31638166308403015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.06415075063705444},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6700000166893005,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G6815742546","display_name":"Programming Model  for Non-Volatile Memory toward Extreme Computing","funder_award_id":"26540050","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1569973175","https://openalex.org/W1992868693","https://openalex.org/W2006554829","https://openalex.org/W2023728671","https://openalex.org/W2039255119","https://openalex.org/W2041097097","https://openalex.org/W2064190272","https://openalex.org/W2082322254","https://openalex.org/W2082695854","https://openalex.org/W2113622448","https://openalex.org/W2127510911","https://openalex.org/W2127766448","https://openalex.org/W2162707967","https://openalex.org/W2258963578","https://openalex.org/W2334150052","https://openalex.org/W6692595670"],"related_works":["https://openalex.org/W2491097902","https://openalex.org/W2084310805","https://openalex.org/W2361382102","https://openalex.org/W2396000835","https://openalex.org/W266629765","https://openalex.org/W2166003657","https://openalex.org/W2493772236","https://openalex.org/W2185401572","https://openalex.org/W1975531513","https://openalex.org/W2585361384"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,112,211],"out-of-core":[3,156],"sorting":[4,106,137,158,196],"acceleration":[5],"technique,":[6],"called":[7],"xtr2sort,":[8],"that":[9,62,121,189],"deals":[10],"with":[11,134,145,166,207,220],"multi-level":[12],"memory":[13,17,20,25,35,45,52,85,222],"hierarchies":[14],"of":[15,37,63,69],"device":[16,84,102,110,184],"(GPU),":[18],"host":[19,94,100,178],"(CPU),":[21],"and":[22,34,86,93,101,104,138,192],"semi-external":[23,44,92],"non-volatile":[24],"(Flash":[26],"NVM)":[27],"for":[28,55,115,215],"leveraging":[29],"the":[30,51,56,61,64,70,74,108,170,177,182],"high":[31],"computational":[32],"performance":[33],"bandwidth":[36],"GPUs,":[38],"while":[39],"offloading":[40],"bandwidth-oblivious":[41],"operations":[42,90],"onto":[43],"in":[46,82,111,176],"order":[47],"to":[48,80,127],"significantly":[49],"increasing":[50],"capacity":[53],"available":[54],"sort":[57,124],"data,":[58],"well":[59,67],"beyond":[60],"GPU":[65,83,109,136,183],"as":[66,68],"CPU.":[71],"xtr2sort":[72,122,149],"splits":[73],"input":[75,171],"records":[76,125,165,172],"into":[77],"several":[78],"chunks":[79],"fit":[81,175],"overlaps":[87],"(1)":[88],"I/O":[89,190],"between":[91,99],"memory,":[95,103,179],"(2)":[96],"data":[97],"transfers":[98],"(3)":[105],"on":[107,162],"asynchronous":[113],"manner":[114],"hiding":[116],"latency.":[117],"Experimental":[118],"results":[119,187],"show":[120],"can":[123],"up":[126],"256":[128],"times":[129,140,153],"larger":[130,141],"than":[131,142,155],"is":[132,143,213],"possible":[133,144],"in-core":[135,146],"16":[139],"CPU":[147,157],"sorting.":[148],"also":[150],"achieves":[151],"4.39":[152],"faster":[154],"using":[159],"72":[160],"threads":[161],"204.8":[163],"giga":[164],"int32_t,":[167],"even":[168],"though":[169],"could":[173],"not":[174],"let":[180],"alone":[181],"memory.":[185],"These":[186],"indicate":[188],"chunking":[191],"latency":[193],"hiding/overlapping":[194],"maintains":[195],"performance,":[197,202],"despite":[198],"slow":[199],"Flash":[200],"NVM":[201],"by":[203],"utilizing":[204],"GPUs":[205],"along":[206],"good":[208],"algorithms.":[209],"Such":[210],"approach":[212],"viable":[214],"accelerating":[216],"future":[217],"computing":[218],"systems":[219],"deep":[221],"hierarchies.":[223]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
