{"id":"https://openalex.org/W2023779084","doi":"https://doi.org/10.1109/msst.2012.6232377","title":"Adaptive pipeline for deduplication","display_name":"Adaptive pipeline for deduplication","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2023779084","doi":"https://doi.org/10.1109/msst.2012.6232377","mag":"2023779084"},"language":"en","primary_location":{"id":"doi:10.1109/msst.2012.6232377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2012.6232377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)","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/A5055082533","display_name":"Jingwei Ma","orcid":"https://orcid.org/0000-0001-7220-5927"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingwei Ma","raw_affiliation_strings":["College of I.T., Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of I.T., Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037628562","display_name":"Bin Zhao","orcid":"https://orcid.org/0000-0002-4950-415X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhao","raw_affiliation_strings":["College of I.T., Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of I.T., Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367433","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0003-0387-2501"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["College of I.T., Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of I.T., Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100390120","display_name":"Xiaoguang Liu","orcid":"https://orcid.org/0000-0002-9010-3278"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Liu","raw_affiliation_strings":["College of C.S., Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055082533"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.3725,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63762129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9754999876022339,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/data-deduplication","display_name":"Data deduplication","score":0.9600199460983276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8433877229690552},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.751509428024292},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6149654388427734},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5140484571456909},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.43835264444351196},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3851628303527832},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20339274406433105},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1886427104473114},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1228998601436615}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9600199460983276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8433877229690552},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.751509428024292},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6149654388427734},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5140484571456909},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.43835264444351196},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3851628303527832},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20339274406433105},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1886427104473114},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1228998601436615},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msst.2012.6232377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2012.6232377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.361.5115","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.361.5115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storageconference.org/2012/Papers/13.Short.1.AdaptivePipeline.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1521407587","https://openalex.org/W1969126835","https://openalex.org/W2041920271","https://openalex.org/W2048377555","https://openalex.org/W2123845384","https://openalex.org/W2148487037","https://openalex.org/W2617867460","https://openalex.org/W2912601938","https://openalex.org/W3150003982","https://openalex.org/W6602837329","https://openalex.org/W6607453207","https://openalex.org/W6608138927","https://openalex.org/W6631269574","https://openalex.org/W6738653283","https://openalex.org/W6793350840"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2144348063","https://openalex.org/W2375218795","https://openalex.org/W2393010557","https://openalex.org/W3044766408"],"abstract_inverted_index":{"Deduplication":[0],"has":[1],"become":[2],"one":[3],"of":[4,11,43,100,123,181],"the":[5,9,41,77,93,97,101,105,109,120,124,134,156,160,168],"hottest":[6],"topics":[7],"in":[8,38,61,80],"field":[10],"data":[12,67,85,102,147,183],"storage.":[13],"Quite":[14],"a":[15],"few":[16],"methods":[17,29],"towards":[18],"reducing":[19],"disk":[20],"I/O":[21],"caused":[22],"by":[23],"deduplication":[24,49,161,180],"have":[25,31],"been":[26,32],"proposed.":[27],"Some":[28],"also":[30],"studied":[33],"to":[34,133,145,164],"accelerate":[35],"computational":[36,44,53,78],"sub-tasks":[37,45,54,79],"deduplication.":[39,81],"However,":[40],"order":[42,122],"can":[46],"affect":[47],"overall":[48],"throughput":[50,162],"significantly,":[51],"because":[52],"exhibit":[55],"quite":[56],"different":[57,62,66,113],"workload":[58],"and":[59,64,87,96,104,108,129,149],"concurrency":[60],"orders":[63],"with":[65,167],"sets.":[68],"This":[69],"paper":[70],"proposes":[71],"an":[72],"adaptive":[73,148,157],"pipelining":[74],"model":[75],"for":[76,178],"It":[82],"takes":[83],"both":[84,146],"type":[86],"hardware":[88,150],"platform":[89],"into":[90],"account.":[91],"Taking":[92],"compression":[94,106],"ratio":[95,99],"duplicate":[98],"stream,":[103],"speed":[107,111],"fingerprinting":[110],"on":[112,185],"processing":[114,135],"units":[115],"as":[116],"parameters,":[117],"it":[118,139,175],"determines":[119],"optimal":[121],"pipeline":[125,158],"stages":[126],"(computational":[127],"sub-tasks)":[128],"assigns":[130],"each":[131],"stage":[132],"unit":[136],"which":[137,172],"processes":[138],"fastest.":[140],"That":[141],"is,":[142],"\u201cadaptive\u201d":[143],"refers":[144],"adaptive.":[151],"Experimental":[152],"results":[153],"show":[154],"that":[155,174],"improves":[159],"up":[163],"50%":[165],"compared":[166],"plain":[169],"fixed":[170],"pipeline,":[171],"implies":[173],"is":[176],"suitable":[177],"simultaneous":[179],"various":[182],"types":[184],"modern":[186],"heterogeneous":[187],"multi-core":[188],"systems.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}