{"id":"https://openalex.org/W1975293930","doi":"https://doi.org/10.1145/1944862.1944877","title":"High throughput data redundancy removal algorithm with scalable performance","display_name":"High throughput data redundancy removal algorithm with scalable performance","publication_year":2011,"publication_date":"2011-01-24","ids":{"openalex":"https://openalex.org/W1975293930","doi":"https://doi.org/10.1145/1944862.1944877","mag":"1975293930"},"language":"en","primary_location":{"id":"doi:10.1145/1944862.1944877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1944862.1944877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on High Performance and Embedded Architectures and Compilers","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/A5021010333","display_name":"Souvik Bhattacherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Souvik Bhattacherjee","raw_affiliation_strings":["IBM Research, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109064591","display_name":"Ankur Narang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankur Narang","raw_affiliation_strings":["IBM Research, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065774663","display_name":"Vikas Garg","orcid":"https://orcid.org/0000-0002-1421-5980"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vikas K. Garg","raw_affiliation_strings":["IBM Research, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021010333"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":3.1507,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91539175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"96"},"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/T11478","display_name":"Caching and Content Delivery","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/T11614","display_name":"Cloud Data Security Solutions","score":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.8507406711578369},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6446243524551392},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6284663677215576},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6104335188865662},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.5887235403060913},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5559828877449036},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4771806001663208},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38400715589523315},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33306267857551575},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3002322316169739},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13832658529281616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507406711578369},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6446243524551392},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6284663677215576},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6104335188865662},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.5887235403060913},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5559828877449036},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4771806001663208},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38400715589523315},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33306267857551575},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3002322316169739},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13832658529281616},{"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:10.1145/1944862.1944877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1944862.1944877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on High Performance and Embedded Architectures and Compilers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W114148695","https://openalex.org/W200233886","https://openalex.org/W1544599463","https://openalex.org/W1558092379","https://openalex.org/W1564712904","https://openalex.org/W1576397915","https://openalex.org/W1982515170","https://openalex.org/W1993284846","https://openalex.org/W2007842132","https://openalex.org/W2023797161","https://openalex.org/W2053449578","https://openalex.org/W2063544484","https://openalex.org/W2108084305","https://openalex.org/W2116967744","https://openalex.org/W2117098909","https://openalex.org/W2121133177","https://openalex.org/W2123845384","https://openalex.org/W2125763460","https://openalex.org/W2125770033","https://openalex.org/W2126540423","https://openalex.org/W2132627996","https://openalex.org/W2135955253","https://openalex.org/W2136986825","https://openalex.org/W2140733653","https://openalex.org/W2142808699","https://openalex.org/W2151823597","https://openalex.org/W2164855881","https://openalex.org/W2167736695","https://openalex.org/W2322524800","https://openalex.org/W2511894128","https://openalex.org/W2665103848"],"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/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W12581771","https://openalex.org/W2133886031"],"abstract_inverted_index":{"The":[0],"ever":[1],"growing":[2],"need":[3,65],"to":[4,107],"process":[5],"and":[6,29,179,189],"analyze":[7],"massive":[8,173],"amounts":[9],"of":[10,74,80,92,111,141,153,159,182],"data":[11,19,37,57,69,75,96,168],"from":[12,47],"diverse":[13],"sources":[14],"such":[15,172],"as":[16,49],"telecom":[17],"call":[18],"records,":[20,120,148],"telescope":[21],"imagery,":[22],"web":[23],"pages,":[24],"stock":[25],"markets,":[26],"medical":[27],"records":[28],"other":[30],"domains":[31,61],"has":[32],"triggered":[33],"worldwide":[34],"research":[35],"in":[36,128],"intensive":[38],"computing.":[39],"A":[40],"key":[41],"requirement":[42],"here":[43],"involves":[44],"removing":[45],"redundancy":[46,97,169],"data,":[48],"this":[50,86,162],"enhances":[51],"the":[52,78,90,109,157,164],"compute":[53],"efficiency":[54],"for":[55,66,71,167,185],"downstream":[56],"processing.":[58],"These":[59],"application":[60],"have":[62],"an":[63],"intense":[64],"high":[67],"throughput":[68,110,140,152,166],"deduplication":[70,127],"huge":[72],"volumes":[73],"flowing":[76],"at":[77],"rate":[79],"1":[81],"GB/s":[82],"or":[83],"more.":[84],"In":[85],"paper,":[87],"we":[88,149],"present":[89,102],"design":[91],"a":[93,103,139,151],"novel":[94],"parallel":[95,113,122],"removal":[98,170],"algorithm.":[99],"We":[100,175],"also":[101,176],"queueing":[104],"theoretic":[105],"analysis":[106],"optimize":[108],"our":[112,121,160,183],"algorithm":[114,123,184],"on":[115,130,171],"multi-core":[116,187],"architectures.":[117,193],"For":[118,145],"500M":[119],"can":[124],"perform":[125],"complete":[126],"255s,":[129],"16":[131],"core":[132],"Intel":[133,190],"Xeon":[134,191],"5570":[135,192],"architecture.":[136],"This":[137],"gives":[138],"around":[142],"2M":[143],"records/s.":[144],"2048":[146],"byte":[147],"achieve":[150],"0.81":[154],"GB/s.":[155],"To":[156],"best":[158],"knowledge,":[161],"is":[163],"highest":[165],"datasets.":[174],"demonstrate":[177],"strong":[178],"weak":[180],"scalability":[181],"both":[186],"Power6":[188]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}