{"id":"https://openalex.org/W4405306208","doi":"https://doi.org/10.1109/nas63802.2024.10781356","title":"ERD: AVX-512-based Enhancement of Resemblance Detection for Post-Deduplication Delta Compression","display_name":"ERD: AVX-512-based Enhancement of Resemblance Detection for Post-Deduplication Delta Compression","publication_year":2024,"publication_date":"2024-11-09","ids":{"openalex":"https://openalex.org/W4405306208","doi":"https://doi.org/10.1109/nas63802.2024.10781356"},"language":"en","primary_location":{"id":"doi:10.1109/nas63802.2024.10781356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas63802.2024.10781356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Networking, Architecture and Storage (NAS)","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/A5078775140","display_name":"T Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyun Chen","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119011578","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-2378-195X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747363","display_name":"Wang Fang","orcid":"https://orcid.org/0000-0001-7628-1185"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Wang","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115408452","display_name":"Weijie Yan","orcid":null},"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":"Weijie Yan","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115408453","display_name":"Ningyuan Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningyuan Mo","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115408454","display_name":"Xiaolei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162213","display_name":"China Electronics Standardization Institute","ror":"https://ror.org/05hxrpj87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210162213","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Liu","raw_affiliation_strings":["China Institute of Electronic Standardization"],"affiliations":[{"raw_affiliation_string":"China Institute of Electronic Standardization","institution_ids":["https://openalex.org/I4210162213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078775140"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25943396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9312999844551086,"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":0.9312999844551086,"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":0.9207000136375427,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9079999923706055,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6978146433830261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5789927244186401},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15421298146247864}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6978146433830261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5789927244186401},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15421298146247864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas63802.2024.10781356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas63802.2024.10781356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Networking, Architecture and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2073370301","https://openalex.org/W2110322986","https://openalex.org/W2148885851","https://openalex.org/W2346147088","https://openalex.org/W2612649108","https://openalex.org/W2999446691","https://openalex.org/W6605032692","https://openalex.org/W6679804201","https://openalex.org/W6705331335","https://openalex.org/W6760689153"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"As":[0],"a":[1,103,127,153],"complementary":[2],"technique":[3,104,157],"to":[4,19,42,65,119,158,203],"data":[5,45],"deduplication,":[6],"delta":[7,32,198],"compression":[8,33,199],"calculates":[9],"and":[10,88,133,164,189],"stores":[11],"differences":[12],"between":[13,85],"highly":[14],"similar":[15,39,92,162],"but":[16],"non-duplicate":[17],"chunks":[18,41,87,163],"reduce":[20],"storage":[21,24],"costs":[22],"in":[23,123],"systems.":[25],"A":[26],"key":[27,112],"aspect":[28],"of":[29,50,57,70],"efficient":[30],"post-deduplication":[31],"is":[34,60,74],"resemblance":[35,58,108,178],"detection,":[36,109],"which":[37,73],"identifies":[38],"reference":[40],"achieve":[43],"significant":[44],"reduction.":[46],"However,":[47],"our":[48],"evaluation":[49],"existing":[51],"methods":[52,80],"indicates":[53],"that":[54,172],"the":[55,61,66,95,135,166,197],"throughput":[56],"detection":[59,167,179],"system":[62],"bottleneck":[63],"due":[64],"computationally":[67],"intensive":[68],"nature":[69],"feature":[71,155,175],"extraction,":[72],"carried":[75],"out":[76],"sequentially.":[77],"Additionally,":[78],"these":[79],"suffer":[81],"from":[82],"low":[83],"similarity":[84],"detected":[86],"miss":[89],"some":[90],"potential":[91],"chunks,":[93],"reducing":[94,140],"redundancy":[96],"elimination":[97],"effect.":[98],"This":[99],"paper":[100],"introduces":[101,152],"ERD,":[102],"aimed":[105],"at":[106],"optimizing":[107],"featuring":[110],"two":[111],"advancements.":[113],"First,":[114],"it":[115,151],"employs":[116],"AVX-512":[117],"instructions":[118],"generate":[120],"rolling":[121],"hashes":[122],"parallel":[124],"based":[125],"on":[126,206],"novel":[128],"overlapping":[129],"sub-chunk":[130],"partition":[131],"strategy,":[132],"optimizes":[134],"linear":[136],"transformation":[137],"process,":[138],"thereby":[139],"computational":[141,145],"overhead":[142],"while":[143,195],"eliminating":[144],"errors":[146],"introduced":[147],"by":[148,180,201],"parallelization.":[149],"Second,":[150],"locality-aware":[154],"matching":[156],"further":[159],"detect":[160],"potentially":[161],"enhance":[165],"capabilities.":[168],"Experimental":[169],"results":[170],"show":[171],"ERD":[173],"accelerates":[174],"extraction":[176],"for":[177],"<tex":[181,190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[182,191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.1\\times\\sim":[183],"2.18\\times$</tex>":[184],"(the":[185],"state-of-the-art":[186],"method":[187],"Finesse)":[188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$5.66\\times\\sim":[192],"6.21\\times$</tex>":[193],"(N-trans)":[194],"increasing":[196],"ratio":[200],"up":[202],"32.5%":[204],"(18.2%":[205],"average)":[207],"(Finesse).":[208]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
