{"id":"https://openalex.org/W4414198693","doi":"https://doi.org/10.1109/dac63849.2025.11133045","title":"PIMDup: An Optimized Deduplication Design on a Real Processing-in-Memory System","display_name":"PIMDup: An Optimized Deduplication Design on a Real Processing-in-Memory System","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414198693","doi":"https://doi.org/10.1109/dac63849.2025.11133045"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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":null,"display_name":"Chun-Le Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Le Yeh","raw_affiliation_strings":["National Cheng Kung University,Department of CSIE,Tainan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of CSIE,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056850965","display_name":"Liang-Chi Chen","orcid":"https://orcid.org/0000-0003-2579-4305"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Liang-Chi Chen","raw_affiliation_strings":["National Cheng Kung University,Department of CSIE,Tainan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of CSIE,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044099250","display_name":"Chien-Chung Ho","orcid":"https://orcid.org/0000-0003-3460-8674"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Chung Ho","raw_affiliation_strings":["National Cheng Kung University,Department of CSIE,Tainan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of CSIE,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860440","display_name":"Yu-Ming Chang","orcid":"https://orcid.org/0000-0002-1409-0874"},"institutions":[{"id":"https://openalex.org/I4210132337","display_name":"GenMont Biotech (Taiwan)","ror":"https://ror.org/0410a6k82","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210132337"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ming Chang","raw_affiliation_strings":["Wolley Inc.,Tainan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Wolley Inc.,Tainan,Taiwan","institution_ids":["https://openalex.org/I4210132337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050773996","display_name":"Da\u2010Wei Chang","orcid":"https://orcid.org/0000-0002-4317-7979"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Wei Chang","raw_affiliation_strings":["National Cheng Kung University,Department of CSIE,Tainan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of CSIE,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":1.3852,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85929809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9883000254631042,"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":0.9883000254631042,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9871000051498413,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.955299973487854,"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/data-deduplication","display_name":"Data deduplication","score":0.9715999960899353},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.8263000249862671},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5964999794960022},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46619999408721924},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.42410001158714294},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.3522999882698059},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.34940001368522644},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.2973000109195709}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9715999960899353},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8263000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199999928474426},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.2728999853134155},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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":26,"referenced_works":["https://openalex.org/W1553098517","https://openalex.org/W1976024527","https://openalex.org/W2038908732","https://openalex.org/W2048606985","https://openalex.org/W2051195564","https://openalex.org/W2056980397","https://openalex.org/W2110322986","https://openalex.org/W2116047956","https://openalex.org/W2139274913","https://openalex.org/W2295528854","https://openalex.org/W2471653467","https://openalex.org/W2536680672","https://openalex.org/W2729713725","https://openalex.org/W2935106878","https://openalex.org/W2945335752","https://openalex.org/W2982008795","https://openalex.org/W3111721177","https://openalex.org/W3202917172","https://openalex.org/W3207769829","https://openalex.org/W4284886102","https://openalex.org/W4297098423","https://openalex.org/W4304699827","https://openalex.org/W4380624154","https://openalex.org/W4386764197","https://openalex.org/W4393407040","https://openalex.org/W4399174482"],"related_works":[],"abstract_inverted_index":{"Data":[0],"deduplication":[1,107,137,164],"enhances":[2],"storage":[3,67],"efficiency":[4],"through":[5,143],"non-destructive":[6],"compression":[7],"but":[8],"is":[9],"often":[10],"hindered":[11],"by":[12,98],"the":[13,19,60,119],"chunking":[14,147,160],"process,":[15],"which":[16],"requires":[17],"scanning":[18],"entire":[20],"dataset.":[21],"While":[22],"traditional":[23],"methods":[24],"leveraging":[25],"conventional":[26],"architectures":[27],"and":[28,33,52,66,79,125,149],"hardware":[29],"accelerators":[30],"(e.g.,":[31],"GPUs":[32],"FPGAs)":[34],"have":[35],"been":[36],"developed":[37],"to":[38,44,48],"address":[39],"this":[40],"issue,":[41],"they":[42],"continue":[43],"face":[45],"challenges":[46],"related":[47],"excessive":[49],"data":[50,96,117,151],"movement":[51,97],"associated":[53],"performance":[54,161],"degradation.":[55],"These":[56],"limitations":[57],"stem":[58],"from":[59],"von":[61],"Neumann":[62],"architecture,":[63],"where":[64],"computation":[65],"are":[68],"separated":[69],"in":[70],"a":[71,90,106,135,167],"processor-centric":[72],"design,":[73],"necessitating":[74],"multiple":[75],"memory":[76],"hierarchy":[77],"traversals":[78],"causing":[80],"inefficiencies.":[81],"To":[82],"overcome":[83],"these":[84,141],"challenges,":[85],"we":[86,132],"explore":[87],"UPMEM\u2019s":[88],"DPU,":[89],"processing-in-memory":[91],"(PIM)":[92],"technology":[93],"that":[94,139,157],"reduces":[95],"performing":[99],"computations":[100],"directly":[101],"within":[102],"memory.":[103],"However,":[104],"designing":[105],"system":[108,138],"for":[109],"DPUs":[110],"presents":[111],"unique":[112],"obstacles,":[113],"including":[114],"restricted":[115],"inter-DPU":[116],"sharing,":[118],"absence":[120],"of":[121],"native":[122],"multiplication":[123],"support,":[124],"significant":[126],"DPU-CPU":[127],"communication":[128],"overhead.":[129],"In":[130],"response,":[131],"propose":[133],"PIMDup,":[134],"DPU-optimized":[136],"addresses":[140],"constraints":[142],"efficient":[144],"parallelization,":[145],"DPU-friendly":[146],"techniques,":[148],"reduced":[150],"transfer":[152],"volumes.":[153],"Experimental":[154],"results":[155],"demonstrate":[156],"PIMDup":[158],"improves":[159],"without":[162],"compromising":[163],"accuracy,":[165],"achieving":[166],"$1.67":[168],"\\times$":[169],"speedup":[170],"over":[171],"CPU-based":[172],"systems":[173],"while":[174],"maintaining":[175],"100%":[176],"result":[177],"consistency.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}