{"id":"https://openalex.org/W4412593892","doi":"https://doi.org/10.1145/3750447","title":"SampDedup: Sampling Prediction for Efficient Inline Data Deduplication on Non-volatile Memory","display_name":"SampDedup: Sampling Prediction for Efficient Inline Data Deduplication on Non-volatile Memory","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4412593892","doi":"https://doi.org/10.1145/3750447"},"language":"en","primary_location":{"id":"doi:10.1145/3750447","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750447","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3750447","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103851608","display_name":"Ziyue Xu","orcid":"https://orcid.org/0009-0000-5171-2794"},"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":"Ziyue Xu","raw_affiliation_strings":["Nankai University","Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-5171-2794","affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yichen Li","orcid":"https://orcid.org/0009-0008-9167-5746"},"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":"Yichen Li","raw_affiliation_strings":["Computer Science, Nankai University","Nankai University","Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0008-9167-5746","affiliations":[{"raw_affiliation_string":"Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119051781","display_name":"Ranzhe Deng","orcid":null},"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":"Ranzhe Deng","raw_affiliation_strings":["Nankai University","Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0005-5631-7415","affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010021903","display_name":"Liping Yi","orcid":"https://orcid.org/0000-0001-6236-3673"},"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":"Liping Yi","raw_affiliation_strings":["Nankai University","Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6236-3673","affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026498734","display_name":"Yusen Li","orcid":"https://orcid.org/0000-0001-6623-350X"},"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":"Yusen Li","raw_affiliation_strings":["Computer Science, Nankai University","Nankai University","Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6623-350X","affiliations":[{"raw_affiliation_string":"Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Computer Science, 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":["Computer Science, Nankai University","Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0387-2501","affiliations":[{"raw_affiliation_string":"Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Computer Science, 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":["Computer Science, Nankai University","Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-9010-3278","affiliations":[{"raw_affiliation_string":"Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1797361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.996999979019165,"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/T11719","display_name":"Data Quality and Management","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8121417760848999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7741459608078003},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5975707173347473},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3749869465827942},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19211405515670776}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8121417760848999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741459608078003},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5975707173347473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3749869465827942},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19211405515670776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3750447","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750447","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3750447","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750447","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3014824142","display_name":null,"funder_award_id":"62272253, 62272252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W178328500","https://openalex.org/W604518226","https://openalex.org/W1969335064","https://openalex.org/W1976024527","https://openalex.org/W1987201308","https://openalex.org/W2073370301","https://openalex.org/W2110322986","https://openalex.org/W2475932436","https://openalex.org/W2605532879","https://openalex.org/W2734941459","https://openalex.org/W2770331085","https://openalex.org/W2903617882","https://openalex.org/W2912601938","https://openalex.org/W2918722987","https://openalex.org/W3004612141","https://openalex.org/W3014193728","https://openalex.org/W3048921870","https://openalex.org/W4249672879","https://openalex.org/W4253550658","https://openalex.org/W4390357255","https://openalex.org/W6736224497"],"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/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W4410300319"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,17,45,57,72,100,136,288,309],"is":[2,103,168,208,225],"an":[3,34,221],"effective":[4],"technique":[5,46],"for":[6,49,181,249],"reducing":[7,139],"redundant":[8],"data":[9,27,121,146,157,251,287,296],"storage":[10,14,36,50,75],"space":[11],"in":[12],"various":[13],"systems.":[15],"Generally,":[16],"consists":[18],"of":[19,66,232],"four":[20,277],"steps:":[21],"chunking,":[22],"fingerprinting,":[23],"fingerprint":[24,84,152,237,244],"lookup,":[25],"and":[26,80,86,142,151,178,193,220,246,258,295],"management.":[28],"Recently,":[29],"Non-volatile":[30],"Memory":[31],"(NVM)":[32],"as":[33,78],"emerging":[35],"device":[37],"has":[38],"received":[39],"widespread":[40],"attention.":[41],"Directly":[42],"applying":[43],"the":[44,67,107,203,213,229,266],"on":[47,58,73,101,128,256,276,290],"NVM":[48,59,96,102,129,291],"cost":[51],"savings":[52],"faces":[53],"many":[54],"challenges:":[55],"(a)":[56,155],"devices":[60,76],"suffers":[61],"from":[62],"computation":[63,140],"bottleneck":[64,69],"instead":[65],"I/O":[68],"faced":[70],"by":[71,144,218,254],"traditional":[74,267],"(such":[77],"HDD":[79],"SSD);":[81],"(b)":[82,199],"new":[83],"indexes":[85],"metadata":[87,247],"are":[88],"required":[89],"to":[90,93,95,106,133,170,174,211,227,264,271],"be":[91,186],"re-designed":[92],"adapt":[94],"characteristics;":[97],"(c)":[98,235],"inline":[99,120,286],"more":[104,301],"sensitive":[105],"latency.":[108],"To":[109],"solve":[110],"these":[111],"challenges,":[112],"we":[113,240,259],"propose":[114],"a":[115,160,242,261],"novel":[116],"Samp":[117],"ling":[118],"prediction-based":[119,162],"Dedup":[122],"lication":[123],"method":[124,164,184,224],"(":[125,165],"SampDedup":[126,282],")":[127,167],"devices.":[130],"It":[131],"aims":[132],"ensure":[134],"high":[135,285],"ratios":[137,289],"while":[138,299],"costs":[141],"latency":[143,231],"optimizing":[145],"chunking":[147,158,163,197,304],",":[148,150,159,202,239],"fingerprinting":[149,201,223,230],"lookup":[153,238],".":[154],"For":[156,200,236],"sampling":[161],"SampChunk":[166,255],"proposed":[169,226],"leverage":[171],"chunk":[172,252],"similarity":[173],"distinguish":[175],"duplicate":[176],"chunks":[177],"skip":[179],"them":[180],"chunking.":[182],"This":[183],"can":[185],"easily":[187],"integrated":[188],"into":[189],"most":[190],"sliding-window":[191],"based":[192,195],"non-window":[194],"CDC":[196],"algorithms.":[198],"commonly":[204],"used":[205],"SHA-1":[206],"algorithm":[207],"further":[209],"optimized":[210],"reduce":[212,228],"extra":[214],"computational":[215],"overhead":[216],"introduced":[217],"SampChunk,":[219],"asynchronous":[222],"unique":[233],"chunks.":[234],"design":[241],"header":[243],"index":[245],"table":[248],"each":[250],"constructed":[253],"NVM,":[257],"use":[260],"fast-read":[262],"buffer":[263],"replace":[265],"slow":[268],"LRU":[269],"cache":[270],"improve":[272],"search":[273],"efficiency.":[274],"Experiments":[275],"real-world":[278],"datasets":[279],"demonstrate":[280],"that":[281],"consistently":[283],"presents":[284],"with":[292,307],"different":[293],"workloads":[294],"partitioning":[297],"algorithms":[298],"saving":[300],"than":[302],"90%":[303],"time":[305],"compared":[306],"state-of-the-art":[308],"baselines.":[310]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}