{"id":"https://openalex.org/W2890624321","doi":"https://doi.org/10.1109/tc.2018.2871116","title":"ApproxSSD: Data Layout Aware Sampling on an Array of SSDs","display_name":"ApproxSSD: Data Layout Aware Sampling on an Array of SSDs","publication_year":2018,"publication_date":"2018-09-20","ids":{"openalex":"https://openalex.org/W2890624321","doi":"https://doi.org/10.1109/tc.2018.2871116","mag":"2890624321"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2018.2871116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2018.2871116","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5005773038","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-5295-4680"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0001-5295-4680","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058026627","display_name":"Huafeng Wu","orcid":"https://orcid.org/0000-0002-3150-3407"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Wu","raw_affiliation_strings":["College of Information Engineering, Shanghai Maritime University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3150-3407","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384682","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-0926-4761"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0926-4761","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56202964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"68","issue":"4","first_page":"471","last_page":"483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8756491541862488},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5858839154243469},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5827503204345703},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.561149537563324},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5369455814361572},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5038346648216248},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.42908358573913574},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42436376214027405},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.41865724325180054},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41782650351524353},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3612782657146454},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2551696300506592},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23609906435012817},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1698535978794098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8756491541862488},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5858839154243469},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5827503204345703},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.561149537563324},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5369455814361572},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5038346648216248},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.42908358573913574},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42436376214027405},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.41865724325180054},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41782650351524353},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3612782657146454},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2551696300506592},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23609906435012817},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1698535978794098},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2018.2871116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2018.2871116","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W142764049","https://openalex.org/W410850256","https://openalex.org/W1504340080","https://openalex.org/W1575777113","https://openalex.org/W1587463421","https://openalex.org/W1788180225","https://openalex.org/W1876812886","https://openalex.org/W1884620995","https://openalex.org/W1945708402","https://openalex.org/W1982063824","https://openalex.org/W1996198089","https://openalex.org/W1999984505","https://openalex.org/W2002791618","https://openalex.org/W2022038016","https://openalex.org/W2044782015","https://openalex.org/W2053076698","https://openalex.org/W2071183703","https://openalex.org/W2071989194","https://openalex.org/W2096635965","https://openalex.org/W2103212156","https://openalex.org/W2117897510","https://openalex.org/W2126603706","https://openalex.org/W2129821171","https://openalex.org/W2130484710","https://openalex.org/W2131975293","https://openalex.org/W2132711844","https://openalex.org/W2134342155","https://openalex.org/W2136225018","https://openalex.org/W2137267093","https://openalex.org/W2141249441","https://openalex.org/W2150915951","https://openalex.org/W2153631439","https://openalex.org/W2155256331","https://openalex.org/W2165068957","https://openalex.org/W2170037597","https://openalex.org/W2170616854","https://openalex.org/W2293724167","https://openalex.org/W2294497304","https://openalex.org/W2409236379","https://openalex.org/W2425594935","https://openalex.org/W2506776957","https://openalex.org/W2578054369","https://openalex.org/W2604445413","https://openalex.org/W2963098024","https://openalex.org/W2963288913","https://openalex.org/W2995564009","https://openalex.org/W3150215247","https://openalex.org/W4232486673","https://openalex.org/W4243947174","https://openalex.org/W4299827484","https://openalex.org/W6605716994","https://openalex.org/W6614148910","https://openalex.org/W6634667783","https://openalex.org/W6638233953","https://openalex.org/W6639324668","https://openalex.org/W6640836205","https://openalex.org/W6650418438","https://openalex.org/W6679248497","https://openalex.org/W6679385738","https://openalex.org/W6679815717","https://openalex.org/W6684515133","https://openalex.org/W6685012337","https://openalex.org/W6696730828","https://openalex.org/W6697158694","https://openalex.org/W6714404938"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W4245701730","https://openalex.org/W2511794504","https://openalex.org/W2911648135","https://openalex.org/W3092201768","https://openalex.org/W2886451445","https://openalex.org/W3108449883","https://openalex.org/W2551093110","https://openalex.org/W2796632413"],"abstract_inverted_index":{"Execution":[0],"of":[1,44,108,113,141,199,227],"analytic":[2],"frameworks":[3,94],"on":[4,162,183],"sample":[5,49,134],"data":[6,16,37,50,68,71,86,92,136,160,181,190],"sets":[7],"is":[8,110,144],"the":[9,31,42,81,85,102,128,131,139,197,206],"current":[10],"trend":[11,132],"in":[12,70,80,91,208,229],"response":[13],"to":[14,61,63,124,147,166,177,195,241,258],"increasing":[15],"size":[17],"and":[18,138,151,192,216],"demand":[19],"for":[20,35],"real-time":[21],"analysis.":[22],"Additionally,":[23],"high-performance,":[24],"energy-efficient":[25],"Solid-State":[26],"Drive":[27],"(SSD)":[28],"arrays":[29,46],"are":[30],"primary":[32],"storage":[33],"subsystem":[34],"parallel":[36],"analysis":[38,93],"systems.":[39],"To":[40],"exploit":[41],"benefits":[43],"SSD":[45,184],"when":[47,256],"executing":[48],"set":[51,135],"analytics,":[52],"several":[53],"key":[54],"areas":[55],"must":[56],"be":[57,125],"considered.":[58],"First,":[59],"due":[60],"logical":[62],"physical":[64],"address":[65],"translation,":[66],"random":[67],"choice":[69],"sampling":[72,182,249,254],"jobs":[73],"can":[74,95,238],"cause":[75],"unbalanced":[76],"workloads":[77,150],"among":[78],"SSDs":[79,109,163],"array.":[82],"Second,":[83],"after":[84],"choice,":[87],"existing":[88],"task":[89,193,209],"schedulers":[90],"introduce":[96],"non-negligible":[97],"resource":[98,153],"contentions":[99,215],"resulting":[100],"from":[101,168,205],"suboptimal":[103,217],"Input/Output":[104],"(I/O).":[105],"The":[106],"performance":[107,169,198],"unpredictable":[111],"because":[112],"their":[114],"varying":[115],"maintenance":[116],"costs":[117],"at":[118,231,246],"runtime,":[119],"which":[120],"renders":[121],"them":[122],"hard":[123],"managed":[126],"by":[127],"scheduler.":[129],"With":[130],"towards":[133],"analytics":[137,161],"use":[140],"SSDs,":[142],"it":[143],"increasingly":[145],"important":[146],"ensure":[148],"balanced":[149],"minimize":[152],"contention.":[154],"Without":[155],"addressing":[156],"these":[157],"areas,":[158],"sample-set":[159],"will":[164],"continue":[165],"suffer":[167],"inefficiencies.":[170],"In":[171],"this":[172],"paper,":[173],"we":[174],"propose":[175],"ApproxSSD":[176,202,228,237],"perform":[178],"on-disk":[179],"layout-aware":[180],"arrays.":[185],"This":[186,211],"proposed":[187],"framework":[188],"leverages":[189],"selection":[191],"scheduling":[194],"improve":[196],"many":[200],"applications.":[201],"decouples":[203],"I/O":[204,214],"computation":[207],"execution.":[210],"avoids":[212],"potential":[213],"workload":[218,255],"balances.":[219],"We":[220],"have":[221],"developed":[222],"an":[223,252],"open-source":[224],"prototype":[225],"system":[226],"Scala":[230],"Github.":[232],"Our":[233],"evaluation":[234],"shows":[235],"that":[236],"achieve":[239],"up":[240,245],"2.7":[242],"times":[243],"speed":[244],"10":[247],"percent":[248],"ratio":[250],"under":[251],"example":[253],"compared":[257],"Spark,":[259],"while":[260],"simultaneously":[261],"maintaining":[262],"high":[263],"output":[264],"accuracy.":[265]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}