{"id":"https://openalex.org/W1993017904","doi":"https://doi.org/10.1109/bigdata.2014.7004238","title":"Virtual chunks: On supporting random accesses to scientific data in compressible storage systems","display_name":"Virtual chunks: On supporting random accesses to scientific data in compressible storage systems","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1993017904","doi":"https://doi.org/10.1109/bigdata.2014.7004238","mag":"1993017904"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5101671477","display_name":"Dongfang Zhao","orcid":"https://orcid.org/0000-0002-0677-634X"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Zhao","raw_affiliation_strings":["Illinois Institute of Technology","Pacific Northwest National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102961198","display_name":"Jian Yin","orcid":"https://orcid.org/0000-0002-4820-0226"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Yin","raw_affiliation_strings":["Pacific Northwest National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109800827","display_name":"Kan Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kan Qiao","raw_affiliation_strings":["Google Inc","Illinois Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030599558","display_name":"Ioan Raicu","orcid":"https://orcid.org/0000-0002-5477-439X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioan Raicu","raw_affiliation_strings":["Argonne National Lab","Illinois Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Lab","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.239,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92403948,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9933000206947327,"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":0.8231045007705688},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5964969396591187},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5726427435874939},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5678048729896545},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.5467610955238342},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.5407443642616272},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5026822090148926},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5012612342834473},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4572257101535797},{"id":"https://openalex.org/keywords/versioning-file-system","display_name":"Versioning file system","score":0.4287574887275696},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.42667242884635925},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32086870074272156},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.24665188789367676},{"id":"https://openalex.org/keywords/device-file","display_name":"Device file","score":0.2190006673336029},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20283737778663635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231045007705688},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5964969396591187},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5726427435874939},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5678048729896545},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5467610955238342},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.5407443642616272},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5026822090148926},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5012612342834473},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4572257101535797},{"id":"https://openalex.org/C166807848","wikidata":"https://www.wikidata.org/wiki/Q3445065","display_name":"Versioning file system","level":4,"score":0.4287574887275696},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.42667242884635925},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32086870074272156},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.24665188789367676},{"id":"https://openalex.org/C193769178","wikidata":"https://www.wikidata.org/wiki/Q14679","display_name":"Device file","level":3,"score":0.2190006673336029},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20283737778663635},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2014.7004238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.1148","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.1148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://datasys.cs.iit.edu/publications/2014_BigData14_virtual-chunks.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W47974043","https://openalex.org/W114584783","https://openalex.org/W125125877","https://openalex.org/W1263893056","https://openalex.org/W1445823765","https://openalex.org/W1547213911","https://openalex.org/W1741747329","https://openalex.org/W1947728686","https://openalex.org/W1976306141","https://openalex.org/W1982183261","https://openalex.org/W1983041039","https://openalex.org/W2004010764","https://openalex.org/W2011669485","https://openalex.org/W2014638002","https://openalex.org/W2032140429","https://openalex.org/W2037724609","https://openalex.org/W2039787039","https://openalex.org/W2047899835","https://openalex.org/W2056980397","https://openalex.org/W2078455494","https://openalex.org/W2081903609","https://openalex.org/W2109485293","https://openalex.org/W2111122809","https://openalex.org/W2119738171","https://openalex.org/W2131645490","https://openalex.org/W2135377936","https://openalex.org/W2137512117","https://openalex.org/W2143172733","https://openalex.org/W2146713313","https://openalex.org/W2146917903","https://openalex.org/W2152101064","https://openalex.org/W2157982158","https://openalex.org/W2158242750","https://openalex.org/W2168067900","https://openalex.org/W2571659063","https://openalex.org/W2913877777","https://openalex.org/W4245521866","https://openalex.org/W4252909492","https://openalex.org/W4285719527","https://openalex.org/W6604616335","https://openalex.org/W6605087653","https://openalex.org/W6628090092","https://openalex.org/W6628236356","https://openalex.org/W6637764636","https://openalex.org/W6653327530","https://openalex.org/W6660107051","https://openalex.org/W6660424939","https://openalex.org/W6670243553","https://openalex.org/W6679471073","https://openalex.org/W6758543619"],"related_works":["https://openalex.org/W3047599943","https://openalex.org/W3080614128","https://openalex.org/W4381744720","https://openalex.org/W2088378984","https://openalex.org/W4200061735","https://openalex.org/W3042208251","https://openalex.org/W196652493","https://openalex.org/W1481669841","https://openalex.org/W4247882433","https://openalex.org/W37510483"],"abstract_inverted_index":{"Data":[0],"compression":[1,22,37,40,66,93,117,163,188],"could":[2,239],"ameliorate":[3],"the":[4,15,24,29,48,56,59,62,72,81,110,132,136,143,156,182,187,214,223,242],"I/O":[5,243],"pressure":[6],"of":[7,18,61,135,173],"scientific":[8,112],"applications":[9],"on":[10,165,177,230],"high-performance":[11],"computing":[12],"systems.":[13],"Unfortunately,":[14],"conventional":[16],"wisdom":[17],"naively":[19],"applying":[20,80],"data":[21,113],"to":[23,47,71,83,104,109,145,160,213,232],"file":[25,137,217,226],"or":[26],"block":[27,86],"brings":[28],"dilemma":[30],"between":[31],"efficient":[32,44,106],"random":[33,45,69,107,152],"accesses":[34,46,70,108],"and":[35,154,194,219],"high":[36,162],"ratios.":[38],"Filelevel":[39],"can":[41],"barely":[42],"support":[43,105],"compressed":[49,63,73,111],"data:":[50],"any":[51],"retrieval":[52],"request":[53],"need":[54],"trigger":[55],"decompression":[57,144],"from":[58,147],"beginning":[60],"file.":[64],"Block-level":[65],"provides":[67],"flexible":[68],"data,":[74],"but":[75,190],"introduces":[76,97],"extra":[77],"overhead":[78,180,200],"when":[79],"compressor":[82],"each":[84],"every":[85],"that":[87,185,198,236],"results":[88,196],"in":[89,208,222],"a":[90,98,211,220],"degraded":[91],"overall":[92],"ratio.":[94,118],"This":[95],"paper":[96],"concept":[99],"called":[100],"virtual":[101,121,174,206,237],"chunks":[102,122,175,207,238],"aiming":[103],"without":[114,130],"sacrificing":[115],"its":[116,178],"In":[119],"essence,":[120],"are":[123],"logical":[124],"blocks":[125],"identified":[126],"by":[127,245],"appended":[128],"references":[129,141],"breaking":[131],"physical":[133,158],"continuity":[134],"content.":[138],"These":[139],"additional":[140,183],"allow":[142],"start":[146],"an":[148],"arbitrary":[149],"position":[150],"(efficient":[151],"access),":[153],"retain":[155],"file's":[157],"entirety":[159],"achieve":[161],"ratio":[164],"par":[166],"with":[167],"file-level":[168],"compression.":[169],"One":[170],"potential":[171],"concern":[172],"lies":[176],"space":[179],"(from":[181],"references)":[184],"degrades":[186],"ratio,":[189],"our":[191],"analytic":[192],"study":[193],"experimental":[195],"demonstrate":[197],"such":[199],"is":[201],"negligible.":[202],"We":[203],"have":[204],"implemented":[205],"two":[209],"forms:":[210],"middleware":[212],"GPFS":[215],"parallel":[216],"system,":[218],"module":[221],"FusionFS":[224],"distributed":[225],"system.":[227],"Large-scale":[228],"evaluations":[229],"up":[231],"1,024":[233],"cores":[234],"showed":[235],"help":[240],"improve":[241],"throughput":[244],"2X":[246],"speedup.":[247]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}