{"id":"https://openalex.org/W3044887024","doi":"https://doi.org/10.1007/s00778-020-00620-x","title":"Faster &amp; strong: string dictionary compression using sampling and fast vectorized decompression","display_name":"Faster &amp; strong: string dictionary compression using sampling and fast vectorized decompression","publication_year":2020,"publication_date":"2020-07-20","ids":{"openalex":"https://openalex.org/W3044887024","doi":"https://doi.org/10.1007/s00778-020-00620-x","mag":"3044887024"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-020-00620-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-020-00620-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-020-00620-x.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00778-020-00620-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001343833","display_name":"Robert Lasch","orcid":"https://orcid.org/0000-0001-6491-001X"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]},{"id":"https://openalex.org/I4210132444","display_name":"Systems, Applications & Products in Data Processing (Germany)","ror":"https://ror.org/03dsc8d33","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210132444"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Robert Lasch","raw_affiliation_strings":["SAP SE, Walldorf, BW, Germany","Technische Universit\u00e4t Ilmenau, Ilmenau, TH, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6491-001X","affiliations":[{"raw_affiliation_string":"SAP SE, Walldorf, BW, Germany","institution_ids":["https://openalex.org/I4210132444"]},{"raw_affiliation_string":"Technische Universit\u00e4t Ilmenau, Ilmenau, TH, Germany","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033453497","display_name":"Ismail Oukid","orcid":"https://orcid.org/0000-0002-4253-4989"},"institutions":[{"id":"https://openalex.org/I4210132444","display_name":"Systems, Applications & Products in Data Processing (Germany)","ror":"https://ror.org/03dsc8d33","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210132444"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ismail Oukid","raw_affiliation_strings":["SAP SE, Walldorf, BW, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP SE, Walldorf, BW, Germany","institution_ids":["https://openalex.org/I4210132444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046346225","display_name":"Roman Dementiev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roman Dementiev","raw_affiliation_strings":["Intel Deutschland GmbH, Neubiberg, BY, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Deutschland GmbH, Neubiberg, BY, Germany","institution_ids":["https://openalex.org/I4210094487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040281275","display_name":"Norman May","orcid":"https://orcid.org/0000-0001-9671-0856"},"institutions":[{"id":"https://openalex.org/I4210132444","display_name":"Systems, Applications & Products in Data Processing (Germany)","ror":"https://ror.org/03dsc8d33","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210132444"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Norman May","raw_affiliation_strings":["SAP SE, Walldorf, BW, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP SE, Walldorf, BW, Germany","institution_ids":["https://openalex.org/I4210132444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058306867","display_name":"S.S. Demirsoy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Suleyman S. Demirsoy","raw_affiliation_strings":["Intel Corporation (UK) Limited, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation (UK) Limited, London, UK","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068875440","display_name":"Kai-Uwe Sattler","orcid":"https://orcid.org/0000-0003-1608-7721"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kai-Uwe Sattler","raw_affiliation_strings":["Technische Universit\u00e4t Ilmenau, Ilmenau, TH, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Ilmenau, Ilmenau, TH, Germany","institution_ids":["https://openalex.org/I119449181"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001343833"],"corresponding_institution_ids":["https://openalex.org/I119449181","https://openalex.org/I4210132444"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.4077,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69554538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"29","issue":"6","first_page":"1263","last_page":"1285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9980000257492065,"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/algorithm","display_name":"Algorithm","score":0.6725581288337708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6512027978897095},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.569778323173523},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5107017159461975},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.45849740505218506},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4425103962421417},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3695352375507355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22138309478759766},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1784254014492035}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6725581288337708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6512027978897095},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.569778323173523},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5107017159461975},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.45849740505218506},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4425103962421417},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3695352375507355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22138309478759766},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1784254014492035},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00778-020-00620-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-020-00620-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-020-00620-x.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},{"id":"pmh:oai:www.db-thueringen.de:dbt_mods_00049424","is_oa":true,"landing_page_url":"https://www.db-thueringen.de/receive/dbt_mods_00049424","pdf_url":null,"source":{"id":"https://openalex.org/S4306400120","display_name":"Common Library Network (Der Gemeinsame Bibliotheksverbund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210149878","host_organization_name":"Verbundzentrale des GBV","host_organization_lineage":["https://openalex.org/I4210149878"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:Article"}],"best_oa_location":{"id":"doi:10.1007/s00778-020-00620-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-020-00620-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-020-00620-x.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324722","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3044887024.pdf","grobid_xml":"https://content.openalex.org/works/W3044887024.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1509727978","https://openalex.org/W1607458528","https://openalex.org/W1798412263","https://openalex.org/W1820209741","https://openalex.org/W1993819379","https://openalex.org/W2000273502","https://openalex.org/W2000568570","https://openalex.org/W2002555321","https://openalex.org/W2013062050","https://openalex.org/W2037192958","https://openalex.org/W2051867864","https://openalex.org/W2086374114","https://openalex.org/W2096496252","https://openalex.org/W2099964107","https://openalex.org/W2123686039","https://openalex.org/W2156930555","https://openalex.org/W2295448598","https://openalex.org/W2396727930","https://openalex.org/W2401640580","https://openalex.org/W2484217851","https://openalex.org/W2602771387","https://openalex.org/W2791275773","https://openalex.org/W2955799495","https://openalex.org/W2979888527","https://openalex.org/W3031206277","https://openalex.org/W3084651990"],"related_works":["https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W2161302774","https://openalex.org/W4383723869","https://openalex.org/W4384298135","https://openalex.org/W4293703255","https://openalex.org/W4383722264","https://openalex.org/W2388481516","https://openalex.org/W2271907651"],"abstract_inverted_index":{"Abstract":[0],"String":[1],"dictionaries":[2],"constitute":[3],"a":[4,58,126,202],"large":[5,101],"portion":[6],"of":[7,11,91,110,213],"the":[8,73,92,211],"memory":[9],"footprint":[10],"database":[12,208],"applications.":[13],"While":[14],"strong":[15,46],"string":[16,47,102,181],"dictionary":[17,48],"compression":[18,27,49,60,67,77,97,165,215],"algorithms":[19,31,71],"exist,":[20],"these":[21],"come":[22],"with":[23],"impractical":[24],"access":[25,122,128,217],"and":[26,179],"times.":[28],"Therefore,":[29],"lightweight":[30],"such":[32],"as":[33],"front":[34],"coding":[35],"(PFC)":[36],"are":[37],"favored":[38],"in":[39,72,86,207],"practice.":[40],"This":[41],"paper":[42],"endeavors":[43],"to":[44,115,120,168],"make":[45],"practical.":[50],"We":[51],"focus":[52],"on":[53,100,193],"Re-Pair":[54],"Front":[55],"Coding":[56],"(RPFC),":[57],"grammar-based":[59],"algorithm,":[61],"since":[62],"it":[63],"consistently":[64],"offers":[65,164],"better":[66],"ratios":[68],"than":[69,177,191],"other":[70],"literature.":[74],"To":[75],"accelerate":[76,121],"times,":[78,123],"we":[79,104,124],"propose":[80,106],"block-based":[81],"RPFC":[82,192,200],"(BRPFC)":[83],"which":[84],"consists":[85],"independently":[87],"compressing":[88],"small":[89],"blocks":[90],"dictionary.":[93],"For":[94],"further":[95],"accelerated":[96],"times":[98,166,218],"especially":[99],"dictionaries,":[103],"also":[105],"an":[107],"alternative":[108],"version":[109],"BRPFC":[111,163],"that":[112,161],"uses":[113],"sampling":[114],"speed":[116],"up":[117,167],"compression.":[118],"Moreover,":[119],"devise":[125],"vectorized":[127],"method,":[129],"using":[130],"$$\\hbox":[131,146],"{Intel}^{\\circledR":[132,147],"}$$":[133,148],"<mml:math":[134,149,172,186,226],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[135,150,173,187,227],"<mml:msup>":[136,151],"<mml:mtext>Intel</mml:mtext>":[137,152],"<mml:mo>\u00ae</mml:mo>":[138,153],"</mml:msup>":[139,154],"</mml:math>":[140,155,175,189,229],"Advanced":[141],"Vector":[142],"Extensions":[143],"512":[144],"(":[145],"AVX-512).":[156],"Our":[157],"experimental":[158],"evaluation":[159],"shows":[160],"sampled":[162],"190":[169],"$$\\times":[170,184,224],"$$":[171,185,225],"<mml:mo>\u00d7</mml:mo>":[174,188,228],"faster":[176,190],"RPFC,":[178],"random":[180],"lookups":[182],"2.3":[183],"average.":[194],"These":[195],"results":[196],"move":[197],"our":[198],"modified":[199],"into":[201],"practical":[203],"range":[204],"for":[205,216],"use":[206],"systems":[209],"because":[210],"overhead":[212],"Re-Pair-based":[214],"can":[219],"be":[220],"reduced":[221],"by":[222],"2":[223],".":[230]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2020-07-29T00:00:00"}
