{"id":"https://openalex.org/W4200118971","doi":"https://doi.org/10.1109/hpec49654.2021.9622826","title":"Privateer: Multi-versioned Memory-mapped Data Stores for High-Performance Data Science","display_name":"Privateer: Multi-versioned Memory-mapped Data Stores for High-Performance Data Science","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200118971","doi":"https://doi.org/10.1109/hpec49654.2021.9622826"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5103003875","display_name":"Karim Youssef","orcid":"https://orcid.org/0000-0003-4544-9613"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karim Youssef","raw_affiliation_strings":["Center for Applied Scientific Computing, Lawrence Livermore National Laboratory","Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Center for Applied Scientific Computing, Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021147616","display_name":"Keita Iwabuchi","orcid":"https://orcid.org/0000-0002-9395-0843"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keita Iwabuchi","raw_affiliation_strings":["Center for Applied Scientific Computing, Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Center for Applied Scientific Computing, Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-Chun Feng","raw_affiliation_strings":["Virginia Tech"],"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046256174","display_name":"Roger Pearce","orcid":"https://orcid.org/0009-0000-6449-6568"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger Pearce","raw_affiliation_strings":["Center for Applied Scientific Computing, Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Center for Applied Scientific Computing, Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103003875"],"corresponding_institution_ids":["https://openalex.org/I1282311441","https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.1528,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53442508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"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":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/T11478","display_name":"Caching and Content Delivery","score":0.998199999332428,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8127102851867676},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.69969242811203},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6558209657669067},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.5195120573043823},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5000159740447998},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4881661534309387},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41678112745285034},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3592754602432251},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.25966209173202515},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2300635278224945},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2261675000190735},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22519639134407043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127102851867676},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.69969242811203},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6558209657669067},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5195120573043823},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5000159740447998},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4881661534309387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41678112745285034},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3592754602432251},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25966209173202515},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2300635278224945},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2261675000190735},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22519639134407043}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1576397915","https://openalex.org/W1859126261","https://openalex.org/W1916385248","https://openalex.org/W2011547799","https://openalex.org/W2068739275","https://openalex.org/W2104846587","https://openalex.org/W2209663295","https://openalex.org/W2584004798","https://openalex.org/W2996801272","https://openalex.org/W2997483548","https://openalex.org/W3011296477","https://openalex.org/W3013987090","https://openalex.org/W3045173794","https://openalex.org/W3123211294","https://openalex.org/W3166667480","https://openalex.org/W3194838959","https://openalex.org/W6634463810","https://openalex.org/W6732409977","https://openalex.org/W6781652579","https://openalex.org/W6796382203","https://openalex.org/W6800097172"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W2011430815","https://openalex.org/W12581771","https://openalex.org/W4321606653","https://openalex.org/W3170260665","https://openalex.org/W3008013744","https://openalex.org/W2884042376","https://openalex.org/W2077135008","https://openalex.org/W223870977","https://openalex.org/W2615141153"],"abstract_inverted_index":{"The":[0],"exponential":[1],"growth":[2],"in":[3,57],"dataset":[4],"sizes":[5,19],"necessitates":[6],"the":[7,18,24,28,32,72,81,111,114,130,172,180,210,222],"use":[8],"of":[9,20,74,84,98,113,174,184,201],"high-performance":[10],"computing":[11],"(HPC)":[12],"for":[13],"large-scale":[14,85],"data":[15,86,101,126,189,205],"science.":[16],"Furthermore,":[17],"these":[21,75],"datasets":[22],"shift":[23],"performance":[25,220],"bottleneck":[26,68],"from":[27],"compute":[29],"subsystem":[30],"towards":[31],"memory":[33],"and":[34,48,94,136,146,155,198],"I/O":[35,60,137,142],"subsystems.":[36],"To":[37,117],"address":[38,118],"this":[39,119],"shift,":[40],"modern":[41],"HPC":[42],"clusters":[43],"are":[44],"equipped":[45],"with":[46,143],"low-latency":[47],"high-bandwidth":[49],"storage":[50,76,82,106,115,133,163,166,211],"devices,":[51],"such":[52],"as":[53,179],"non-volatile":[54],"memory,":[55],"and,":[56],"turn,":[58],"re-designed":[59],"subsystems":[61],"to":[62,71,151,164,221],"improve":[63],"performance.":[64,138],"However,":[65],"an":[66,147,202],"overlooked":[67],"arises":[69],"due":[70],"size":[73,112],"devices":[77],"being":[78],"dwarfed":[79],"by":[80,176,214],"footprint":[83,107],"science":[87],"applications.":[88],"For":[89],"instance,":[90],"applications":[91],"that":[92,108,128,195],"process":[93],"store":[95,127],"consistent":[96],"snapshots":[97,200],"incrementally":[99,196],"growing":[100],"streams":[102],"require":[103],"a":[104,124,186,193],"significant":[105],"far":[109],"outstrips":[110],"devices.":[116],"bottleneck,":[120],"we":[121],"present":[122],"Privateer,":[123],"general-purpose":[125],"optimizes":[129],"tradeoff":[131],"between":[132],"space":[134,167,212],"utilization":[135],"Privateer":[139,175,207],"uses":[140,161],"memory-mapped":[141],"private":[144],"mapping":[145],"optimized":[148],"writeback":[149],"mechanism":[150],"maximize":[152],"write":[153],"parallelism":[154],"eliminate":[156],"redundant":[157],"writes;":[158],"it":[159,178],"also":[160],"content-addressable":[162],"optimize":[165],"via":[168],"de-duplication.":[169],"We":[170],"evaluate":[171],"effectiveness":[173],"using":[177],"data-store":[181],"management":[182],"layer":[183],"Metall,":[185],"persistent":[187],"C++":[188],"structure":[190],"allocator.":[191],"Using":[192],"micro-benchmark":[194],"constructs":[197],"stores":[199],"incremental":[203],"graph":[204],"structure,":[206],"can":[208],"reduce":[209],"used":[213],"approximately":[215],"30%":[216],"while":[217],"delivering":[218],"comparable":[219],"baseline":[223],"Metall":[224],"implementation.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}