{"id":"https://openalex.org/W2783445342","doi":"https://doi.org/10.1109/bigdata.2017.8258331","title":"Scalable parallel data loading in SciDB","display_name":"Scalable parallel data loading in SciDB","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783445342","doi":"https://doi.org/10.1109/bigdata.2017.8258331","mag":"2783445342"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103696231","display_name":"Sang\u2010Chul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangchul Kim","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748040","display_name":"Junhee Lee","orcid":"https://orcid.org/0000-0002-0305-6099"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junhee Lee","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379045","display_name":"Taehoon Kim","orcid":"https://orcid.org/0000-0003-1819-968X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taehoon Kim","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006334513","display_name":"Bongki Moon","orcid":"https://orcid.org/0000-0001-9382-8306"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bongki Moon","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.1859751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3443","last_page":"3446"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/loader","display_name":"Loader","score":0.8013301491737366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929220199584961},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.721416711807251},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6094117760658264},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5740165710449219},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5261932015419006},{"id":"https://openalex.org/keywords/data-conversion","display_name":"Data conversion","score":0.5225493311882019},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5217393636703491},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5081493854522705},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.5010547637939453},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.48355838656425476},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4730226993560791},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44501882791519165},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41753262281417847},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3276548683643341},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26009243726730347},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.16989970207214355},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1058969795703888}],"concepts":[{"id":"https://openalex.org/C2779041774","wikidata":"https://www.wikidata.org/wiki/Q650550","display_name":"Loader","level":2,"score":0.8013301491737366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929220199584961},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.721416711807251},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6094117760658264},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5740165710449219},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5261932015419006},{"id":"https://openalex.org/C1232282","wikidata":"https://www.wikidata.org/wiki/Q1783551","display_name":"Data conversion","level":2,"score":0.5225493311882019},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5217393636703491},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5081493854522705},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.5010547637939453},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.48355838656425476},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4730226993560791},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44501882791519165},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41753262281417847},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3276548683643341},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26009243726730347},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.16989970207214355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1058969795703888}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1597588355","https://openalex.org/W1946667270","https://openalex.org/W1987822482","https://openalex.org/W2014830756","https://openalex.org/W2083036673","https://openalex.org/W2132624318","https://openalex.org/W6635700016"],"related_works":["https://openalex.org/W2380079908","https://openalex.org/W2360782200","https://openalex.org/W4385385304","https://openalex.org/W2365471860","https://openalex.org/W3086422166","https://openalex.org/W2053247611","https://openalex.org/W2151707824","https://openalex.org/W3024941504","https://openalex.org/W2367527146","https://openalex.org/W2195425355"],"abstract_inverted_index":{"SciDB":[0],"is":[1,19,47],"an":[2],"array-based":[3],"DBMS":[4],"popularly":[5],"used":[6],"for":[7,95],"scientific":[8,17],"data":[9,18,32,45,55,108],"analysis.":[10],"One":[11],"major":[12],"hurdle":[13],"in":[14,79],"processing":[15],"large-scale":[16],"pre-processing":[20],"before":[21],"loading":[22,46,80,109],"data,":[23],"which":[24,38,53,93],"includes":[25],"extraneous":[26],"file":[27],"conversion":[28,72],"from":[29],"a":[30,35,40,96],"raw":[31],"format":[33],"to":[34,56,65,115],"software-specific":[36],"format,":[37],"causes":[39],"significant":[41],"I/O":[42],"overhead.":[43],"Moreover,":[44],"typically":[48],"followed":[49],"by":[50,61],"array":[51],"transformation,":[52],"requires":[54],"be":[57,112],"sorted":[58],"and":[59,74,91],"redistributed":[60],"hashing.":[62],"In":[63,82],"order":[64],"reduce":[66],"the":[67,71,76,100,107,119],"overhead,":[68],"we":[69,84],"streamline":[70],"process":[73],"modify":[75],"distribution":[77],"method":[78],"stages.":[81],"addition,":[83],"eliminate":[85],"two":[86],"heavy-duty":[87],"steps,":[88],"namely":[89],"sort":[90],"redistribution,":[92],"account":[94],"dominant":[97],"portion":[98],"of":[99,122],"redimensioning":[101],"cost.":[102],"Our":[103],"experiments":[104],"show":[105],"that":[106],"time":[110],"can":[111],"reduced":[113],"up":[114],"65%":[116],"compared":[117],"with":[118],"vanilla":[120],"loader":[121],"SciDB.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}