{"id":"https://openalex.org/W2034675860","doi":"https://doi.org/10.1109/padsw.2014.7097856","title":"Simplifying index file structure to improve I/O performance of parallel indexing","display_name":"Simplifying index file structure to improve I/O performance of parallel indexing","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2034675860","doi":"https://doi.org/10.1109/padsw.2014.7097856","mag":"2034675860"},"language":"en","primary_location":{"id":"doi:10.1109/padsw.2014.7097856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","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/A5018147496","display_name":"Hsuan-Te Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hsuan-Te Chiu","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, TW","[National Tsing Hua Univ., Taiwan]"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, TW","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"[National Tsing Hua Univ., Taiwan]","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005498754","display_name":"Jerry Chou","orcid":"https://orcid.org/0000-0001-7851-1140"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jerry Chou","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, TW","[National Tsing Hua Univ., Taiwan]"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, TW","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"[National Tsing Hua Univ., Taiwan]","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006278241","display_name":"Venkat Vishwanath","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkat Vishwanath","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, US","Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, US","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062233562","display_name":"Suren Byna","orcid":"https://orcid.org/0000-0003-3048-3448"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surendra Byna","raw_affiliation_strings":["E O Lawrence Berkeley National Laboratory, Berkeley, CA, US","Lawrence  Berkeley National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"E O Lawrence Berkeley National Laboratory, Berkeley, CA, US","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence  Berkeley National Laboratory, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043129695","display_name":"Kesheng Wu","orcid":"https://orcid.org/0000-0002-6907-3393"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kesheng Wu","raw_affiliation_strings":["E O Lawrence Berkeley National Laboratory, Berkeley, CA, US","Lawrence  Berkeley National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"E O Lawrence Berkeley National Laboratory, Berkeley, CA, US","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence  Berkeley National Laboratory, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018147496"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.8734,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73929398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"576","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","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"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8548712730407715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8424108028411865},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5867363214492798},{"id":"https://openalex.org/keywords/parallel-i/o","display_name":"Parallel I/O","score":0.5494763255119324},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.49115797877311707},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4828822910785675},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.478633314371109},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4430028796195984},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.4380190372467041},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43460705876350403},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4279380440711975},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.42541781067848206},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4234873652458191},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4181944727897644},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3731708824634552},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14844977855682373},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07912874221801758},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0774381160736084}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8548712730407715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424108028411865},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5867363214492798},{"id":"https://openalex.org/C2781057727","wikidata":"https://www.wikidata.org/wiki/Q9941","display_name":"Parallel I/O","level":2,"score":0.5494763255119324},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.49115797877311707},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4828822910785675},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.478633314371109},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4430028796195984},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.4380190372467041},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43460705876350403},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4279380440711975},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.42541781067848206},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4234873652458191},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4181944727897644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3731708824634552},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14844977855682373},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07912874221801758},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0774381160736084},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/padsw.2014.7097856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","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":20,"referenced_works":["https://openalex.org/W56918557","https://openalex.org/W597956076","https://openalex.org/W1501548698","https://openalex.org/W1521479407","https://openalex.org/W1999354630","https://openalex.org/W2028710687","https://openalex.org/W2048211535","https://openalex.org/W2053009162","https://openalex.org/W2071774356","https://openalex.org/W2092916950","https://openalex.org/W2110020044","https://openalex.org/W2124851765","https://openalex.org/W2125184461","https://openalex.org/W2140980002","https://openalex.org/W2156077349","https://openalex.org/W2161694911","https://openalex.org/W4234825580","https://openalex.org/W4247616591","https://openalex.org/W6602324189","https://openalex.org/W6657788412"],"related_works":["https://openalex.org/W2166828374","https://openalex.org/W2041604065","https://openalex.org/W2064254674","https://openalex.org/W3097895792","https://openalex.org/W51042773","https://openalex.org/W1494199733","https://openalex.org/W1516963140","https://openalex.org/W2135038095","https://openalex.org/W2898657440","https://openalex.org/W2151048758"],"abstract_inverted_index":{"Complex":[0],"indexing":[1,17,55,130,187],"techniques":[2],"are":[3,111],"needed":[4],"to":[5,34,41,66,86,113,127,148,222,232],"reduce":[6],"the":[7,36,43,92,129,150,165,171,200,209,214,227,233],"time":[8,23,152,230],"of":[9,32,186,195,208,220,226],"analyzing":[10],"massive":[11],"scientific":[12,60,71,99],"datasets,":[13],"but":[14],"generating":[15],"these":[16,107],"data":[18,68,100,108,131,160,166],"structures":[19,132],"can":[20,169,205],"be":[21],"very":[22],"consuming.":[24],"In":[25],"this":[26,141,144],"work,":[27],"we":[28,119,146,168],"propose":[29],"a":[30,53,74,188,196,218],"set":[31],"strategies":[33],"simplify":[35],"index":[37,47],"file":[38,95],"structure":[39],"and":[40,56,89,175,216],"improve":[42],"I/O":[44,151,172,179,203,211,239],"performance":[45],"during":[46],"construction":[48],"using":[49,192],"FastQuery,":[50],"which":[51],"is":[52],"parallel":[54,98,137],"querying":[57],"system":[58,96],"for":[59,181],"data.":[61],"FastQuery":[62,83,235],"has":[63],"been":[64],"used":[65],"analyze":[67],"from":[69],"various":[70],"applications,":[72],"including":[73],"trillion":[75,189],"plasma":[76],"particles":[77],"simulation.":[78],"To":[79,139],"accelerate":[80],"query":[81],"process,":[82],"uses":[84],"FastBit":[85],"build":[87],"indexes,":[88],"then":[90],"stores":[91],"indexes":[93,155],"into":[94,133,156],"through":[97],"format":[101,109],"libraries,":[102],"such":[103],"as":[104],"HDF5.":[105],"Although":[106],"libraries":[110],"designed":[112],"support":[114],"more":[115,177],"complex":[116],"multi-dimensional":[117],"arrays,":[118,134],"observed":[120],"that":[121,199],"it":[122],"still":[123],"takes":[124],"considerable":[125],"work":[126],"map":[128],"especially":[135],"on":[136,213],"machines.":[138],"address":[140],"problem,":[142],"in":[143,224],"paper,":[145],"attempt":[147],"minimize":[149,170],"by":[153],"storing":[154,182],"our":[157],"self-defined":[158],"binary":[159,202],"format.":[161],"By":[162],"fully":[163],"controlling":[164],"structure,":[167],"synchronization":[173],"overhead":[174],"explore":[176],"efficient":[178],"strategy":[180],"indexes.":[183],"Our":[184],"experiments":[185],"particle":[190],"dataset":[191],"20,000":[193],"cores":[194],"supercomputer":[197],"show":[198],"proposed":[201],"driver":[204],"reach":[206],"85%":[207],"peak":[210],"bandwidth":[212],"system,":[215],"achieves":[217],"speedup":[219],"up":[221],"4X":[223],"terms":[225],"total":[228],"execution":[229],"comparing":[231],"previous":[234],"implementation":[236],"with":[237],"HDF5":[238],"driver.":[240]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}