{"id":"https://openalex.org/W2988724757","doi":"https://doi.org/10.1109/cluster.2019.8890992","title":"Compact Filters for Fast Online Data Partitioning","display_name":"Compact Filters for Fast Online Data Partitioning","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2988724757","doi":"https://doi.org/10.1109/cluster.2019.8890992","mag":"2988724757"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2019.8890992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8890992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5048606069","display_name":"Qing Zheng","orcid":"https://orcid.org/0000-0002-7457-9874"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qing Zheng","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060965148","display_name":"Charles D. Cranor","orcid":"https://orcid.org/0000-0003-2427-9627"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles D. Cranor","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103876321","display_name":"Ankush Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankush Jain","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037557529","display_name":"Gregory R. Ganger","orcid":"https://orcid.org/0000-0002-3065-7316"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory R. Ganger","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041431830","display_name":"Garth A. Gibson","orcid":"https://orcid.org/0000-0002-6656-7080"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garth A. Gibson","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013339702","display_name":"George Amvrosiadis","orcid":"https://orcid.org/0000-0002-7328-1857"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Amvrosiadis","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015295183","display_name":"Bradley W. Settlemyer","orcid":"https://orcid.org/0000-0002-9299-2654"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley W. Settlemyer","raw_affiliation_strings":["Los Alamos National Laboratory"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015145749","display_name":"Gary Grider","orcid":"https://orcid.org/0000-0001-5749-3377"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Grider","raw_affiliation_strings":["Los Alamos National Laboratory"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5048606069"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17256665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8425267934799194},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6774665117263794},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6114146113395691},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.597044050693512},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5355181097984314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5162184238433838},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48628151416778564},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.44677096605300903},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4455106854438782},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.41019758582115173},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2943522334098816},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2648143172264099},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.11485013365745544},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.10150641202926636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425267934799194},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6774665117263794},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6114146113395691},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.597044050693512},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5355181097984314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5162184238433838},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48628151416778564},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.44677096605300903},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4455106854438782},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.41019758582115173},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2943522334098816},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2648143172264099},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.11485013365745544},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.10150641202926636},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2019.8890992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8890992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1504483039","https://openalex.org/W1838765419","https://openalex.org/W1929619420","https://openalex.org/W1939090615","https://openalex.org/W1966142043","https://openalex.org/W1967373117","https://openalex.org/W1981812667","https://openalex.org/W2003421875","https://openalex.org/W2015673362","https://openalex.org/W2021361430","https://openalex.org/W2027758281","https://openalex.org/W2028705462","https://openalex.org/W2028811868","https://openalex.org/W2042661579","https://openalex.org/W2048211535","https://openalex.org/W2077850713","https://openalex.org/W2086322743","https://openalex.org/W2087946700","https://openalex.org/W2097590615","https://openalex.org/W2098638772","https://openalex.org/W2105321788","https://openalex.org/W2113913767","https://openalex.org/W2116435146","https://openalex.org/W2117702591","https://openalex.org/W2118992966","https://openalex.org/W2123845384","https://openalex.org/W2125184461","https://openalex.org/W2125901106","https://openalex.org/W2132462387","https://openalex.org/W2136245133","https://openalex.org/W2137985407","https://openalex.org/W2138143219","https://openalex.org/W2146387131","https://openalex.org/W2147330767","https://openalex.org/W2153423033","https://openalex.org/W2157891964","https://openalex.org/W2165231728","https://openalex.org/W2167208373","https://openalex.org/W2168067900","https://openalex.org/W2267406438","https://openalex.org/W2340076492","https://openalex.org/W2605800201","https://openalex.org/W2612838847","https://openalex.org/W2613215397","https://openalex.org/W2725946184","https://openalex.org/W2754016293","https://openalex.org/W2765113847","https://openalex.org/W2765924002","https://openalex.org/W2798891709","https://openalex.org/W2902685930","https://openalex.org/W2907571246","https://openalex.org/W2912601938","https://openalex.org/W2942055784","https://openalex.org/W3148190289","https://openalex.org/W3150827651","https://openalex.org/W4238102692","https://openalex.org/W4247616591","https://openalex.org/W4251708617","https://openalex.org/W6630343179","https://openalex.org/W6638678886","https://openalex.org/W6675903601","https://openalex.org/W6681265431","https://openalex.org/W6682662481","https://openalex.org/W6693436320","https://openalex.org/W6743677923","https://openalex.org/W6757216772"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W3024364549","https://openalex.org/W2910064364","https://openalex.org/W4200136508"],"abstract_inverted_index":{"We":[0,161,192],"are":[1],"approaching":[2],"a":[3,62,76,211],"point":[4],"in":[5,138,151],"time":[6],"when":[7],"it":[8,18,36,99],"will":[9],"be":[10,101],"infeasible":[11],"to":[12,39,142,190,199,214,236],"catalog":[13],"and":[14,103,135,158,189,208,216],"query":[15],"data":[16,29,34,49,68,86,93,146,166,172,184],"after":[17],"has":[19,24,53],"been":[20],"generated.":[21],"This":[22,112],"trend":[23],"fueled":[25],"research":[26],"on":[27,33],"in-situ":[28,48],"processing":[30],"(i.e.":[31],"operating":[32],"as":[35,61,85,118,155],"is":[37,47,87,114,130,148],"streamed":[38],"storage).":[40],"One":[41],"important":[42],"example":[43],"of":[44,57,75,125,174,183,203],"this":[45,194],"approach":[46,113],"indexing.":[50],"Prior":[51],"work":[52],"shown":[54],"the":[55,72,95,106,110,180,187,204],"feasibility":[56],"indexing":[58],"at":[59],"scale":[60],"two-step":[63],"process.":[64],"First,":[65],"one":[66],"partitions":[67],"by":[69,105,234],"key":[70],"across":[71,238],"CPU":[73,240],"cores":[74],"parallel":[77],"job.":[78],"Then":[79],"each":[80],"core":[81,107,127],"indexes":[82],"its":[83],"subset":[84],"persisted.":[88],"Online":[89],"partitioning":[90,147,173,197,232],"requires":[91],"transferring":[92],"over":[94,186],"network":[96,188],"so":[97],"that":[98,129,224],"can":[100,226],"indexed":[102],"stored":[104],"responsible":[108],"for":[109,132,169],"data.":[111],"becoming":[115],"increasingly":[116],"costly":[117],"new":[119],"computing":[120],"platforms":[121],"emphasize":[122],"parallelism":[123],"instead":[124,202],"individual":[126],"performance":[128],"crucial":[131],"communication":[133],"libraries":[134],"systems":[136],"software":[137],"general.":[139],"In":[140],"addition":[141],"indexing,":[143],"scalable":[144],"online":[145,171],"also":[149],"useful":[150],"other":[152],"contexts":[153],"such":[154],"load":[156],"balancing":[157],"efficient":[159,165],"compression.":[160],"present":[162],"FilterKV,":[163],"an":[164],"management":[167],"scheme":[168],"fast":[170],"key-value":[175],"(KV)":[176],"pairs.":[177],"FilterKV":[178,225],"reduces":[179],"total":[181,228],"amount":[182],"sent":[185],"storage.":[191],"achieve":[193],"by:":[195],"(a)":[196],"pointers":[198],"KV":[200,205,218],"pairs":[201,206],"themselves":[207],"(b)":[209],"using":[210],"compact":[212],"format":[213],"represent":[215],"store":[217],"pointers.":[219],"Results":[220],"from":[221],"LANL":[222],"show":[223],"reduce":[227],"write":[229],"slowdown":[230],"(including":[231],"overhead)":[233],"up":[235],"3x":[237],"4096":[239],"cores.":[241]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}