{"id":"https://openalex.org/W2484802798","doi":"https://doi.org/10.1145/2908961.2931692","title":"Automatic Improvement of Apache Spark Queries using Semantics-preserving Program Reduction","display_name":"Automatic Improvement of Apache Spark Queries using Semantics-preserving Program Reduction","publication_year":2016,"publication_date":"2016-07-20","ids":{"openalex":"https://openalex.org/W2484802798","doi":"https://doi.org/10.1145/2908961.2931692","mag":"2484802798"},"language":"en","primary_location":{"id":"doi:10.1145/2908961.2931692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2908961.2931692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://dspace.stir.ac.uk/bitstream/1893/26444/1/main.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050968209","display_name":"Zoltan A. Kocsis","orcid":"https://orcid.org/0000-0002-5542-4156"},"institutions":[{"id":"https://openalex.org/I12093191","display_name":"University of Stirling","ror":"https://ror.org/045wgfr59","country_code":"GB","type":"education","lineage":["https://openalex.org/I12093191"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zoltan A. Kocsis","raw_affiliation_strings":["University of Stirling, Stirling, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stirling, Stirling, United Kingdom","institution_ids":["https://openalex.org/I12093191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031005435","display_name":"John H. Drake","orcid":"https://orcid.org/0000-0002-6699-8323"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John H. Drake","raw_affiliation_strings":["Queen Mary University of London, London, UNK, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, UNK, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052238984","display_name":"Douglas Carson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149610","display_name":"Keysight Technologies (United Kingdom)","ror":"https://ror.org/04g81mm64","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210115805","https://openalex.org/I4210149610"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Douglas Carson","raw_affiliation_strings":["Keysight Technologies, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keysight Technologies, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I4210149610"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037668386","display_name":"Jerry Swan","orcid":"https://orcid.org/0000-0003-1944-7147"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jerry Swan","raw_affiliation_strings":["University of York, York, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of York, York, United Kingdom","institution_ids":["https://openalex.org/I52099693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050968209"],"corresponding_institution_ids":["https://openalex.org/I12093191"],"apc_list":null,"apc_paid":null,"fwci":2.3626,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89909154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1141","last_page":"1146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.994700014591217,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.994700014591217,"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":0.9922999739646912,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.9000123739242554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8732224106788635},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7455648183822632},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.61956387758255},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5179271101951599},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5028569102287292},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49884963035583496},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4930703341960907},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48417928814888},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4779232144355774},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4676969051361084},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4622471332550049},{"id":"https://openalex.org/keywords/program-transformation","display_name":"Program transformation","score":0.44271060824394226},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4344249963760376},{"id":"https://openalex.org/keywords/in-memory-processing","display_name":"In-Memory Processing","score":0.42782503366470337},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32428956031799316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2056267261505127},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.16428625583648682},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.14836189150810242},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.08001148700714111}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9000123739242554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8732224106788635},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7455648183822632},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.61956387758255},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5179271101951599},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5028569102287292},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49884963035583496},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4930703341960907},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48417928814888},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4779232144355774},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4676969051361084},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4622471332550049},{"id":"https://openalex.org/C2778361913","wikidata":"https://www.wikidata.org/wiki/Q7248437","display_name":"Program transformation","level":2,"score":0.44271060824394226},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4344249963760376},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.42782503366470337},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32428956031799316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2056267261505127},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.16428625583648682},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.14836189150810242},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.08001148700714111},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2908961.2931692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2908961.2931692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.stir.ac.uk:1893/26444","is_oa":true,"landing_page_url":"http://hdl.handle.net/1893/26444","pdf_url":"http://dspace.stir.ac.uk/bitstream/1893/26444/1/main.pdf","source":{"id":"https://openalex.org/S4306400268","display_name":"Stirling Online Research Repository (University of Stirling)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12093191","host_organization_name":"University of Stirling","host_organization_lineage":["https://openalex.org/I12093191"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/16086","is_oa":false,"landing_page_url":"http://qmro.qmul.ac.uk/xmlui/handle/123456789/16086","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:dspace.stir.ac.uk:1893/26444","is_oa":true,"landing_page_url":"http://hdl.handle.net/1893/26444","pdf_url":"http://dspace.stir.ac.uk/bitstream/1893/26444/1/main.pdf","source":{"id":"https://openalex.org/S4306400268","display_name":"Stirling Online Research Repository (University of Stirling)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12093191","host_organization_name":"University of Stirling","host_organization_lineage":["https://openalex.org/I12093191"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6794522244","display_name":null,"funder_award_id":"EP/J017515/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320316520","display_name":"Keysight Technologies","ror":"https://ror.org/02903cd17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2484802798.pdf","grobid_xml":"https://content.openalex.org/works/W2484802798.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W215851492","https://openalex.org/W1495226832","https://openalex.org/W1514583064","https://openalex.org/W1517760837","https://openalex.org/W1528098570","https://openalex.org/W1558832481","https://openalex.org/W1576818901","https://openalex.org/W1758861635","https://openalex.org/W1908420220","https://openalex.org/W1969951522","https://openalex.org/W1984074188","https://openalex.org/W1997415302","https://openalex.org/W2040581748","https://openalex.org/W2106683494","https://openalex.org/W2108088242","https://openalex.org/W2131975293","https://openalex.org/W2139657973","https://openalex.org/W2153889808","https://openalex.org/W2159588611","https://openalex.org/W2208923056","https://openalex.org/W2231324206","https://openalex.org/W2518957057","https://openalex.org/W2614938337","https://openalex.org/W4206031975","https://openalex.org/W4285719527","https://openalex.org/W4298845221","https://openalex.org/W6633513001"],"related_works":["https://openalex.org/W2558523485","https://openalex.org/W4379407450","https://openalex.org/W2408437972","https://openalex.org/W2905107896","https://openalex.org/W2895375519","https://openalex.org/W4313062323","https://openalex.org/W2510748453","https://openalex.org/W2353943211","https://openalex.org/W2267922067","https://openalex.org/W4382751403"],"abstract_inverted_index":{"Apache":[0],"Spark":[1,41,84],"is":[2,56],"a":[3,36,70],"popular":[4],"framework":[5],"for":[6,38],"large-scale":[7],"data":[8,67,101],"analytics.":[9],"Unfortunately,":[10],"Spark's":[11],"performance":[12],"can":[13,87],"be":[14],"difficult":[15],"to":[16,28,106],"optimise,":[17],"since":[18],"queries":[19,42],"freely":[20],"expressed":[21],"in":[22,44,109,118],"source":[23,45],"code":[24,46],"are":[25],"not":[26],"amenable":[27],"traditional":[29],"optimisation":[30,104],"techniques.":[31],"This":[32,72,103],"article":[33],"describes":[34],"Hylas,":[35],"tool":[37],"automatically":[39],"optimising":[40],"embedded":[43],"via":[47],"the":[48],"application":[49],"of":[50,62],"semantics-preserving":[51],"transformations.":[52],"The":[53],"transformation":[54],"method":[55],"inspired":[57],"by":[58],"functional":[59],"programming":[60],"techniques":[61],"\"deforestation\",":[63],"which":[64],"eliminate":[65],"intermediate":[66],"structures":[68],"from":[69],"computation.":[71],"contrasts":[73],"with":[74,112],"approaches":[75],"defined":[76],"entirely":[77],"within":[78],"structured":[79],"query":[80],"formats":[81],"such":[82],"as":[83],"SQL.":[85],"Hylas":[86],"identify":[88],"certain":[89],"computationally":[90],"expensive":[91],"operations":[92],"and":[93],"ensure":[94],"that":[95],"performing":[96],"them":[97],"creates":[98],"no":[99],"superfluous":[100],"structures.":[102],"leads":[105],"significant":[107],"improvements":[108],"execution":[110],"time,":[111],"over":[113],"10,000":[114],"times":[115],"improvement":[116],"observed":[117],"some":[119],"cases.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
