{"id":"https://openalex.org/W2409939811","doi":"https://doi.org/10.1145/2933349.2933357","title":"SIMD-accelerated regular expression matching","display_name":"SIMD-accelerated regular expression matching","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2409939811","doi":"https://doi.org/10.1145/2933349.2933357","mag":"2409939811"},"language":"en","primary_location":{"id":"doi:10.1145/2933349.2933357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2933349.2933357","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2933357&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2933357&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063629406","display_name":"Evangelia Sitaridi","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evangelia Sitaridi","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077806101","display_name":"Orestis Polychroniou","orcid":"https://orcid.org/0000-0002-3164-0137"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Orestis Polychroniou","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021663937","display_name":"Kenneth A. Ross","orcid":"https://orcid.org/0000-0001-9397-6990"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth A. Ross","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063629406"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":3.5229,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92561231,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9969000220298767,"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/simd","display_name":"SIMD","score":0.8457616567611694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8432912826538086},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.8401713967323303},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.804694414138794},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6795538663864136},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.588377833366394},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.474672794342041},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.46601393818855286},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4493374228477478},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.232462078332901},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.19079264998435974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12819871306419373}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8457616567611694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432912826538086},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8401713967323303},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.804694414138794},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6795538663864136},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.588377833366394},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.474672794342041},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.46601393818855286},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4493374228477478},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.232462078332901},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.19079264998435974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12819871306419373},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2933349.2933357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2933349.2933357","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2933357&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2933349.2933357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2933349.2933357","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2933357&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2413409116","display_name":null,"funder_award_id":"IIS-1218222","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3175909512","display_name":null,"funder_award_id":"IIS-1218222, IIS-1422488","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5186389501","display_name":null,"funder_award_id":"IIS-1422488","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5292489514","display_name":"III: Small: Database Algorithms for Modern CPU Memory Hierarchies","funder_award_id":"1422488","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G692492870","display_name":"III: Small: Database Processing on GPUs","funder_award_id":"1218222","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323220","display_name":"Alexander S. Onassis Public Benefit Foundation","ror":"https://ror.org/017nq0d63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974048680","https://openalex.org/W1977655625","https://openalex.org/W1985108724","https://openalex.org/W2051250732","https://openalex.org/W2062666276","https://openalex.org/W2082964163","https://openalex.org/W2086977914","https://openalex.org/W2091448692","https://openalex.org/W2099964107","https://openalex.org/W2122493035","https://openalex.org/W2132774949","https://openalex.org/W2134826720","https://openalex.org/W2157059791","https://openalex.org/W2163243079","https://openalex.org/W2257971564"],"related_works":["https://openalex.org/W3129463312","https://openalex.org/W52396946","https://openalex.org/W2298204719","https://openalex.org/W1564013439","https://openalex.org/W2395807140","https://openalex.org/W2351800092","https://openalex.org/W2119057313","https://openalex.org/W3112977702","https://openalex.org/W3175353343","https://openalex.org/W1492858093"],"abstract_inverted_index":{"String":[0],"processing":[1],"tasks":[2],"are":[3,54,99],"common":[4,112],"in":[5,15,89,143],"analytical":[6],"queries":[7],"powering":[8],"business":[9],"intelligence.":[10],"Besides":[11],"substring":[12],"matching,":[13],"provided":[14],"SQL":[16],"by":[17,35,104],"the":[18,44,62,66,69,87,107,135],"like":[19],"operator,":[20],"popular":[21],"DBMSs":[22],"also":[23],"support":[24,142],"regular":[25,52,78,140],"expressions":[26,53,79],"as":[27],"selective":[28],"filters.":[29],"Substring":[30],"matching":[31,74],"can":[32],"be":[33],"optimized":[34],"using":[36,80],"specialized":[37],"SIMD":[38],"instructions":[39],"on":[40,60,125,134],"mainstream":[41,127],"CPUs,":[42],"reaching":[43],"performance":[45],"of":[46,68],"numeric":[47],"column":[48],"scans.":[49],"However,":[50],"generic":[51],"harder":[55],"to":[56,93,119,131],"evaluate,":[57],"being":[58],"dependent":[59],"both":[61],"DFA":[63],"size":[64],"and":[65,129],"irregularity":[67],"input.":[70],"Here,":[71],"we":[72],"optimize":[73],"string":[75,113],"columns":[76],"against":[77],"SIMD-vectorized":[81],"code.":[82],"Our":[83],"approach":[84],"avoids":[85],"accessing":[86],"strings":[88,98],"lockstep":[90],"without":[91],"branching,":[92],"exploit":[94],"cases":[95],"when":[96],"some":[97],"accepted":[100],"or":[101],"rejected":[102],"early":[103],"looking":[105],"at":[106],"first":[108],"few":[109],"characters.":[110],"On":[111],"lengths,":[114],"our":[115],"implementation":[116],"is":[117],"up":[118,130],"2X":[120],"faster":[121,133],"than":[122],"scalar":[123],"code":[124],"a":[126],"CPU":[128],"5X":[132],"Xeon":[136],"Phi":[137],"co-processor,":[138],"improving":[139],"expression":[141],"DBMSs.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}