{"id":"https://openalex.org/W2935423094","doi":"https://doi.org/10.1145/3297858.3304008","title":"Scalable Processing of Contemporary Semi-Structured Data on Commodity Parallel Processors - A Compilation-based Approach","display_name":"Scalable Processing of Contemporary Semi-Structured Data on Commodity Parallel Processors - A Compilation-based Approach","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2935423094","doi":"https://doi.org/10.1145/3297858.3304008","mag":"2935423094"},"language":"en","primary_location":{"id":"doi:10.1145/3297858.3304008","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304008","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304008","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304008","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080088006","display_name":"Lin Jiang","orcid":"https://orcid.org/0000-0002-1571-5901"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lin Jiang","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054367652","display_name":"Xiaofan Sun","orcid":"https://orcid.org/0000-0002-6650-8507"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofan Sun","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048619460","display_name":"Umar Farooq","orcid":"https://orcid.org/0000-0001-7229-9847"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umar Farooq","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013940261","display_name":"Zhijia Zhao","orcid":"https://orcid.org/0000-0003-2616-4241"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhijia Zhao","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080088006"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.743,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.73598303,"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":"79","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9876000285148621,"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":0.9198192358016968},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.7673691511154175},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.535355806350708},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5266672968864441},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4955822229385376},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4681943356990814},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4604860246181488},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4325195550918579},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2592664659023285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9198192358016968},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.7673691511154175},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.535355806350708},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5266672968864441},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4955822229385376},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4681943356990814},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4604860246181488},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4325195550918579},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2592664659023285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297858.3304008","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304008","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304008","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3297858.3304008","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297858.3304008","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297858.3304008","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G1849604498","display_name":"CAREER: Transducer-Centric Parallelization for Scalable Semi-Structured Data Processing","funder_award_id":"1751392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G43105557","display_name":null,"funder_award_id":"1565928,1751392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8253765332","display_name":null,"funder_award_id":"1565928","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/F4320311968","display_name":"Hellman Foundation","ror":"https://ror.org/02g98ya79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2935423094.pdf","grobid_xml":"https://content.openalex.org/works/W2935423094.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1502938876","https://openalex.org/W1527356121","https://openalex.org/W1995751017","https://openalex.org/W2007419011","https://openalex.org/W2030377171","https://openalex.org/W2062949766","https://openalex.org/W2064580935","https://openalex.org/W2091397950","https://openalex.org/W2098569470","https://openalex.org/W2103985768","https://openalex.org/W2113606713","https://openalex.org/W2132774949","https://openalex.org/W2135039871","https://openalex.org/W2135421348","https://openalex.org/W2140447297","https://openalex.org/W2143462372","https://openalex.org/W2160562938","https://openalex.org/W2164637360","https://openalex.org/W2171177618","https://openalex.org/W2179349885","https://openalex.org/W2298276167","https://openalex.org/W2507706987","https://openalex.org/W2580280030","https://openalex.org/W2617288171","https://openalex.org/W2619959750","https://openalex.org/W2766073137","https://openalex.org/W2790011209","https://openalex.org/W2805816674","https://openalex.org/W2889015391","https://openalex.org/W2904896921","https://openalex.org/W2963026732","https://openalex.org/W3009142854","https://openalex.org/W3110792960","https://openalex.org/W4285719527","https://openalex.org/W4372267129","https://openalex.org/W6718556738"],"related_works":["https://openalex.org/W2753132265","https://openalex.org/W4234766820","https://openalex.org/W4321232174","https://openalex.org/W3117520771","https://openalex.org/W2482048793","https://openalex.org/W4388027365","https://openalex.org/W2938860153","https://openalex.org/W4312551432","https://openalex.org/W3138386522","https://openalex.org/W2499279132"],"abstract_inverted_index":{"JSON":[0,175,222],"(JavaScript":[1],"Object":[2],"Notation)":[3],"and":[4,80,148,173,193,247],"its":[5],"derivatives":[6],"are":[7],"essential":[8],"in":[9,25,49,73],"the":[10,34,51,59,70,77,82,93,108,146,171,174,185,191,196,213,217,233],"modern":[11],"computing":[12],"infrastructure.":[13],"However,":[14,85],"existing":[15],"software":[16],"often":[17,36,62],"fails":[18],"to":[19,38,64,68,75,98,189,199,215,239],"process":[20],"such":[21],"types":[22],"of":[23,187],"data":[24,52,71,83],"a":[26,40,102,113,120,140,164,179,206],"scalable":[27,114],"way,":[28],"mainly":[29],"for":[30],"two":[31],"reasons:":[32],"(i)":[33],"processing":[35,50,142],"requires":[37,88],"build":[39],"memory-consuming":[41],"parse":[42,157],"tree;":[43],"(ii)":[44],"there":[45],"exist":[46],"inherent":[47],"dependences":[48,192],"stream,":[53],"preventing":[54],"any":[55,155],"data-level":[56],"parallelization.":[57],"Facing":[58],"challenges,":[60],"developers":[61],"have":[63],"construct":[65],"ad-hoc":[66],"pre-parsers":[67],"split":[69],"stream":[72,141],"order":[74],"reduce":[76,232],"memory":[78,135,234],"consumption":[79,235],"increase":[81],"parallelism.":[84],"this":[86,110],"strategy":[87],"more":[89],"programming":[90],"efforts.":[91],"Moreover,":[92],"pre-parsing":[94],"itself":[95],"is":[96],"non-trivial":[97],"parallelize,":[99],"thus":[100],"introducing":[101],"new":[103],"serial":[104],"bottleneck.":[105],"To":[106,159],"solve":[107],"dilemma,":[109],"work":[111],"introduces":[112],"yet":[115],"fully":[116],"automatic":[117],"solution":[118],"-":[119],"compilation":[121,167],"system,":[122],"namely":[123],"JPStream,":[124],"that":[125,144,169,208,229],"compiles":[126,170],"standard":[127,225],"JSONPath":[128,226],"queries":[129,172,227],"into":[130,150,178],"parallel":[131],"executables":[132],"with":[133,224],"bounded":[134],"footprints.":[136],"First,":[137],"JPStream":[138,162,183,230],"adopts":[139],"design":[143],"combines":[145],"querying":[147],"parsing":[149],"one":[151],"pass,":[152],"without":[153],"generating":[154],"in-memory":[156],"tree.":[158],"achieve":[160],"this,":[161],"uses":[163],"novel":[165],"joint":[166],"technique":[168],"syntax":[176],"together":[177],"single":[180],"automaton.":[181],"Furthermore,":[182],"leverages":[184],"\"enumerability''":[186],"automaton":[188],"break":[190],"reason":[194],"about":[195],"transition":[197],"rules":[198],"prune":[200],"infeasible":[201],"states.":[202],"It":[203],"also":[204],"features":[205],"runtime":[207],"learns":[209],"structural":[210],"constraints":[211],"from":[212],"input":[214],"enhance":[216],"pruning.":[218],"Evaluation":[219],"on":[220,245],"real-world":[221],"datasets":[223],"shows":[228],"can":[231],"significantly,":[236],"by":[237],"up":[238],"95%,":[240],"meanwhile":[241],"achieving":[242],"near-linear":[243],"speedup":[244],"multicore":[246],"manycore":[248],"processors.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}