{"id":"https://openalex.org/W7204157867","doi":"https://doi.org/10.48550/arxiv.2608.22476","title":"JetStream: Generating Query Accelerators for Existing Database Systems","display_name":"JetStream: Generating Query Accelerators for Existing Database Systems","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204157867","doi":"https://doi.org/10.48550/arxiv.2608.22476"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22476","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22476","pdf_url":"https://arxiv.org/pdf/2608.22476","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015247886","display_name":"Akhilesh Balasingam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balasingam, Akhilesh","raw_affiliation_strings":["MIT CSAIL Cambridge , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL Cambridge , MA , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080321727","display_name":"Amadou Ngom","orcid":"https://orcid.org/0009-0000-8422-5212","observed_orcids":["https://orcid.org/0009-0000-8422-5212"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngom, Amadou","raw_affiliation_strings":["MIT CSAIL Cambridge , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL Cambridge , MA , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046724740","display_name":"Geoffrey X. Yu","orcid":"https://orcid.org/0009-0005-3186-1465","observed_orcids":["https://orcid.org/0009-0005-3186-1465"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu, Geoffrey X.","raw_affiliation_strings":["MIT CSAIL Cambridge , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL Cambridge , MA , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759","observed_orcids":["https://orcid.org/0009-0003-2414-2759"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kraska, Tim","raw_affiliation_strings":["MIT CSAIL Cambridge , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL Cambridge , MA , USA","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.00019999999494757503,"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/T11106","display_name":"Data Management and Algorithms","score":9.999999747378752e-05,"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/large-language-models","display_name":"large language models","score":0.6840000152587891},{"id":"https://openalex.org/keywords/database-maintenance","display_name":"database maintenance","score":0.46000000834465027},{"id":"https://openalex.org/keywords/dynamic-workloads","display_name":"dynamic workloads","score":0.6010000109672546},{"id":"https://openalex.org/keywords/tpc-h","display_name":"TPC-H","score":0.6449999809265137},{"id":"https://openalex.org/keywords/olap","display_name":"OLAP","score":0.44699999690055847},{"id":"https://openalex.org/keywords/agentic-workflows","display_name":"agentic workflows","score":0.45899999141693115},{"id":"https://openalex.org/keywords/query-optimization","display_name":"query optimization","score":0.30399999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521999716758728},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.8041999936103821},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5429999828338623},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5386000275611877},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C44060867","wikidata":"https://www.wikidata.org/wiki/Q12129","display_name":"Parsec","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C72108876","wikidata":"https://www.wikidata.org/wiki/Q844565","display_name":"Transaction processing","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.3504999876022339},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C204495577","wikidata":"https://www.wikidata.org/wiki/Q1205349","display_name":"Callback","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C2779628075","wikidata":"https://www.wikidata.org/wiki/Q1253258","display_name":"Downgrade","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22476","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22476","pdf_url":"https://arxiv.org/pdf/2608.22476","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22476","doi":"https://doi.org/10.48550/arxiv.2608.22476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22476","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22476","pdf_url":"https://arxiv.org/pdf/2608.22476","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204157867.pdf","grobid_xml":"https://content.openalex.org/works/W7204157867.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2082171780","https://openalex.org/W2102729946","https://openalex.org/W2108290652","https://openalex.org/W2921688135","https://openalex.org/W2970148517","https://openalex.org/W3020084632","https://openalex.org/W3029541804","https://openalex.org/W3029564598","https://openalex.org/W3085441975","https://openalex.org/W3176153696","https://openalex.org/W3197796305","https://openalex.org/W3198839277","https://openalex.org/W4226461508","https://openalex.org/W4281718197","https://openalex.org/W4285160575","https://openalex.org/W4312621027","https://openalex.org/W4317639412","https://openalex.org/W4386128201","https://openalex.org/W4386768482","https://openalex.org/W4402043623","https://openalex.org/W4403885061","https://openalex.org/W4413827406","https://openalex.org/W7133310058","https://openalex.org/W7133346882","https://openalex.org/W7159649516"],"related_works":["https://openalex.org/W7222352703","https://openalex.org/W7133346882","https://openalex.org/W7170680950","https://openalex.org/W7159649516","https://openalex.org/W7167806456","https://openalex.org/W7133310058","https://openalex.org/W7163037029","https://openalex.org/W2096464786","https://openalex.org/W3150241674","https://openalex.org/W2887134689"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"shown":[3],"that":[4,40,94,171,193],"LLMs":[5],"can":[6,197],"synthesize":[7],"highly":[8],"specialized":[9],"database":[10,126],"systems":[11],"for":[12,36,77,148,152],"fixed":[13],"workloads,":[14,177],"but":[15],"existing":[16,44,202],"approaches":[17],"typically":[18],"assume":[19],"static":[20],"data":[21],"and":[22,58,83,110,121,150,186,204],"replace":[23],"the":[24,74,96,99,125],"database's":[25],"native":[26],"storage":[27],"with":[28,146,201],"generated":[29,134,195],"representations.":[30],"We":[31,168],"present":[32],"JetStream,":[33],"a":[34,52,69,86,112,163],"system":[35],"generating":[37],"query-specific":[38,60],"accelerators":[39,133],"instead":[41],"extend":[42],"an":[43,138],"DBMS.":[45],"JetStream":[46,105,136,161,172],"consists":[47],"of":[48,182],"three":[49],"parts.":[50],"First,":[51],"staged,":[53],"measurement-driven":[54],"agentic":[55],"workflow":[56,89],"generates":[57,90,107],"optimizes":[59],"accelerators,":[61,104],"including":[62],"persistent":[63],"auxiliary":[64],"state":[65,81],"when":[66],"beneficial.":[67],"Second,":[68],"fixed,":[70],"engine-neutral":[71],"substrate":[72,97],"provides":[73],"common":[75],"interfaces":[76],"execution,":[78],"transaction":[79],"coordination,":[80],"management,":[82],"maintenance.":[84],"Third,":[85],"separate":[87],"synthesis":[88],"engine-specific":[91],"backend":[92],"adapters":[93],"connect":[95],"to":[98,115,174],"underlying":[100],"engine.":[101],"For":[102],"stateful":[103,132],"also":[106,169],"maintenance":[108],"logic":[109],"uses":[111],"runtime":[113],"policy":[114],"choose":[116],"among":[117],"incremental":[118],"maintenance,":[119],"rebuilds,":[120],"lazy":[122],"repair":[123],"as":[124],"changes.":[127],"On":[128],"TPC-H":[129,156],"at":[130],"SF=20,":[131],"by":[135],"achieve":[137],"833x":[139],"geomean":[140,165,179],"read-only":[141,180],"speedup":[142],"over":[143,184,188],"DuckDB,":[144],"compared":[145],"34.07x":[147],"GenDB":[149],"12.35x":[151],"Bespoke":[153],"OLAP.":[154],"Under":[155],"refreshes":[157],"every":[158],"60":[159],"seconds,":[160],"maintains":[162],"375x":[164],"workload":[166],"speedup.":[167],"show":[170,192],"generalizes":[173],"new,":[175],"unseen":[176],"achieving":[178],"speedups":[181],"102x":[183],"DuckDB":[185],"486x":[187],"PostgreSQL.":[189],"These":[190],"results":[191],"aggressive":[194],"specialization":[196],"be":[198],"integrated":[199],"seamlessly":[200],"DBMSes":[203],"support":[205],"dynamic":[206],"workloads.":[207]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}