{"id":"https://openalex.org/W7204244176","doi":"https://doi.org/10.5281/zenodo.22103818","title":"DataKernelBench: Can LLMs Optimize Database Queries on GPUs?","display_name":"DataKernelBench: Can LLMs Optimize Database Queries on GPUs?","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204244176","doi":"https://doi.org/10.5281/zenodo.22103818"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22103818","doi":"https://doi.org/10.5281/zenodo.22103818","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22103818","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22103818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048139334","display_name":"Gokul Karthik Kumar","orcid":"https://orcid.org/0000-0003-2848-7095","observed_orcids":["https://orcid.org/0000-0003-2848-7095"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Gokul Karthik","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2848-7095","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068497719","display_name":"Yotam Perlitz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Perlitz, Yotam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067564596","display_name":"Corey Lammie","orcid":"https://orcid.org/0000-0001-5564-1356","observed_orcids":["https://orcid.org/0000-0001-5564-1356"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lammie, Corey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135894420","display_name":"Andrea Giovannini","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giovannini, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132642646","display_name":"Katja Hose","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hose, Katja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.7968999743461609,"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":0.7968999743461609,"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":0.12929999828338623,"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/T10260","display_name":"Software Engineering Research","score":0.025299999862909317,"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/cuda","display_name":"CUDA","score":0.5429999828338623},{"id":"https://openalex.org/keywords/triton","display_name":"Triton","score":0.9629999995231628},{"id":"https://openalex.org/keywords/tpc-h","display_name":"TPC-H","score":0.8510000109672546},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5149999856948853},{"id":"https://openalex.org/keywords/pytorch","display_name":"PyTorch","score":0.48100000619888306},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5149999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077999949455261},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6468999981880188},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6065999865531921},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.3409999907016754},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2984286706","wikidata":"https://www.wikidata.org/wiki/Q400708","display_name":"Sql server","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2989070954","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database query","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.2750000059604645},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.22103818","doi":"https://doi.org/10.5281/zenodo.22103818","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22103818","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22103818","doi":"https://doi.org/10.5281/zenodo.22103818","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22103818","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2632601261","display_name":null,"funder_award_id":"101168951","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417070084","https://openalex.org/W2246861528","https://openalex.org/W7108903566","https://openalex.org/W7168106423","https://openalex.org/W7165188477","https://openalex.org/W4404404113","https://openalex.org/W7222597486","https://openalex.org/W7203748250","https://openalex.org/W7167844994","https://openalex.org/W4415163048"],"abstract_inverted_index":{"DataKernelBench":[0,8],"Can":[1],"LLMs":[2,10,39],"optimize":[3,44],"database":[4,17],"queries":[5,18],"on":[6,11],"GPUs?":[7],"evaluates":[9,38,99],"a":[12,29,34,93],"novel":[13],"task:":[14],"optimizing":[15],"analytical":[16],"as":[19,28],"GPU":[20],"kernels.":[21],"It":[22,36],"first":[23],"represents":[24],"each":[25],"SQL":[26],"query":[27,53],"validated":[30],"PyTorch":[31],"program":[32],"called":[33],"TorchPlan.":[35],"then":[37],"by":[40],"asking":[41],"them":[42],"to":[43],"either":[45],"the":[46,51,77,83],"tensor-intensive":[47],"core":[48],"(core)":[49],"or":[50,58],"full":[52],"implementation":[54],"(full)":[55],"using":[56,73],"CUDA":[57,81],"Triton,":[59],"with":[60,80,92],"execution-guided":[61],"repair.":[62],"The":[63,97],"benchmark":[64],"covers":[65],"all":[66],"22":[67],"TPC-H":[68,71],"queries.":[69],"On":[70],"SF10":[72],"one":[74],"NVIDIA":[75],"H100,":[76],"strongest":[78],"configuration\u2014GPT-5.5":[79],"at":[82],"full-query":[84],"level\u2014achieves":[85],"2.11\u00d7":[86],"overall":[87],"speedup":[88],"over":[89],"compiled":[90],"TorchPlan":[91],"100%":[94],"pass":[95],"rate.":[96],"paper":[98],"ten":[100],"proprietary":[101],"and":[102,105,113,118],"open-weight":[103],"models":[104],"analyzes":[106],"how":[107],"model":[108],"strength,":[109],"backend,":[110],"optimization":[111],"scope,":[112],"prompt":[114],"context":[115],"affect":[116],"correctness":[117],"performance.":[119],"Links:":[120],"Project":[121],"page":[122],"\u00b7":[123,125,127,131],"Paper":[124],"Code":[126],"Data:":[128],"Hugging":[129],"Face":[130],"Zenodo":[132]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}