Record link: 
http://hdl.handle.net/20.500.12708/230964
-
Title: 
DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
en
Citation: 
Kumar, G. K., Perlitz, Y., Lammie, C., Giovannini, A., & Hose, K. (2026). DataKernelBench: Can LLMs Optimize Database Queries on GPUs? arXiv. https://doi.org/10.48550/ARXIV.2608.25061
-
Publisher DOI: 
10.48550/ARXIV.2608.25061
-
Publication Type: 
Preprint
en
Language: 
English
-
Authors: 
Kumar, Gokul Karthik 
Perlitz, Yotam 
Lammie, Corey 
Giovannini, Andrea 
Hose, Katja 
-
Organisational Unit: 
E194-07 - Forschungsbereich Data Management 
E056-23 - Fachbereich Innovative Combinations and Applications of AI and ML (iCAIML) 
-
ArXiv ID: 
2608.25061
-
Date (published): 
27-Aug-2026
-
Preprint Server: 
arXiv 
-
Keywords: 
LLM-generated GPU kernels; Query Optimization; Execution-Guided Benchmarking
en
Project title: 
ARMADA: reliAble conveRsational doMAin-specific Data exploration and Analysis: 101168951 (European Commission) 
-
Research Areas: 
Logic and Computation: 20%
Information Systems Engineering: 80%
-
Science Branch: 
1020 - Informatik: 90%
1010 - Mathematik: 10%
-
Appears in Collections:
Preprint

Show full item record

Page view(s)

7
checked on Sep 21, 2026

Google ScholarTM

Check