EUVIMEDEUVIMED entdecken
Crossref

Into the CUDA Multiverse of Runtime Compilation: Exploring Kernel Fusion Strategies for GPU Database Systems

Maha Alwahibi, Bachana Jangebashvili, Maximilian E. Schüle

Proceedings of the VLDB Endowment · 01.08.2026 · 19 (12) · 4658-4661

DOI: 10.14778/3827998.3828090 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 14.09.2026. Verfasst von Maha Alwahibi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 13 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This demonstration presents the CUDA Code-General, a query compilation framework for GPU database systems. The interface allows selecting any of the 22 TPC-H benchmark queries or entering arbitrary SQL, to choose between runtime or static compilation and to inspect the generated CUDA code for three kernel fusion strategies side by side: fused multiple sequential kernels, cooperative groups, and dynamic parallelism. Users can observe how the number of generated pipelines affects compilation cost, how cooperative groups fuse them into a single kernel with synchronisation barriers, and how dynamic parallelism delegates kernel launches to the device.

Zitieren

APA

Alwahibi, M., Jangebashvili, B., & Schüle, M. E. (2026). Into the CUDA Multiverse of Runtime Compilation: Exploring Kernel Fusion Strategies for GPU Database Systems. Proceedings of the VLDB Endowment, 19(12), 4658-4661. https://doi.org/10.14778/3827998.3828090

Vancouver

Alwahibi M, Jangebashvili B, Schüle ME. Into the CUDA Multiverse of Runtime Compilation: Exploring Kernel Fusion Strategies for GPU Database Systems. Proceedings of the VLDB Endowment. 2026;19(12):4658-4661. doi:10.14778/3827998.3828090

BibTeX
@article{Alwahibi2026,
  author = {Alwahibi, Maha and Jangebashvili, Bachana and Schüle, Maximilian E.},
  title = {Into the CUDA Multiverse of Runtime Compilation: Exploring Kernel Fusion Strategies for GPU Database Systems},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {19},
  number = {12},
  pages = {4658--4661},
  doi = {10.14778/3827998.3828090}
}
Kostenlos starten →