EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic Generation of GPU Code Using Multi-Dimensional Homomorphisms: A Conjugate-Gradient Case Study

Bazargul Matkerim, Nurislam Kassymbek, Moldir Nakibayeva, Nurdaulet Kabdygaliyev, Rahim Ahmed Druba, Sergei Gorlatch

Computation · 18.11.2026 · 14 (11) · 297

DOI: 10.3390/computation14110297 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computation, online erschienen am 18.11.2026. Verfasst von Bazargul Matkerim und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Higher Education of the Republic of Kazakhstan, German Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Developing efficient, performance-portable GPU code for multi-stage numerical pipelines is difficult; automated compilers struggle to parallelize them. We address this using Multi-Dimensional Homomorphisms (MDH), generating correct-by-construction GPU code from high-level formulations, tuned via an automated (scripted) sweep, cross-checked against the auto-tuning framework (ATF). We apply this to the conjugate-gradient (CG) method for the matrix-free 2D/3D Poisson equation, generating the stencil, dot product, and vector update; CG is not claimed to be the fastest algorithm for this problem, addressed via a multigrid comparison. On two NVIDIA GPUs (RTX 3050 Laptop, RTX 5090), up to 268 million unknowns, tuned MDH kernels take 0.91 to 1.12 times the time of a hand-tuned kernel, and PPCG with tuned tile and block sizes takes 0.83 to 1.09 times the time of tuned MDH, neither uniformly faster; the up-to-8× gap against PPCG’s default schedule comes from engaging a single streaming multiprocessor. The fully generated GPU-resident CG iteration, run to convergence, is 1.62 to 1.99 times faster than CSR and cuSPARSE beyond the cache. A geometric multigrid solver, run to CG’s own 3.2×10−6 accuracy target, outperforms all CG variants by 1.6× to 5.3×; ILU(0) preconditioning reduces iteration counts but increases wall-clock time.

Förderung

  • Ministry of Science and Higher Education of the Republic of Kazakhstan
  • German Research Foundation

Zitieren

APA

Matkerim, B., Kassymbek, N., Nakibayeva, M., Kabdygaliyev, N., Druba, R. A., & Gorlatch, S. (2026). Automatic Generation of GPU Code Using Multi-Dimensional Homomorphisms: A Conjugate-Gradient Case Study. Computation, 14(11), 297. https://doi.org/10.3390/computation14110297

Vancouver

Matkerim B, Kassymbek N, Nakibayeva M, Kabdygaliyev N, Druba RA, Gorlatch S. Automatic Generation of GPU Code Using Multi-Dimensional Homomorphisms: A Conjugate-Gradient Case Study. Computation. 2026;14(11):297. doi:10.3390/computation14110297

BibTeX
@article{Matkerim2026,
  author = {Matkerim, Bazargul and Kassymbek, Nurislam and Nakibayeva, Moldir and Kabdygaliyev, Nurdaulet and Druba, Rahim Ahmed and Gorlatch, Sergei},
  title = {Automatic Generation of GPU Code Using Multi-Dimensional Homomorphisms: A Conjugate-Gradient Case Study},
  journal = {Computation},
  year = {2026},
  volume = {14},
  number = {11},
  pages = {297},
  doi = {10.3390/computation14110297}
}
Kostenlos starten →