Metraipolis › archive › dc_43916f0cb501
Portable to Efficient: Auto-Tuning Hardware-Agnostic GPU Kernels in Julia — arXiv:2608.21227
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21227
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:26:32.250Z
- SHA-256 of the archived text
789108700b9f6860bd3f5ae210f3ca5be576837e48f75fd0b18e2342858e68d9- Stable URL of this page
https://metraipolis.com/documento/dc_43916f0cb501
How to cite
Portable to Efficient: Auto-Tuning Hardware-Agnostic GPU Kernels in Julia — arXiv:2608.21227 — arXiv (en), https://arxiv.org/abs/2608.21227 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43916f0cb501 (Metraipolis archive dc_43916f0cb501, sha256 789108700b9f6860bd3f5ae210f3ca5be576837e48f75fd0b18e2342858e68d9)
BibTeX
@misc{dc43916f0cb501,
title = {Portable to Efficient: Auto-Tuning Hardware-Agnostic GPU Kernels in Julia — arXiv:2608.21227},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21227},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43916f0cb501; sha256 789108700b9f6860bd3f5ae210f3ca5be576837e48f75fd0b18e2342858e68d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21227. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Traditionally, GPU kernels have been developed and optimized within vendor-specific programming models to achieve high performance, resulting in software that is difficult to optimize and adapt across increasingly heterogeneous computing systems. Hardware-agnostic programming models offer a more sustainable approach to GPU software development by improving portability and maintainability, but achieving efficient execution across diverse architectures remains challenging. We address this challenge by integrating auto-tuning into hardware-agnostic GPU kernels written in Julia. We rebuild the established Kernel Tuner auto-tuning framework with Julia support, enabling systematic exploration of kernel configurations for hardware-agnostic GPU kernels targeting NVIDIA, AMD, Intel, and Apple GPUs. We demonstrate this approach on hardware-agnostic singular value decomposition (SVD) as implemented in the this http URL linear algebra library. The results show that auto-tuning is essential for creating resource-efficient hardware-agnostic GPU kernels across a variety of hardware. Optimal configurations improve kernel performance by a factor of 3x to 7x compared to median parameter configurations, demonstrating the substantial impact of tuning on efficient hardware utilization. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-24 in cs.PF). Categorie arXiv: Performance (cs.PF). Pagina del lavoro: https://arxiv.org/abs/2608.21227 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T10:19:05.012Z dalla pagina https://arxiv.org/catchup/cs.PF/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).