Metraipolis › archive › dc_07491297dee4
Exploring spectral element methods on the Tenstorrent RISC-V accelerator — arXiv:2608.22964
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22964
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:50:11.756Z
- SHA-256 of the archived text
db8647a965fcca0538d99525e4d721f1d0be0434f1990d045987633c814d2697- Stable URL of this page
https://metraipolis.com/documento/dc_07491297dee4
How to cite
Exploring spectral element methods on the Tenstorrent RISC-V accelerator — arXiv:2608.22964 — arXiv (en), https://arxiv.org/abs/2608.22964 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07491297dee4 (Metraipolis archive dc_07491297dee4, sha256 db8647a965fcca0538d99525e4d721f1d0be0434f1990d045987633c814d2697)
BibTeX
@misc{dc07491297dee4,
title = {Exploring spectral element methods on the Tenstorrent RISC-V accelerator — arXiv:2608.22964},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22964},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07491297dee4; sha256 db8647a965fcca0538d99525e4d721f1d0be0434f1990d045987633c814d2697},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22964. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The growing availability of commodity RISC-V hardware has sparked interest in its use for High Performance Computing (HPC), with PCIe accelerator cards offering a practical near-term pathway to adoption. The Tenstorrent Wormhole is one example, with dedicated vector and matrix units across 128 Tensix cores, and is widely available. In this paper, we explore porting the AX kernel of Nekbone, a widely used HPC mini-application derived from the Gordon Bell Prize-winning Nek5000 spectral element solver, onto the Wormhole accelerator. This kernel evaluates the Poisson operator, and we describe the mapping of the algorithm onto the Tensix. The initial performance results reveal that the host-side data transposition, required for the z-direction gradient computation, is a severe bottleneck. Consequently, we investigated two optimisation strategies that yield dramatic improvements, achieving 242.97 GFLOPS for 100000 elements across 128 Tensix cores, outperforming a 24-core Xeon Platinum CPU and drawing approximately 7 times less power. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2608.22964 — 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 2026-10-18T07:47:32.957Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).