EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sparse matrix–vector product on RISC-V processors with SIMD units

Andrés E. Tomás, Héctor Martínez, Sandra Catalán, Patricia Siwinska, Adrián Castelló, Marc Casas, Enrique S. Quintana-Ortí

Computing · 2026-05 · 108 (5)

DOI: 10.1007/s00607-026-01658-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computing, online erschienen am 13.04.2026. Verfasst von Andrés E. Tomás und 6 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitat Politècnica de València.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The sparse matrix–vector multiplication ( SpMV ) kernel is a key kernel in scientific and engineering applications, forming the core of many iterative solvers for linear systems and eigenvalue problems. Due to its low arithmetic intensity and irregular memory access patterns, SpMV remains memory-bound on modern architectures, making its efficient implementation particularly challenging. This paper presents vectorized SpMV routines for RISC-V processors with SIMD support, exploiting the RISC-V Vector Extension (RVV 1.0). We implement and evaluate three storage formats—CSR (Compressed Sparse Row), SELL- p (a vector-friendly variant of ELLPACK), and JDS (Jagged Diagonal Storage)—providing low-level implementations that leverage RVV intrinsics. Performance is assessed on two commercial RISC-V platforms (CanMV-K230 and BananaPi F3) with 128-bit and 256-bit vector registers, and on the EPAC research system featuring 16,384-bit vectors. Results show that the vectorized routines significantly outperform scalar baselines, achieving a variety of speed-ups depending on the format and architecture. These findings highlight the potential of open RISC-V architectures for high-performance sparse linear algebra and provide a foundation for future vector-aware sparse kernel optimizations.

Förderung

  • Universitat Politècnica de València

Zitieren

APA

Tomás, A. E., Martínez, H., Catalán, S., Siwinska, P., Castelló, A., Casas, M., & Quintana-Ortí, E. S. (2026). Sparse matrix–vector product on RISC-V processors with SIMD units. Computing, 108(5). https://doi.org/10.1007/s00607-026-01658-5

Vancouver

Tomás AE, Martínez H, Catalán S, Siwinska P, Castelló A, Casas M, et al. Sparse matrix–vector product on RISC-V processors with SIMD units. Computing. 2026;108(5). doi:10.1007/s00607-026-01658-5

BibTeX
@article{Toms2026,
  author = {Tomás, Andrés E. and Martínez, Héctor and Catalán, Sandra and Siwinska, Patricia and Castelló, Adrián and Casas, Marc and Quintana-Ortí, Enrique S.},
  title = {Sparse matrix–vector product on RISC-V processors with SIMD units},
  journal = {Computing},
  year = {2026},
  volume = {108},
  number = {5},
  doi = {10.1007/s00607-026-01658-5}
}
Kostenlos starten →