EUVIMEDEUVIMED entdecken
Crossref

Generating Sparsity Patterns for Inverse Preconditioning on SIMD Architectures

Hantao Xiong, Haotian Wang, Chubo Liu, Wangdong Yang, Kenli Li, Marc Casas

IEEE Transactions on Computers · 2026-09 · 75 (9) · 3169-3181

DOI: 10.1109/tc.2026.3701883 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2026-09. Verfasst von Hantao Xiong und 5 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Conjugate Gradient method is a prevalent iterative approach for solving sparse linear systems $Ax=b$ A x = b , where $A$ A is a symmetric positive definite matrix. In this scenario, the Factorized Sparse Approximate Inverse (FSAI) preconditioner is commonly used. The FSAI approximates $A^{-1}$ A − 1 by the matrix product $G^{T}G$ G T G , where $G$ G is a lower triangular matrix. The numerical properties of FSAI mainly depend on the sparsity pattern of $G$ G . This work presents an approach to generate FSAI sparsity patterns tailored to SIMD architectures, which play a pivotal role in current high-performance computing systems. First, we implement FSAI-S, an FSAI preconditioner based on the SELL- C - $\sigma$ σ format for SIMD architectures. To further improve iterative performance, we propose a padding-aware preconditioner, FSAI-P, which leverages the zero padding inherent in the SELL- C - $\sigma$ σ to extend the sparsity pattern with minimal computational and storage overhead. We evaluate our approach on three SIMD architectures: a Skylake processor implementing the AVX-512 ISA, a RISC-V processor supporting the RISC-V “V” Vector ISA, and an Nvidia A100 GPU. Experimental results show that FSAI-P provides performance gains across all evaluated platforms. Specifically, average speedups are 12.51% (vs. FSAI) and 11.66% (vs. FSAI-cache) on Skylake, 57.79% (vs. FSAI) on RISC-V, and 18.33% (vs. FSAI) on the A100 GPU.

Zitieren

APA

Xiong, H., Wang, H., Liu, C., Yang, W., Li, K., & Casas, M. (2026). Generating Sparsity Patterns for Inverse Preconditioning on SIMD Architectures. IEEE Transactions on Computers, 75(9), 3169-3181. https://doi.org/10.1109/tc.2026.3701883

Vancouver

Xiong H, Wang H, Liu C, Yang W, Li K, Casas M. Generating Sparsity Patterns for Inverse Preconditioning on SIMD Architectures. IEEE Transactions on Computers. 2026;75(9):3169-3181. doi:10.1109/tc.2026.3701883

BibTeX
@article{Xiong2026,
  author = {Xiong, Hantao and Wang, Haotian and Liu, Chubo and Yang, Wangdong and Li, Kenli and Casas, Marc},
  title = {Generating Sparsity Patterns for Inverse Preconditioning on SIMD Architectures},
  journal = {IEEE Transactions on Computers},
  year = {2026},
  volume = {75},
  number = {9},
  pages = {3169--3181},
  doi = {10.1109/tc.2026.3701883}
}
Kostenlos starten →