.png){kind=icon}
.png){kind=icon}
Return
Exploiting repeated matrix block structures for more efficient CFD on modern supercomputers
.png){kind=icon}
OA
AI
DOI：10.1016/j.cpc.2026.110232.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Boosts CFD arithmetic intensity by exploiting repeated sparse matrix structures • Introduces inline mesh refinement to reduce statistical convergence wall-clock time • Multiplies repeated blocks with vectors in batches to boost performance • Extends the approach to divergence, gradient, and Laplacian operators • Demonstrates consistent gains in channel flow and Rayleigh-Bénard convection
Keywords:
Computational Fluid Dynamics
Arithmetic intensity
Sparse matrix-vector product
Sparse matrix-matrix product
High-performance computing
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.4
Papers:
1.2W
Citations:
3.7W