Auto-tuned Krylov methods on cluster of graphics processing unit
DOI10.1080/00207160.2014.930137zbMath1314.65049OpenAlexW2070483007MaRDI QIDQ5248096
Roman Putanowicz, Abal-Kassim Cheik Ahamed, Frédéric Magoulès
Publication date: 27 April 2015
Published in: International Journal of Computer Mathematics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/00207160.2014.930137
algorithmiterative methodsnumerical experimentlinear algebrasparse matrix-vector productKrylov methodsCUDAGPUCUBLASauto-tuningCuspCUSPARSEcompressed-sparse row formatcoordinate (Coo) formatELLPACK (ELL) formathybrid (HYB) format
Computational methods for sparse matrices (65F50) Iterative numerical methods for linear systems (65F10) Parallel numerical computation (65Y05) Numerical algorithms for specific classes of architectures (65Y10)
Related Items (1)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Optimized Schwarz methods without overlap for highly heterogeneous media
- Algebraic approximation of Dirichlet-to-Neumann maps for the equations of linear elasticity
- Lagrangian formulation of domain decomposition methods: a unified theory
- Algebraic Dirichlet-to-Neumann mapping for linear elasticity problems with extreme contrasts in the coefficients
- Improved ad hoc interface conditions for Schwarz solution procedure tuned to highly heterogeneous media
- Non-overlapping Schwarz methods with optimized transmission conditions for the Helmholtz equation
- A Block FSAI-ILU Parallel Preconditioner for Symmetric Positive Definite Linear Systems
- Algebraic approach to absorbing boundary conditions for the Helmholtz equation
- ALGEBRAIC WAY TO DERIVE ABSORBING BOUNDARY CONDITIONS FOR THE HELMHOLTZ EQUATION
- Optimal convergence properties of the FETI domain decomposition method
This page was built for publication: Auto-tuned Krylov methods on cluster of graphics processing unit
