NekRS, a GPU-accelerated spectral element Navier–Stokes solver
The development of NekRS, a GPU-oriented thermal-fluids simulation code based on the
spectral element method (SEM) is described. For performance portability, the code is based …
spectral element method (SEM) is described. For performance portability, the code is based …
ViennaCL---linear algebra library for multi-and many-core architectures
CUDA, OpenCL, and OpenMP are popular programming models for the multicore
architectures of CPUs and many-core architectures of GPUs or Xeon Phis. At the same time …
architectures of CPUs and many-core architectures of GPUs or Xeon Phis. At the same time …
[HTML][HTML] Multi-GPU acceleration of large-scale density-based topology optimization
D Herrero-Pérez, PJM Castejón - Advances in Engineering Software, 2021 - Elsevier
This work presents a parallel implementation of density-based topology optimization using
distributed GPU computing systems. The use of multiple GPU devices allows us accelerating …
distributed GPU computing systems. The use of multiple GPU devices allows us accelerating …
Efficient parallel implementations of sparse triangular solves for GPU architectures
The sparse triangular matrix solve (SpTrSV) is an important computation kernel that is
demanded by a variety of numerical methods such as the Gauss-Seidel iterations. However …
demanded by a variety of numerical methods such as the Gauss-Seidel iterations. However …
A GPU accelerated discontinuous Galerkin incompressible flow solver
We present a GPU-accelerated version of a high-order discontinuous Galerkin discretization
of the unsteady incompressible Navier–Stokes equations. The equations are discretized in …
of the unsteady incompressible Navier–Stokes equations. The equations are discretized in …
High-performance algebraic multigrid solver optimized for multi-core based distributed parallel systems
Algebraic Multigrid (AMG) is a linear solver, well known for its linear computational
complexity and excellent parallelization scalability. As a result, AMG is expected to be a …
complexity and excellent parallelization scalability. As a result, AMG is expected to be a …
GPU accelerated spectral finite elements on all-hex meshes
This paper presents a spectral element finite element scheme that efficiently solves elliptic
problems on unstructured hexahedral meshes. The discrete equations are solved using a …
problems on unstructured hexahedral meshes. The discrete equations are solved using a …
A new class of AMG interpolation methods based on matrix-matrix multiplications
A new class of distance-two interpolation methods for algebraic multigrid (AMG) that can be
formulated in terms of sparse matrix-matrix multiplications is presented and analyzed …
formulated in terms of sparse matrix-matrix multiplications is presented and analyzed …
A GPU-accelerated adaptive FSAI preconditioner for massively parallel simulations
G Isotton, C Janna, M Bernaschi - The International Journal …, 2022 - journals.sagepub.com
The solution of linear systems of equations is a central task in a number of scientific and
engineering applications. In many cases the solution of linear systems may take most of the …
engineering applications. In many cases the solution of linear systems may take most of the …
A dynamic pattern factored sparse approximate inverse preconditioner on graphics processing units
M Bernaschi, M Carrozzo, A Franceschini… - SIAM Journal on Scientific …, 2019 - SIAM
One of the most time-consuming tasks in the procedures for the numerical study of PDEs is
the solution to linear systems of equations. To that purpose, iterative solvers are viewed as a …
the solution to linear systems of equations. To that purpose, iterative solvers are viewed as a …