Tesla

Subscribe
GPU Applications

Computational Fluid Dynamics

Several ongoing projects on Navier-Stokes models and Lattice Boltzman methods have shown very large speedups using CUDA-enabled GPUs. This work is highlighted below starting with some charts, followed by links to technical reports. There is also work on weather modeling and ocean modeling using GPUs.

GPU Technology Conference

Join us at GTC 2014

Explore all the great CFD content. >>
 

Incompressible Navier-Stokes
Thibault and Senocak

Lattice Boltzman Methods
Tolke and Krafczyk

 


For information on key ISVs and applications, please visit the GPU Applications page.


Other Relevant Software Using CUDA
> OpenCurrent: Open-Source library of CUDA-Accelerated PDE (partial differential equation) Solvers Over Regular Grids
> Sailfish: CFD Solver using the Lattice Boltzman method
> ANDSolver: Solves Euler Equations on Unstrcutred Meshes of Polyhedrals
> Library of PCG and BIGSTAB Linear Iterative Solvers Linked with OpenFOAM
> Elegant Mathematics: Boltzmann Solver, Conjugate Gradient, GMRES
   

CUDA-Acceleration in Related Verticals
> Weather and Ocean modeling on CUDA
> MATLAB®
   
 
Technical Reports on CFD on CUDA
> Unstructured Grid Based CFD Solvers using CUDA GPUs (Code is also available)
> A Fast Double Precision CFD Code using CUDA
> 2D & 3D Euler Solvers from Pullan Group
> Video comparing 2D CFD on CPU and GPU
> Discontinuous Galerkin Methods on GPUs by Andreas Klockner
> Plasma Turbulence Modeling with CUDA

Lattice-Boltzmann

> Lattice Boltzmann-based 3D CFD
> Lattice Boltzman for lighting
> 3D LB solver
> Lattice-Boltzman-based PDE solver

Navier-Stokes

> Finite Element Simulations and Navier-Stokes Solver using GPUs
> Navier-Stokes Stanford University Solver (NSSUS) on CUDA

Core Kernels for CFD on CUDA GPUs

Sparse Matrix Linear Solvers : Iterative solvers

> SpMV from NVIDIA: Code
> Paper 1
> Paper 2
> Iterative CUDA

Sparse Matrix Linear Solvers : Direct solvers

> ANSYS Direct Solver
> PARDISO with CUDA

Multigrid Solvers

> Algebraic multi-grid on CUDA GPUs
> Using MG as a Preconditioner and Domain Decomposition with Unstructured Grids

Flux Computation

> 3D finite difference calculations using CUDA (structured grids)
> A Fast Double Precision CFD Code on CUDA (structured grids)
> Nodal Discontinuous Galerkin (DG) Code for Unstructured Codes on GPUs

Multiblock, Codes

> 2D Euler Solver on CUDA
> 3D Hypersonic flow Over Vehicle
> AMR (Adaptive Mesh Refinement) Code for Astrophysics
 
See Also
> Tesla/CUDA Success stories
> Other Tesla Vertical Solutions
> CUDA Software development tools & libraries
> ArrayFire GPU function library for C, C++, FORTRAN
> Buy Tesla

MATLAB is a registered trademark of The MathWorks, Inc.
ArrayFire is a trademark of AccelerEyes