CUDA Research Center

Mission:

The CUDA Research Center at the Czech Technical University in Prague concentrates mainly on the research and development of new numerical methods for solving partial differential equations in many domains like image processing, medical data processing, material science, combustion and models of atmosphere. Our aim is not only to solve the mentioned problems but also to systematically develop library for easy and efficient numerical computing on the GPU based on CUDA. For this purpose we intensively work on more fundamental problems like efficient sparse matrix formats for GPUs, matrix solvers, multigrid and domain decomposition methods. GPUs also allow us to do more complex computations in higher precision arithmetic and to study its effect on numerical simulations of highly non-linear or chaotic physical phenomena.

Terminology:

The research center is established within the academic collaboration program of the NVIDIA Corporation producing the GPU (Graphics Processing Unit) hardware.

Program website:

CUDA Research Center at the Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague

Collaboration:

• Atsushi Suzuki (Laboratoire Jacques-Louis Lions, Université Pierre et Marie Curie, Paris) - efficient solvers for the Navier Stokes equations
• František Hakl (Institute of Computer Science, Czech Academy of Sciences) - neural networks on GPU
• Petr Bauer (Institute of Thermomechanics, Czech Academy of Sciences, and Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague)

Involved students:

• Vítězslav Žabka - PhD student - efficient solvers for saddle-point problems on GPU
• Vladimír Klement - PhD student - multigrid methods for Navier Stokes equations solved on GPU
• Vladimír Španihel - PhD student - implementation of neural networks on GPU
• Ladislav Horký - master student - fuzzy filters in image processing on GPU
• Matěj Novotný - master student - high precision arithmethic on GPU
• Martin Černý - bachelor thesis - Implementation of Matrix Solvers on GPU, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, 2011
• Martin Heller - bachelor thesis - Implementation of Matrix Solvers on GPU, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, 2010
• Jan Hofta - diploma thesis - Parallelization of Genetic Algorithms Using GPU, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, 2009
• Jan Vacata - diploma thesis - General Purpose Computing on GPU, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, 2008

The CUDA Research Center is looking for new collaborators in the following areas:

• Graduate students for the study in the branches Mathematical Engineering and Mathematical Informatics of the Czech study programme at the Faculty of Nuclear Sciences and Physical Engineering
• PhD students world-wide to be engaged

Questions and applications should be sent to:

Tomáš Oberhuber
Department of Mathematics
Faculty of Nuclear Sciences and Physical Engineering
Czech Technical University in Prague
Trojanova 13, 120 00 Prague 2
Czech Republic

Tel: +420 2 2435 8540, Fax: 2 2491 8643
E-mail: tomas.oberhuber (at) fjfi.cvut.cz
URL: http://geraldine.fjfi.cvut.cz/

Copyright © 2024 MMG FNSPE CTU in Prague. All rights reserved.