News articles

TU Wien Named an NVIDIA GPU Research Center

TU Wien today announced that it has been named a GPU Research Center by NVIDIA, the world leader in visual computing.

[Translate to English:]

© TU Wien

1 of 4 images or videos

[Translate to English:]

[Translate to English:]

[Translate to English:]

© TU Wien

1 of 4 images or videos

[Translate to English:]

[Translate to English:]

[Translate to English:]

© TU Wien

1 of 4 images or videos

[Translate to English:]

[Translate to English:]

[Translate to English:]

1 of 4 images or videos

[Translate to English:]

[Translate to English:]

GPU Research Centers are institutions that embrace and utilize GPU technologies across multiple research fields, and are at the forefront of some of the world’s most innovative scientific research. GPU computing leverages the parallel processing capabilities of GPU accelerators and enabling software to deliver dramatic increases in performance for scientific, artificial intelligence, deep learning, graphics, engineering, and other demanding applications.

TU Wien was recognized for its advanced research in parallel linear algebra, fast iterative solvers and advanced preconditioners using GPUs. Significant contributions in the field of GPU computing have been made via the free open source software library ViennaCL headed by Karl Rupp and actively developed at the Institute for Microelectronics, TU Wien. Together with his colleagues Josef Weinbub and Florian Rudolf and the PETSc team at the Argonne National Laboratory, USA, GPU-accelerated routines for supercomputers will be developed and optimized for optimal performance in this GPU Research Center. This will allow practitioners all over the world to leverage the computational power of current and future supercomputers for research in such areas as fluid dynamics, structural mechanics, finance, and nanoelectronics.

According to Karl Rupp, the team is pleased to be recognized as an NVIDIA GPU Research Center at TU Wien, because it recognizes their research as well as their ambitions to provide the best GPU-enabled codes to the scientific community and the general public. At the same time, it is a motivation for them to further pursue their innovative approaches. More concretely, the team will look into techniques for the assembly of large system matrices in finite element methods, as well as the efficient solution of these systems using asynchronous algebraic multigrid methods. As a GPU Research Center, TU Wien will have pre-release access to NVIDIA GPU hardware and software, the opportunity to attend exclusive events with key researchers and academics, a designated NVIDIA technical liaison, and access to specialized online and in-person training sessions. GPU Research Centers were formerly known as CUDA Research Centers.

For further information, contact:
Karl Rupp
Institute for Microelectronics, TU Wien
+43 1 58801 36027
<link>rupp@iue.tuwien.ac.at