Vít Vondrák, Ph.D. is the scientific director at IT4Innovations National Supercomputing Center and associate professor at VŠB-Technical University of Ostrava (VSB-TUO). His expertise is in numerical linear algebra, optimization methods, and high performance computing. His working experience also includes several research stays at Aalborg University in Denmark (1997-2007), University of Colorado Boulder (2004) and Stanford University (2006). He is a member of management boards and national coordinator of several European and national research and infrastructure projects. Vít Vondrák is an author of more than sixty scientific papers.
VŠB – Technical University of Ostrava (VŠB – TUO) is the fourth largest university in the Czech Republic which traditionally provides higher education in technical and economic fields of study. Study and research at VŠB-TUO are historically formed by close ties with major international companies, as well as by joint research and mobility programs with university partners from all over the world. In order to keep up with the trends in ICT the IT4Innovations National Supercomputing Centre was founded in 2011 as one of the university research institutes.
The Intel® Parallel Computing Center (s) (Intel® PCC) at IT4 Innovations National Supercomputing Center is developing highly parallel algorithms and libraries optimized for the latest Intel parallel technologies. Main activities of the center are divided into two pillars: development of highly parallel algorithms and libraries, and development and support of HPC community codes. The pillar development of highly parallel algorithms and libraries focuses on the development of the state-of-the-art sparse iterative linear solvers combined with appropriate preconditioners and domain decomposition methods, suitable for solution of very large problems distributed over tens of thousands of Intel® Xeon Phi™ coprocessor accelerated nodes. Developed solvers will become part of the IT4I in-house ESPRESO (ExaScale PaRallel FETI SOlver) library. Development and support of HPC community codes includes creating an interface between ESPRESO and existing community codes Elmer and OpenFOAM Extend Project.
All activities will leverage the new installation of the IT4Innovations Salomon supercomputer. It will be the largest installation of an Intel® Xeon Phi™ coprocessor accelerated cluster in Europe. It will consist of 432 compute nodes with 864 Intel Xeon Phi™ coprocessors (two Intel Xeon Phi 7120P per node) and will be available in Q2/2015.
- March 6, 2018, Rendering in Blender Cycles using AVX512 Vectorization, IXPUG Spring 2018
- Jan Zapletal, Michal Merta, September 21, 2016, Boundary Element Method for Manycore Architectures, IXPUG