High Performance Computing Projects at FIT CTU

Lecture:   High Performance Computing Projects at FIT CTU
Lecturers:     Daniel Langr, Tomáš Dytrych, Jiří Chudoba, Tomáš Oberhuber
Date and time: 4th March 2013, 6–7:30 p.m.
Place:       FIT CTU in Prague, 9 Thákurova Street, New Building CTU, lecture room T9:107
Language: Czech


In this lecture, we will introduce several interesting research problems and corresponding computational tasks where high-performance computing and parallel algorithms come to the game. We will present non-traditional methods for modelling in nuclear physics that lead to extremely high computational and memory complexity requiring implementation on massively parallel computer systems with hundred-thousand   processors  (T.Dytrych, LSU, D.Langr, FIT CTU). Next, we will describe the architecture and technology of large computational grids for solving high-performance computing tasks from physics and astronomy (J. Chudoba, IP AS CR, CERN). The last part will focus on numerical computations on GPU platforms (T. Oberhuber, FJFI CTU). 


Short CV's:

Daniel Langr is a part-time PhD student in the doctoral degree study program Informatics at FIT CTU. His research interests are in parallel algorithms for peta-scale computing (peta = 10^15).

Tomáš Dytrych received his PhD at Louisiana State University where he is currently pursuing research in modelling of the structures of nuclear physics.

Jiří Chudoba received his PhD at MFF UK. He received a research fellowship at CERN. He currently works at the Institute of Physics of AS CR, where he also acts as a manager of the Computing center. His is involved in the distributed computing for CERN experiments and astro-particle physics project Pierre Auger Observatory.

Tomáš Oberhuber received his  PhD  at FJFI CTU. His research interests include GPU-based methods for modelling of physical processes. 

Free entrance. 


Last modified: 8.4.2013, 11:19