ИСТИНА

Ultrascale computing systems make special demands on the level of professional training of specialists working on these systems. These requirements are expressed in the knowledge of mathematical models of the different scientific domains, numerical methods and algorithms, as well as software, instrumental systems and tools for parallel programming. The basis for the training of such specialists is educational programs in the field of Computational Science. Of particular importance in this training is the ability to consolidate the theoretical knowledge gained in practice. In this talk the experience of teaching supercomputer disciplines to students at the Department of Computational Mathematics and Cybernetics of Moscow State Lomonosov University will be presented. We will focus on the description of the course “Supercomputer Modeling and Technologies”, which is offered as part of the Master’s degree training program at the CMC Department. The content and setting of the practical assignments will be considered. Emphasis will be placed on aspects related to description of the structure and properties of the parallel algorithms and their implementation on ultrascale computing systems.