Introduction to programming of HPC systems

The course will provide the basics of creating parallel applications, including parallel processing and optimization techniques, depending on the target parallel architecture.

Student will be able to:
- actively use the new concepts of parallel programming
- analyze the algorithm, propose a suitable decomposition for its parallelization
- analyze the efficiency of the parallelization design
- implement and optimize algorithm using processor kernel-level parallelization, using multi-core (multicore (CPU) and manycore (MIC) computing capabilities) through OpenMP directives and using multiple computational computing power through MPI inter-process communications.