Syllabus
1. What is High Performance Computing. History plus how the development at IT4I goes.. X86 vs. GPU, vs. what is the compiler, parallelization etc.
2. Basic Unix commands, editing files by Nano, etc.
3. Scheduler, Modules, basic usages of batch system (Slurm, PBSPro) etc.. graphics visualization, detecting different nodes, etc.
4. Queues, detecting nodes, projects accounting, limits of queues, etc.
5. Easybuild and its control, how to use it and tailor it, making group and usage of module within the group
6. Libraries for mathematical operations (linear algebra packages) LAPACK, BLAS, etc.
7. Basics of Fortran
8. Makefile, compiling of the code (eg. Fortran), change and linking. Static vs. Dynamical libraries.
9. Basic of bash, loops for, while, basic math, etc.
10. Profiling of the code 11 -14 i) Practical parts - Quantum-Mechanical Calculations of Electronic structure of simple elements, equilibrium lattice constant, bulk modulus, demonstration of the power of prediction. It’s possible to include problems proposed by students
Annotation
High Performance Computing in Physics. General rules, basic methods how to work with sustem used at largest clusters of Czech national supercomputing center (IT4Innovations) and similar centres.
Preparation of computationally intensive problems (optimization, parallelization), execution of jobs at computational clusters and other practical aspects. Recommended for bc. students of physics.
Precondition is to be capable of basic handling of Unix/Linux systems.