9600-1029/02 – Advanced methods of programming of HPC systems (PMHPC)
Gurantor department | IT4Innovations | Credits | 6 |
Subject guarantor | Mgr. Branislav Jansík, Ph.D. | Subject version guarantor | Mgr. Branislav Jansík, Ph.D. |
Study level | undergraduate or graduate | Requirement | Compulsory |
Year | 2 | Semester | summer |
| | Study language | English |
Year of introduction | 2019/2020 | Year of cancellation | 2023/2024 |
Intended for the faculties | FEI | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
Upon completion of the course the student will be able to:
- implement demanding parallel algorithms for hybrid platforms, with a complicated interprocessor communication structure.
- practical understand the possibilities and limitations of state-of-the-art parallel programming methods will allow the choice of the optimal algorithm parallelization tool
- debug, profile and optimize parallel applications
Teaching methods
Lectures
Seminars
Tutorials
Summary
Compulsory literature:
1. http://upc.lbl.gov
UPC Language and Library Specifications, Version 1.3
2. http://mpi-forum.org
MPI: A Message-Passing Interface Standard
3. http://openmp.org
OpenMP Application Program Interface
4. http://www.gpi-site.com
Gaspi: Global Address Space Programming Interface, Specifcation of a PGAS API for communication
Recommended literature:
1. http://docs.it4i.cz
Scalasca, Vampir, TotalView, Allinea DDT/MAP/Performance reports
Additional study materials
Way of continuous check of knowledge in the course of semester
E-learning
Other requirements
Knowledge of the C / C ++ or Fortran programming languages in any version
Prerequisities
Co-requisities
Subject has no co-requisities.
Subject syllabus:
1. OpenMP 4.0 standard, task based programming
2. MPI 3.0 standard, working with intercoms, MPI - IO, MPI one-sided communication
GPI-2 standard, one-sided communication, extremely parallel algorithms, failure mechanism
4. Unified Parallel C, PGAS standard, programming with Berkley UPC, shared shared memory.
5. Tuning and profiling of parallel applications
6. OpenMP 4.5 Standard, Accelerator Programming
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction
Předmět neobsahuje žádné hodnocení.