FPF:UFUF016 Methods of Parallel Computing - Course Information
UFUF016 Methods of Parallel Computing in Physics
Faculty of Philosophy and Science in OpavaSummer 2016
- Extent and Intensity
- 0/2/0. 3 credit(s). Type of Completion: z (credit).
- Teacher(s)
- Mgr. Karel Adámek, Ph.D. (seminar tutor)
- Guaranteed by
- Mgr. Karel Adámek, Ph.D.
Centrum interdisciplinárních studií – Faculty of Philosophy and Science in Opava - Course Enrolment Limitations
- The course is also offered to the students of the fields other than those the course is directly associated with.
- fields of study / plans the course is directly associated with
- Astrophysics (programme FPF, B1701 Fyz)
- Computer Technology and its Applications (programme FPF, B1702 AplF)
- Course objectives
- Making students acquainted with basic paradigmas of parallel computing and its use in theoretical physics.
- Syllabus
- 1. Introduction to parallel programing
- Architecture of parallel systems, Flynn's taxonomy - SISD, SIMD, MISD,MIMD, Serial vs. parallel paradigm
- Speed up factor, Amdhal's law, Efficiency, Scalability
- Parallel compution today.
- Basics of MPI
2. Design of parallel program
- Partitioning - Domain decomposition, Functional decomposition
- Communication - Divide and conquer
- Agglomeration
- Mapping
3. Global communication
- Broadcast, Reduce, Gather, Scatter
4. Data grouping
- Derived data types, Pack/Unpack
5. Communication models and topologies
- Communicator, Topology
- Matrix multiplication
6. Advanced point to point communication
- Non-blocking communication, Persistent communication requests
- Synchronous mode, Buffered mode, Ready mode
- 1. Introduction to parallel programing
- Language of instruction
- Czech
- Further comments (probably available only in Czech)
- The course can also be completed outside the examination period.
- Teacher's information
- Will be communicated at the beginning of semester.
- Enrolment Statistics (recent)
- Permalink: https://is.slu.cz/course/fpf/summer2016/UFUF016