SubjectsSubjects(version: 963)
Course, academic year 2024/2025
  
Distributed Data Processing - M445015
Title: Distribuované zpracování dat
Guaranteed by: Department of Mathematics, Informatics and Cybernetics (446)
Faculty: Faculty of Chemical Engineering
Actual: from 2021
Semester: winter
Points: winter s.:4
E-Credits: winter s.:4
Examination process: winter s.:
Hours per week, examination: winter s.:2/2, MC [HT]
Capacity: unlimited / unlimited (unknown)
Min. number of students: unlimited
State of the course: taught
Language: Czech
Teaching methods: full-time
Teaching methods: full-time
Level:  
Additional information: http://moodle.vscht.cz/course/view.php?id=116
Note: course can be enrolled in outside the study plan
enabled for web enrollment
Guarantor: Cejnar Pavel RNDr. Mgr. Ph.D.
Interchangeability : N445073
Annotation -
The course covers the basics of parallel programming and distributed processing of computationally intensive tasks and procedures. The aim of the course is to analyze the process communication and time complexity of process subtasks with respect to design the procedures with optimized parallel performance. Implementation of the studied methods is predominantly in programming languages JAVA and MATLAB.
Last update: Cejnar Pavel (12.09.2021)
Aim of the course -

Students will be able to:

  • Distinguish whether it is easy to make given task or procedure parallel.

  • Design effective parallel procedures.

  • Propose other possible acceleration of calculations for tasks with hard parallelization.

Last update: Pátková Vlasta (20.04.2018)
Course completion requirements -

To complete the course, student must successfully pass an exam test covering the student's practical skills and pass the oral exam covering the theoretical knowledge. The final mark is determined by the points for attendance (max. 40 p, in selected cases can be replaced by the test), from the exam test (max. 30 p) and from the oral exam (max 30 p).

Last update: Švihlík Jan (26.04.2018)
Literature -

R: Tvrdík, P.: Parallel Algorithms and Computing. ČVUT Praha, 2010. ISBN 978-80-01-04333-2.

A: Lea, D.: Concurrent Programming in Java: Design Principles and Pattern (2nd Edition). Prentice Hall, 1999. ISBN 978-0-201-31009-2.

A: Eckel, B.: Thinking in Java. Prentice Hall, 2006. ISBN 978-0131872486.

A: Patterson, A. D., Henessy, L. J.: Computer Organization and Design, Fourth Edition: The Hardware/Software Interface (The Morgan Kaufmann Series in Computer Architecture and Design).Morgan Kaufmann, 2011. ISBN 978-0123747501.

A: Wilkinson, B., Allen, M.: Parallel Programming: Techniques and Applications Using Networked Workstations and Parallel Computers. Prentice Hall, 1999.ISBN 0-13-671710-1.

Last update: Švihlík Jan (25.04.2018)
Teaching methods -

Lectures and courses.

Last update: Pátková Vlasta (20.04.2018)
Syllabus -

1. Distributed and parallel data processing, parallelization on multicore computer processors. Software optimization of computer procedures.

2. Simple synchronization operations, blocking synchronization primitives.

3. Model problems in synchronization. Synchronization support in programming language.

4. Asymptotic time and space complexity for parallel algorithms. PRAM parallel computation model.

5. Recursive procedures and their parallelization. Parallel matrix multiplication.

6. Parallel sort algorithms.

7. Parallel prefix sum algorithm and its applications (parallel addition, RadixSort, SPPS).

8. Parallelization of graph algorithms and linear algebra algorithms.

9. Distributed data processing and communications. Remote procedure call.

10. Current hardware architectures for parallel data computation.

11. CASE STUDY: Distributed and parallel data processing in MATLAB.

12. CASE STUDY: Distributed and parallel data processing in Python, C++, and using GPU.

13. Advanced parallelization techniques. Distributed and parallel processing optimization.

Last update: Cejnar Pavel (04.09.2023)
Learning resources -
  • electronic materials are available at http://moodle.vscht.cz/course/view.php?id=116 (in Czech language)

  • Java SE API Documentation, http://java.sun.com >> http://www.oracle.com/technetwork/java/index.html

  • electronic help and documentation for MATLAB Parallel Computing Toolbox, MATLAB Distributed Computing Server

Last update: Pátková Vlasta (20.04.2018)
Registration requirements -
  • Mathematics I or any equivalent subject

  • one subject in the topic of computer programming in any object oriented language (JAVA, Python, C++, MATLAB)
Last update: Cejnar Pavel (09.06.2023)
Teaching methods
Activity Credits Hours
Konzultace s vyučujícími 0.1 2
Účast na přednáškách 1 28
Práce na individuálním projektu 0.5 14
Příprava na zkoušku a její absolvování 1.4 40
Účast na seminářích 1 28
4 / 4 112 / 112
 
VŠCHT Praha