SubjectsSubjects(version: 948)
Course, academic year 2023/2024
  
Distributed Data Processing - N445073
Title: Distribuované zpracování dat
Guaranteed by: Department of Computing and Control Engineering (445)
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: unknown / unknown (unknown)
Min. number of students: unlimited
Language: Czech
Teaching methods: full-time
Teaching methods: full-time
Level:  
Is provided by: M445015
For type:  
Additional information: http://moodle.vscht.cz/course/view.php?id=116
Guarantor: Cejnar Pavel RNDr. Mgr. Ph.D.
Is interchangeable with: M445015
Examination dates   Schedule   
Annotation -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (30.07.2013)
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 the JAVA programming language.
Aim of the course -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (30.07.2013)

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.

Literature -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (25.04.2018)

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.

Learning resources -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (06.02.2018)
  • 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

Teaching methods -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (30.07.2013)

Lectures and courses.

Syllabus -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (30.07.2013)

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

2. Simple synchronization operations and synchronization blocking primitives.

3. Synchronization model problems. Synchronization support in programming language.

4. Algorithms asymptotic sequential and parallel time and space complexity and their application.

5. PRAM parallel computation model and basic terms of parallel computation theory. Recursion procedures and their parallelization. Parallel matrix multiplication.

6. Parallel sort algorithms.

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

8. Parallelization of graph algorithms and linear algebra algorithms. Available parallel implementations of mathematical libraries.

9. Distributed data processing and communications. Remote procedures 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 C++ in Unix environment.

13. CASE STUDY: distributed and parallel data processing using GPU.

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

Registration requirements -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (30.07.2013)
  • Mathematics I or any equivalent subject

  • one subject in the topic of computer programming in any object oriented language (JAVA, C++)
Course completion requirements -
Last update: Cejnar Pavel RNDr. Mgr. Ph.D. (26.04.2018)

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.

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
Coursework assessment
Form Significance
Regular attendance 40
Examination test 30
Oral examination 30

 
VŠCHT Praha