Description:

21st century in computer architectures is primarily influenced by the shift of the Moore's law into parallelization of CPUs at the level of computing cores. Parallel computing systems are becoming a ubiquitous commodity and parallel programming becomes the basic paradigm of development of efficient applications for these platforms. Students get acquainted with architectures of parallel and distributed computing systems, their models, theory of interconnection networks and collective communication operations, and languages and environments for parallel programming of shared and distributed memory computers. They get acquianted with fundamental parallel algorithms and on selected problems, they will learn the techniques of design of efficient and scalable parallel algorithms and methods of performance evaluation of their implementations. The course includes a semester project of practical programming in OpenMP and MPI for solving a particular nontrivial problem.

Contents:

1. Introduction into parallel and distributed programming.
2. Introduction into OpenMP.
3. Parallel algorithms for the state space search.
4. Prpgramming and performance tuning in OpenMP.
5. Parallel sorting in OpenMP.
6. Introduction into MPI.
7. Interconnection networks of parallel computers I.
8. Interconnection networks of parallel computers II.
9. Collective communication operations.
10. Parallel reduction and parallel scan. Parallel I/O.
11. Parallel algorithms in OpenMP/MPI I.
12. Parallel algorithms in OpenMP/MPI II.

Seminar contents:

1. Design and implementation of a sequential algorithm in C/C++.
2. Design and implementation of a parallel algorithm using OpenMP task parallel constructs.
3. Design and implementation of a parallel algorithm using OpenMP data parallel constructs.
4. Design and implementation of a parallel algorithm using MPI on a cluster.
5. Analysis of parallel performance and scalability of the resulting program and writing a technical report.

Recommended literature:

[1] Mattson, T.G. - Sanders, B.A. - Massingill, B.L.: Patterns for Parallel Programming. Addison-Wesley Professional. 2004. 978-0321940780.
[2] Kumar, V. - Grama, A. - Gupta, A. - Karpis, G.: Introduction to Parallel Computing: Design and Analysis of Parallel Algorithms. Benjamin-Cummings. 1994. 0805331700.
[3] Miller, R. - Boxer, L.: Algorithms Sequential and Parallel: A Unified Approach. Pearson Education. 1999. 0130863734.
[4] Wilkinson, B. - Allen, M.: Parallel Programming: Techniques and Applications Using Networked Workstations and Parallel Computers. Prentice Hall. 1998. 0136717101.
[5] Jaja, J.: An Introduction to Parallel Algorithms. Addison-Wesley. 1992. 0201548569.

Keywords:

parallel algorithms, parallel programming, distributed programming, shared memory, message passing, OpenMP, MPI.

Abbreviations used:

Semester:

• W ... winter semester (usually October - February)
• S ... spring semester (usually March - June)
• W,S ... both semesters

Mode of completion of the course:

• A ... Assessment (no grade is given to this course but credits are awarded. You will receive only P (Passed) of F (Failed) and number of credits)
• GA ... Graded Assessment (a grade is awarded for this course)
• EX ... Examination (a grade is awarded for this course)
• A, EX ... Examination (the award of Assessment is a precondition for taking the Examination in the given subject, a grade is awarded for this course)

Weekly load (hours per week):

• P ... lecture
• C ... seminar
• L ... laboratory
• R ... proseminar
• S ... seminar