Course details
Applications of Parallel Computers
PDD Acad. year 2013/2014 Winter semester
The course gives an overview of usable parallel platforms and models of programming, mainly shared-memory programming (OpenMP), message passing (MPI) and data-parallel programming (CUDA, OpenCL). A parallelization methodology is completed by performance studies and applied to a particular problem. The emphasis is put on practical aspects and implementation.
Guarantor
Language of instruction
Completion
Time span
- 39 hrs lectures
Department
Subject specific learning outcomes and competences
To learn how to parallelize various classes of problems and predict their performance. To be able to utilize parallelism and communication at thread- and process level. To get acquainted with state-of-the-art standard interfaces, language extensions and other tools for parallel programming (MPI, OpenMP). Write and debug a parallel program for a selected task.
Parallel architectures with distributed and shared memory, programming in C/C++ with MPI and OpenMP, GPGPU, parallelization of basic numerical methods.
Learning objectives
To clarify possibilities of parallel programming on multi-core processors, on clusters and on GP GPUs. View over synchronization and communication techniques. Get to know a method of parallelization and performance prediction of selected real-world applications, the design of correct programs and the use parallel computing in practice.
Prerequisite knowledge and skills
Types of parallel computers, programming in C/C++, basic numerical methods
Study literature
Fundamental literature
- Pacecho, P.: Introduction to Parallel Programming. Morgan Kaufman Publishers, 2011, 392 s., ISBN: 9780123742605
- Kirk, D., and Hwu, W.: Programming Massively Parallel Processors: A Hands-on Approach, Elsevier, 2010, s. 256, ISBN: 978-0-12-381472-2
Syllabus of lectures
- Parallel computer architectures, performance measures and their prediction
- Shared variable and message-passing programming: OpenMP and MPI.
- Patterns for parallel programming
- Parallel linear algebra
- Graph partitioning
- Disrete optimization
- PDEs
- N-body problem
- Parallel and distributed simulation
- Graphics and visualization
- Data and knowledge mining
- Languages, compilers, libraries, and tools.
Progress assessment
Study evaluation is based on marks obtained for specified items. Minimimum number of marks to pass is 50.
Teaching methods and criteria
The course uses teaching methods in form of Lecture - 3 teaching hours per week.
Controlled instruction
Defence of a software project based on a variant of parallel programming.
Course inclusion in study plans