Welcome, Guest . Login . Türkçe
Where Am I: Ninova / Courses / Institute of Informatics / HBM 514E - Koşut Sayısal Algoritmalar ve Araçlar

HBM 514E - Parallel Numer.Algor.&Tools

Course Objectives

The goal of the course is to give the students sufficient skills in the area of parallel computing so that they will be able to (i) read and understand descriptions of parallel algorithms, (ii) understand, in general terms, the size of the potential gain in execution time for a given problem when ported to a parallel computer, (iii) choose a suitable parallel algorithm for a given problem, (iv) modify the standard algorithms, described in the course, so that they suit to a given non-standard problem, (v) write scalable parallel numerical algorithms for the scientific and engineering problems in general sense. We will concentrate upon the message-passing methods of parallel computing and use some standard parallel computing tools such as MPI (Message Passing Interface), OpenMP and Multilevel Parallel Programming (Hybrid programming) techniques for SMP and Distributed Computer Architectures. Algebraic equations, ODE’s, PDE’s, dense and sparse matrix operations, iterative and direct solution methods for large scale linear set of equations and FFT are re-revisited and their algorithms are reconstructed in terms of parallel programming concepts and tools learned in the course.

Course Description

Science and engineering have undergone a major transformation at the research level as well as at the development and technology levels. The modern scientist and engineer spend more and more time in front of a laptop, a workstation, or a parallel supercomputer and less and less time in the physical laboratory or in the workshop.
In this course, we review and expand the role of parallelism in computing and introduce the parallel numerical programming models that serve as the basis for subsequent discussion of algorithm design, performance analysis, and implementation. We will learn parallel numerical computing techniques and algorithms, and have practical experiences writing parallel programs on a both shared memory and distributed memory computers. We will also focus on how numerical algorithms can be made efficient on these parallel computers.

Course Coordinator
Mustafa Serdar Çelebi
Course Language
Courses . Help . About
Ninova is an ITU Office of Information Technologies Product. © 2024