Druckansicht der Internetadresse:

Faculty of Mathematics, Physics & Computer Science

Scientific Computing, Master of Science (M.Sc.)

Seite drucken

Practical Course on Parallel Numerical Methods

The Practical Course on Parallel Numerical Methods is held every year at the end of the winter term by the Chair of Parallel and Distributed Systems in cooperation with the Chair of Scientific Computing.

Supervisor: Thomas Rau (Scientific Computing)

Next course: 28. March 2021 -  8. April 2021

Location: tba

Organization

The course will take place in digital form. The schedule is as follows, subject to change:

TimeDay 1Day 2Day 3Day 4Day 5
10:00 - 12:00Introduction Linux, C/C++, cmakeTheoretical Basics Parallel ProgrammingIntroduction OpenMPIntroduction MPIIntroduction Use of clusters
12:00 - 13:30LunchLunchLunchLunchLunch
13:30 - 17:30Introduction PCG, Sparse data formatsProgrammingProgrammingProgrammingProgramming

     

Time Day 6Day 7Day 8Day 9Day 10
10:00 - 12:00Introduction FEM, DealIntroduction FEM, DealQuestion time for the presentationProgrammingProgramming
12:00 - 13:30LunchLunchLunchLunchLunch
13:30 - 17:30ProgrammingPorgrammingProgrammingProgrammingProgramming

   

The time for the final presentations is April 13th from 10:00 am to 5:00 pm.

Content

In this practical course, students implement manageable numerical problems (such as PCG method, finite element discretization of 2d Laplacian, etc.) on parallel computers using the programming language C/C++ and standard software libraries (LAPACK/BLAS, OpenMP, OpenMPI). The resulting parallel efficiency is observed depending on the chosen implementation (naive or advanced such as Schwarz methods).

Recommended Prerequisities

  • A1: Numerical Methods for Differential Equations
  • C1.3: Parallel and Distributed Systems I
  • D1.1: Efficient Treatment of Non-local Operators

Grading

Implementation and presentation of approaches; active participation and discussion

Courses

1. Course on Parallel Numerical Methods (Summer 2020): 27.07.20 - 07.08.20 online


Verantwortlich für die Redaktion: Maximilian Bauer

Facebook Twitter Youtube-Kanal Instagram Blog UBT-A Contact