Plan

Lecture with practical project part (VU), attendendance is mandatory and really recommended. Lectures by Jesper Larsson Träff.
Lectures on Thursdays 13.00 - 15.00 in lecture hall EI 4, Reithoffer, Gusshausstrasse 25, see TISS and TUWEL.

Overview

The aim of this lecture is to given an introduction to parallel computing on different types of larger, dedicated, parallel computing systems. This includes basic concepts on how to achieve and estimate parallel performance, and practical exposure to the most common, current programming models, frameworks and paradigms.
Contents: basic concepts, history, motivation. Shared-memory parallel computing, concrete languages: pthreads, OpenMP and Cilk. Distributed memory computing, concrete interface: MPI. New architectures (GPU and others), new languages, other paradigms.

Announcements

Lectures, material

  1. Thursday, 14.3.2019: Planning, Intro, Basics
  2. Thursday, 21.3.2019:
  3. Thursday, 28.3.2019:
  4. Thursday, 4.4.2019:
  5. Thursday, 11.4.2019:
  6. Thursday, 18.4.2019: No lecture (Easter holidays)
  7. Thursday, 25.04.2019: No lecture (Easter holidays)
  8. Thursday, 2.5.2019:
  9. Thursday, 9.5.2019:
  10. Thursday, 16.5.2019:
  11. Thursday, 23.5.2019:
  12. Thursday, 30.5.2019: No lecture (Ascension)
  13. Thursday, 6.6.2019:
  14. Thursday, 13.6.2019:

Exercises

Programming project

The programming project (MPI) is mandatory, hand-in deadline see TUWEL. Benchmarking will have to be done on the system provided for this lecture (Hydra), see TUWEL for instructions and use.
Special exercise (mandatory): Getting access to the systems (key upload)

Exam

Resources

Standards

Canonical, indispensable when programming and debugging

Programs

Literature

Additional literature

The lecture covers material not in these books (and vice versa). Reading at least one of these books is highly recommended.