Lecture: High Performance Computing

Course Number 17164-01
Lecturers Florina M. Ciorba
Assistants Aurélien Cavelan
Danilo Guerrera
Ali Omar Abdelazim Mohammed
Ahmed Eleliemy
Time and Location Thu 10:15 - 12:00; Seminarraum 00.003, Spiegelgasse 1
Start 01-03-2018
Exercises Thu 12:15 - 13:00; Computer-Labor U1.001, Spiegelgasse 1
Prerequisites Students are expected to have basic knowledge of:
* Computer Architecture,
* Programming (C or C++)
* Algorithms and Data Structures,
* Numerical Computing, and
* Foundations of Distributed Systems (MA lecture offered in the fall semesters)
Objectives Advanced understanding how parallel applications can be programmed and how they perform and interact on parallel architectures.
Overview of current HPC programming models and practical use of HPC systems.
Contents Deepend and expand the knowledge of parallel and distributed computing systems. We will discuss:
* Parallel systems architectures
* Parallel applications workloads
* Advanced parallel programming models and languages (OpenMP, MPI, CUDA, and combinations thereof)
* Fault tolerance and resilience
* Performance engineering and performance reproducibility
* Novel/upcoming models of computation
Literature Books titles and web links provided in course.
Assessment Lehrveranst.-begleitend

Please note: The assessment of the lecture will be in the form of a *written examination*.
The grade of the written examination represents the final grade for the lecture.
To be allowed to take the exam, students must achieve a minimum of 50% of the number of points associated with *each* of the exercises accompanying the lecture.

Examination date:
Credit Points 4
Grades 1-6 0,5
Registration Services (Requires login)