Universität Wien
Warning! The directory is not yet complete and will be amended until the beginning of the term.

269015 VU Computer Architecture and High Performance Computing (2021S)

3.00 ECTS (2.00 SWS), SPL 26 - Physik
Continuous assessment of course work
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 15 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

The course will start as online-course. Depending on the COVID-19 pandemic adaptations are possible during the semester.

  • Monday 08.03. 09:45 - 11:15 Digital
  • Monday 15.03. 09:45 - 11:15 Digital
  • Monday 22.03. 09:45 - 11:15 Digital
  • Monday 12.04. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 19.04. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 26.04. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 03.05. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 10.05. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 17.05. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 31.05. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 07.06. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 14.06. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 21.06. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG
  • Monday 28.06. 09:45 - 11:15 Digital
    Seminarraum 11, Währinger Straße 29 2.OG

Information

Aims, contents and method of the course

Understand fundamental concepts of computer architectures and numerical high performance computing. Understand the interaction between problem data, algorithm, implementation of the algorithm, hardware, performance and accuracy. Understand basic concepts for optimized implementations of high performance matrix algorithms, based on a detailed discussion of dense linear solvers for large linear systems.

Method: Integration of lecture and discussions of homework problems in class, programming required (numerical code in a high-level programming language, programming of distributed-memory systems).

Assessment and permitted materials

Two homework projects with several components (implementation, experimentation and analysis), whose results have to be summarized (project report), presented and discussed in class. Oral exam at the end of the semester.

Minimum requirements and assessment criteria

Contributions to the total grade: First homework project 50%, second homework project 50%. Students have to achieve a positive grade for each of the two homework projects to pass the course. Grading of the second homework project includes an oral exam about the project and lecture slides.

Examination topics

Material presented in class and contents of homework projects.

Reading list

Association in the course directory

CO-INF3

Last modified: Fr 12.05.2023 00:22