EventoWeb
Zürcher Hochschule für Angewandte Wissenschaften
Menu Home User Menu
Not registered Login
[ German (Switzerland) German (Switzerland) ]   [ English ]
[ de de ]   [ en ]
Not registered Login
n.BA.AD.OHPC.24HS (Optimisation and High Performance Computing) 
Module: Optimisation and High Performance Computing
This information was generated on: 12 November 2025
No.
n.BA.AD.OHPC.24HS
Title
Optimisation and High Performance Computing
Credits
4

Description

Version: 2.0 start 01 August 2025

 

Study Programme Applied Digital Life Sciences
Regulations Applicable RPO, 29 January 2008, School of Life Sciences and Facility Management Academic Regulations, 15 Dec. 2009, Annex for the Bachelor of Applied Digital Life Sciences degree programme
Module Type  
X Compulsory Module    Elective Module    Optional Module
Planned Semester 5th Semester
Module Coordinator Simone Ulzega
Telephone / E-Mail +41 (0)58 934 54 75 / simone.ulzega@zhaw.ch
Lecturer(s),
Speaker(s),
Associate(s)		 Simone Ulzega, Pascal Häussler, Stefan Weber
Entrance Requirements Programmieren, Numerische Grundlagen der Data Sciences
Learning Outcomes and Competencies Technical competencies:
The students
  • have an overview and general understanding of the relevant topics and basic concepts in the field of optimisation methods.
  • are able to analyze problems and design parameterized algorithms.
  • can use different methods to solve optimisation problems.
  • understand the basic structure and the functionalities of a High Performance Computing cluster.
  • understand basic HPC-related concepts such as shared and distributed memory.
  • can design software for HPC applications.
 
Interdisciplinary competencies:
Students are able to
  • describe and analyse problems.
  • assess parallelisation opportunities and apply relevant methods.
Module Content Optimisation methods
  • Formulation of an optimisation problem: objective function, variables, constraints.
  • First and second order methods (e.g., gradient descent, Newton’s method).
  • High-dimensional problems.
  • Data-driven optimisation.
  • Hyperparameter optimisation.
  • Stochastic methods (e.g., Simulated Annealing).
High Performance Computing (HPC)
  • Conceptually understand HPC: cluster, applications, possibilities, diversity, fair sharing
  • Working with the Earth Cluster: operating procedures, workload management (SLURM), modules, use and install software in HPC environments, resource planning
  • Software design for HPC: design patterns, parallelization, IO patterns and data access and structure
  • Shared and Distributed Memory Parallelization; Hybrid approach; GPU parallelization
Follow-up Modules -
Methods of Instruction  Lectures, exercises
Digital Resources Moodle, Earth Cluster
Lesson Structure / Workload  
 Contact Hours 28
 Guided Self-Study 28
 Independent Self-Study 64
 Total Workload 120
Classroom Attendance Attendance is encouraged, but not enforced with attendance list
Assessment The final assessment (Course work 100%) is calculated as follows:
  • 50%: written in-person exam (individual work). The exam will take place in early November and will cover topics discussed in the course up to that date. 
  • 50%: final project (group work). It will be assigned in mid-November. Students are expected to hand in a written report and the resulting source code along with associated scripts, etc.
Language of Instruction  English
Comments -

 

Note

Course: Optimisation and High Performance Computing
No.
n.BA.AD.OHPC.24HS.V
Title
Optimisation and High Performance Computing

Note

  • No module description is available in the system for the cut-off date of 12 November 2025.