Download our brochure

Home // Studies // FSTM // Master in Hi... // Learning Outcomes

Master in High Performance Computing

This new specialisation will have feature modules dedicated to HPC/HPDA/AI. In the context
of the government’s strategy on AI and data economy, Luxembourg has massively invested
in the HPC/HPDA/AI domain, which will increase further. Therefore, it would eventually
attract more participants to take this study profile. It is expected that this specialisation will
have an impact on the HPC/HPDA/AI-based companies and R&D areas.

For the first year, students will focus on the following modules (fundamentals):

● Mathematical Methods and Statistics: Parallel Numerical Algorithms, Linear Algebra,
Linear Programming, Optimization, Numerical Methods and Analysis, Probability,
Statistic Estimation, Data Analysis, Design of Experiments
● Software Engineering: Application life-cycle, Application Design Methods and Tools,
Component Integration, Software Releases, Software Validation and Verification,
Generic Programming (currently C++, Python), Code Management Tools (currently
● Parallel Programming: Shared-Memory vs Distributed Memory Programming,
Distributed Systems, Software Engineering and Parallel Programming, Basic
Operating System Support, File Systems, Concurrency, Synchronisation, Generic
Programming (currently C++, Python), Code Management Tools (currently Git)
● Computer Architecture: Processor architecture, Memory Hierarchy, Pipelined and
Superscalar Processors, Datapath, Structural, Control and Data Hazards, Branch
Prediction, Exception Handling, Devices, I/O, Storage, Networking, Clusters, Cloud
For the second year, students will focus on the specialization (track) focusing on
Graduates of the track/specialisation offered by the University of Luxembourg should have
acquired the following skills and competencies upon completion of the programme:
● Demonstrate a broad understanding of artificial intelligence, high performance data
analytics, and multidisciplinary knowledge of machine learning and data analytics.
● Demonstrate a broad understanding of parallel programming, distributed systems,
middleware technologies, software engineering, compilers, parallel programming
design, applications & parallel performance analysis and quantum computing.
● Demonstrate a broad understanding of application life-cycle, component integration,
software stacks, operating systems, kernel development, parallel file systems,
high-speed networking, synchronisation, container technologies, virtualisation
technologies, and integration of HPC and cloud.
● Demonstrate a broad understanding of SoC design, NoC design, microarchitecture,
memory systems, circuit design (VLSI design flow), power dissipation, low-power
design techniques, thermal power models, and multiprocessor design.
● Ability to use transversal/soft skills and competencies in order to facilitate integration
into the job market.
● Ability to develop research topics & write proposals and critically evaluate the
problem & analysis skills.
● Ability to carry out a project risk assessment and constructively manage failure.
● Ability to work in a multicultural group environment.