Software Atelier: Simulation, Data Science & Supercomputing

In this software atelier, students will select one of the proposed software atelier projects, designed by the course director in collaboration with research or industrial partners, and work in potentially interdisciplinary teams to address research questions. The proposed topics will be centered around: 

• Supercomputing: Students will explore the architecture and operational principles of supercomputers, optimizing and parallelizing algorithms for high-performance computing (HPC) environments.
• Data science and machine learning: Students will analyze and interpret large-scale data sets, employing machine learning and statistical methods to derive meaningful insights.

This project-based course is designed to equip students with cutting-edge skills in high-performance computing, simulation studies, and data science, and to help them tackle complex computational challenges across various scientific and engineering domains.

In presence

• Project-based learning: Students will participate in collaborative projects addressing real-world computational problems, similar as the EUMaster4HPC student challenge in Fall 2026. Group work will be encouraged on a per-project basis.
• Preparation of scientific reports or posters: The expected outcome of each software atelier project is a scientific report or scientific posters that will be published in the Technical Reports series of USI, or presented as a publication or poster in top-tier ACM/IEEE Swiss-based conferences [1, 2]. The final grade will be based on an oral evaluation of these reports or posters.
• Expert guidance: Students will be closely guided by academic researchers from USI and collaborating institutions, and depending on the project’s nature, by industry professionals.
• Eligibility: The course is available to MSc students from the MCS/MDS program. Students from other programs might be accepted after the approval by the course directors.
   
  [1] ACM Platform for Advanced Scientific Computing (PASC)
  [2] IEEE Swiss Data Science for the Sciences 

This is a project-based class - the grade is composed of a final project report and/or a poster that will be reviewed and discussed with an oral exam during the official exam period.