High Performance Computing for Python (1V+1U, 3.0 LP)
|SWS||Type||Course Form||CP (Effort)||Presence-Time / Self-Study|
|-||K||Lecture with exercise classes (V/U)||3.0 CP||62 h|
|1||U||Exercise class (in small groups)||14 h|
|(1V+1U)||3.0 CP||28 h||62 h|
|CP, Effort||3.0 CP = 90 h|
|Position of the semester||1 Sem. in WiSe|
|Level|| Master (General)|
|Area of study||[INF-VIS] Visualisation and Scientific Computing|
Lecture plus programming exercises.
Possible Study achievement
- Verification of study performance: proof of successful participation in the exercise classes (ungraded)
- Details of the examination (type, duration, criteria) will be announced at the beginning of the course.
Python's powerful elegance has driven its adoption at clusters for High Performance Computing (HPC) for job orchestration, visualisation, exploratory data analysis, and even numerical simulations. But maximising performance from Python applications can be challenging especially on supercomputing architectures. This course will outline a variety of performance optimisation strategies, tools for measuring and addressing performance problems, and establish best practices for Python for HPC.
Competencies / intended learning achievements
Programming for Computations, S. Linge, H. P. Langtangen, Springer 2020
Requirements for attendance (informal)
Basic knowledge in Python is mandatory.