Introduction to High Performance Computing

This course is intended for students who are interested in computing-intensive research. In the course, a number of algorithms that are being used within a diversity of research areas are considered. The scaling behavior of these algorithms in case of increasing problem size and/or an increasing number of processors is analyzed. Attention is paid to those aspects of computer architectures that are important to understanding the resulting performance, such as the memory hierarchy and the interconnection network. By analyzing their computing-intensive characters, determine the possible bottlenecks of several case studies (applications). Based on performance analysis, it will be indicated how the effect of those bottlenecks can be reduced. The goal is to learn how to achieve high performance with the available hardware architecture.

The lab exercises will be done on the supercomputer at TU Delft. The emphasis will be on designing efficient parallel algorithms and optimizing for high performance. During the lab exercises, the following types of problems will be elaborated on: a parallel Poisson solver, a parallel finite element simulation, a parallel N-body simulation, and matrix computation on GPUs. More information, such as handouts and slides, can be found on Brightspace.

Note: This course is the same as the previous ocurse IN4049TU. Starting from 2024/2025, lectures and exams will be given under the new course code WI4049TU (which is equivalent to IN4049TU)