The Newsletter 2020-10-07
CUDA Course Apr. 13, 2021

Introduction to Programming on the GPU with CUDA
organized for
Researchers and Students (PhD, MSc)
April 13, 2021


The Graphics Processing Unit or GPU is nowadays a mainstream component in Scientific Computing. For relatively little money one can have supercomputer performance. However, some extra work has to be done to make an ordinary sequential program suitable for use on the GPU.
One of the most important tools for using GPUs is currently "CUDA" (Compute Unified Device Architecture). This is basically an extension to the C programming language, which can be used to program the GPU in an easy way. Another tool is OpenCL, but this is less mature than CUDA and performs less on especially the newest GPUs, the focus will be currently on CUDA.

Course goal: In this 1-day course we will explain the basic principles of GPU programming and let you practise with many examples on several types of GPUs in our lab room. After this course you should be able to make simple CUDA programs which can be run on a GPU.

Preliminaries: We recommend having a (rudimentary) understanding of a C-like programming language, such as C++, Java or similar. Fortran or Python should be fine as well. Interest in iterative solvers can be helpful.

Teachers: Kees Vuik, Ir. Kees Lemmens

Costs: For members of DCSE this course is free. For other participants the costs are €100,- online and on campus €200,- including lunch (only for on campus participants) with course material.

Location: Online and on campus EEMCS building 28, Penguin Lab (E0.380), van Mourik Broekmanweg 6, Delft.


09:30 - 09:45 Introduction

09:45 - 10:30 Intro Parallel and GPU programming Kees Vuik

10:45 - 11:30 Basics of the CUDA Programming toolkit Kees Lemmens

11:45 - 12:30 Unified memory and shared memory Kees Lemmens

12:45 - 13:30 Lunch

13:45 - 14:30 Using libraries like CUFFT and CUBLAS Kees Lemmens

14:45 - 15:30 Debugging and Profiling with cuda-gdb and nvprof / nvvp Kees Lemmens

15:45 - 16:30 Singularity containers and Cuda 10/11 Kees Lemmens

16:30         Wrap up

Notes: The number of participants is restricted to 35. (10 participants on campus and 25 participants online)

Register: In order to attend this course please register at


More info:
Email contact: or