%0 Generic
%A Herten, Andreas
%A Meinke, Jan
%A Haghighi Mood, Kaveh
%A Hrywniak, Markus
%A Kraus, Jiri
%T PRACE Training Course: GPU Programming with CUDA
%M FZJ-2021-05271
%D 2021
%Z Online course within the PRACE and FZJ training program.
%X GPU-accelerated computing drives current scientific research. Writing fast numeric algorithms for GPUs offers high application performance by offloading compute-intensive portions of the code to an NVIDIA GPU. The course will cover basic aspects of GPU architectures and programming. Focus is on the usage of the parallel programming language CUDA-C which allows maximum control of NVIDIA GPU hardware. Examples of increasing complexity are used to demonstrate optimization and tuning of scientific applications.Topics covered include:    Introduction to GPU/Parallel computing    Programming model CUDA    GPU libraries like CuBLAS and CuFFT    Tools for debugging and profiling    Performance optimizationsThis course is a PRACE training course.
Y2 26 Apr 2021 - 30 Apr 2021
%F PUB:(DE-HGF)17
%9 Lecture
%U https://juser.fz-juelich.de/record/903617