143112a Advanced Programming of Massively Parallel Processors

Zuletzt geändert:	01.10.2025 / Radicke
EDV-Nr:	143112a
Studiengänge:	Computer Science and Media (Master), Prüfungsleistung im Modul Advanced Programming of Massively Parallel Processors in Semester 1 2 3 Häufigkeit: unregelmäßig
Dozent:	Prof. Dr. Stefan Radicke
Link zur Veranstaltung / zum E-Learning-Kurs:	GitLab Pages - coming soon! MI Cloud - coming soon! Password: TBA
Sprache:	Deutsch, Englisch auf Anfrage
Art:	-
Umfang:	2 SWS
ECTS-Punkte:	5
Prüfungsform:
Beschreibung:	Heterogeneous data parallel computing Parallel Patterns Convolution Stencil Parallel histogram Reduction and minimizing divergence Prefix sum (scan) Merge Performance measurement and optimization Advanced Parallel Patterns (selected by students) Sorting Sparse matrix computation Graph traversal Deep learning Iterative MRI reconstruction Electrostatic potential map
English Title:	Advanced Programming of Massively Parallel Processors
English Abstract:	Students learn how to utilize the Compute Unified Device Architecture (CUDA) programming model in order to leverage the potential of modern massively parallel Graphics Processing Unit (GPU) architectures in advanced software applications and in research projects.
Literatur:	Wen-mei W. Hwu, David B. Kirk, Izzat El Hajj, "Programming Massively Parallel Processors: A Hands-on Approach", Fourth Edition, Morgan Kaufmann, 2022, ISBN ‎978-0323912310, [available online] Weitere Literatur finden Sie in der HdM-Bibliothek.
Internet:	CUDA Toolkit Documentation