User: Guest  Login
Document type:
Bachelorarbeit
Type detailled:
Theoretisch
Author(s):
Rafael Piñán
Title:
Targeting High-Performance Applications with NVIDIA Tensor Cores: Precision and Performance Insights
Subtitle:
Zur Nutzung von NVIDIA Tensor Cores für High-Performance-Anwendungen: Untersuchungen zu Genauigkeit und Rechenleistung
Abstract:
This work gives a complete overview of performing dense matrix multiplication and accumulating floating-point operations on NVIDIA Tensor Cores. In 2017, NVIDIA unveiled the first Generation of Tensor Cores as part of the Volta architecture. Nowadays, Tensor Cores are an essential part of the computation hardware of data centers worldwide. As NVIDIA GPUs and these computation units developed, the possibilities expanded. This work reviews the current capabilities of Tensor Cores and how to levera...     »
Advisor:
Mario Wille
Referee:
Prof. Dr. Michael Bader
Year:
2024
Quarter:
3. Quartal
Year / month:
2024-08
Month:
Aug
Language:
en
University:
Technical University of Munich
Faculty:
TUM School of Computation, Information and Technology
TUM Institution:
Department of Computer Science
 BibTeX