Designing and optimizing compute kernels on NVIDIA GPUs

Designing and optimizing compute kernels on NVIDIA GPUs

The availability of high performance compute capability in NVIDIA GPUs has expanded their use in CAD environments. We will describe the basic compute models including host/device programming models, device multi-thread programming models, as well optimization and performance tuning techniques.

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Jamsek, D.A.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Acceleration
Algorithm design and analysis
Availability
Computational modeling
Design automation
Design optimization
Graphics processing unit
High performance computing
Kernel
Programming
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The availability of high performance compute capability in NVIDIA GPUs has expanded their use in CAD environments. We will describe the basic compute models including host/device programming models, device multi-thread programming models, as well optimization and performance tuning techniques.
ISSN:2153-6961
2153-697X
DOI:10.1109/ASPDAC.2009.4796484