Multi-dimensional Homomorphisms and Their Implementation in OpenCL

Homomorphisms (traditionally defined on lists) are functions that can be parallelized by the divide-and-conquer paradigm. In this paper, we introduce an extension of the traditional homomorphism concept— multi-dimensional homomorphisms (MDHs) —which capture parallelism on multi-dimensional arrays. W...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	International journal of parallel programming Jg. 46; H. 1; S. 101 - 119
Hauptverfasser:	Rasch, Ari, Gorlatch, Sergei
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.02.2018 Springer Nature B.V
Schlagworte:	Central processing units Computer Science CPUs Graphics processing units Homomorphisms Linear algebra Lists Machine learning Mathematical analysis Matrix algebra Matrix methods Microprocessors Nesting Parallel processing Parallel programming Processor Architectures Software Engineering/Programming and Operating Systems Theory of Computation Homomorphisms Auto-tuning Multi-core Matrix–vector multiplication OpenCL Algorithmic skeletons GPU computing
ISSN:	0885-7458, 1573-7640
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!