Optimization of Finite-Differencing Kernels for Numerical Relativity Applications

A simple optimization strategy for the computation of 3D finite-differencing kernels on many-cores architectures is proposed. The 3D finite-differencing computation is split direction-by-direction and exploits two level of parallelism: in-core vectorization and multi-threads shared-memory paralleliz...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of low power electronics and applications 2018-06, Vol.8 (2), p.15
Hauptverfasser: Alfieri, Roberto, Bernuzzi, Sebastiano, Perego, Albino, Radice, David
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A simple optimization strategy for the computation of 3D finite-differencing kernels on many-cores architectures is proposed. The 3D finite-differencing computation is split direction-by-direction and exploits two level of parallelism: in-core vectorization and multi-threads shared-memory parallelization. The main application of this method is to accelerate the high-order stencil computations in numerical relativity codes. Our proposed method provides substantial speedup in computations involving tensor contractions and 3D stencil calculations on different processor microarchitectures, including Intel Knight Landing.
ISSN:2079-9268
2079-9268
DOI:10.3390/jlpea8020015