Optimization of Finite-Differencing Kernels for Numerical Relativity Applications

Roberto Alfieri, Sebastiano Bernuzzi, Albino Perego, David Radice

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

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.

Original languageEnglish (US)
Title of host publicationParallel Computing is Everywhere
EditorsGerhard R. Joubert, Patrizio Dazzi, Frans Peters, Marco Danelutto, Sanzio Bassini
PublisherIOS Press BV
Pages743-749
Number of pages7
ISBN (Electronic)9781614998426
DOIs
StatePublished - Jan 1 2018

Publication series

NameAdvances in Parallel Computing
Volume32
ISSN (Print)0927-5452
ISSN (Electronic)1879-808X

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Optimization of Finite-Differencing Kernels for Numerical Relativity Applications'. Together they form a unique fingerprint.

Cite this