Detail publikace

Many Core Acceleration of the Boundary Element Method

MERTA, M. ZAPLETAL, J. JAROŠ, J.

Originální název

Many Core Acceleration of the Boundary Element Method

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

The paper presents the boundary element method accelerated by the Intel Xeon Phi coprocessors. An overview of the boundary element method for the 3D Laplace equation is given followed by the discretization and its parallelization using OpenMP and the offload features of the Xeon Phi coprocessor are discussed. The results of numerical experiments for both single- and double-layer boundary integral operators are presented. In most cases the accelerated code significantly outperforms the original code running solely on Intel Xeon processors.

Klíčová slova

Boundary Element Method, Intel Xeon Phi, MIC, Many Integrated Cores, Acceration

Autoři

MERTA, M.; ZAPLETAL, J.; JAROŠ, J.

Vydáno

3. 6. 2016

Nakladatel

Springer International Publishing

Místo

Basel

ISBN

978-3-319-40360-1

Kniha

Proceedings of High Performance Computing in Science and Engineering

Edice

Lecture Notes in Computer Science

Strany od

116

Strany do

125

Strany počet

10

URL

BibTex

@inproceedings{BUT130911,
  author="Michal {Merta} and Jan {Zapletal} and Jiří {Jaroš}",
  title="Many Core Acceleration of the Boundary Element Method",
  booktitle="Proceedings of High Performance Computing in Science and Engineering",
  year="2016",
  series="Lecture Notes in Computer Science",
  volume="9611",
  pages="116--125",
  publisher="Springer International Publishing",
  address="Basel",
  doi="10.1007/978-3-319-40361-8\{_}8",
  isbn="978-3-319-40360-1",
  url="http://link.springer.com/chapter/10.1007%2F978-3-319-40361-8_8"
}