End-to-end Parallel Simulations with APES

Harald Klimach, Kartik Jain, Sabine Roller

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

10 Citations (Scopus)

Abstract

Simulations at extreme scale generate large amounts of data. As sufficiently large resources to handle the large data sets are generally available only in a distributed form, the complete tool chain deployed to obtain simulation results needs to be usable on distributed systems. In this work we present the APES framework which provides such a tool chain for mesh based simulations. We show the scaling behavior of two solvers from that framework, both of which are capable to deal with complex geometries but target different application domains. The scalability is investigated on the SuperMUC system installed at the Leibniz-Rechenzentrum in Munich including an analysis of single node behavior and the sustained performance.
Original languageEnglish
Title of host publicationParallel computing
Subtitle of host publicationAccelerating computational science and engineering (CSE)
EditorsMichael Bader, Arndt Bode, Hans-Joachim Bungartz, Michael Gerndt, Gerhard R. Joubert, Frans Peters
PublisherIOS
Pages703-711
Volume25
ISBN (Print)978-1-61499-380-3
DOIs
Publication statusPublished - 2014
Externally publishedYes
EventInternational Conference on Parallel Computing, ParCo 2013 - Garching, Germany
Duration: 10 Sep 201313 Sep 2013

Publication series

NameAdvances in Parallel Computing
Volume25
ISSN (Print)0927-5452
ISSN (Electronic)1879-808X

Conference

ConferenceInternational Conference on Parallel Computing, ParCo 2013
Abbreviated titleParCo
CountryGermany
CityGarching
Period10/09/1313/09/13

Keywords

  • Scalability
  • Octree
  • Space-filling-curves
  • Distributed computing

Cite this