Cluster Optimization and Parallelization of Simulations with Dynamically Adaptive Grids

Handle URI:
http://hdl.handle.net/10754/597784
Title:
Cluster Optimization and Parallelization of Simulations with Dynamically Adaptive Grids
Authors:
Schreiber, Martin; Weinzierl, Tobias; Bungartz, Hans-Joachim
Abstract:
The present paper studies solvers for partial differential equations that work on dynamically adaptive grids stemming from spacetrees. Due to the underlying tree formalism, such grids efficiently can be decomposed into connected grid regions (clusters) on-the-fly. A graph on those clusters classified according to their grid invariancy, workload, multi-core affinity, and further meta data represents the inter-cluster communication. While stationary clusters already can be handled more efficiently than their dynamic counterparts, we propose to treat them as atomic grid entities and introduce a skip mechanism that allows the grid traversal to omit those regions completely. The communication graph ensures that the cluster data nevertheless are kept consistent, and several shared memory parallelization strategies are feasible. A hyperbolic benchmark that has to remesh selected mesh regions iteratively to preserve conforming tessellations acts as benchmark for the present work. We discuss runtime improvements resulting from the skip mechanism and the implications on shared memory performance and load balancing. © 2013 Springer-Verlag.
Citation:
Schreiber M, Weinzierl T, Bungartz H-J (2013) Cluster Optimization and Parallelization of Simulations with Dynamically Adaptive Grids. Lecture Notes in Computer Science: 484–496. Available: http://dx.doi.org/10.1007/978-3-642-40047-6_50.
Publisher:
Springer Science + Business Media
Journal:
Lecture Notes in Computer Science
KAUST Grant Number:
UK-c0020
Issue Date:
2013
DOI:
10.1007/978-3-642-40047-6_50
Type:
Book Chapter
ISSN:
0302-9743; 1611-3349
Sponsors:
This work was supported by the German Research Foun-dation (DFG) as part of the Transregional Collaborative Research Centre “Inva-sive Computing (SFB/TR 89). It is partially based on work supported by AwardNo. UK-c0020, made by the King Abdullah University of Science and Technology(KAUST). All software is freely available athttp://www5.in.tum.de/sierpinski.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorSchreiber, Martinen
dc.contributor.authorWeinzierl, Tobiasen
dc.contributor.authorBungartz, Hans-Joachimen
dc.date.accessioned2016-02-25T12:56:40Zen
dc.date.available2016-02-25T12:56:40Zen
dc.date.issued2013en
dc.identifier.citationSchreiber M, Weinzierl T, Bungartz H-J (2013) Cluster Optimization and Parallelization of Simulations with Dynamically Adaptive Grids. Lecture Notes in Computer Science: 484–496. Available: http://dx.doi.org/10.1007/978-3-642-40047-6_50.en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.doi10.1007/978-3-642-40047-6_50en
dc.identifier.urihttp://hdl.handle.net/10754/597784en
dc.description.abstractThe present paper studies solvers for partial differential equations that work on dynamically adaptive grids stemming from spacetrees. Due to the underlying tree formalism, such grids efficiently can be decomposed into connected grid regions (clusters) on-the-fly. A graph on those clusters classified according to their grid invariancy, workload, multi-core affinity, and further meta data represents the inter-cluster communication. While stationary clusters already can be handled more efficiently than their dynamic counterparts, we propose to treat them as atomic grid entities and introduce a skip mechanism that allows the grid traversal to omit those regions completely. The communication graph ensures that the cluster data nevertheless are kept consistent, and several shared memory parallelization strategies are feasible. A hyperbolic benchmark that has to remesh selected mesh regions iteratively to preserve conforming tessellations acts as benchmark for the present work. We discuss runtime improvements resulting from the skip mechanism and the implications on shared memory performance and load balancing. © 2013 Springer-Verlag.en
dc.description.sponsorshipThis work was supported by the German Research Foun-dation (DFG) as part of the Transregional Collaborative Research Centre “Inva-sive Computing (SFB/TR 89). It is partially based on work supported by AwardNo. UK-c0020, made by the King Abdullah University of Science and Technology(KAUST). All software is freely available athttp://www5.in.tum.de/sierpinski.en
dc.publisherSpringer Science + Business Mediaen
dc.subjectcluster skippingen
dc.subjectdynamic adaptivityen
dc.subjectshared memory load balancingen
dc.subjectspace-filling curveen
dc.titleCluster Optimization and Parallelization of Simulations with Dynamically Adaptive Gridsen
dc.typeBook Chapteren
dc.identifier.journalLecture Notes in Computer Scienceen
dc.contributor.institutionTechnische Universitat Munchen, Munich, Germanyen
kaust.grant.numberUK-c0020en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.