CaltechAUTHORS
  A Caltech Library Service

Extreme-Scale AMR

Burstedde, Carsten and Ghattas, Omar and Gurnis, Michael and Isaac, Tobin and Stadler, Georg and Warburton, Tim and Wilcox, Lucas C. (2010) Extreme-Scale AMR. In: 2010 International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE , Piscataway, NJ, pp. 1-12. ISBN 978-1-4244-7557-5. http://resolver.caltech.edu/CaltechAUTHORS:20121119-100717889

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20121119-100717889

Abstract

Many problems are characterized by dynamics occurring on a wide range of length and time scales. One approach to overcoming the tyranny of scales is adaptive mesh refinement/coarsening (AMR), which dynamically adapts the mesh to resolve features of interest. However, the benefits of AMR are difficult to achieve in practice, particularly on the petascale computers that are essential for difficult problems. Due to the complex dynamic data structures and frequent load balancing, scaling dynamic AMR to hundreds of thousands of cores has long been considered a challenge. Another difficulty is extending parallel AMR techniques to high-order-accurate, complex-geometry-respecting methods that are favored for many classes of problems. Here we present new parallel algorithms for parallel dynamic AMR on forest-ofoctrees geometries with arbitrary-order continuous and discontinuous finite/spectral element discretizations. The implementations of these algorithms exhibit excellent weak and strong scaling to over 224,000 Cray XT5 cores for multiscale geophysics problems.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/SC.2010.25DOIUNSPECIFIED
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5644907PublisherUNSPECIFIED
Additional Information:© 2010 IEEE. Date of Current Version: 29 November 2010; Issue Date: 13-19 November 2010. This work was partially supported by NSF (OCI-0749334, OCI-0748898, CCF-0427985, DMS-0724746, OPP-0941678), AFOSR (FA9550-09-1-0608), and DOE (06ER25782, 08ER25860, 08NA28615, SC0002710). We thank Laura Alisic, George Biros, Martin Burtscher, Rahul Sampath, and Tiankai Tu for extended discussions. We also thank TACC for providing access to Ranger under TeraGrid award MCA04N026, and the NCCS/ORNL for early-user access to Jaguar.
Group:Seismological Laboratory
Funders:
Funding AgencyGrant Number
NSFOCI- 0749334
NSFOCI-0748898
NSFCCF-0427985
NSFDMS-0724746
NSFOPP-0941678
AFOSRFA9550-09-1-0608
Department of Energy (DOE)06ER25782
Department of Energy (DOE)08ER25860
Department of Energy (DOE)08NA28615
Department of Energy (DOE)SC0002710
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number11675879
Record Number:CaltechAUTHORS:20121119-100717889
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20121119-100717889
Official Citation:Burstedde, C.; Ghattas, O.; Gurnis, M.; Isaac, T.; Stadler, G.; Warburton, T.; Wilcox, L.; , "Extreme-Scale AMR," High Performance Computing, Networking, Storage and Analysis (SC), 2010 International Conference for , vol., no., pp.1-12, 13-19 Nov. 2010 doi: 10.1109/SC.2010.25
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:35534
Collection:CaltechAUTHORS
Deposited By: Jason Perez
Deposited On:19 Nov 2012 19:35
Last Modified:23 Aug 2016 10:21

Repository Staff Only: item control page