Extreme-scale AMR

Carsten Burstedde, Omar Ghattas, Michael Gurnis, Tobin Isaac, Georg Stadler, Tim Warburton, Lucas C. Wilcox

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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-of-octrees 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.

Original languageEnglish (US)
Title of host publication2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010
DOIs
StatePublished - 2010
Event2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010 - New Orleans, LA, United States
Duration: Nov 13 2010Nov 19 2010

Other

Other2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010
CountryUnited States
CityNew Orleans, LA
Period11/13/1011/19/10

Fingerprint

Coarsening
Geophysics
Geometry
Parallel algorithms
Resource allocation
Data structures

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Burstedde, C., Ghattas, O., Gurnis, M., Isaac, T., Stadler, G., Warburton, T., & Wilcox, L. C. (2010). Extreme-scale AMR. In 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010 [5644907] https://doi.org/10.1109/SC.2010.25

Extreme-scale AMR. / Burstedde, Carsten; Ghattas, Omar; Gurnis, Michael; Isaac, Tobin; Stadler, Georg; Warburton, Tim; Wilcox, Lucas C.

2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010. 2010. 5644907.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Burstedde, C, Ghattas, O, Gurnis, M, Isaac, T, Stadler, G, Warburton, T & Wilcox, LC 2010, Extreme-scale AMR. in 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010., 5644907, 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010, New Orleans, LA, United States, 11/13/10. https://doi.org/10.1109/SC.2010.25
Burstedde C, Ghattas O, Gurnis M, Isaac T, Stadler G, Warburton T et al. Extreme-scale AMR. In 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010. 2010. 5644907 https://doi.org/10.1109/SC.2010.25
Burstedde, Carsten ; Ghattas, Omar ; Gurnis, Michael ; Isaac, Tobin ; Stadler, Georg ; Warburton, Tim ; Wilcox, Lucas C. / Extreme-scale AMR. 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010. 2010.
@inproceedings{9726faa22bbe4ef1a3790f0a11be3fc1,
title = "Extreme-scale AMR",
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-of-octrees 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.",
author = "Carsten Burstedde and Omar Ghattas and Michael Gurnis and Tobin Isaac and Georg Stadler and Tim Warburton and Wilcox, {Lucas C.}",
year = "2010",
doi = "10.1109/SC.2010.25",
language = "English (US)",
isbn = "9781424475575",
booktitle = "2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010",

}

TY - GEN

T1 - Extreme-scale AMR

AU - Burstedde, Carsten

AU - Ghattas, Omar

AU - Gurnis, Michael

AU - Isaac, Tobin

AU - Stadler, Georg

AU - Warburton, Tim

AU - Wilcox, Lucas C.

PY - 2010

Y1 - 2010

N2 - 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-of-octrees 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.

AB - 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-of-octrees 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.

UR - http://www.scopus.com/inward/record.url?scp=78650851765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650851765&partnerID=8YFLogxK

U2 - 10.1109/SC.2010.25

DO - 10.1109/SC.2010.25

M3 - Conference contribution

AN - SCOPUS:78650851765

SN - 9781424475575

BT - 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010

ER -