Scholars@Duke

Propagation pattern for moment representation of the lattice Boltzmann method.

Publication ,  Journal Article
Gounley, J; Vardhan, M; Draeger, EW; Valero-Lara, P; Moore, SV; Randles, A
Published in: IEEE transactions on parallel and distributed systems : a publication of the IEEE Computer Society
March 2022
Published version (DOI)

A propagation pattern for the moment representation of the regularized lattice Boltzmann method (LBM) in three dimensions is presented. Using effectively lossless compression, the simulation state is stored as a set of moments of the lattice Boltzmann distribution function, instead of the distribution function itself. An efficient cache-aware propagation pattern for this moment representation has the effect of substantially reducing both the storage and memory bandwidth required for LBM simulations. This paper extends recent work with the moment representation by expanding the performance analysis on central processing unit (CPU) architectures, considering how boundary conditions are implemented, and demonstrating the effectiveness of the moment representation on a graphics processing unit (GPU) architecture.

Duke Scholars

Amanda Randles
Author Amanda Randles Biomedical Engineering
Altmetric Attention Stats
Dimensions Citation Stats

Published In

IEEE transactions on parallel and distributed systems : a publication of the IEEE Computer Society

DOI

10.1109/tpds.2021.3098456

EISSN

1558-2183

ISSN

1045-9219

Publication Date

March 2022

Volume

33

Issue

3

Start / End Page

642 / 653

Related Subject Headings

  • Distributed Computing
  • 4606 Distributed computing and systems software
  • 1005 Communications Technologies
  • 0805 Distributed Computing
  • 0803 Computer Software
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Gounley, J., Vardhan, M., Draeger, E. W., Valero-Lara, P., Moore, S. V., & Randles, A. (2022). Propagation pattern for moment representation of the lattice Boltzmann method. IEEE Transactions on Parallel and Distributed Systems : A Publication of the IEEE Computer Society, 33(3), 642–653. https://doi.org/10.1109/tpds.2021.3098456
Gounley, John, Madhurima Vardhan, Erik W. Draeger, Pedro Valero-Lara, Shirley V. Moore, and Amanda Randles. “Propagation pattern for moment representation of the lattice Boltzmann method.” IEEE Transactions on Parallel and Distributed Systems : A Publication of the IEEE Computer Society 33, no. 3 (March 2022): 642–53. https://doi.org/10.1109/tpds.2021.3098456.
Gounley J, Vardhan M, Draeger EW, Valero-Lara P, Moore SV, Randles A. Propagation pattern for moment representation of the lattice Boltzmann method. IEEE transactions on parallel and distributed systems : a publication of the IEEE Computer Society. 2022 Mar;33(3):642–53.
Gounley, John, et al. “Propagation pattern for moment representation of the lattice Boltzmann method.” IEEE Transactions on Parallel and Distributed Systems : A Publication of the IEEE Computer Society, vol. 33, no. 3, Mar. 2022, pp. 642–53. Epmc, doi:10.1109/tpds.2021.3098456.
Gounley J, Vardhan M, Draeger EW, Valero-Lara P, Moore SV, Randles A. Propagation pattern for moment representation of the lattice Boltzmann method. IEEE transactions on parallel and distributed systems : a publication of the IEEE Computer Society. 2022 Mar;33(3):642–653.

Published In

IEEE transactions on parallel and distributed systems : a publication of the IEEE Computer Society

DOI

10.1109/tpds.2021.3098456

EISSN

1558-2183

ISSN

1045-9219

Publication Date

March 2022

Volume

33

Issue

3

Start / End Page

642 / 653

Related Subject Headings

  • Distributed Computing
  • 4606 Distributed computing and systems software
  • 1005 Communications Technologies
  • 0805 Distributed Computing
  • 0803 Computer Software