A Framework for Hybrid Parallel Flow Simulations with a Trillion Cells in Complex Geometries

Beitrag bei einer Tagung


Details zur Publikation

Autor(en): Godenschwager C, Schornbaum F, Bauer M, Köstler H, Rüde U
Titel Sammelwerk: International Conference for High Performance Computing, Networking, Storage and Analysis, SC
Verlag: IEEE Computer Society
Jahr der Veröffentlichung: 2013
Tagungsband: Proceedings of SC13: International Conference for High Performance Computing, Networking, Storage and Analysis
Seitenbereich: 35-1 -- 35-12
ISSN: 2167-4337
Sprache: Englisch


Abstract


waLBerla is a massively parallel software framework for simulating complex ows with the lattice Boltzmann method (LBM). Performance and scalability results are presented for SuperMUC, the world's fastest x86-based supercomputer ranked number 6 on the Top500 list, and JUQUEEN, a Blue Gene/Q system ranked as number 5. We reach resolutions with more than one trillion cells and perform up to 1.93 trillion cell updates per second using 1.8 million threads. The design and implementation of waLBerla is driven by a careful analysis of the performance on current petascale supercomputers. Our fully distributed data structures and algorithms allow for efficient, massively parallel simulations on these machines. Elaborate node level optimizations and vectorization using SIMD instructions result in highly optimized compute kernels for the single- and two-relaxation-time LBM. Excellent weak and strong scaling is achieved for a complex vascular geometry of the human coronary tree. Copyright 2013 ACM.



FAU-Autoren / FAU-Herausgeber

Bauer, Martin
Lehrstuhl für Informatik 10 (Systemsimulation)
Godenschwager, Christian
Lehrstuhl für Informatik 10 (Systemsimulation)
Köstler, Harald PD Dr.
Lehrstuhl für Informatik 10 (Systemsimulation)
Rüde, Ulrich Prof. Dr.
Lehrstuhl für Informatik 10 (Systemsimulation)
Schornbaum, Florian
Lehrstuhl für Informatik 10 (Systemsimulation)


Zitierweisen

APA:
Godenschwager, C., Schornbaum, F., Bauer, M., Köstler, H., & Rüde, U. (2013). A Framework for Hybrid Parallel Flow Simulations with a Trillion Cells in Complex Geometries. In Proceedings of SC13: International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 35-1 -- 35-12). Denver, US: IEEE Computer Society.

MLA:
Godenschwager, Christian, et al. "A Framework for Hybrid Parallel Flow Simulations with a Trillion Cells in Complex Geometries." Proceedings of the SC13: International Conference for High Performance Computing, Networking, Storage and Analysis, Denver IEEE Computer Society, 2013. 35-1 -- 35-12.

BibTeX: 

Zuletzt aktualisiert 2018-21-10 um 12:40