Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver

Abstract : This paper describes the design and the performance of DOMINO, a 3D Cartesian SN solver that implements two nested levels of parallelism (multicore+SIMD) on shared memory computation nodes. DOMINO is written in C++, a multi-paradigm programming language that enables the use of powerful and generic parallel programming tools such as Intel TBB and Eigen. These two libraries allow us to combine multi-thread parallelism with vector operations in an efficient and yet portable way. As a result, DOMINO can exploit the full power of modern multi-core processors and is able to tackle very large simulations, that usually require large HPC clusters, using a single computing node. The very high Flops/Watt ratio of DOMINO makes it a very interesting building block for a future many-nodes nuclear simulation tool.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-00986975
Contributor : Pierre Ramet <>
Submitted on : Monday, May 5, 2014 - 11:26:42 AM
Last modification on : Tuesday, March 6, 2018 - 3:58:03 PM
Long-term archiving on : Tuesday, August 5, 2014 - 11:46:15 AM

File

SNA.pdf
Files produced by the author(s)

Identifiers

Citation

Salli Moustafa, Ivan Dutka Malen, Laurent Plagne, Angélique Ponçot, Pierre Ramet. Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver. Annals of Nuclear Energy, Elsevier Masson, 2014, Special Issue SNA+MC 2013, pp.1-10. ⟨10.1016/j.anucene.2014.08.034⟩. ⟨hal-00986975⟩

Share

Metrics

Record views

419

Files downloads

353