Issue |
2014
SNA + MC 2013 - Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo
|
|
---|---|---|
Article Number | 04105 | |
Number of page(s) | 9 | |
Section | 4. Advanced Parallelism and HPC Strategies: a. Deterministic Methods, Parallelism and HPC | |
DOI | https://doi.org/10.1051/snamc/201404105 | |
Published online | 06 June 2014 |
Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver
1 EDF R&D 1, Av du Général de Gaulle F92141 CLAMART CEDEX France
2 INRIA-University of Bordeaux, France
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. For example, DOMINO solves a 3D full core PWR eigenvalue problem involving 26 energy groups, 288 angular directions (S16), 46 × 106 spatial cells and 1 × 1012 DoFs within 11 hours on a single 32-core SMP node. This represents a sustained performance of 235 GFlops and 40:74% of the SMP node peak performance for the DOMINO sweep implementation. The very high Flops/Watt ratio of DOMINO makes it a very interesting building block for a future many-nodes nuclear simulation tool.
Key words: Deterministic transport / SN / multicore processor / wavefront / TBB / SIMD
© Owned by the authors, published by EDP Sciences, 2014