A task-based parallelism and vectorized approach to 3D Method of Characteristics (MOC) reactor simulation for high performance computing architectures
Name
Forget_A task-based parallelism.pdf
Size
672.15 KB
Format
Adobe PDF
Checksum (MD5)
31a55317201683366d53c91f31bd5db4
Author(s)
He, Tim
Siegel, Andrew R.
Tramm, John Robert
Gunow, Geoffrey Alexander
Smith, Kord S.
Forget, Benoit Robert Yves
Date Issued
January 2016
Journal
Computer Physics Communications
Publisher
Elsevier
Citation
Tramm, John R. et al. “A Task-Based Parallelism and Vectorized Approach to 3D Method of Characteristics (MOC) Reactor Simulation for High Performance Computing Architectures.” Computer Physics Communications 202 (May 2016): 141–150 © 2016 Elsevier B.V.
Version
Author's final manuscript
Abstract
In this study we present and analyze a formulation of the 3D Method of Characteristics (MOC) technique applied to the simulation of full core nuclear reactors. Key features of the algorithm include a task-based parallelism model that allows independent MOC tracks to be assigned to threads dynamically, ensuring load balancing, and a wide vectorizable inner loop that takes advantage of modern SIMD computer architectures. The algorithm is implemented in a set of highly optimized proxy applications in order to investigate its performance characteristics on CPU, GPU, and Intel Xeon Phi architectures. Speed, power, and hardware cost efficiencies are compared. Additionally, performance bottlenecks are identified for each architecture in order to determine the prospects for continued scalability of the algorithm on next generation HPC architectures. Keywords: Method of Characteristics; Neutron transport; Reactor simulation; High performance computing
MIT Department
Massachusetts Institute of Technology. Department of Nuclear Science and Engineering
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/J.CPC.2016.01.007
