@InProceedings{Supelec505,
author = {Wilfried Kirschenmann and Laurent Plagne and S. Ploix and A. Ponçot and Stephane Vialle},
title = {{Massively Parallel Solving of 3D Simplified PN Equations on Graphics Processing Units}},
year = {2009},
booktitle = {{International Conference on Advances in Mathematics, Computational Methods, and Reactor Physics (M\&C 2009)}},
pages = {12 pages},
month = {May 3-7},
address = {Saratoga Springs, New York. USA},
url = {http://www.metz.supelec.fr/metz/recherche/publis_pdf/Supelec505.pdf},
isbn = {978-0-89448-069-0},
abstract = {This paper presents a successful parallel implementation on
Graphics Processing Units (GPUs) for
the Simplified PN (SPN) calculations in the 3D case. For a
nuclear operator such as EDF, the time
required to compute nuclear reactor core simulations is rather
critical. The SPN method provides
a convenient trade-off between accuracy and numerical complexity
and is used in several industrial
simulations. The reduction of the computation time required to
solve the eigenvalue problem goes
through the parallelization of the algorithm. To solve the
problem on distributed memory machines
such as PC clusters, Domain Decomposition Methods have been
investigated. Complementary to
this approach, present work aims at using emerging massively
parallel processors such as the GPUs.
Based on a fine grained parallelism, this solution offers the
opportunity to achieve good performances
for a very low cost. Indeed, GPUs provide a huge computational
power and some specific
optimizations allow to near the hardware limits. Our
implementation solves 3D SPN problems on
GPUs 30 times faster than their sequential CPU couterpart.}
}