TY - JOUR
T1 - Implementation and evaluation of an AMR framework for FDM applications
AU - Matsumoto, Masaharu
AU - Mori, Futoshi
AU - Ohshima, Satoshi
AU - Jitsumoto, Hideyuki
AU - Katagiri, Takahiro
AU - Nakajima, Kengo
N1 - Funding Information:
This work is funded by JST (Japan Science and Technology Agency)/CREST (Core Research for Evolutional Science and Technology). The computation in the present study was performed with the Oakleaf-FX supercomputer systemof Information Technology Center at the University of Tokyo.
PY - 2014
Y1 - 2014
N2 - In order to execute various finite-difference method applications on large-scale parallel computers with a reasonable cost of computer resources, a framework using an adaptive mesh refinement (AMR) technique has been developed. AMR can realize high-resolution simulations while saving computer resources by generating and removing hierarchical grids dynamically. In the AMR framework, a dynamic domain decomposition (DDD) technique, as a dynamic load balancing method, is also implemented to correct the computational load imbalance between each process associated with parallelization. By performing a 3D AMR test simulation, it is confirmed that dynamic load balancing can be achieved and execution time can be reduced by introducing the DDD technique.
AB - In order to execute various finite-difference method applications on large-scale parallel computers with a reasonable cost of computer resources, a framework using an adaptive mesh refinement (AMR) technique has been developed. AMR can realize high-resolution simulations while saving computer resources by generating and removing hierarchical grids dynamically. In the AMR framework, a dynamic domain decomposition (DDD) technique, as a dynamic load balancing method, is also implemented to correct the computational load imbalance between each process associated with parallelization. By performing a 3D AMR test simulation, it is confirmed that dynamic load balancing can be achieved and execution time can be reduced by introducing the DDD technique.
UR - http://www.scopus.com/inward/record.url?scp=84902820908&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902820908&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2014.05.084
DO - 10.1016/j.procs.2014.05.084
M3 - Conference article
AN - SCOPUS:84902820908
SN - 1877-0509
VL - 29
SP - 936
EP - 946
JO - Procedia Computer Science
JF - Procedia Computer Science
T2 - 14th Annual International Conference on Computational Science, ICCS 2014
Y2 - 10 June 2014 through 12 June 2014
ER -