TY - GEN
T1 - Performance issues for parallel implementations of Bootstrap Simulation algorithm
AU - Czekster, Ricardo M.
AU - Fernandes, Paulo
AU - Sales, Afonso
AU - Webber, Thais
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - The solution of state-based stochastic models is usually a demanding application, then it is a natural subject to high performance techniques. We are particularly interested in the speedup of Bootstrap Simulation of structured Markovian models. This approach is a quite recent development in the performance evaluation area, and it brings a considerable improvement in the results accuracy, despite the intrinsic effect of randomness in simulation experiments. Unfortunately, Bootstrap Simulation has higher computational cost than other alternatives. We present experiments with different options to optimize the parallel solution of Bootstrap Simulation applied to three practical examples described in Stochastic Automata Networks (SAN) formalism. This paper contribution resides in the discussion of theoretical implementation issues, the obtained speedup and the actual processing and communication times for all experiments. Additionally, we also suggest future works to improve even more the proposed solution and we discuss some interesting insights for parallelization of similar applications.
AB - The solution of state-based stochastic models is usually a demanding application, then it is a natural subject to high performance techniques. We are particularly interested in the speedup of Bootstrap Simulation of structured Markovian models. This approach is a quite recent development in the performance evaluation area, and it brings a considerable improvement in the results accuracy, despite the intrinsic effect of randomness in simulation experiments. Unfortunately, Bootstrap Simulation has higher computational cost than other alternatives. We present experiments with different options to optimize the parallel solution of Bootstrap Simulation applied to three practical examples described in Stochastic Automata Networks (SAN) formalism. This paper contribution resides in the discussion of theoretical implementation issues, the obtained speedup and the actual processing and communication times for all experiments. Additionally, we also suggest future works to improve even more the proposed solution and we discuss some interesting insights for parallelization of similar applications.
KW - Discrete-event simulation
KW - Parallel applications
KW - Performance evaluation
KW - Stochastic modeling
UR - http://www.scopus.com/inward/record.url?scp=78650737993&partnerID=8YFLogxK
U2 - 10.1109/SBAC-PAD.2010.28
DO - 10.1109/SBAC-PAD.2010.28
M3 - Conference contribution
AN - SCOPUS:78650737993
SN - 9780769542164
T3 - Proceedings - 22nd International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2010
SP - 167
EP - 174
BT - Proceedings - 22nd International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2010
T2 - 22nd International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2010
Y2 - 27 October 2010 through 30 October 2010
ER -