DocumentCode :
2958257
Title :
Load Balancing of Dynamical Nucleation Theory Monte Carlo Simulations through Resource Sharing Barriers
Author :
Arafat, Humayun ; Sadayappan, P. ; Dinan, James ; Krishnamoorthy, Sriram ; Windus, Theresa L.
Author_Institution :
Dept. Comp. Sci. & Eng., Ohio State Univ., Columbus, OH, USA
fYear :
2012
fDate :
21-25 May 2012
Firstpage :
285
Lastpage :
295
Abstract :
The dynamical nucleation theory Monte Carlo (DNTMC) application from the NW Chem computational chemistry suite utilizes a Markov chain Monte Carlo, two-level parallel structure, with periodic synchronization points that assemble the results of independent finer-grained calculations. Like many such applications, the existing code employs a static partitioning of processes into groups and assigns each group a piece of the finer-grained parallel calculation. A significant cause of performance degradation is load imbalance among groups since the time requirements of the inner-parallel calculation varies widely with the input problem and as a result of the Monte Carlo simulation. We present a novel approach to load balancing such calculations with minimal changes to the application. We introduce the concept of a resource sharing barrier (RSB) - a barrier that allows process groups waiting on other processes´ work to actively contribute to their completion. The RSB load balancing technique is applied to the production DNTMC application code, resulting in a small code change of 200 lines and a reduction in execution time of up to 37%.
Keywords :
Monte Carlo methods; chemistry computing; nucleation; parallel programming; resource allocation; synchronisation; DNTMC; Markov chain Monte Carlo; NWChem computational chemistry; RSB; dynamical nucleation theory Monte Carlo; fine grained parallel calculation; load balancing; load imbalance; parallel structure; periodic synchronization; resource sharing barrier; static process partitioning; Computational modeling; Context; Load modeling; Markov processes; Monte Carlo methods; Parallel processing; Resource management; Global Arrays; Load balancing; Monte Carlo Simulation; PGAS; Parallel processing; Resource management;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel & Distributed Processing Symposium (IPDPS), 2012 IEEE 26th International
Conference_Location :
Shanghai
ISSN :
1530-2075
Print_ISBN :
978-1-4673-0975-2
Type :
conf
DOI :
10.1109/IPDPS.2012.35
Filename :
6267843
Link To Document :
بازگشت