Speed-up and efficiency of parallelized Monte Carlo integration on homogeneous and heterogeneous clusters

Authors

Ryan Carlos M. Tabernilla National Institute of Physics, University of the Philippines Diliman
John Kevin R. Sanchez National Institute of Physics, University of the Philippines Diliman
Joshua Gregor A. Dizon National Institute of Physics, University of the Philippines Diliman
Francis N. C. Paraan National Institute of Physics, University of the Philippines Diliman

Abstract

We evaluate the performance of parallelized Monte Carlo integration algorithms on homogeneous and heterogeneous clusters of the Structure and Dynamics Laboratory. In this study, intrinsic pseudorandom number generators for Fortran and Python were used and parallelization achieved by MPI libraries. On an example using 10⁹ samples, the parallelized Python code proved to be scalable on a cluster of up to 44 processors. The Fortran parallelized code performed less well on scalability but had a much shorter execution time. It was also observed that the overhead cost of parallelization saturates as the number of processors used increased.

Downloads

Issue

2014: Proceedings of the 32nd Samahang Pisika ng Pilipinas Physics Congress

Article ID

SPP2014-2C-06

Section

Complex Systems

Published

2014-10-17

How to Cite

[1]

RCM Tabernilla, JKR Sanchez, JGA Dizon, and FNC Paraan, Speed-up and efficiency of parallelized Monte Carlo integration on homogeneous and heterogeneous clusters, Proceedings of the Samahang Pisika ng Pilipinas 32, SPP2014-2C-06 (2014). URL: https://proceedings.spp-online.org/article/view/1783.