NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS

Stochastic simulation is of key importance for scientific computing. Parallel stochastic simulations are becoming popular since the Monte Carlo method is easily parallelized. However, the main interests we observe in related publications deal with the following issues: simulation performance, a...

Full description

Saved in:
Bibliographic Details
Main Author: Van Toan Dao, Hong Quang Nguyen, Lydia Maigne, Vincent Breton, David R.C. Hill
Format: Article
Language:English
Published: 2016
Subjects:
Online Access:http://repository.vnu.edu.vn/handle/VNU_123/9836
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Vietnam National University, Hanoi
Language: English
id oai:112.137.131.14:VNU_123-9836
record_format dspace
spelling oai:112.137.131.14:VNU_123-98362016-05-16T20:01:49Z NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS Van Toan Dao, Hong Quang Nguyen, Lydia Maigne, Vincent Breton, David R.C. Hill Stochastic simulation, pseudo random number generators, reproducibility, portability, performance and Intel Xeon Phi Stochastic simulation is of key importance for scientific computing. Parallel stochastic simulations are becoming popular since the Monte Carlo method is easily parallelized. However, the main interests we observe in related publications deal with the following issues: simulation performance, applicability of the simulation, model design, etc. Even if these interests are justified, accuracy and reproducibility, especially for numerical simulation experiments, must remain a major concern in the process of increasing and diffusing scientific knowledge. We recently realized that this essential question of reproducibility is sometimes overlooked. In this paper we study the essence of reproducibility for stochastic simulations by focusing on some of the best random number generators because they are at the heart of stochastic simulations. We have identified some reproducibility problems linked to different compilers, operating systems and also with a virtual machine. In this paper, we check the portability and performances of modern pseudo-random number generators that are tested on hybrid computing nodes with the latest Xeon Phi processors. 2016-05-16T08:04:26Z 2016-05-16T08:04:26Z 2014 Article http://repository.vnu.edu.vn/handle/VNU_123/9836 en application/pdf
institution Vietnam National University, Hanoi
building VNU Library & Information Center
country Vietnam
collection VNU Digital Repository
language English
topic Stochastic simulation, pseudo random number generators, reproducibility, portability, performance and Intel Xeon Phi
spellingShingle Stochastic simulation, pseudo random number generators, reproducibility, portability, performance and Intel Xeon Phi
Van Toan Dao, Hong Quang Nguyen, Lydia Maigne, Vincent Breton, David R.C. Hill
NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS
description Stochastic simulation is of key importance for scientific computing. Parallel stochastic simulations are becoming popular since the Monte Carlo method is easily parallelized. However, the main interests we observe in related publications deal with the following issues: simulation performance, applicability of the simulation, model design, etc. Even if these interests are justified, accuracy and reproducibility, especially for numerical simulation experiments, must remain a major concern in the process of increasing and diffusing scientific knowledge. We recently realized that this essential question of reproducibility is sometimes overlooked. In this paper we study the essence of reproducibility for stochastic simulations by focusing on some of the best random number generators because they are at the heart of stochastic simulations. We have identified some reproducibility problems linked to different compilers, operating systems and also with a virtual machine. In this paper, we check the portability and performances of modern pseudo-random number generators that are tested on hybrid computing nodes with the latest Xeon Phi processors.
format Article
author Van Toan Dao, Hong Quang Nguyen, Lydia Maigne, Vincent Breton, David R.C. Hill
author_facet Van Toan Dao, Hong Quang Nguyen, Lydia Maigne, Vincent Breton, David R.C. Hill
author_sort Van Toan Dao, Hong Quang Nguyen, Lydia Maigne, Vincent Breton, David R.C. Hill
title NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS
title_short NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS
title_full NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS
title_fullStr NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS
title_full_unstemmed NUMERICAL REPRODUCIBILITY, PORTABILITY AND PERFORMANCE OF MODERN PSEUDO RANDOM NUMBER GENERATORS
title_sort numerical reproducibility, portability and performance of modern pseudo random number generators
publishDate 2016
url http://repository.vnu.edu.vn/handle/VNU_123/9836
_version_ 1680966409088139264