Overhead Analysis of Loop Parallelization with OpenMP Directives-Reference-Cited by-同舟云学术

Overhead Analysis of Loop Parallelization with OpenMP Directives

Published:2014-09 Issue: Volume:644-650 Page:3394-3397
ISSN:1662-7482
Container-title:Applied Mechanics and Materials
language:
Short-container-title:AMM

Author:

Xiang Li Yun¹,Fang Zhi Yi¹,Wang Ying¹,Qu Guan Nan¹,Chen Zhong²

Affiliation:

1. Jilin University

2. High Performance Computing Center of Jilin Province, Changchun

Abstract

OpenMP is one of the most popular parallel programming technique nowadays. Using openMP, programmers parallelized their serial programs by inserting directives. However, in addition to parallel algorithm related overhead which depends on how to design the parallel program, performing openMP also leads to overhead. In this paper, we give a model to evaluate the overhead, and design 5 groups of experiment to evaluate the overhead caused by starting openMP, scheduling and synchronizations. We also analyze the changes of the overhead with different scale of the problems and the number of parallel threads.

Publisher

Trans Tech Publications, Ltd.

Link

https://www.scientific.net/AMM.644-650.3394.pdf

Reference6 articles.

1. The OpenMP Architecture Review Board, http: /www. openmp. org/drupal.

2. OpenMP Version 4. 0 Specification, http: /openmp. org/wp/openmp-specifications/, (2013).

3. Bull, J. Mark. Measuring synchronisation and scheduling overheads in OpenMP., Proceedings of First European Workshop on OpenMP. Vol. 8. (1999).

4. LAI Jianxin, et. al., Analysis of Task Schedule Overhead and Load Balance in openMP, Computer Engineering, Vol. 32, No. 18, p.58 – 60, (2006).

5. Zhu, Weirong, Juan Del Cuvillo, and Guang R. Gao. Performance Characteristics of OpenMP Language Constructs on a Many-core-on-a-chip Architecture., OpenMP Shared Memory Parallel Programming. Springer Berlin Heidelberg, 2008. 230-241.