Paper
28 November 2007 Research of the grid computing system applied in optical simulation
Wei-wei Jin, Yu-dong Wang, Qiangsheng Liu, Zhao-feng Cen, Xiao-tong Li, Yi-qun Lin
Author Affiliations +
Abstract
A grid computing in the field of optics is presented in this paper. Firstly, the basic principles and research background of grid computing are outlined in this paper, along with the overview of its applications and the development status quo. The paper also discusses several typical tasks scheduling algorithms. Secondly, it focuses on describing a task scheduling of grid computing applied in optical computation. The paper gives details about the task scheduling system, including the task partition, granularity selection and tasks allocation, especially the structure of the system. In addition, some details of communication on grid computing are also illustrated. In this system, the "makespan" and "load balancing" are comprehensively considered. Finally, we build a grid model to test the task scheduling strategy, and the results are analyzed in detail. Compared to one isolated computer, a grid comprised of one server and four processors can shorten the "makespan" to 1/4. At the same time, the experimental results of the simulation also illustrate that the proposed scheduling system is able to balance loads of all processors. In short, the system performs scheduling well in the grid environment.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei-wei Jin, Yu-dong Wang, Qiangsheng Liu, Zhao-feng Cen, Xiao-tong Li, and Yi-qun Lin "Research of the grid computing system applied in optical simulation", Proc. SPIE 6834, Optical Design and Testing III, 68342S (28 November 2007); https://doi.org/10.1117/12.756433
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Computing systems

Telecommunications

Optical simulations

Data communications

Computer simulations

Error analysis

Process modeling

RELATED CONTENT


Back to Top