Stochastic Simulation Efficiency of Parallel CFD Solver on Elastic Cloud Environment
Omran Malik Omer Awad1, Awad Hag Ali Ahmed2, Abdelmonem M. Ali Artoli3
1Omran Malik Omer Awad, Department of Commuter Science, Alneelain University – Faculty of Computer Science and Information Technology, Khartoum, Sudan.
2Prof. Awad Hag Ali Ahmed, Department of Computer Science, Alneelain University – Faculty of Computer Science and Information Technology.
3Prof. Abdelmonem Mohamed Ali Artoli, Computer Science Department, College of Computer & Information Sciences King Saud University, Riyadh, Kingdom of Saudi Arabia.
Manuscript received on February 26, 2014. | Revised Manuscript received on March 02, 2014. | Manuscript published on March 05, 2014. | PP: 123-128 | Volume-4 Issue-1, March 2014. | Retrieval Number: A2110034114/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Computational fluid dynamics applications become crucial for scientist to understand various Natural phenomenon. These applications require high performance computing resources that most small academic institutions cannot afford. Elastic cloud clusters are best suited environment for those small academic institutions to gain high performance computing power and enable researchers to explore new trends in scientific computing with reasonable cost. This work aims to study the parallelism efficiency; in term of communication time and execution time for a highly optimized parallel lattice Boltzmann solver on elastic cloud clusters. On these elastic clusters we have found that the lattice Boltzmann implementation is fully adaptive, highly flexible and cost effective to use for solving complex large fluid mechanical systems.
Keywords: Computational Fluid Dynamics, Elastic Cloud Computing, Multi-core Programming, Lattice Boltzmann.