Computational Technology Resources - CCP

Keywords: glass furnace, parallel, combustion, SIMPLER algorithm, OpenMP.

Summary

In this paper, we consider the parallelization of a sequential legacy code that was developed and used in Sisecam for the design and operation of glass furnaces. The mathematical model for glass furnaces employs revised version of Patankar and Spalding's semi-implicit method for pressure-linked equations method called SIMPLER. Our main objective is to parallelize the sequential modelling programs using OpenMP for shared-memory multi-core architectures. The sequential program uses the tri-diagonal matrix algorithm and Stone's strongly implicit procedure for solving the resulting linear systems of equations. The sequential code is analyzed by profiling in order to locate loops that have long running times. Radiation calculations and linear system solvers which are the most computational intensive parts of the program are parallelized. The performance of the parallelized code is compared to that of the sequential code. Results obtained on an Intel 12-core Xeon system show that speed-ups in the range 5 to 7.4 are possible for various configurations of the code.

purchase the full-text of this paper (price £20)

go to the next paper
return to the table of contents
return to the book description
purchase this book (price £45 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 107 PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, GRID AND CLOUD COMPUTING FOR ENGINEERING Edited by: Paper 1 Parallelization of a Glass Furnace Mathematical Model for Multi-core Systems E. Domazet¹, C. Ozturan¹, L. Önsel² and Z. Eltutar² ¹Computer Engineering Department, Bogazici University, Istanbul, Turkey ²Sisecam, Science and Technology Center, Istanbul, Turkey doi:10.4203/ccp.107.1 purchase the full-text of this paper Full Bibliographic Reference for this paper , "Parallelization of a Glass Furnace Mathematical Model for Multi-core Systems", in , (Editors), "Proceedings of the Fourth International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 1, 2015. doi:10.4203/ccp.107.1 Keywords: glass furnace, parallel, combustion, SIMPLER algorithm, OpenMP. Summary In this paper, we consider the parallelization of a sequential legacy code that was developed and used in Sisecam for the design and operation of glass furnaces. The mathematical model for glass furnaces employs revised version of Patankar and Spalding's semi-implicit method for pressure-linked equations method called SIMPLER. Our main objective is to parallelize the sequential modelling programs using OpenMP for shared-memory multi-core architectures. The sequential program uses the tri-diagonal matrix algorithm and Stone's strongly implicit procedure for solving the resulting linear systems of equations. The sequential code is analyzed by profiling in order to locate loops that have long running times. Radiation calculations and linear system solvers which are the most computational intensive parts of the program are parallelized. The performance of the parallelized code is compared to that of the sequential code. Results obtained on an Intel 12-core Xeon system show that speed-ups in the range 5 to 7.4 are possible for various configurations of the code. purchase the full-text of this paper (price £20) go to the next paper return to the table of contents return to the book description purchase this book (price £45 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions