Computational Technology Resources - CCP

A. Wakatani, "GPGPU Implementation of a Multi-Dimensional ADI Iterative Method based on the Thomas Method", in P. Iványi, B.H.V. Topping, (Editors), "Proceedings of the Fourth International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 42, 2015. doi:10.4203/ccp.107.42

Keywords: multithreading, parallel processing, partial differential equation, iterative method, optimization, CUDA.

Summary

The Alternating Direction Implicit (ADI) iterative method is used for solving D dimensional partial differential equations, and it can be parallelized easily because the D-1 dimensional calculations are independent of each other. However, since the rest of the dimensions are solved sequentially using Thomas method, the parallel efficiency may be degraded when the sizes of the dimensions are not balanced. On the other hand, recent GPUs (graphics processing units) are used not only for graphic processing applications but also for general purpose applications. In this paper, a scalable and parallel algorithm is implemented for the ADI iterative method by using the Compute Unified Device Architecture (CUDA) and its performance is evaluated by comparing a simple parallel algorithm.

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

go to the previous paper
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: P. Iványi and B.H.V. Topping Paper 42 GPGPU Implementation of a Multi-Dimensional ADI Iterative Method based on the Thomas Method A. Wakatani Faculty of Intelligence and Informatics, Konan University, Japan doi:10.4203/ccp.107.42 purchase the full-text of this paper Full Bibliographic Reference for this paper A. Wakatani, "GPGPU Implementation of a Multi-Dimensional ADI Iterative Method based on the Thomas Method", in P. Iványi, B.H.V. Topping, (Editors), "Proceedings of the Fourth International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 42, 2015. doi:10.4203/ccp.107.42 Keywords: multithreading, parallel processing, partial differential equation, iterative method, optimization, CUDA. Summary The Alternating Direction Implicit (ADI) iterative method is used for solving D dimensional partial differential equations, and it can be parallelized easily because the D-1 dimensional calculations are independent of each other. However, since the rest of the dimensions are solved sequentially using Thomas method, the parallel efficiency may be degraded when the sizes of the dimensions are not balanced. On the other hand, recent GPUs (graphics processing units) are used not only for graphic processing applications but also for general purpose applications. In this paper, a scalable and parallel algorithm is implemented for the ADI iterative method by using the Compute Unified Device Architecture (CUDA) and its performance is evaluated by comparing a simple parallel algorithm. purchase the full-text of this paper (price £20) go to the previous paper 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