Computational Technology Resources - CCP

Paper II.2

Tuning the Domain Decomposition Solution Algorithm for Superscalar Architectures

G.P. Nikishkov*, H. Kanda* and A. Makinouchi+

*Information Systems and Technology Centre, University of Aizu, Aizu-Wakamatsu, Japan
+Materials Fabrication Laboratory, Institute of Physical and Chemical Research, Wako, Japan

doi:10.4203/ccp.53.2.2

purchase the full-text of this paper

G.P. Nikishkov, H. Kanda, A. Makinouchi, "Tuning the Domain Decomposition Solution Algorithm for Superscalar Architectures", in B.H.V. Topping, (Editor), "Advances in Engineering Computational Technology", Civil-Comp Press, Edinburgh, UK, pp 19-26, 1998. doi:10.4203/ccp.53.2.2

Abstract

The domain decomposition method (DDM) is an efficient algorithmic tool for the parallelization of finite element computer codes. This paper describes a simple technique that considerably improves execution rate of computationally-intensive routines of the DDM. The technique uses block matrix operations and loop unrolling to reduce load instructions from cache memory and to increase instruction-level parallelism. For superscalar RISC processors, experimental results show that it is possible to improve performance of the DDM solution procedure by several times.

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 £75 +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: 53 ADVANCES IN ENGINEERING COMPUTATIONAL TECHNOLOGY Edited by: B.H.V. Topping Paper II.2 Tuning the Domain Decomposition Solution Algorithm for Superscalar Architectures G.P. Nikishkov, H. Kanda and A. Makinouchi+ *Information Systems and Technology Centre, University of Aizu, Aizu-Wakamatsu, Japan +Materials Fabrication Laboratory, Institute of Physical and Chemical Research, Wako, Japan doi:10.4203/ccp.53.2.2 purchase the full-text of this paper Full Bibliographic Reference for this paper G.P. Nikishkov, H. Kanda, A. Makinouchi, "Tuning the Domain Decomposition Solution Algorithm for Superscalar Architectures", in B.H.V. Topping, (Editor), "Advances in Engineering Computational Technology", Civil-Comp Press, Edinburgh, UK, pp 19-26, 1998. doi:10.4203/ccp.53.2.2 Abstract The domain decomposition method (DDM) is an efficient algorithmic tool for the parallelization of finite element computer codes. This paper describes a simple technique that considerably improves execution rate of computationally-intensive routines of the DDM. The technique uses block matrix operations and loop unrolling to reduce load instructions from cache memory and to increase instruction-level parallelism. For superscalar RISC processors, experimental results show that it is possible to improve performance of the DDM solution procedure by several times. 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 £75 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions