Solution of a million by million complex matrix equation by Gaussian elimination with partial pivotting using parallel out-of-core solvers
- 1 April 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 575-578
Abstract
The future of computational electromagnetics is changing drastically with the new generation of computer chips, which are multi-core instead of single core. Previously, advancements in chip technology meant an increase in clock speed, which was typically a benefit that computational code users could enjoy. This is no longer the case. In the new roadmaps for chip manufacturers, speed has been sacrificed for improved power consumption. The general trend in processor development has been from dual-, quad-, and eight-core chips to ones with tens or even hundreds of cores. This change represents something of a cataclysmic shift for software. As a result, parallel programming has suddenly become relevant for all computer systems. The burden now falls on the software programmer to revamp existing codes and add new functionality to enable computational codes to run efficiently on this new generation of multi-core processors.Keywords
This publication has 2 references indexed in Scilit:
- Performance comparison between two commercial EM softwares using higher order and piecewise RWG basis functionsMicrowave and Optical Technology Letters, 2009
- A survey of various computer architectures for solution of large matrix equationsInternational Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 1995