Pipeline schwarzwaveform relaxation
Document Type
Conference Proceeding
Publication Date
2016
Department
Department of Mathematical Sciences
Abstract
To leverage the computational capability of modern supercomputers, existing algorithms need to be reformulated in a manner that allows for many concurrent operations. In this paper, we outline a framework that reformulates classical Schwarz waveform relaxation so that successive waveform iterates can be computed in a parallel pipeline fashion after an initial start-up cost. The communication costs for various implementations are discussed, and numerical scaling results are presented.
Publication Title
Lecture Notes in Computational Science and Engineering
ISBN
978-3-319-18827-0
Recommended Citation
Ong, B.,
High, S.,
&
Kwok, F.
(2016).
Pipeline schwarzwaveform relaxation.
Lecture Notes in Computational Science and Engineering,
104, 363-370.
http://doi.org/10.1007/978-3-319-18827-0_36
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/4081