Improving scalability of parallel unstructured mesh-based adaptive workflows

Thumbnail Image
Files
178283_Smith_rpi_0185E_11080.pdf (53.96 MB)
Authors
Smith, Cameron Walter
Issue Date
2017-05
Type
Electronic thesis
Thesis
Language
ENG
Keywords
Computer science
Research Projects
Organizational Units
Journal Issue
Alternative Title
Abstract
Partition improvement methods defined in this work enable improved application strong scaling on over one million processors through careful control of the balancing requirements. Applied to a computational fluid dynamics simulation running on 524,288 processes with 1.2 billion elements these methods reduce the time of the dominant computational step by up to 28% versus the best existing methods.
Description
May 2017
School of Science
Full Citation
Publisher
Rensselaer Polytechnic Institute, Troy, NY
Terms of Use
Journal
Volume
Issue
URI
https://hdl.handle.net/20.500.13015/1977
PubMed ID
DOI
ISSN
EISSN
Collections
RPI Theses Online (Complete)