1.
G. Vaz J. Hawkes, A. B. Phillips
On the strong scalability of maritime CFD Journal Article
In: Journal of Marine Science and Technology, no. DOI: 10.1007/s00773-017-0457-7, 2017.
@article{Hawkes2017,
title = {On the strong scalability of maritime CFD},
author = {J. Hawkes, G. Vaz, A. B. Phillips, S. J. Cox, S. R. Turnock},
url = {http://www.marin.nl/web/Publications/Publication-items/On-the-strong-scalability-of-maritime-CFD.htm},
year = {2017},
date = {2017-05-01},
booktitle = {Journal of Marine Science and Technology},
journal = {Journal of Marine Science and Technology},
number = {DOI: 10.1007/s00773-017-0457-7},
abstract = {Since 2004, supercomputer growth has been constrained by energy efficiency rather than raw hardware speeds. To maintain exponential growth of overall computing power, a massive growth in parallelization is under way. To keep up with these changes, computational fluid dynamics (CFD) must improve its strong scalability—its ability to handle lower cells-per-core ratios and achieve finer-grain parallelization. A maritime-focused, unstructured, finite-volume code (ReFRESCO) is used to investigate the scalability problems for incompressible, viscous CFD using two classical test-cases. Existing research suggests that the linear equation-system solver is the main bottleneck to incompressible codes, due to the stiff Poisson pressure equation. Here, these results are expanded by analysing the reasons for this poor scalability. In particular, a number of alternative linear solvers and preconditioners are tested to determine if the scalability problem can be circumvented, including GMRES, Pipelined-GMRES, Flexible-GMRES and BCGS. Conventional block-wise preconditioners are tested, along with multi-grid preconditioners and smoothers in various configurations. Memory-bandwidth constraints and global communication patterns are found to be the main bottleneck, and no stateof-the-art solution techniques which solve the strong-scalability problem satisfactorily could be found. There is significant incentive for more research and development in this area.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Since 2004, supercomputer growth has been constrained by energy efficiency rather than raw hardware speeds. To maintain exponential growth of overall computing power, a massive growth in parallelization is under way. To keep up with these changes, computational fluid dynamics (CFD) must improve its strong scalability—its ability to handle lower cells-per-core ratios and achieve finer-grain parallelization. A maritime-focused, unstructured, finite-volume code (ReFRESCO) is used to investigate the scalability problems for incompressible, viscous CFD using two classical test-cases. Existing research suggests that the linear equation-system solver is the main bottleneck to incompressible codes, due to the stiff Poisson pressure equation. Here, these results are expanded by analysing the reasons for this poor scalability. In particular, a number of alternative linear solvers and preconditioners are tested to determine if the scalability problem can be circumvented, including GMRES, Pipelined-GMRES, Flexible-GMRES and BCGS. Conventional block-wise preconditioners are tested, along with multi-grid preconditioners and smoothers in various configurations. Memory-bandwidth constraints and global communication patterns are found to be the main bottleneck, and no stateof-the-art solution techniques which solve the strong-scalability problem satisfactorily could be found. There is significant incentive for more research and development in this area.
2017
G. Vaz J. Hawkes, A. B. Phillips
On the strong scalability of maritime CFD Journal Article
In: Journal of Marine Science and Technology, no. DOI: 10.1007/s00773-017-0457-7, 2017.
Abstract | Links | BibTeX | Tags: High-performance computing, Linear solvers, Software profiling, Strong scalability
@article{Hawkes2017,
title = {On the strong scalability of maritime CFD},
author = {J. Hawkes, G. Vaz, A. B. Phillips, S. J. Cox, S. R. Turnock},
url = {http://www.marin.nl/web/Publications/Publication-items/On-the-strong-scalability-of-maritime-CFD.htm},
year = {2017},
date = {2017-05-01},
booktitle = {Journal of Marine Science and Technology},
journal = {Journal of Marine Science and Technology},
number = {DOI: 10.1007/s00773-017-0457-7},
abstract = {Since 2004, supercomputer growth has been constrained by energy efficiency rather than raw hardware speeds. To maintain exponential growth of overall computing power, a massive growth in parallelization is under way. To keep up with these changes, computational fluid dynamics (CFD) must improve its strong scalability—its ability to handle lower cells-per-core ratios and achieve finer-grain parallelization. A maritime-focused, unstructured, finite-volume code (ReFRESCO) is used to investigate the scalability problems for incompressible, viscous CFD using two classical test-cases. Existing research suggests that the linear equation-system solver is the main bottleneck to incompressible codes, due to the stiff Poisson pressure equation. Here, these results are expanded by analysing the reasons for this poor scalability. In particular, a number of alternative linear solvers and preconditioners are tested to determine if the scalability problem can be circumvented, including GMRES, Pipelined-GMRES, Flexible-GMRES and BCGS. Conventional block-wise preconditioners are tested, along with multi-grid preconditioners and smoothers in various configurations. Memory-bandwidth constraints and global communication patterns are found to be the main bottleneck, and no stateof-the-art solution techniques which solve the strong-scalability problem satisfactorily could be found. There is significant incentive for more research and development in this area.},
keywords = {High-performance computing, Linear solvers, Software profiling, Strong scalability},
pubstate = {published},
tppubtype = {article}
}
Since 2004, supercomputer growth has been constrained by energy efficiency rather than raw hardware speeds. To maintain exponential growth of overall computing power, a massive growth in parallelization is under way. To keep up with these changes, computational fluid dynamics (CFD) must improve its strong scalability—its ability to handle lower cells-per-core ratios and achieve finer-grain parallelization. A maritime-focused, unstructured, finite-volume code (ReFRESCO) is used to investigate the scalability problems for incompressible, viscous CFD using two classical test-cases. Existing research suggests that the linear equation-system solver is the main bottleneck to incompressible codes, due to the stiff Poisson pressure equation. Here, these results are expanded by analysing the reasons for this poor scalability. In particular, a number of alternative linear solvers and preconditioners are tested to determine if the scalability problem can be circumvented, including GMRES, Pipelined-GMRES, Flexible-GMRES and BCGS. Conventional block-wise preconditioners are tested, along with multi-grid preconditioners and smoothers in various configurations. Memory-bandwidth constraints and global communication patterns are found to be the main bottleneck, and no stateof-the-art solution techniques which solve the strong-scalability problem satisfactorily could be found. There is significant incentive for more research and development in this area.