Performance analysis of massively-parallel computational
fluid dynamics
Performance analysis of massively-parallel computational
fluid dynamics
As modern supercomputers edge towards exascale, their architectures are becoming more parallel. In order for computational fluid dynamics (CFD) simulations to operate efficiently on newer machines, a complete harmony between hardware, software and numerical algorithms is required. In the work presented here, a typical CFD code is instrumented, and a strong-scalability study performed to identify areas of the execution which require improvement, using the well-known KVLCC2 test case. The effects of changing discretization schemes, mesh structure, turbulence models and linear solvers are all tested. The results show that data exchange among cores and the inner-loop pre-conditioners both have a large impact on performance in a massively-parallel environment, and should be the focus of future developments.
Hawkes, J.
ce02055e-0912-4d84-b9f1-03cced861bbd
Turnock, S.R.
d6442f5c-d9af-4fdb-8406-7c79a92b26ce
Cox, S.J.
0e62aaed-24ad-4a74-b996-f606e40e5c55
Phillips, A.B.
f565b1da-6881-4e2a-8729-c082b869028f
Vaz, G.
7fe43ac2-1513-440b-8332-aa64d61fce9d
19 October 2014
Hawkes, J.
ce02055e-0912-4d84-b9f1-03cced861bbd
Turnock, S.R.
d6442f5c-d9af-4fdb-8406-7c79a92b26ce
Cox, S.J.
0e62aaed-24ad-4a74-b996-f606e40e5c55
Phillips, A.B.
f565b1da-6881-4e2a-8729-c082b869028f
Vaz, G.
7fe43ac2-1513-440b-8332-aa64d61fce9d
Hawkes, J., Turnock, S.R., Cox, S.J., Phillips, A.B. and Vaz, G.
(2014)
Performance analysis of massively-parallel computational
fluid dynamics.
11th International Conference on Hydrodynamics (ICHD 2014), Singapore, Singapore.
19 - 24 Oct 2014.
8 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
As modern supercomputers edge towards exascale, their architectures are becoming more parallel. In order for computational fluid dynamics (CFD) simulations to operate efficiently on newer machines, a complete harmony between hardware, software and numerical algorithms is required. In the work presented here, a typical CFD code is instrumented, and a strong-scalability study performed to identify areas of the execution which require improvement, using the well-known KVLCC2 test case. The effects of changing discretization schemes, mesh structure, turbulence models and linear solvers are all tested. The results show that data exchange among cores and the inner-loop pre-conditioners both have a large impact on performance in a massively-parallel environment, and should be the focus of future developments.
Text
ICHD.pdf
- Author's Original
Text
__userfiles.soton.ac.uk_Users_slb1_mydocuments_ichd_158.pdf
- Other
More information
Published date: 19 October 2014
Venue - Dates:
11th International Conference on Hydrodynamics (ICHD 2014), Singapore, Singapore, 2014-10-19 - 2014-10-24
Organisations:
National Oceanography Centre, Fluid Structure Interactions Group
Identifiers
Local EPrints ID: 369873
URI: http://eprints.soton.ac.uk/id/eprint/369873
PURE UUID: b5671973-2164-4d48-9a1f-c4a94497d4c9
Catalogue record
Date deposited: 17 Oct 2014 13:36
Last modified: 15 Mar 2024 03:21
Export record
Contributors
Author:
J. Hawkes
Author:
A.B. Phillips
Author:
G. Vaz
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics