Developing a scalable and flexible high-resolution DNS code for two-phase flows

Iain Bethune; Antonia Collis; Lennon O. Naraigh; David Scott; Prashant Valluri

doi:10.3233/978-1-61499-621-7-459

Developing a scalable and flexible high-resolution DNS code for two-phase flows

Iain Bethune, Antonia Collis, Lennon O. Naraigh, David Scott, Prashant Valluri

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

We introduce TPLS (Two-Phase Level Set), an MPI-parallel Direct Numerical Simulation code for two-phase flows in channel geometries. Recent developments to the code are discussed which improve the performance of the solvers and I/O by using the PETSc and NetCDF libraries respectively. Usability and functionality improvements enabled by code refactoring and merging of a separate OpenMP-parallelized version are also outlined. The overall scaling behaviour of the code is measured, and good strong scaling up to 1152 cores is observed for a 5.6 million element grid. A comparison is made between the legacy serial text-formatted I/O and new NetCDF implementations, showing speedups of up to 17x. Finally, we explore the effects of output file striping on the Lustre parallel file system on ARCHER, a Cray XC30 supercomputer, finding performance gains of up to 12% over the default striping settings.

Original language	English
Title of host publication	Parallel Computing: On the Road to Exascale
Editors	Gerhard Joubert, Hugh Leather, Mark Parsons, Frans Peters, Mark Sawyer
Publisher	IOS Press
Pages	459
Number of pages	468
Volume	27
ISBN (Electronic)	978-1-61499-621-7
ISBN (Print)	978-1-61499-620-0
DOIs	https://doi.org/10.3233/978-1-61499-621-7-459
Publication status	Published - 2016
Event	International Conference on Parallel Computing (ParCo) 2015 - Edinburgh, United Kingdom Duration: 1 Sept 2015 → 4 Sept 2015

Publication series

Name	Advances In Parallel Computing
ISSN (Print)	0927-5452
ISSN (Electronic)	1879-808X

Conference

Conference	International Conference on Parallel Computing (ParCo) 2015
Country/Territory	United Kingdom
City	Edinburgh
Period	1/09/15 → 4/09/15

Access to Document

10.3233/978-1-61499-621-7-459Licence: Unspecified

http://www2.epcc.ed.ac.uk/~ibethune/files/tpls.pdfLicence: Unspecified

EPSRC-ARCHER eCSE: TPLS: Optimised Parallel I/O and Visualisation
Valluri, P., Bethune, I., Collis, T. & Naraigh, L. O.
1/04/14 → 31/12/14
Project: Awarded Facility Time

Cite this

Bethune, I., Collis, A., Naraigh, L. O., Scott, D., & Valluri, P. (2016). Developing a scalable and flexible high-resolution DNS code for two-phase flows. In G. Joubert, H. Leather, M. Parsons, F. Peters, & M. Sawyer (Eds.), Parallel Computing: On the Road to Exascale (Vol. 27, pp. 459). (Advances In Parallel Computing). IOS Press. https://doi.org/10.3233/978-1-61499-621-7-459

@inproceedings{600e0a7f1da14533a391383534776d56,

title = "Developing a scalable and flexible high-resolution DNS code for two-phase flows",

abstract = "We introduce TPLS (Two-Phase Level Set), an MPI-parallel Direct Numerical Simulation code for two-phase flows in channel geometries. Recent developments to the code are discussed which improve the performance of the solvers and I/O by using the PETSc and NetCDF libraries respectively. Usability and functionality improvements enabled by code refactoring and merging of a separate OpenMP-parallelized version are also outlined. The overall scaling behaviour of the code is measured, and good strong scaling up to 1152 cores is observed for a 5.6 million element grid. A comparison is made between the legacy serial text-formatted I/O and new NetCDF implementations, showing speedups of up to 17x. Finally, we explore the effects of output file striping on the Lustre parallel file system on ARCHER, a Cray XC30 supercomputer, finding performance gains of up to 12% over the default striping settings.",

author = "Iain Bethune and Antonia Collis and Naraigh, {Lennon O.} and David Scott and Prashant Valluri",

note = "Acceptance date unknown (likewise exact publication date unknown). Used acceptance date of 31st March 2016 to remove from our monthly reports for action. If this should be used for REF2021contact Open Access team.; International Conference on Parallel Computing (ParCo) 2015 ; Conference date: 01-09-2015 Through 04-09-2015",

year = "2016",

doi = "10.3233/978-1-61499-621-7-459",

language = "English",

isbn = "978-1-61499-620-0",

volume = "27",

series = "Advances In Parallel Computing",

publisher = "IOS Press",

pages = "459",

editor = "Gerhard Joubert and Hugh Leather and Mark Parsons and Frans Peters and Mark Sawyer",

booktitle = "Parallel Computing: On the Road to Exascale",

}

Bethune, I, Collis, A, Naraigh, LO, Scott, D & Valluri, P 2016, Developing a scalable and flexible high-resolution DNS code for two-phase flows. in G Joubert, H Leather, M Parsons, F Peters & M Sawyer (eds), Parallel Computing: On the Road to Exascale. vol. 27, Advances In Parallel Computing, IOS Press, pp. 459, International Conference on Parallel Computing (ParCo) 2015, Edinburgh, United Kingdom, 1/09/15. https://doi.org/10.3233/978-1-61499-621-7-459

Developing a scalable and flexible high-resolution DNS code for two-phase flows. / Bethune, Iain; Collis, Antonia; Naraigh, Lennon O. et al.
Parallel Computing: On the Road to Exascale. ed. / Gerhard Joubert; Hugh Leather; Mark Parsons; Frans Peters; Mark Sawyer. Vol. 27 IOS Press, 2016. p. 459 (Advances In Parallel Computing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Developing a scalable and flexible high-resolution DNS code for two-phase flows

AU - Bethune, Iain

AU - Collis, Antonia

AU - Naraigh, Lennon O.

AU - Scott, David

AU - Valluri, Prashant

N1 - Acceptance date unknown (likewise exact publication date unknown). Used acceptance date of 31st March 2016 to remove from our monthly reports for action. If this should be used for REF2021contact Open Access team.

PY - 2016

Y1 - 2016

N2 - We introduce TPLS (Two-Phase Level Set), an MPI-parallel Direct Numerical Simulation code for two-phase flows in channel geometries. Recent developments to the code are discussed which improve the performance of the solvers and I/O by using the PETSc and NetCDF libraries respectively. Usability and functionality improvements enabled by code refactoring and merging of a separate OpenMP-parallelized version are also outlined. The overall scaling behaviour of the code is measured, and good strong scaling up to 1152 cores is observed for a 5.6 million element grid. A comparison is made between the legacy serial text-formatted I/O and new NetCDF implementations, showing speedups of up to 17x. Finally, we explore the effects of output file striping on the Lustre parallel file system on ARCHER, a Cray XC30 supercomputer, finding performance gains of up to 12% over the default striping settings.

AB - We introduce TPLS (Two-Phase Level Set), an MPI-parallel Direct Numerical Simulation code for two-phase flows in channel geometries. Recent developments to the code are discussed which improve the performance of the solvers and I/O by using the PETSc and NetCDF libraries respectively. Usability and functionality improvements enabled by code refactoring and merging of a separate OpenMP-parallelized version are also outlined. The overall scaling behaviour of the code is measured, and good strong scaling up to 1152 cores is observed for a 5.6 million element grid. A comparison is made between the legacy serial text-formatted I/O and new NetCDF implementations, showing speedups of up to 17x. Finally, we explore the effects of output file striping on the Lustre parallel file system on ARCHER, a Cray XC30 supercomputer, finding performance gains of up to 12% over the default striping settings.

U2 - 10.3233/978-1-61499-621-7-459

DO - 10.3233/978-1-61499-621-7-459

M3 - Conference contribution

SN - 978-1-61499-620-0

VL - 27

T3 - Advances In Parallel Computing

SP - 459

BT - Parallel Computing: On the Road to Exascale

A2 - Joubert, Gerhard

A2 - Leather, Hugh

A2 - Parsons, Mark

A2 - Peters, Frans

A2 - Sawyer, Mark

PB - IOS Press

T2 - International Conference on Parallel Computing (ParCo) 2015

Y2 - 1 September 2015 through 4 September 2015

ER -

Developing a scalable and flexible high-resolution DNS code for two-phase flows

Abstract / Description of output

Publication series

Conference

Access to Document

Fingerprint

Projects

EPSRC-ARCHER eCSE: TPLS: Optimised Parallel I/O and Visualisation

Cite this