Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations

Gihan R. Mudalige; Istvan Z. Reguly; Arun Prabhakar; Dario Amirante; Leigh Lapworth; Stephen A. Jarvis

doi:10.1109/CLUSTER51413.2022.00034

Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations

Gihan R. Mudalige, Istvan Z. Reguly, Arun Prabhakar, Dario Amirante, Leigh Lapworth, Stephen A. Jarvis

Engineering and Physical Sciences

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

Abstract

We present the large-scale, computational fluid dy-namics (CFD) simulation of a full gas-turbine engine compressor, demonstrating capability towards overcoming current limitations for virtual certification of aero-engine design. The simulation is carried out through a performance portable code-base on multi-core/many-core HPC clusters with a CFD-to-CFD coupled execution, combining an industrial CFD solver linked using custom coupler software. The application innovates in its design for performance portability through the OP2 domain specific library for the CFD components, allowing the automatic generation of highly optimized platform-specific parallelizations for both multi-core (CPU) and many-core (GPU) clusters from a single high-level source. The code is used for the simulation of a 4.58B node, full-annulus 10-row production-grade test compressor (DLR's Rig250), using a coupled sliding-plane setup on the ARCHER2 and Cirrus supercomputers at EPCC. The OP2 generated multiple parallelizations, together with optimized coupler configurations on heterogeneous/hybrid settings achieve, for the first time, execution of 1 revolution in less than 6 hours on 512 nodes of ARCHER2 (65k cores), with a parallel scaling efficiency of over 80 % compared to a 107 node run. Results indicate a speed up of the CFD suite by an order of a magnitude (˜30 x) relative to current production capability. Benchmarking and performance modelling project a time-to-solution of less than 5 hours on a cluster of 488xNVIDIA V100 GPUs, about 3x-4 x speedup over CPU clusters. The work demonstrates a step-change towards achieving virtual certification of aircraft engines with the requisite fidelity and tractable time-to-solution that was previously out of reach under production settings.

Original language	English
Title of host publication	2022 IEEE International Conference on Cluster Computing (CLUSTER)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	206-217
Number of pages	12
ISBN (Electronic)	9781665498562
ISBN (Print)	9781665498579
DOIs	https://doi.org/10.1109/CLUSTER51413.2022.00034
Publication status	Published - 18 Oct 2022
Event	2022 IEEE International Conference on Cluster Computing: CLUSTER 2022 - Heidelberg, Germany Duration: 6 Sept 2022 → 9 Sept 2022 https://clustercomp.org/2022/

Publication series

Name	IEEE International Conference on Cluster Computing
Publisher	IEEE
Volume	2022-September
ISSN (Print)	1552-5244
ISSN (Electronic)	2168-9253

Conference

Conference	2022 IEEE International Conference on Cluster Computing
Country/Territory	Germany
City	Heidelberg
Period	6/09/22 → 9/09/22
Internet address	https://clustercomp.org/2022/

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Code Coupling
DSL
Gas Turbine Engines
Virtual Certification

ASJC Scopus subject areas

Software
Hardware and Architecture
Signal Processing

Access to Document

10.1109/CLUSTER51413.2022.00034Licence: None: All rights reserved

Cite this

Mudalige, G. R., Reguly, I. Z., Prabhakar, A., Amirante, D., Lapworth, L., & Jarvis, S. A. (2022). Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations. In 2022 IEEE International Conference on Cluster Computing (CLUSTER) (pp. 206-217). (IEEE International Conference on Cluster Computing; Vol. 2022-September). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CLUSTER51413.2022.00034

@inproceedings{8a4d4eccd80e47f0a3abc70abbd1af0a,

title = "Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations",

abstract = "We present the large-scale, computational fluid dy-namics (CFD) simulation of a full gas-turbine engine compressor, demonstrating capability towards overcoming current limitations for virtual certification of aero-engine design. The simulation is carried out through a performance portable code-base on multi-core/many-core HPC clusters with a CFD-to-CFD coupled execution, combining an industrial CFD solver linked using custom coupler software. The application innovates in its design for performance portability through the OP2 domain specific library for the CFD components, allowing the automatic generation of highly optimized platform-specific parallelizations for both multi-core (CPU) and many-core (GPU) clusters from a single high-level source. The code is used for the simulation of a 4.58B node, full-annulus 10-row production-grade test compressor (DLR's Rig250), using a coupled sliding-plane setup on the ARCHER2 and Cirrus supercomputers at EPCC. The OP2 generated multiple parallelizations, together with optimized coupler configurations on heterogeneous/hybrid settings achieve, for the first time, execution of 1 revolution in less than 6 hours on 512 nodes of ARCHER2 (65k cores), with a parallel scaling efficiency of over 80 \% compared to a 107 node run. Results indicate a speed up of the CFD suite by an order of a magnitude (˜30 x) relative to current production capability. Benchmarking and performance modelling project a time-to-solution of less than 5 hours on a cluster of 488xNVIDIA V100 GPUs, about 3x-4 x speedup over CPU clusters. The work demonstrates a step-change towards achieving virtual certification of aircraft engines with the requisite fidelity and tractable time-to-solution that was previously out of reach under production settings.",

keywords = "Code Coupling, DSL, Gas Turbine Engines, Virtual Certification",

author = "Mudalige, \{Gihan R.\} and Reguly, \{Istvan Z.\} and Arun Prabhakar and Dario Amirante and Leigh Lapworth and Jarvis, \{Stephen A.\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Cluster Computing : CLUSTER 2022 ; Conference date: 06-09-2022 Through 09-09-2022",

year = "2022",

month = oct,

day = "18",

doi = "10.1109/CLUSTER51413.2022.00034",

language = "English",

isbn = "9781665498579",

series = "IEEE International Conference on Cluster Computing",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "206--217",

booktitle = "2022 IEEE International Conference on Cluster Computing (CLUSTER)",

url = "https://clustercomp.org/2022/",

}

Mudalige, GR, Reguly, IZ, Prabhakar, A, Amirante, D, Lapworth, L & Jarvis, SA 2022, Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations. in 2022 IEEE International Conference on Cluster Computing (CLUSTER). IEEE International Conference on Cluster Computing, vol. 2022-September, Institute of Electrical and Electronics Engineers (IEEE), pp. 206-217, 2022 IEEE International Conference on Cluster Computing, Heidelberg, Germany, 6/09/22. https://doi.org/10.1109/CLUSTER51413.2022.00034

Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations. / Mudalige, Gihan R.; Reguly, Istvan Z.; Prabhakar, Arun et al.
2022 IEEE International Conference on Cluster Computing (CLUSTER). Institute of Electrical and Electronics Engineers (IEEE), 2022. p. 206-217 (IEEE International Conference on Cluster Computing; Vol. 2022-September).

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

TY - GEN

T1 - Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations

AU - Mudalige, Gihan R.

AU - Reguly, Istvan Z.

AU - Prabhakar, Arun

AU - Amirante, Dario

AU - Lapworth, Leigh

AU - Jarvis, Stephen A.

PY - 2022/10/18

Y1 - 2022/10/18

N2 - We present the large-scale, computational fluid dy-namics (CFD) simulation of a full gas-turbine engine compressor, demonstrating capability towards overcoming current limitations for virtual certification of aero-engine design. The simulation is carried out through a performance portable code-base on multi-core/many-core HPC clusters with a CFD-to-CFD coupled execution, combining an industrial CFD solver linked using custom coupler software. The application innovates in its design for performance portability through the OP2 domain specific library for the CFD components, allowing the automatic generation of highly optimized platform-specific parallelizations for both multi-core (CPU) and many-core (GPU) clusters from a single high-level source. The code is used for the simulation of a 4.58B node, full-annulus 10-row production-grade test compressor (DLR's Rig250), using a coupled sliding-plane setup on the ARCHER2 and Cirrus supercomputers at EPCC. The OP2 generated multiple parallelizations, together with optimized coupler configurations on heterogeneous/hybrid settings achieve, for the first time, execution of 1 revolution in less than 6 hours on 512 nodes of ARCHER2 (65k cores), with a parallel scaling efficiency of over 80 % compared to a 107 node run. Results indicate a speed up of the CFD suite by an order of a magnitude (˜30 x) relative to current production capability. Benchmarking and performance modelling project a time-to-solution of less than 5 hours on a cluster of 488xNVIDIA V100 GPUs, about 3x-4 x speedup over CPU clusters. The work demonstrates a step-change towards achieving virtual certification of aircraft engines with the requisite fidelity and tractable time-to-solution that was previously out of reach under production settings.

AB - We present the large-scale, computational fluid dy-namics (CFD) simulation of a full gas-turbine engine compressor, demonstrating capability towards overcoming current limitations for virtual certification of aero-engine design. The simulation is carried out through a performance portable code-base on multi-core/many-core HPC clusters with a CFD-to-CFD coupled execution, combining an industrial CFD solver linked using custom coupler software. The application innovates in its design for performance portability through the OP2 domain specific library for the CFD components, allowing the automatic generation of highly optimized platform-specific parallelizations for both multi-core (CPU) and many-core (GPU) clusters from a single high-level source. The code is used for the simulation of a 4.58B node, full-annulus 10-row production-grade test compressor (DLR's Rig250), using a coupled sliding-plane setup on the ARCHER2 and Cirrus supercomputers at EPCC. The OP2 generated multiple parallelizations, together with optimized coupler configurations on heterogeneous/hybrid settings achieve, for the first time, execution of 1 revolution in less than 6 hours on 512 nodes of ARCHER2 (65k cores), with a parallel scaling efficiency of over 80 % compared to a 107 node run. Results indicate a speed up of the CFD suite by an order of a magnitude (˜30 x) relative to current production capability. Benchmarking and performance modelling project a time-to-solution of less than 5 hours on a cluster of 488xNVIDIA V100 GPUs, about 3x-4 x speedup over CPU clusters. The work demonstrates a step-change towards achieving virtual certification of aircraft engines with the requisite fidelity and tractable time-to-solution that was previously out of reach under production settings.

KW - Code Coupling

KW - DSL

KW - Gas Turbine Engines

KW - Virtual Certification

UR - https://www.scopus.com/pages/publications/85140889485

U2 - 10.1109/CLUSTER51413.2022.00034

DO - 10.1109/CLUSTER51413.2022.00034

M3 - Conference contribution

AN - SCOPUS:85140889485

SN - 9781665498579

T3 - IEEE International Conference on Cluster Computing

SP - 206

EP - 217

BT - 2022 IEEE International Conference on Cluster Computing (CLUSTER)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2022 IEEE International Conference on Cluster Computing

Y2 - 6 September 2022 through 9 September 2022

ER -

Mudalige GR, Reguly IZ, Prabhakar A, Amirante D, Lapworth L, Jarvis SA. Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations. In 2022 IEEE International Conference on Cluster Computing (CLUSTER). Institute of Electrical and Electronics Engineers (IEEE). 2022. p. 206-217. (IEEE International Conference on Cluster Computing). doi: 10.1109/CLUSTER51413.2022.00034

Towards Virtual Certification of Gas Turbine Engines With Performance-Portable Simulations

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this