Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows
Military, space, and high-speed civilian applications will continue contributing to the renewed interest in compressible, high-speed turbulent boundary layers. To further complicate matters, these flows present complex computational challenges ranging from the pre-processing to the execution and sub...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/4/823 |
| _version_ | 1797434230576250880 |
|---|---|
| author | Christian Lagares Wilson Rivera Guillermo Araya |
| author_facet | Christian Lagares Wilson Rivera Guillermo Araya |
| author_sort | Christian Lagares |
| collection | DOAJ |
| description | Military, space, and high-speed civilian applications will continue contributing to the renewed interest in compressible, high-speed turbulent boundary layers. To further complicate matters, these flows present complex computational challenges ranging from the pre-processing to the execution and subsequent post-processing of large-scale numerical simulations. Exploring more complex geometries at higher Reynolds numbers will demand scalable post-processing. Modern times have brought application developers and scientists the advent of increasingly more diversified and heterogeneous computing hardware, which significantly complicates the development of performance-portable applications. To address these challenges, we propose Aquila, a distributed, out-of-core, performance-portable post-processing library for large-scale simulations. It is designed to alleviate the burden of domain experts writing applications targeted at heterogeneous, high-performance computers with strong scaling performance. We provide two implementations, in C++ and Python; and demonstrate their strong scaling performance and ability to reach 60% of peak memory bandwidth and 98% of the peak filesystem bandwidth while operating out of core. We also present our approach to optimizing two-point correlations by exploiting symmetry in the Fourier space. A key distinction in the proposed design is the inclusion of an out-of-core data pre-fetcher to give the illusion of in-memory availability of files yielding up to 46% improvement in program runtime. Furthermore, we demonstrate a parallel efficiency greater than 70% for highly threaded workloads. |
| first_indexed | 2024-03-09T10:28:16Z |
| format | Article |
| id | doaj.art-81fa94c7f5584ebca7b47f91b7ddd9bc |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T10:28:16Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-81fa94c7f5584ebca7b47f91b7ddd9bc2023-12-01T21:28:54ZengMDPI AGSymmetry2073-89942022-04-0114482310.3390/sym14040823Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid FlowsChristian Lagares0Wilson Rivera1Guillermo Araya2High Performance Computing and Visualization Laboratory, Department of Mechanical Engineering, University of Puerto Rico, Mayaguez 00681, Puerto RicoDepartment of Computer Science and Engineering, University of Puerto Rico, Mayaguez 00681, Puerto RicoHigh Performance Computing and Visualization Laboratory, Department of Mechanical Engineering, University of Puerto Rico, Mayaguez 00681, Puerto RicoMilitary, space, and high-speed civilian applications will continue contributing to the renewed interest in compressible, high-speed turbulent boundary layers. To further complicate matters, these flows present complex computational challenges ranging from the pre-processing to the execution and subsequent post-processing of large-scale numerical simulations. Exploring more complex geometries at higher Reynolds numbers will demand scalable post-processing. Modern times have brought application developers and scientists the advent of increasingly more diversified and heterogeneous computing hardware, which significantly complicates the development of performance-portable applications. To address these challenges, we propose Aquila, a distributed, out-of-core, performance-portable post-processing library for large-scale simulations. It is designed to alleviate the burden of domain experts writing applications targeted at heterogeneous, high-performance computers with strong scaling performance. We provide two implementations, in C++ and Python; and demonstrate their strong scaling performance and ability to reach 60% of peak memory bandwidth and 98% of the peak filesystem bandwidth while operating out of core. We also present our approach to optimizing two-point correlations by exploiting symmetry in the Fourier space. A key distinction in the proposed design is the inclusion of an out-of-core data pre-fetcher to give the illusion of in-memory availability of files yielding up to 46% improvement in program runtime. Furthermore, we demonstrate a parallel efficiency greater than 70% for highly threaded workloads.https://www.mdpi.com/2073-8994/14/4/823CFD post-processingKokkosdistributed memoryshared memoryscalabilityout-of-core processing |
| spellingShingle | Christian Lagares Wilson Rivera Guillermo Araya Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows Symmetry CFD post-processing Kokkos distributed memory shared memory scalability out-of-core processing |
| title | Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows |
| title_full | Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows |
| title_fullStr | Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows |
| title_full_unstemmed | Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows |
| title_short | Scalable Post-Processing of Large-Scale Numerical Simulations of Turbulent Fluid Flows |
| title_sort | scalable post processing of large scale numerical simulations of turbulent fluid flows |
| topic | CFD post-processing Kokkos distributed memory shared memory scalability out-of-core processing |
| url | https://www.mdpi.com/2073-8994/14/4/823 |
| work_keys_str_mv | AT christianlagares scalablepostprocessingoflargescalenumericalsimulationsofturbulentfluidflows AT wilsonrivera scalablepostprocessingoflargescalenumericalsimulationsofturbulentfluidflows AT guillermoaraya scalablepostprocessingoflargescalenumericalsimulationsofturbulentfluidflows |