Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture
High-order numerical schemes implemented on high-performance parallel computers are of special interest for contemporary numerical simulations, especially in computational fluid dynamics. In this study, first, a high-order parallel flow solver is presented for some test cases of aerodynamic simulati...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2020-03-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0001521 |
| _version_ | 1818189774190542848 |
|---|---|
| author | Amjad Ali Hamayun Farooq Gullnaz Shahzadi Muhammad Umar Khalid Saifullah Syed |
| author_facet | Amjad Ali Hamayun Farooq Gullnaz Shahzadi Muhammad Umar Khalid Saifullah Syed |
| author_sort | Amjad Ali |
| collection | DOAJ |
| description | High-order numerical schemes implemented on high-performance parallel computers are of special interest for contemporary numerical simulations, especially in computational fluid dynamics. In this study, first, a high-order parallel flow solver is presented for some test cases of aerodynamic simulations. The flow solver is based on a discontinuous Galerkin finite element method on arbitrary grids with different orders of polynomial approximation for solving the compressible flow model. Second, the distributed-memory parallel implementation of the flow solver is benchmarked on a shared-memory multicore system. A distributed-memory parallel application can be executed on shared-memory architectures by assuming that each of the parallel processes assumes separate memory address space, although all are present in a common memory bank. This approach can offer an effective measure to address several issues related to limited resources, especially for uninterrupted electric supply. The scalability of the parallel application is analyzed by varying the problem workload per process for the test cases. For some test cases in the present study, over 90% parallel efficiency per process is also observed. The performance of the distributed-memory program on the shared-memory architecture establishes suitability and robustness of the approach for small to medium scale problems, at least. |
| first_indexed | 2024-12-11T23:48:09Z |
| format | Article |
| id | doaj.art-7c964b3bf0a944f18ac6d413257ea8c0 |
| institution | Directory Open Access Journal |
| issn | 2158-3226 |
| language | English |
| last_indexed | 2024-12-11T23:48:09Z |
| publishDate | 2020-03-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj.art-7c964b3bf0a944f18ac6d413257ea8c02022-12-22T00:45:34ZengAIP Publishing LLCAIP Advances2158-32262020-03-01103035031035031-1310.1063/5.0001521Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architectureAmjad Ali0Hamayun Farooq1Gullnaz Shahzadi2Muhammad Umar3Khalid Saifullah Syed4Centre for Advanced Studies in Pure and Applied Mathematics, Bahauddin Zakariya University, Multan, PakistanCentre for Advanced Studies in Pure and Applied Mathematics, Bahauddin Zakariya University, Multan, PakistanDepartment of Mechanical Engineering, École de Technologie Supérieure ÉTS, 1100 Notre-Dame W, Montreal, Québec H3C 1K3, CanadaCentre for Advanced Studies in Pure and Applied Mathematics, Bahauddin Zakariya University, Multan, PakistanCentre for Advanced Studies in Pure and Applied Mathematics, Bahauddin Zakariya University, Multan, PakistanHigh-order numerical schemes implemented on high-performance parallel computers are of special interest for contemporary numerical simulations, especially in computational fluid dynamics. In this study, first, a high-order parallel flow solver is presented for some test cases of aerodynamic simulations. The flow solver is based on a discontinuous Galerkin finite element method on arbitrary grids with different orders of polynomial approximation for solving the compressible flow model. Second, the distributed-memory parallel implementation of the flow solver is benchmarked on a shared-memory multicore system. A distributed-memory parallel application can be executed on shared-memory architectures by assuming that each of the parallel processes assumes separate memory address space, although all are present in a common memory bank. This approach can offer an effective measure to address several issues related to limited resources, especially for uninterrupted electric supply. The scalability of the parallel application is analyzed by varying the problem workload per process for the test cases. For some test cases in the present study, over 90% parallel efficiency per process is also observed. The performance of the distributed-memory program on the shared-memory architecture establishes suitability and robustness of the approach for small to medium scale problems, at least.http://dx.doi.org/10.1063/5.0001521 |
| spellingShingle | Amjad Ali Hamayun Farooq Gullnaz Shahzadi Muhammad Umar Khalid Saifullah Syed Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture AIP Advances |
| title | Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture |
| title_full | Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture |
| title_fullStr | Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture |
| title_full_unstemmed | Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture |
| title_short | Benchmarking of a distributed-memory, high-order discontinuous finite element flow solver on a shared-memory parallel architecture |
| title_sort | benchmarking of a distributed memory high order discontinuous finite element flow solver on a shared memory parallel architecture |
| url | http://dx.doi.org/10.1063/5.0001521 |
| work_keys_str_mv | AT amjadali benchmarkingofadistributedmemoryhighorderdiscontinuousfiniteelementflowsolveronasharedmemoryparallelarchitecture AT hamayunfarooq benchmarkingofadistributedmemoryhighorderdiscontinuousfiniteelementflowsolveronasharedmemoryparallelarchitecture AT gullnazshahzadi benchmarkingofadistributedmemoryhighorderdiscontinuousfiniteelementflowsolveronasharedmemoryparallelarchitecture AT muhammadumar benchmarkingofadistributedmemoryhighorderdiscontinuousfiniteelementflowsolveronasharedmemoryparallelarchitecture AT khalidsaifullahsyed benchmarkingofadistributedmemoryhighorderdiscontinuousfiniteelementflowsolveronasharedmemoryparallelarchitecture |