An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media
The traditional finite element program is executed on the CPU; however, it is challenging for the CPU to compute the ultra-large scale finite element model. In this paper, we present a set of efficient algorithms based on GPU acceleration technology for the dynamic response of fluid-saturated porous...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/2/181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588053197094912 |
|---|---|
| author | Wancang Lin Qinglong Zhou Xinyi Chen Wenhao Shi Jie Ai |
| author_facet | Wancang Lin Qinglong Zhou Xinyi Chen Wenhao Shi Jie Ai |
| author_sort | Wancang Lin |
| collection | DOAJ |
| description | The traditional finite element program is executed on the CPU; however, it is challenging for the CPU to compute the ultra-large scale finite element model. In this paper, we present a set of efficient algorithms based on GPU acceleration technology for the dynamic response of fluid-saturated porous media, named PNAM, encompassing the assembly of the global matrix and the iterative solution of equations. In the assembly part, the CSR storage format of the global matrix is directly obtained from the element matrix. For data with two million degrees of freedom, it merely takes approximately 1 s to generate all the data of global matrices, which is significantly superior to the CPU version. Regarding the iterative solution of equations, a novel algorithm based on the CUDA kernel function is proposed. For a data set with two million degrees of freedom, it takes only about 0.05 s to compute an iterative step and transfer the data to the CPU. The program is designed to calculate either in single or double precision. The change in precision has little impact on the assembly of the global matrix, but the calculation time of double precision is generally 1.5 to 2 times that of single precision in the iterative solution part for a model with 2 million degrees of freedom. PNAM has high computational efficiency and great compatibility, which can be used to solve not only saturated fluid problems but also a variety of other problems. |
| format | Article |
| id | doaj-art-45c733f9a61b455fa1c86581445c5e0a |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-45c733f9a61b455fa1c86581445c5e0a2025-01-24T13:39:39ZengMDPI AGMathematics2227-73902025-01-0113218110.3390/math13020181An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous MediaWancang Lin0Qinglong Zhou1Xinyi Chen2Wenhao Shi3Jie Ai4School of Resources and Security Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Security Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Security Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Security Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Security Engineering, Central South University, Changsha 410083, ChinaThe traditional finite element program is executed on the CPU; however, it is challenging for the CPU to compute the ultra-large scale finite element model. In this paper, we present a set of efficient algorithms based on GPU acceleration technology for the dynamic response of fluid-saturated porous media, named PNAM, encompassing the assembly of the global matrix and the iterative solution of equations. In the assembly part, the CSR storage format of the global matrix is directly obtained from the element matrix. For data with two million degrees of freedom, it merely takes approximately 1 s to generate all the data of global matrices, which is significantly superior to the CPU version. Regarding the iterative solution of equations, a novel algorithm based on the CUDA kernel function is proposed. For a data set with two million degrees of freedom, it takes only about 0.05 s to compute an iterative step and transfer the data to the CPU. The program is designed to calculate either in single or double precision. The change in precision has little impact on the assembly of the global matrix, but the calculation time of double precision is generally 1.5 to 2 times that of single precision in the iterative solution part for a model with 2 million degrees of freedom. PNAM has high computational efficiency and great compatibility, which can be used to solve not only saturated fluid problems but also a variety of other problems.https://www.mdpi.com/2227-7390/13/2/181CUDAu-p dynamic formulationfinite elementsspeedupGPU-acceleration |
| spellingShingle | Wancang Lin Qinglong Zhou Xinyi Chen Wenhao Shi Jie Ai An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media Mathematics CUDA u-p dynamic formulation finite elements speedup GPU-acceleration |
| title | An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media |
| title_full | An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media |
| title_fullStr | An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media |
| title_full_unstemmed | An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media |
| title_short | An Efficient GPU-Accelerated Algorithm for Solving Dynamic Response of Fluid-Saturated Porous Media |
| title_sort | efficient gpu accelerated algorithm for solving dynamic response of fluid saturated porous media |
| topic | CUDA u-p dynamic formulation finite elements speedup GPU-acceleration |
| url | https://www.mdpi.com/2227-7390/13/2/181 |
| work_keys_str_mv | AT wancanglin anefficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT qinglongzhou anefficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT xinyichen anefficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT wenhaoshi anefficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT jieai anefficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT wancanglin efficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT qinglongzhou efficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT xinyichen efficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT wenhaoshi efficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia AT jieai efficientgpuacceleratedalgorithmforsolvingdynamicresponseoffluidsaturatedporousmedia |