Optimization Research of Heterogeneous 2D-Parallel Lattice Boltzmann Method Based on Deep Computing Unit
Source abstract
Abstract
Currently, research on the lattice Boltzmann method mainly focuses on its numerical simulation and applications, and there is an increasing demand for large-scale simulations in practical scenarios. In response to this situation, this study successfully implemented a large-scale heterogeneous parallel algorithm for the lattice Boltzmann method using OpenMP, MPI, Pthread, and OpenCL parallel technologies on the “Dongfang” supercomputer system. The accuracy and effectiveness of this algorithm were verified through the lid-driven cavity flow simulation. The paper focused on optimizing the algorithm in four aspects: Firstly, non-blocking communication was employed to overlap communication and computation, thereby improving parallel efficiency. Secondly, high-speed shared memory was utilized to enhance memory access performance and reduce latency. Thirdly, a balanced computation between the central processing unit and the accelerator was achieved through proper task partitioning and load-balancing strategies. Lastly, memory access efficiency was improved by adjusting the memory layout. Performance testing demonstrated that the optimized algorithm exhibited improved parallel efficiency and scalability, with computational performance that is 4 times greater than before optimization and 20 times that of a 32-core CPU.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Lattice Boltzmann Simulation Studies · Aerosol Filtration and Electrostatic Precipitation · Generative Adversarial Networks and Image Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, Qingdao University, Qingdao 266071, China
Funding
the Shandong Province Natural Science Foundation · GHFund A · the National Key R&D Program of China
References (34)
Show source-provided references
1. The Lattice Boltzmann Equation: A New Tool for Computational Fluid-Dynamics10.1016/0167-2789(91)90292-H ↗
2. Dam-Break Modeling: LBM as the Way towards Fully 3D, Large-Scale Applications10.1061/(ASCE)HY.1943-7900.0001879 ↗
3. Development and Application of a High Density Ratio Pseudopotential Based Two-Phase LBM Solver to Study Cavitating Bubble Dynamics in Pressure Driven Channel Flow at Low Reynolds Number10.1016/j.euromechflu.2018.12.004 ↗
4. Application of the LBM with Adaptive Grid on Water Hammer Simulation10.2166/hydro.2016.164 ↗
5. Impact of Mesh Partitioning Methods in CFD for Large Scale Parallel Computing10.1016/j.compfluid.2014.07.016 ↗
6. Performance Portability Study for Massively Parallel Computational Fluid Dynamics Application on Scalable Heterogeneous Architectures10.1016/j.jpdc.2019.02.005 ↗
7. Wang, Y., Jiang, J., and Wang, Y. (2023). High-Performance Computing and Artificial Intelligence for Geosciences. Appl. Sci., 13.10.3390/books978-3-0365-8181-1 ↗
8. GPU Accelerated Lattice Boltzmann Method in Neutron Kinetics Problems II: Neutron Transport Calculation10.1016/j.anucene.2019.06.020 ↗
9. Qi, Y., Li, Q., Zhao, Z., Zhang, J., Gao, L., Yuan, W., Lu, Z., Nie, N., Shang, X., and Tao, S. (2022). Heterogeneous Parallel Implementation of Large-Scale Numerical Simulation of Saint-Venant Equations. Appl. Sci., 12.10.3390/app12115671 ↗
10. A Systematic Evaluation of Accelerating Indoor Airflow Simulations Using Cross-Platform Parallel Computing10.1080/19401493.2016.1212933 ↗
11. Accelerated Lattice Boltzmann Simulation Using GPU and OpenACC with Data Management10.1016/j.ijheatmasstransfer.2017.02.032 ↗
12. OpenCL vs OpenACC: Lessons from Development of Lattice QCD Simulation Code10.1016/j.procs.2015.05.316 ↗
13. Kokkos Implementation of an Ewald Coulomb Solver and Analysis of Performance Portability10.1016/j.jpdc.2019.12.003 ↗
14. Assessing the Performance Portability of Modern Parallel Programming Models Using TeaLeaf10.1002/cpe.4117 ↗
15. Productivity, Performance, and Portability for Computational Fluid Dynamics Applications10.1016/j.compfluid.2020.104425 ↗
16. Implementation of a Lattice Boltzmann Kernel Using the Compute Unified Device Architecture Developed by nVIDIA10.1007/s00791-008-0120-2 ↗
17. A New Approach to the Lattice Boltzmann Method for Graphics Processing Units10.1016/j.camwa.2010.01.054 ↗
18. GPU Implementation of Lattice Boltzmann Method for Flows with Curved Boundaries10.1016/j.cma.2012.03.011 ↗
19. Multi Relaxation Time Lattice Boltzmann Simulations of Transition in Deep 2D Lid Driven Cavity Using GPU10.1016/j.compfluid.2012.01.018 ↗
20. Multi-GPU Performance of Incompressible Flow Computation by Lattice Boltzmann Method on GPU Cluster
21. Multi-GPU Implementation of the Lattice Boltzmann Method10.1016/j.camwa.2011.02.020 ↗
22. Performance Modeling and Analysis of Heterogeneous Lattice Boltzmann Simulations on CPU–GPU Clusters10.1016/j.parco.2014.12.003 ↗
23. Parallelizing and Optimizing Large-scale 3D Multi-phase Flow Simulations on the Tianhe-2 Supercomputer10.1002/cpe.3717 ↗
24. Liu, Z., Chu, X., Lv, X., Meng, H., Shi, S., Han, W., Xu, J., Fu, H., and Yang, G. (2019, January 20–24). Sunwaylb: Enabling Extreme-Scale Lattice Boltzmann Method Based Computing Fluid Dynamics Simulations on Sunway Taihulight. Proceedings of the 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Rio de Janeiro, Brazil.10.1109/IPDPS.2019.00065 ↗
25. Riesinger, C., Bakhtiari, A., Schreiber, M., Neumann, P., and Bungartz, H.-J. (2017). A Holistic Scalable Implementation Approach of the Lattice Boltzmann Method for CPU/GPU Heterogeneous Clusters. Computation, 5.10.3390/computation5040048 ↗
26. Watanabe, S., and Hu, C. (2022, January 7). Performance Evaluation of Lattice Boltzmann Method for Fluid Simulation on A64FX Processor and Supercomputer Fugaku. Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region, ACM, Virtual Event, Japan.10.1145/3492805.3492811 ↗
27. An MPI Parallel DEM-IMB-LBM Framework for Simulating Fluid-Solid Interaction Problems10.1016/j.jrmge.2024.01.007 ↗
28. A Simple and Efficient Parallel Immersed Boundary-Lattice Boltzmann Method for Fully Resolved Simulations of Incompressible Settling Suspensions10.1016/j.compfluid.2022.105322 ↗
29. Liu, Z., Chen, Y., Xiao, W., Song, W., and Li, Y. (2023). Large-Scale Cluster Parallel Strategy for Regularized Lattice Boltzmann Method with Sub-Grid Scale Model in Large Eddy Simulation. Appl. Sci., 13.10.3390/app131911078 ↗
30. Lbmpy: Automatic Code Generation for Efficient Parallel Lattice Boltzmann Methods10.1016/j.jocs.2020.101269 ↗
31. Suban, I.B. (2021). Medical Image Segmentation Using a Combination of Lattice Boltzmann Method and Fuzzy Clustering Based on GPU CUDA Parallel Processing. Int. J. Online Biomed. Eng., 17.10.3991/ijoe.v17i11.24459 ↗
32. Palabos: Parallel Lattice Boltzmann Solver10.1016/j.camwa.2020.03.022 ↗
33. Parallel Unstructured Finite Volume Lattice Boltzmann Method for High-Speed Viscid Compressible Flows10.1142/S0129183122500668 ↗
34. Simulation of Cavity Flow by the Lattice Boltzmann Method10.1006/jcph.1995.1103 ↗