1.上海大学计算机工程与科学学院,上海 200444
2.上海大学力学与工程科学学院,上海 200072
[ "何 鹏 男,1994年6月出生于湖北省荆州市.上海大学计算机工程与科学学院博士研究生,主要研究方向为高性能计算、计算流体力学.E-mail: 2359597269@qq.com" ]
[ "王良军 男,1991年1月出生于安徽省阜阳市.现就职于上海大学,研究方向为高性能计算、计算流体力学. E-mail: shu_wlj@shu.edu.cn" ]
[ "张 武 男,1957年11月出生于江西省武宁县,上海大学力学与工程科学学院教授、博士生导师,研究方向为计算流体力学、并行计算算法与软件. E-mail: wzhang@shu.edu.cn" ]
[ "朱文浩 男,1979年9月出生于江苏省昆山市,上海大学计算机工程与科学学院教授、博士生导师,研究方向包括人工智能、文本处理、大数据应用等. E-mail: whzhu@shu.edu.cn" ]
收稿:2023-08-26,
修回:2024-02-01,
纸质出版:2024-09-25
移动端阅览
何鹏, 王良军, 张武, 等. 格子Boltzmann方法多层网格负载均衡算法优化研究[J]. 电子学报, 2024, 52(09): 3097-3110.
HE Peng, WANG Liang-jun, ZHANG Wu, et al. Optimization Study of the Load Balancing Algorithm in the Multi-Layer Lattice Boltzmann Method[J]. Acta Electronica Sinica, 2024, 52(09): 3097-3110.
何鹏, 王良军, 张武, 等. 格子Boltzmann方法多层网格负载均衡算法优化研究[J]. 电子学报, 2024, 52(09): 3097-3110. DOI:10.12263/DZXB.20230809
HE Peng, WANG Liang-jun, ZHANG Wu, et al. Optimization Study of the Load Balancing Algorithm in the Multi-Layer Lattice Boltzmann Method[J]. Acta Electronica Sinica, 2024, 52(09): 3097-3110. DOI:10.12263/DZXB.20230809
基于格子Boltzmann方法的多层网格局部加密技术,通过多尺度网格计算不同层次的流动特征,避免了单层均匀笛卡尔网格中的低效率与计算资源的浪费,但仍存在并行性能上的不良影响.本文考虑并行计算中的负载均衡效应,从单层网格出发,通过考虑多层网格的运算特点来研究基于负载均衡的网格划分方法.同时,将网格划分与程序实现进行分离,在单层和多层网格中均完成了任意网格划分下的并行计算.在单层网格中,以二维血管流动的不同并行策略为例,研究了负载量划分与不同进程的各自时间开销的关系.在多层网格中,首先论述了多尺度网格在运算顺序上的特征,其次以三种不同的多层网格验证二维翼型绕流的计算结果,最后在每种网格中均使用三种不同的网格划分方法进一步探讨负载均衡与时间开销的关系.在128核的高性能计算平台上进行并行性能测试,强可扩展性可达到60%左右,弱可扩展性可达到82.78%.这种高可扩展性结果表明本文通过改进负载均衡性能,明显提升了多层网格计算中的并行性能.
The local encryption technique for multi-layer grids based on the lattice Boltzmann method computes the flow characteristics at different levels through multi-layer grids
which avoids the inefficiency and waste of computational resources in single-layer uniform Cartesian grids. But there is still an undesirable effect on the parallel performance. The load-balancing effect in parallel computing is considered in this paper. Starting from a single-layer grid
we study the load-balancing-based grid partitioning method by considering the computational characteristics of multi-layer grids. At the same time
the grid partitioning is separated from the program implementation
and parallel computation with arbitrary grid partitioning is achieved in both single-layer and multi-layer grids. The relationship between load partitioning and the respective time overheads of the different processes is investigated in a single-layer grid with different parallel strategies for 2D vascular flow. The characteristics of multiscale grids with respect to the order of operations is first discussed for multi-layer grids. Second
three different multi-layer grids are used to verify the computational results of the two-dimensional aerofoils. Finally
the relationship between load balancing and time overhead is further investigated by using three different meshing methods in each grid. Parallel performance tests on a 128-core HPC (High Performance Computing) platform show that the strong scalability can reach up to 60%
and the weak scalability can reach 82.78%. This high scalability result shows the significant improvement of the parallel performance in multi-layer grid computing by improving the load balancing performance.
BOON J P . The lattice boltzmann equation for fluid dynamics and beyond [J ] . European Journal of Mechanics - B , 2003 , 22 ( 1 ): 101 .
SHEIKHOLESLAMI M , GANJI D D . Entropy generation of nanofluid in presence of magnetic field using lattice Boltzmann method [J ] . Physica A Statistical Mechanics and Its Applications , 2015 , 417 : 273 - 286 .
QIAN Y H , D'HUMIÈRES D , LALLEMAND P . Lattice BGK models for navier-stokes equation [J ] . Europhysics Letters , 1992 , 17 ( 6 ): 479 - 484 .
CHEN S , CHEN H , MARTNEZ D , et al . Lattice Boltzmann model for simulation of magnetohydrodynamics [J ] . Physical Review Letters , 1991 , 67 ( 27 ): 3776 - 3779 .
HOU S , STERLING J , CHEN S , et al . A lattice Boltzmann subgrid model for high Reynolds number flows [EB/OL ] . ( 1994-01-28 )[ 2023-02-01 ] . http://arxiv.org/abs/comp-gas/9401004 http://arxiv.org/abs/comp-gas/9401004
张凌明 , 赵悦 , 李鹏程 , 等 . 基于局部注意力机制的三维牙齿模型分割网络 [J ] . 电子学报 , 2022 , 50 ( 3 ): 681 - 690 .
ZHANG L M , ZHAO Y , LI P C , et al . Dental model segmentation network based on local attention mechanism [J ] . Acta Electronica Sinica , 2022 , 50 ( 3 ): 681 - 690 . (in Chinese)
WELLEIN G , ZEISER T , HAGER G , et al . On the single processor performance of simple lattice Boltzmann kernels [J ] . Computers & Fluids , 2006 , 35 ( 8/9 ): 910 - 919 .
KÖRNER C , POHL T , RÜDE U , et al . Parallel lattice Boltzmann methods for CFD applications [C ] // Numerical Solution of Partial Differential Equations on Parallel Computers . Berlin : Springer , 2006 , 439 - 466 .
DELANAYE M , AFTOSMIS M , BERGER M , et al . Automatic hybrid-Cartesian grid generation for high-Reynolds number flows around complex geometries [C ] // Proceedings of the 37th Aerospace Sciences Meeting and Exhibit . Reston : AIAA , 1999 : AIAA1999-777.
FILIPPOVA O , HÄNEL D . Grid refinement for lattice-BGK models [J ] . Journal of Computational Physics , 1998 , 147 ( 1 ): 219 - 228 .
TÖLKE J , KRAFCZYK M , RANK E . A multigrid-solver for the discrete boltzmann equation [J ] . Journal of Statistical Physics , 2002 , 107 ( 1 ): 573 - 591 .
YU D Z , MEI R W , SHYY W . A multi-block lattice Boltzmann method for viscous fluid flows [J ] . International Journal for Numerical Methods in Fluids , 2002 , 39 ( 2 ): 99 - 120 .
王相海 , 宋若曦 , 曲思洁 , 等 . 图像多尺度几何分析域隐马尔可夫树模型研究进展 [J ] . 电子学报 , 2022 , 50 ( 1 ): 238 - 249 .
WANG X H , SONG R X , QU S J , et al . Advance in multiscale geometric analysis image hidden markov tree model [J ] . Acta Electronica Sinica , 2022 , 50 ( 1 ): 238 - 249 . (in Chinese)
NEUMANN P , NECKEL T . A dynamic mesh refinement technique for Lattice Boltzmann simulations on octree-like grids [J ] . Computational Mechanics , 2013 , 51 ( 2 ): 237 - 253 .
HASERT M , MASILAMANI K , ZIMNY S , et al . Complex fluid simulations with the parallel tree-based Lattice Boltzmann solver Musubi [J ] . Journal of Computational Science , 2014 , 5 ( 5 ): 784 - 794 .
袁海英 , 曾智勇 , 成君鹏 . 面向灵活并行度的稀疏卷积神经网络加速器 [J ] . 电子学报 , 2022 , 50 ( 8 ): 1811 - 1818 .
YUAN H Y , ZENG Z Y , CHENG J P . A sparsity-aware convolutional neural network accelerator with flexible parallelism [J ] . Acta Electronica Sinica , 2022 , 50 ( 8 ): 1811 - 1818 . (in Chinese)
LIU Z X , RUAN J , SONG W , et al . Parallel scheme for multi-layer refinement non-uniform grid lattice boltzmann method based on load balancing [J ] . Energies , 2022 , 15 ( 21 ): 7884 .
LIU Z X , CHEN R L , XU L . Parallel unstructured finite volume lattice Boltzmann method for high-speed viscid compressible flows [J ] . International Journal of Modern Physics C , 2022 , 33 ( 5 ): 2250066 .
GUO Z L , ZHENG C G , SHI B C . Non-equilibrium extrapolation method for velocity and pressure boundary conditions in the lattice Boltzmann method [J ] . Chinese Physics , 2002 , 11 ( 4 ): 366 - 374 .
YU D Z , MEI R W , SHYY W . A unified boundary treatment in lattice Boltzmann method [C ] // Proceedings of the 41st Aerospace Sciences Meeting and Exhibit . Reston : AIAA , 2003 : AIAA2003-953.
QI J X , KLIMACH H , ROLLER S . Implementation of the compact interpolation within the octree based Lattice Boltzmann solver Musubi [J ] . Computers & Mathematics with Applications , 2019 , 78 ( 4 ): 1131 - 1141 .
GE S , XIE J , WANG H Y , et al . Large-scale lattice Boltzmann method simulations of stenosed carotid bifurcation [C ] // 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS) . Piscataway : IEEE , 2019 : 1076 - 1084 .
KURTULUS D F . On the unsteady behavior of the flow around NACA 0012 airfoil with steady external conditions at Re=1000 [J ] . International Journal of Micro Air Vehicles , 2015 , 7 ( 3 ): 301 - 326 .
0
浏览量
10
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621