OpenFoam中多面体网格生成的MPI+OpenMP混合并行方法

网格生成是计算流体力学中非常重要的一环,大规模数值模拟过程中对网格精度要求的提高会导致网格生成所耗的时间增加.文中基于OpenFoam开源软件中的网格生成算法,主要研究多面体网格的并行生成,并提出OpenMP和MPI混合并行的多面体网格生成方法.通过理论分析得到,使用混合并行方法生成相同质量的网格时,混合并行方法生成网...     

多重网格格子Boltzmann方法的并行算法

针对复杂流动数值模拟中的格子Boltzmann方法存在计算网格量大、收敛速度慢的缺点,提出了基于三维几何边界的多重笛卡儿网格并行生成算法,并基于该网格生成方法提出了多重网格并行格子Boltzmann方法（LBM）。该方法结合不同尺度网格间的耦合计算,有效减少了计算网格量,提高了收敛速度;而且测试结果也表明该并行算法具有良好的可扩展性。     

GPU通用计算在LBM方法中的应用

提出了一种结合GPU通用计算与计算流体力学中的LBM算法来模拟二维流场的方法.根据GPU通用计算和LBM方法的基本原理,利用OpenGL的离屏渲染技术FBO和Cg语言,基于LBM方法中的D2Q9模型对二维方腔流进行数值模拟,并设计出基于OpenGL的GPU通用计算的二维流场数值计算框架.实验结果表明,利用GPU模拟与CPU模拟流场的数值结果相当吻合,特别地,利用GPU进行数值模拟实验的速度是利用CPU的4倍左右.     

基于结构网格的大规模并行计算研究

通过求解RANS方程和Menter's k-Omega SST两方程湍流模型,以及采用多重网格加速收敛技术、基于多块结构网格的通用数据传输方法和区域分解负载平衡技术,实现CFD软件的并行计算。在国家超算长沙中心的"天河"系统上完成了软件的移植、测试,并实现翼身组合体外形的2048处理器核数、网格规模上亿单元的大规模并行计算,并行效率达到48%,较大幅度地缩短了计算周期,提高了工作效率。通过对DLR-F6的模拟,在气动力系数精确求解、超大规模网格模拟的快速收敛和网格收敛性研究等方面取得了初步结果,为下一步大规模工程实际应用打下了坚实基础。     

WCNS高精度并行软件的大规模计算研究

本文通过求解任意坐标系下的定常雷诺平均N-S方程和SST两方程湍流模型,采用五阶精度的加权紧致非线性格式(WCNS-E-5),实现流场的高精度数值模拟;基于分布式存储系统,采用MPI并行编程环境、非堵塞通信机制和遗传算法负载平衡,实现高精度模拟软件的并行化。在国防科学技术大学高性能计算应用研究中心的"天河"系统上完成软件移植、测试,通过对DLR-F6翼身组合体的模拟,说明软件并行策略和开发的正确性。最后,实现某民机全机的高精度并行模拟,网格规模达到1亿,为下一步WCNS高精度并行软件的大规模工程实际应用打下了坚实基础。     

基于结构网格的增升构型失速特性大规模并行数值模拟

针对民机增升构型失速特性的数值模拟,我们基于贪婪负载平衡算法的剖分工具对多块结构网格进行区域分割,在某新型超级计算机系统上完成求解软件的移植、优化和测试,采用 2 亿量级的计算网格开展大规模并行计算研究,测试完成了万核级负载平衡的网格区域分割,实现了增升构型失速特性的 4 096 核数并行计算,并行效率达到 50% 以上,提高了工程应用中对复杂流动现象的数值模拟能力。数值模拟结果加深了对增升构型失速流动机理的理解,可以为增升装置设计优化提供有意义的参考依据。     

高精度湍流直接数值模拟程序的异构并行优化分析

在众核处理器应用中,主要难点在于异构并行应用模式和负载均衡的策略,对于计算流体力学,需要针对相关应用设计相应的方案。我们针对湍流直接数值模拟中串行程序含有部分并行度较高的子程序或函数的特点,设计了一种新的并行计算模式,给出了一种异构平台优化方案,并在中科院超级计算系统"元"上进行了测试和分析,对领域内的典型算例进行了性能测试,着重讨论了不同规模下采用offload模式的CPU和MIC异构并行的扩展性能。     

二维弹塑性流体力学LSPIC并行程序研究

针对二维弹塑性流体力学非结构网格拉氏应用程序(LSPIC),应用双线性插值、点排序和网格排序三种方法对计算区域进行分解。基于格式所需邻区网格的个数实现区与区之间的消息传递,建立一种非结构网格拉氏程序并行化方法,实现二维弹塑性流体力学拉氏应用程序(LSPIC)程序的并行化。同时进行程序测试和并行效率分析。     

有限元网格积分算法在MIC众核平台上的并行实现

基于英特尔集成众核(Many Integrated Core,MIC)架构,将有限元网格积分算法在至强融核(Xeon Phi)协处理器做了移植和性能分析。该应用全面测试了有限元分析的核心计算过程在MIC上的加速效果,实现了卸载模式(offload)[1]下利用OpenMP在MIC上的线程并行化。计算性能测试结果显示集成众核平台可以有效地加速有限元网格积分算法:1)一块被充分利用的MIC设备卡(3115A)的计算能力超过两路16核Intel XeonTM E5-2670 CPU;2)MIC并发的物理线程可能由于公共缓存访问存在竞争而降低程序的扩展性。测试结果还显示了在多CPU多MIC平台上进一步移植完整的MPI并行有限元模拟软件的可行性。这项工作有助于推动与有限元网格相关的科学和工程高性能计算的研究。     

非结构粘性直角网格并行算法建立与应用

开展了基于粘性直角非结构网格的并行CFD解算软件的开发研究,工作分两部分：网格分区实现和解算器并行实施,文章介绍了关于CFD解算器并行的实施情况,给出了并行过程中的操作流程,并对一些关键问题进行了讨论。并行计算结果表明项目所采用的并行途径和方法有效,计算结果可靠。     

An efficient swap algorithm for the lattice Boltzmann method

During the last decade, the lattice-Boltzmann method (LBM) as a valuable tool in computational fluid dynamics has been increasingly acknowledged. The widespread application of LBM is partly due to the simplicity of its coding. The most well-known algorithms for the implementation of the standard lattice-Boltzmann equation (LBE) are the two-lattice and two-step algorithms. However, implementations of the two-lattice or the two-step algorithm suffer from high memory consumption or poor computational performance, respectively. Ultimately, the computing resources available decide which of the two disadvantages is more critical. Here we introduce a new algorithm, called the swap algorithm, for the implementation of LBE. Simulation results demonstrate that implementations based on the swap algorithm can achieve high computational performance and have very low memory consumption. Furthermore, we show how the performance of its implementations can be further improved by code optimization.     

基于机群的湍流燃烧数值模拟平台的构建与应用

首先对机群系统的特点和软硬件配置环境进行阐述,然后基于MPI和开源工具OpenFOAM实现一个计算流体力学机群系统的搭建,并对这个机群系统的性能和并行效率进行测试和分析。通过利用此机群系统对湍流燃烧流动反应进行数值模拟及并行计算得到模拟效果的三维流场。实验结果表明,该机群系统针对湍流燃烧数值模拟可以明显提高计算效率并得到较好的仿真效果。     

Highly interactive computational steering for coupled 3D flow problems utilizing multiple GPUs

Most computational fluid dynamics (CFD) simulations require massive computational power which is usually provided by traditional High Performance Computing (HPC) environments. Although interactivity of the simulation process is highly appreciated by scientists and engineers, due to limitations of typical HPC environments, present CFD simulations are usually executed non interactively. A recent trend is to harness the parallel computational power of graphics processing units (GPUs) for general purpose applications. As an alternative to traditional massively parallel computing, GPU computing has also gained popularity in the CFD community, especially for its application to the lattice Boltzmann method (LBM). For instance, Tölke and others presented very efficient implementations of the LBM for 2D as well as 3D space (Toelke J, in Comput Visual Sci. (2008); Toelke J and Krafczk M, in Int J Comput Fluid Dyn 22(7): 443–456 (2008)). In this work we motivate the use of GPU computing to facilitate interactive CFD simulations. In our approach, the simulation is executed on multiple GPUs instead of traditional HPC environments, which allows the integration of the complete simulation process into a single desktop application. To demonstrate the feasibility of our approach, we show a fully bidirectional fluid-structure-interaction for self induced membrane oscillations in a turbulent flow. The efficiency of the approach allows a 3D simulation close to realtime.     

Parallelization Strategies for Computational Fluid Dynamics Software: State of the Art Review

Computational fluid dynamics (CFD) is one of the most emerging fields of fluid mechanics used to analyze fluid flow situation. This analysis is based on simulations carried out on computing machines. For complex configurations, the grid points are so large that the computational time required to obtain the results are very high. Parallel computing is adopted to reduce the computational time of CFD by utilizing the available resource of computing. Parallel computing tools like OpenMP, MPI, CUDA, combination of these and few others are used to achieve parallelization of CFD software. This article provides a comprehensive state of the art review of important CFD areas and parallelization strategies for the related software. Issues related to the computational time complexities and parallelization of CFD software are highlighted. Benefits and issues of using various parallel computing tools for parallelization of CFD software are briefed. Open areas of CFD where parallelization is not much attempted are identified and parallel computing tools which can be useful for parallelization of CFD software are spotlighted. Few suggestions for future work in parallel computing of CFD software are also provided.     

LBM算法在GPU组中的应用

为提高大规模并行计算的并行效率,充分发挥CPU与GPU的功能特点,特别是体现GPU强大的运算能力,提出了用消息传递接口(MPI)将一组GPU连接起来。使GPU通用计算与计算流体力学中的LBM(latticeBoltzmannmethod)算法相结合。根据GPU通用计算与LBM算法的原理,使MPI作为计算分配的机制,CUDA(compute unified device architecture)作为主要的计算执行引擎,建立支持CUDA的GPU集群,在集群上对LBM算法中的D2Q9模型进行二维方腔流数值模拟。实验结果表明,利用GPU组模拟与CPU模拟结果一致,更充分发挥了GPU的计算能力,提高了并行效率。     

Leveraging parallel computing in multibody dynamics

At a time when sequential computing is limited to marginal year-to-year gains in speed, multi- and many-core architectures provide teraflop-grade performance to cost-conscious users. The ongoing shift to parallel computing spurs new research into solution methods that emphasize algorithmic concurrency. It also provides an opportunity to revisit complex real-life applications whose solutions have been until recently infeasible due to prohibitively heavy computational burdens. This paper concentrates on the use of commodity parallel computing in the field of multibody dynamics by illustrating how many-body frictional-contact dynamics, fluid–solid interaction analysis, and proximity computation have benefited from parallel computing. Preliminary results are encouraging and show one to two orders of magnitude reductions in simulation times. A set of open questions and final remarks round up the contribution.     

短程力分子模拟在Hadoop上的实现及优化

在Hadoop开源云计算平台上运行分子模拟程序,具有节省软硬件投资、缩短模拟时间等研究意义。然而,该平台并不擅长科学计算类应用中所涉及的快速迭代和子任务间通信。为此,在原子分解法基础上提出了三种解决方案并利用"读写HDFS同步法"实现短程作用力有效的分子动力学模拟的并行算法。在一个Hadoop集群上测试和分析了程序的可扩展性、加速比和各部分耗时情况,结果表明在大规模体系模拟中有较好的效果,最高取得了28倍的加速比。实验证明,Hadoop并行技术在分子模拟中有着较高的经济价值和实用价值。     

多物理场耦合软件GTEA开发及应用

围绕多物理场耦合问题,基于连续介质假设,采用非结构化网格和有限体积方法开发多物理场耦合并行计算软件GTEA。该软件包括计算流体力学、结构应力波传播、流 声耦合和声 固耦合等4个功能模块。介绍GTEA前处理网格读取、网格格式转换、求解器开发等关键技术。通过柴油机缸内工作过程模拟、船舶水动力计算、自然对流与辐射传热耦合作用、流场动力噪声计算和结构 声耦合计算等5个典型应用展示该软件的应用能力和适用范围。     

Physis语言框架在WENO高阶数值格式异构计算中的应用

WENO(weighted essentially non-oscillatory)是计算流体力学中广泛采用的一种高阶数值格式。由于算法本身和异构计算编程的复杂性,需要开展异构计算代码自动生成的研究,以加速更多的应用。本文基于Physis这一领域编程语言框架,针对三维五阶WENO计算的天文应用,实现了其异构代码的自动生成。在超级计算机"元"上的测试结果表明,自动生成的异构计算代码具有良好的可扩展性,计算性能达到手工优化异构代码的72%,可为相关流体计算的异构代码生成提供借鉴。