Hardware accelerator for molecular dynamics: MDGRAPE-2

We developed MDGRAPE-2, a hardware accelerator that calculates forces at high speed in molecular dynamics (MD) simulations. MDGRAPE-2 is connected to a PC or a workstation as an extension board. The sustained performance of one MDGRAPE-2 board is 15 Gflops, roughly equivalent to the peak performance of the fastest supercomputer processing element. One board is able to calculate all forces between 10 000 particles in 0.28 s (i.e. 310000 time steps per day). If 16 boards are connected to one computer and operated in parallel, this calculation speed becomes ∼10 times faster. In addition to MD, MDGRAPE-2 can be applied to gravitational N-body simulations, the vortex method and smoothed particle hydrodynamics in computational fluid dynamics.     

Numerical simulation of cloud droplet formation in a tank

Using the computational fluid dynamics (CFD) code FLUENT 6 together with the fine particle model (FPM), numerical simulations of droplet dynamics in a 12.4 m³ cloud tank were conducted. The coupled fields of water vapor, temperature, flow velocity, particle number concentration, and particle mass concentration inside the cloud tank were computed.The system responses to changes of the wall's temperature and mass fraction of water vapor, respectively, were investigated. Typical times for mixing the cloud tank's contents are in the range of some tens of seconds. The maximum volume-averaged deviations from the mean of temperature and mass fraction of water vapor are around 5% of the respective parameter changes applied to the wall.Time-dependent simulations were performed in order to study the growth of ammonium-sulfate particles in humid air at around room temperature. Supersaturation up to (S_w–1)=8.2×10⁻³ was achieved by the expansion of the gas. The particles were activated and grew rapidly to a maximum diameter of 5.2×10⁻⁶ m after critical supersaturation was reached. After S_w fell again below the equilibrium value, the particles shrank quickly and deactivated roughly 60 s after activation.The spatial inhomogeneities of temperature and water-vapor concentration cause volume-averaged deviations of the particle number N and diameter d_g of up to 2.3% and 36%, respectively.     

An implementation of granular dynamics for simulating frictional elastic particles based on the DL_POLY code

We have modified Daresbury Laboratory's replicated data strategy (RDS) parallel molecular dynamics (MD) package DL_POLY (version 2.13) to study the granular dynamics of frictional elastic particles. DL_POLY [Smith and Forester, The DL_POLY_2 User Manual v2.13, 2001; Forester and Smith, The DL_POLY_2 Reference Manual v2.13, 2001] is a MD package originally developed to study liquid state and macromolecular systems by accounting for various molecular interaction forces. The particles of interest in this study are macroscopic grains in pharmaceutical powders, with sizes ranging from tens to hundreds of microns. We have therefore substituted the molecular interaction forces with contact forces (including linear-dashpot, HKK interaction forces and Coulombic friction) while taking advantage of the RDS scheme. In effect, we have created a parallel Discrete Element Simulation (DES) code. In this paper, we describe the modifications made to the original DL_POLY code and the results from the validation tests of the granular dynamics simulations for systems of monodisperse spherical particles settling under gravity. The code can also be utilized to study particle packings generated via uniaxial compaction and, in some cases, simultaneous application of shear, at constant strain.     

Dynamical geometry for multiscale dissipative particle dynamics

In this paper, we review the computational aspects of a multiscale dissipative particle dynamics model for complex fluid simulations based on the feature-rich geometry of the Voronoi tessellation. The geometrical features of the model are critical since the mesh is directly connected to the physics by the interpretation of the Voronoi volumes of the tessellation as coarse-grained fluid clusters. The Voronoi tessellation is maintained dynamically in time to model the fluid in the Lagrangian frame of reference, including imposition of periodic boundary conditions. Several algorithms to construct and maintain the periodic Voronoi tessellation are reviewed in two and three spatial dimensions and their parallel performance discussed. The insertion of polymers and colloidal particles in the fluctuating hydrodynamic solvent is described using surface boundaries.     

Parallelizing and optimizing large‐scale 3D multi‐phase flow simulations on the Tianhe‐2 supercomputer

The lattice Boltzmann method (LBM) is a widely used computational fluid dynamics method for flow problems with complex geometries and various boundary conditions. Large‐scale LBM simulations with increasing resolution and extending temporal range require massive high‐performance computing (HPC) resources, thus motivating us to port it onto modern many‐core heterogeneous supercomputers like Tianhe‐2. Although many‐core accelerators such as graphics processing unit and Intel MIC have a dramatic advantage of floating‐point performance and power efficiency over CPUs, they also pose a tough challenge to parallelize and optimize computational fluid dynamics codes on large‐scale heterogeneous system. In this paper, we parallelize and optimize the open source 3D multi‐phase LBM code openlbmflow on the Intel Xeon Phi (MIC) accelerated Tianhe‐2 supercomputer using a hybrid and heterogeneous MPI+OpenMP+Offload+single instruction, mulitple data (SIMD) programming model. With cache blocking and SIMD‐friendly data structure transformation, we dramatically improve the SIMD and cache efficiency for the single‐thread performance on both CPU and Phi, achieving a speedup of 7.9X and 8.8X, respectively, compared with the baseline code. To collaborate CPUs and Phi processors efficiently, we propose a load‐balance scheme to distribute workloads among intra‐node two CPUs and three Phi processors and use an asynchronous model to overlap the collaborative computation and communication as far as possible. The collaborative approach with two CPUs and three Phi processors improves the performance by around 3.2X compared with the CPU‐only approach. Scalability tests show that openlbmflow can achieve a parallel efficiency of about 60% on 2048 nodes, with about 400K cores in total. To the best of our knowledge, this is the largest scale CPU‐MIC collaborative LBM simulation for 3D multi‐phase flow problems. Copyright © 2015 John Wiley & Sons, Ltd.     

Leveraging legacy codes to distributed problem‐solving environments: a Web services approach

This paper presents WSOWG, a Web‐services‐oriented wrapper generator for automatically wrapping non‐networked legacy codes as Web services for reuse in distributed problem‐solving environments. Using WSOWG, a finite element based computational fluid dynamics (CFD) legacy code has been wrapped as a Web service. A problem‐solving environment for simulating incompressible Navier–Stokes flows has also been implemented. A user makes use of the CFD service through a Web page without knowing the exact implementation of the service. In this way, a user's computing environment can be extended to a heterogeneous distributed computing environment. Performance evaluation shows that the overhead to invoke the CFD Web service generated by WSOWG using Simple Object Access Protocol (SOAP) and CORBA Internet Inter‐ORB Protocol (IIOP) is reasonable compared with that of invoking another CFD Web service manually wrapped from the CFD legacy code using SOAP only. Copyright © 2004 John Wiley & Sons, Ltd.     

基于面向对象的粒子类模拟并行计算研究

针对经典分子动力学和PIC方法等粒子类模拟方法具有粒子动态移动、粒子计算局部性好等共性,首先,提出了粒子量数据片对象.该对象是单网格片上的一团粒子,其中网格片是包含多个网格单元的矩形区域.然后,设计了并行算法,包括对象之间的粒子迁移和数据交换以及动态负载平衡.最后,在JASMIN框架上具体实现,进而开发了并行经典分子动力学程序和并行PIC程序.在64个处理器上实测表明,并行PIC程序模拟包含3百万个网格、2千万个粒子的复杂物理模型时,获得了80%的并行效率.     

Lagrangian particle model for multiphase flows

A Lagrangian particle model for multiphase multicomponent fluid flow, based on smoothed particle hydrodynamics (SPH), was developed and used to simulate the flow of an emulsion consisting of bubbles of a non-wetting liquid surrounded by a wetting liquid. In SPH simulations, fluids are represented by sets of particles that are used as discretization points to solve the Navier-Stokes fluid dynamics equations. In the multiphase multicomponent SPH model, a modified van der Waals equation of state is used to close the system of flow equations. The combination of the momentum conservation equation with the van der Waals equation of state results in a particle equation of motion in which the total force acting on each particle consists of many-body repulsive and viscous forces, two-body (particle-particle) attractive forces, and body forces such as gravitational forces. Similar to molecular dynamics, for a given fluid component the combination of repulsive and attractive forces causes phase separation. The surface tension at liquid-liquid interfaces is imposed through component dependent attractive forces. The wetting behavior of the fluids is controlled by phase dependent attractive interactions between the fluid particles and stationary particles that represent the solid phase. The dynamics of fluids away from the interface is governed by purely hydrodynamic forces. Comparison with analytical solutions for static conditions and relatively simple flows demonstrates the accuracy of the SPH model.     

Adaptive particles for incompressible fluid simulation

We propose a particle-based technique for simulating incompressible fluid that includes adaptive refinement of particle sampling. Each particle represents a mass of fluid in its local region. Particles are split into several particles for finer sampling in regions of complex flow. In regions of smooth flow, neighboring particles can be merged. Depth below the surface and Reynolds number are exploited as our criteria for determining whether splitting or merging should take place. For the fluid dynamics calculations, we use the hybrid FLIP method, which is computationally simple and efficient. Since the fluid is incompressible, each particle has a volume proportional to its mass. A kernel function, whose effective range is based on this volume, is used for transferring and updating the particle’s physical properties such as mass and velocity. Our adaptive particle-based simulation is demonstrated in several scenarios that show its effectiveness in capturing fine detail of the flow, where needed, while efficiently sampling regions where less detail is required.     

Experimental and numerical investigation on particle–particle interaction of multi-particle separation in an alternating and repetitive microchannel

Inertial focusing plays a major role in size-based cell separation or enrichment for microfluidic applications in many medical areas such as diagnostics and treatment. These applications often deal with suspensions of different particles which cause interactions between particles with different diameters such as particle–particle collision. In this study, particle–particle interaction in a laminar flow through a low aspect ratio alternating and repetitive microchannel is investigated both numerically and experimentally. It is revealed that particle–particle collision affects high quality particle focusing. computational fluid dynamics simulations are conducted for demonstrating the effect of the flow field in the transverse cross-section on the focusing quality and position. The experiments and simulations both revealed that if the flow is seeded with a mixture of particles of 3.3 and 9.9 µm diameters, the quality of focusing intensity is degenerated compared to the focusing features obtained by particles with a diameter of 9.9 µm solely. The results clearly show that particle–particle collision between the 3.3 and 9.9 µm particles has a negative effect on particle focusing behavior of the 9.9 µm particles.

     

Extended Narrow Band FLIP for Liquid Simulations

The Fluid Implicit Particle method (FLIP) reduces numerical dissipation by combining particles with grids. To improve performance, the subsequent narrow band FLIP method (NB‐FLIP) uses a FLIP‐based fluid simulation only near the liquid surface and a traditional grid‐based fluid simulation away from the surface. This spatially‐limited FLIP simulation significantly reduces the number of particles and alleviates a computational bottleneck. In this paper, we extend the NB‐FLIP idea even further, by allowing a simulation to transition between a FLIP‐like fluid simulation and a grid‐based simulation in arbitrary locations, not just near the surface. This approach leads to even more savings in memory and computation, because we can concentrate the particles only in areas where they are needed. More importantly, this new method allows us to seamlessly transition to smooth implicit surface geometry wherever the particle‐based simulation is unnecessary. Consequently, our method leads to a practical algorithm for avoiding the noisy surface artifacts associated with particle‐based liquid simulations, while simultaneously maintaining the benefits of a FLIP simulation in regions of dynamic motion.     

Visualizing the Phase Space of Heterogeneous Inertial Particles in 2D Flows

In many scientific disciplines, the motion of finite‐sized objects in fluid flows plays an important role, such as in brownout engineering, sediment transport, oceanology or meteorology. These finite‐sized objects are called inertial particles and, in contrast to traditional tracer particles, their motion depends on their current position, their own particle velocity, the time and their size. Thus, the visualization of their motion becomes a high‐dimensional problem that entails computational and perceptual challenges. So far, no visualization explored and visualized the particle trajectories under variation of all seeding parameters. In this paper, we propose three coordinated views that visualize the different aspects of the high‐dimensional space in which the particles live. We visualize the evolution of particles over time, showing that particles travel different distances in the same time, depending on their size. The second view provides a clear illustration of the trajectories of different particle sizes and allows the user to easily identify differences due to particle size. Finally, we embed the trajectories in the space‐velocity domain and visualize their distance to an attracting manifold using ribbons. In all views, we support interactive linking and brushing, and provide abstraction through density volumes that are shown by direct volume rendering and isosurface slabs. Using our method, users gain deeper insights into the dynamics of inertial particles in 2D fluids, including size‐dependent separation, preferential clustering and attraction. We demonstrate the effectiveness of our method in multiple steady and unsteady 2D flows.     

MPM simulation of interacting fluids and solids

The material point method (MPM) has attracted increasing attention from the graphics community, as it combines the strengths of both particle‐ and grid‐based solvers. Like the smoothed particle hydrodynamics (SPH) scheme, MPM uses particles to discretize the simulation domain and represent the fundamental unknowns. This makes it insensitive to geometric and topological changes, and readily parallelizable on a GPU. Like grid‐based solvers, MPM uses a background mesh for calculating spatial derivatives, providing more accurate and more stable results than a purely particle‐based scheme. MPM has been very successful in simulating both fluid flow and solid deformation, but less so in dealing with multiple fluids and solids, where the dynamic fluid‐solid interaction poses a major challenge. To address this shortcoming of MPM, we propose a new set of mathematical and computational schemes which enable efficient and robust fluid‐solid interaction within the MPM framework. These versatile schemes support simulation of both multiphase flow and fully‐coupled solid‐fluid systems. A series of examples is presented to demonstrate their capabilities and performance in the presence of various interacting fluids and solids, including multiphase flow, fluid‐solid interaction, and dissolution.     

Parallel‐optimizing SPH fluid simulation for realistic VR environments

In virtual environments, real‐time simulation and rendering of dynamic fluids have always been the pursuit for virtual reality research. In this paper, we present a real‐time framework for realistic fluid simulation and rendering on graphics processing unit. Because of the high demand for interactive fluids with larger particle set, the computational need is becoming higher. The proposed framework can effectively reduce the computational burden through avoiding the computation in inactive areas, where many particles with similar properties and low local pressure cluster together. While in active areas, the computation is fully carried out; thus, the fluid dynamics are largely preserved. Here, a robust particle classification technique is introduced to classify particles into either active or inactive. The test results have shown that the technique improves the time performance of fluid simulation largely. We then incorporate parallel surface reconstruction technique using marching cubes to extract the surfaces of the fluid. The introduced histogram pyramid‐based marching cubes technique is fast and memory efficiency. As a result, we are able to produce plausible and interactive fluids with the proposed framework for large‐scale virtual environments. Copyright © 2013 John Wiley & Sons, Ltd.     

Computational simulation and analysis of double-swept blade in BVI noise reduction

The TURNS computational fluid dynamics (CFD) code with the Beddoes prescribed wake and the WOPWOP computational acoustics code is used to study blade-sweep blade–vortex interaction (BVI) noise reduction design. The CFD three-dimensional unsteady solutions of blade surface pressure distributions are used as the input to WOPWOP acoustics computational code to produce the overall sound pressure level (OASPL) on a 3-rotor radiation observer hemisphere around the helicopter rotor. To study the effects of blade sweep on BVI noise reduction, computations are performed on a baseline rectangular blade and a corresponding double-swept blade to better understand the impact of blade sweep on BVI noise reduction in relation to the interaction angle between blade leading edge and the shed tip-vortex. The present study indicates that tip-region blade forward sweep produces favorable BVI angles for dominate BVIs to reduce the maximum BVI noise level on the advancing side, while increasing noise level on the retreating side. Increasing in the noise level on the retreating side as a trade-off for decreasing in the maximum noise level on the advancing side results favorably in the reduction of the overall maximum noise level and in changing the ‘hot’ noise spots into a more desirable ‘less hot’ noise region.     

Combined inverse and gradient iterative learning control: performance,monotonicity, robustness and non‐minimum‐phase zeros

Based on recent papers that have demonstrated that robust iterative learning control can be based on parameter optimization using either the inverse plant or gradient concepts, this paper presents a unification of these ideas for discrete‐time systems that not only retains the convergence properties and the robustness properties derived in previous papers but also permits the inclusion of filters in the input update formula and a detailed analysis of the effect of non‐minimum‐phase dynamics on algorithm performance in terms of a ‘plateauing’ or ‘flat‐lining’ effect in the error norm evolution. Although the analysis is in the time domain, the robustness conditions are expressed as frequency domain inequalities. The special case of a version of the inverse algorithm that can be used to construct a robust stable anti‐causal inverse non‐minimum‐phase plant is presented and analysed in detail. Copyright © 2012 John Wiley & Sons, Ltd.     

Virtual Rheoscopic Fluids

We present a visualization technique for simulated fluid dynamics data that visualizes the gradient of the velocity field in an intuitive way. Our work is inspired by rheoscopic particles, which are small, flat particles that, when suspended in fluid, align themselves with the shear of the flow. We adopt the physical principles of real rheoscopic particles and apply them, in model form, to 3D velocity fields. By simulating the behavior and reflectance of these particles, we are able to render 3D simulations in a way that gives insight into the dynamics of the system. The results can be rendered in real time, allowing the user to inspect the simulation from all perspectives. We achieve this by a combination of precomputations and fast ray tracing on the GPU. We demonstrate our method on several different simulations, showing their complex dynamics in the process.     

A new algorithm for simulating flows of conducting fluids in the presence of electric fields

We propose an algorithm based on dissipative particle dynamics (DPD) for simulations of conducting fluids in the presence of an electric field. In this model, the electrostatic equations are solved in each DPD time step to determine the charge density at the fluid surfaces. These surface charges are distributed on a thin layer of fluid particles near the interface, and the corresponding interfacial electric forces are added to other DPD forces. The algorithm is applied to the electrospinning process at the Taylor cone formation stage. It is shown that, when the applied voltage is sufficiently high, the algorithm captures the formation of a Taylor cone with analytical apex angle 98.6°. Our results demonstrate the potential of the presented DPD algorithm for simulating two-phase problems in the presence of an electric field with non-periodic boundary conditions.     

Mesoscale simulations of particulate flows with parallel distributed Lagrange multiplier technique

Fluid particulate flows are common phenomena in nature and industry. Modeling of such flows at micro and macro levels as well establishing relationships between these approaches are needed to understand properties of the particulate matter. We propose a computational technique based on the direct numerical simulation of the particulate flows. The numerical method is based on the distributed Lagrange multiplier technique following the ideas of Glowinski et al. [16] and Patankar [30]. Each particle is explicitly resolved on an Eulerian grid as a separate domain, using solid volume fractions. The fluid equations are solved through the entire computational domain, however, Lagrange multiplier constrains are applied inside the particle domain such that the fluid within any volume associated with a solid particle moves as an incompressible rigid body. Mutual forces for the fluid-particle interactions are internal to the system. Particles interact with the fluid via fluid dynamic equations, resulting in implicit fluid-rigid body coupling relations that produce realistic fluid flow around the particles (i.e., no-slip boundary conditions). The particle-particle interactions are implemented using explicit force-displacement interactions for frictional inelastic particles similar to the DEM method of Cundall et al. [10] with some modifications using a volume of an overlapping region as an input to the contact forces. The method is flexible enough to handle arbitrary particle shapes and size distributions. A parallel implementation of the method is based on the SAMRAI (Structured Adaptive Mesh Refinement Application Infrastructure) library, which allows handling of large amounts of rigid particles and enables local grid refinement. Accuracy and convergence of the presented method has been tested against known solutions for a falling particle as well as by examining fluid flows through stationary particle beds (periodic and cubic packing). To evaluate code performance and validate particle contact physics algorithm, we performed simulations of a representative experiment conducted at the U.C. Berkeley Thermal Hydraulic Lab for pebble flow through a narrow opening.     

A computationally efficient method for simulating fluid flow in elastic pipes in three dimensions

We propose a new method for carrying out lattice-Boltzmann simulations of pulsatile fluid flow in three-dimensional elastic pipes. It is based on estimating the distances from sites at the edge of the simulation box to the wall along the lattice directions from the displacement of the closest point on the wall and the curvature there, followed by application of a nonequilibrium extrapolation method. Viscous flow in an elastic pipe is studied in three dimensions at a wall displacement of 5% of the radius of the pipe, which is realistic for blood flow through large cerebral arteries. The numerical results for the pressure difference, wall displacement and flow velocity agree well with the analytical predictions. At all sites, the calculation depends only on information from nearest neighbours, so the method proposed is suitable for efficient computation on multicore machines. Compared to simulations with rigid walls, simulations with elastic walls require only 13% more computational effort at the parameters chosen in this study.