PIXIE3D: An efficient, fully implicit, parallel, 3D extended MHD code for fusion plasma modeling
PIXIE3D is a modern, parallel, state-of-the-art extended MHD code that employs fully implicit methods for efficiency and accuracy. It features a general geometry formulation, and is therefore suitable for the study of many magnetic fusion configurations of interest. PIXIE3D advances the state of the art in extended MHD modeling in two fundamental ways. Firstly, it employs a novel conservative finite volume scheme which is remarkably robust and stable, and demands very small physical and/or numerical dissipation. This is a fundamental requirement when one wants to study fusion plasmas with realistic conductivities. Secondly, PIXIE3D features fully-implicit time stepping, employing Newton-Krylov methods for inverting the associated nonlinear systems. These methods have been shown to be scalable and efficient when preconditioned properly. Novel preconditioned ideas (so-called physics based), which were prototypes in the context of reduced MHD, have been adapted for 3D primitive-variable resistive MHD in PIXIE3D, and are currently being extended to Hall MHD. PIXIE3D is fully parallel, employing PETSc for parallelism. PIXIE3D has been thoroughly benchmarked against linear theory and against other available extended MHD codes on nonlinear test problems (such as the GEM reconnection challenge). We are currently in the process of extending such comparisons to fusion-relevant problems in realistic geometries. In this talk, we will describe both the spatial discretization approach and the preconditioning strategy employed for extended MHD in PIXIE3D. We will report on recent benchmarking studies between PIXIE3D and other 3D extended MHD codes, and will demonstrate its usefulness in a variety of fusion-relevant configurations such as Tokamaks and Reversed Field Pinches. (Author)
Novel Kinetic 3D MHD Algorithm for High Performance Parallel Computing Systems
Chetverushkin, B; Saveliev, V
2013-01-01
The impressive progress of the kinetic schemes in the solution of gas dynamics problems and the development of effective parallel algorithms for modern high performance parallel computing systems led to the development of advanced methods for the solution of the magnetohydrodynamics problem in the important area of plasma physics. The novel feature of the method is the formulation of the complex Boltzmann-like distribution function of kinetic method with the implementation of electromagnetic interaction terms. The numerical method is based on the explicit schemes. Due to logical simplicity and its efficiency, the algorithm is easily adapted to modern high performance parallel computer systems including hybrid computing systems with graphic processors.
3-D Relativistic MHD Simulations
Nishikawa, K.-I.; Frank, J.; Koide, S.; Sakai, J.-I.; Christodoulou, D. M.; Sol, H.; Mutel, R. L.
1998-12-01
We present 3-D numerical simulations of moderately hot, supersonic jets propagating initially along or obliquely to the field lines of a denser magnetized background medium with Lorentz factors of W = 4.56 and evolving in a four-dimensional spacetime. The new results are understood as follows: Relativistic simulations have consistently shown that these jets are effectively heavy and so they do not suffer substantial momentum losses and are not decelerated as efficiently as their nonrelativistic counterparts. In addition, the ambient magnetic field, however strong, can be pushed aside with relative ease by the beam, provided that the degrees of freedom associated with all three spatial dimensions are followed self-consistently in the simulations. This effect is analogous to pushing Japanese ``noren'' or vertical Venetian blinds out of the way while the slats are allowed to bend in 3-D space rather than as a 2-D slab structure.
3D simulation studies of tokamak plasmas using MHD and extended-MHD models
The M3D (Multi-level 3D) tokamak simulation project aims at the simulation of tokamak plasmas using a multi-level tokamak code package. Several current applications using MHD and Extended-MHD models are presented; high-β disruption studies in reversed shear plasmas using the MHD level MH3D code, ω*i stabilization and nonlinear island saturation of TAE mode using the hybrid particle/MHD level MH3D-K code, and unstructured mesh MH3D++ code studies. In particular, three internal mode disruption mechanisms are identified from simulation results which agree which agree well with experimental data
3D simulation studies of tokamak plasmas using MHD and extended-MHD models
The M3D (Multi-level 3D) tokamak simulation project aims at the simulation of tokamak plasmas using a multi-level tokamak code package. Several current applications using MHD and Extended-MHD models are presented; high-β disruption studies in reversed shear plasmas using the MHD level MH3D code, ω*i stabilization and nonlinear island rotation studies using the two-fluid level MH3D-T code, studies of nonlinear saturation of TAE modes using the hybrid particle/MHD level MH3D-K code, and unstructured mesh MH3D++ code studies. In particular, three internal mode disruption mechanisms are identified from simulation results which agree well with experimental data
3D simulation studies of tokamak plasmas using MHD and extended-MHD models
The M3D (Multi-level 3D) tokamak simulation project aims at the simulation of tokamak plasmas using a multi-level tokamak code package. Several current applications using MHD and Extended-MHD models are presented: high-β disruption studies in reversed shear plasmas using the MHD level MH3D code; ω*i stabilization and nonlinear island rotation studies using the two-fluid level MH3D-T code; studies of nonlinear saturation of TAE modes using the hybrid particle/MHD level MH3D-K code; and unstructured mesh MH3D++ code studies. In particular, three internal mode disruption mechanisms are identified from simulation results which agree well with experimental data. (author). 18 refs, 5 figs
3D MHD Flux emergence experiments
Hood, A.W.; Archontis, V.; Mactaggart, David
2012-01-01
This paper reviews some of the many 3D numerical experiments of the emergence of magnetic fields from the solar interior and the subsequent interaction with the pre-existing coronal magnetic field. The models described here are idealised, in the sense that the internal energy equation only involv...
Suppression of Magnetic Flux Diffusion in Reduced 3D MHD
Bayliss, A.; Ware, A. S.; Diamond, P. H.; Kim, E.-J.
1999-11-01
The important impact of small scale magnetic fields on self-organization (i.e., dynamo) in MHD turbulence was originally pin-pointed by the observation that magnetic flux diffusion (anomalous resistivity) is drastically reduced in 2D MHD turbulence. This reduction is a consequence of mean square magnetic potential in two dimensions. It is natural, then, to investigate magnetic flux diffusion in 3D reduced MHD; since in that system conservation is broken only by linear field line bending (symptomatic of Alfvén wave propagation along B_z), and resistive dissipation. In particular, the Ohm's Law nonlinearity conserves . Not surprisingly, it is possible to derive an exact constraint upon the spatial flux of magnetic potential from the condition of balance. This expression may then be used to simplify the calculation of the turbulent resistivity, which is found to be suppressed, as in 2D MHD, up to corrections resulting from hat z-direction Alfvén wave propagation effects. These corrections vanish in the limit of unity magnetic Prandtl number. Work on understanding the self-consistent alpha effect in reduced MHD is ongoing and will be discussed.
Implementation of a 3-D nonlinear MHD [magnetohydrodynamics] calculation on the Intel hypercube
The optimization of numerical schemes and increasing computer capabilities in the last ten years have improved the efficiency of 3-D nonlinear resistive MHD calculations by about two to three orders of magnitude. However, we are still very limited in performing these types of calculations. Hypercubes have a large number of processors with only local memory and bidirectional links among neighbors. The Intel Hypercube at Oak Ridge has 64 processors with 0.5 megabytes of memory per processor. The multiplicity of processors opens new possibilities for the treatment of such computations. The constraint on time and resources favored the approach of using the existing RSF code which solves as an initial value problem the reduced set of MHD equations for a periodic cylindrical geometry. This code includes minimal physics and geometry, but contains the basic three dimensionality and nonlinear structure of the equations. The code solves the reduced set of MHD equations by Fourier expansion in two angular coordinates and finite differences in the radial one. Due to the continuing interest in these calculations and the likelihood that future supercomputers will take greater advantage of parallelism, the present study was initiated by the ORNL Exploratory Studies Committee and funded entirely by Laboratory Discretionary Funds. The objectives of the study were: to ascertain the suitability of MHD calculation for parallel computation, to design and implement a parallel algorithm to perform the computations, and to evaluate the hypercube, and in particular, ORNL's Intel iPSC, for use in MHD computations
3D MHD simulation of polarized emission in SN 1006
Schneiter, E M; Reynoso, E M; Esquivel, A; De Colle, F
2015-01-01
We use three dimensional magnetohydrodynamic (MHD) simulations to model the supernova remnant SN 1006. From our numerical results, we have carried out a polarization study, obtaining synthetic maps of the polarized intensity, the Stokes parameter $Q$, and the polar-referenced angle, which can be compared with observational results. Synthetic maps were computed considering two possible particle acceleration mechanisms: quasi-parallel and quasi-perpendicular. The comparison of synthetic maps of the Stokes parameter $Q$ maps with observations proves to be a valuable tool to discern unambiguously which mechanism is taking place in the remnant of SN 1006, giving strong support to the quasi-parallel model.
Testing Observational Techniques with 3D MHD Jets in Clusters
Mendygral, Peter J; Jones, Tom W
2009-01-01
Observations of X-ray cavities formed by powerful jets from AGN in galaxy cluster cores are commonly used to estimate the mechanical luminosity of these sources. We test the reliability of observationally measuring this power with synthetic X-ray observations of 3-D MHD simulations of jets in a galaxy cluster environment. We address the role that factors such as jet intermittency and orientation of the jets on the sky have on the reliability of observational measurements of cavity enthalpy and age. An estimate of the errors in these quantities can be made by directly comparing ``observationally'' derived values with values from the simulations. In our tests, cavity enthalpy, age and mechanical luminosity derived from observations are within a factor of two of the simulation values.
FARGO3D: A new GPU-oriented MHD code
Benítez-Llambay, Pablo
2016-01-01
We present the FARGO3D code, recently publicly released. It is a magnetohydrodynamics code developed with special emphasis on protoplanetary disks physics and planet-disk interactions, and parallelized with MPI. The hydrodynamics algorithms are based on finite difference upwind, dimensionally split methods. The magnetohydrodynamics algorithms consist of the constrained transport method to preserve the divergence-free property of the magnetic field to machine accuracy, coupled to a method of characteristics for the evaluation of electromotive forces and Lorentz forces. Orbital advection is implemented, and an N-body solver is included to simulate planets or stars interacting with the gas. We present our implementation in detail and present a number of widely known tests for comparison purposes. One strength of FARGO3D is that it can run on both "Graphical Processing Units" (GPUs) or "Central Processing unit" (CPUs), achieving large speed up with respect to CPU cores. We describe our implementation choices, whi...
3-D Relativistic MHD Simulations of Extragalactic Jets
Nishikawa, K.-I.; Koide, S.; Sakai, J.-I.; Frank, J.; Christodoulou, D. M.; Sol, H.; Mutel, R. L.
1997-12-01
We present the numerical simulations of relativistic jets propagating initially oblique to the field lines of a magnetized ambient medium. Our simulations incorporate relativistic MHD in a four-dimensional spacetime and clearly show that (a) relatively weak, oblique fields (at 1/16 of the equipartition value) have only a negligible influence on the propagating jet and they are passively pushed away by the relativistically moving head; (b) oblique fields in equipartition with the ambient plasma provide more resistance and cause bending at the jet head, but the magnitude of this deflection and the associated backflow are small compared to those identified by previous studies with a 2-D slab model. The new results are understood as follows: Relativistic simulations have consistently shown that these jets are effectively heavy and so they do not suffer substantial momentum losses and are not decelerated as efficiently as their nonrelativistic counterparts. In addition, the ambient magnetic field, however strong, can be pushed aside with relative ease by the beam, provided that the degrees of freedom associated with all three spatial dimensions are followed self-consistently during the simulations. The effect is analogous to pushing Japanese ``noren'' or vertical Venetian blinds out of the way while the slats are allowed to bend in 3-D space rather than as a 2-D slab structure. Applied to relativistic extragalactic jets from blazars, the new results are encouraging since superluminal outflows exhibit bending near their sources and their environments are profoundly magnetized---but observations do not provide support for irregular kinematics such as large-scale vortical motions and pronounced reverse flows near the points of origin.
FARGO3D: A New GPU-oriented MHD Code
Benítez-Llambay, Pablo; Masset, Frédéric S.
2016-03-01
We present the FARGO3D code, recently publicly released. It is a magnetohydrodynamics code developed with special emphasis on the physics of protoplanetary disks and planet-disk interactions, and parallelized with MPI. The hydrodynamics algorithms are based on finite-difference upwind, dimensionally split methods. The magnetohydrodynamics algorithms consist of the constrained transport method to preserve the divergence-free property of the magnetic field to machine accuracy, coupled to a method of characteristics for the evaluation of electromotive forces and Lorentz forces. Orbital advection is implemented, and an N-body solver is included to simulate planets or stars interacting with the gas. We present our implementation in detail and present a number of widely known tests for comparison purposes. One strength of FARGO3D is that it can run on either graphical processing units (GPUs) or central processing units (CPUs), achieving large speed-up with respect to CPU cores. We describe our implementation choices, which allow a user with no prior knowledge of GPU programming to develop new routines for CPUs, and have them translated automatically for GPUs.
Parallel Simulations in Turbulent MHD
The large-scale dynamics of plasma flows can often be described within a fluidistic approximation known as one-fluid magnetohydrodynamics. Complex flows such as those corresponding to turbulent regimes are ubiquitous in laboratory plasmas and in astrophysics, because of their typically very large Reynolds numbers. Numerical simulations have become a powerful tool for the study of complex plasma flows in recent years. The aim of the present paper is to introduce the reader to some of the standard numerical approximations used for the integration of the magnetohydrodynamic equations. In particular, we focus on pseudo-spectral methods and on how to develop parallel codes to speed up large Reynolds number simulations. We show the results arising from numerical simulations of astrophysical interest such as the development of turbulent flows in reduced magnetohydrodynamics and the generation of magnetic fields by dynamo mechanisms in three dimensional magnetohydrodynamics
Parallel Simulations in Turbulent MHD
Gomez, Daniel O. [C. Universitaria, Buenos Aires (Argentina). Dept. of Physics, Pabellon I; Mininni, Pablo D. [National Center for Atmospheric Research, Boulder, CO (United States). Advanced Study Program; Dmitruk, Pablo [Univ. of Delaware, Newark (United States). Bartol Research Inst.
2005-04-01
The large-scale dynamics of plasma flows can often be described within a fluidistic approximation known as one-fluid magnetohydrodynamics. Complex flows such as those corresponding to turbulent regimes are ubiquitous in laboratory plasmas and in astrophysics, because of their typically very large Reynolds numbers. Numerical simulations have become a powerful tool for the study of complex plasma flows in recent years. The aim of the present paper is to introduce the reader to some of the standard numerical approximations used for the integration of the magnetohydrodynamic equations. In particular, we focus on pseudo-spectral methods and on how to develop parallel codes to speed up large Reynolds number simulations. We show the results arising from numerical simulations of astrophysical interest such as the development of turbulent flows in reduced magnetohydrodynamics and the generation of magnetic fields by dynamo mechanisms in three dimensional magnetohydrodynamics.
Hayek, W; Carlsson, M; Trampedach, R; Collet, R; Gudiksen, B V; Hansteen, V H; Leenaarts, J
2010-01-01
We present the implementation of a radiative transfer solver with coherent scattering in the new BIFROST code for radiative magneto-hydrodynamical (MHD) simulations of stellar surface convection. The code is fully parallelized using MPI domain decomposition, which allows for large grid sizes and improved resolution of hydrodynamical structures. We apply the code to simulate the surface granulation in a solar-type star, ignoring magnetic fields, and investigate the importance of coherent scattering for the atmospheric structure. A scattering term is added to the radiative transfer equation, requiring an iterative computation of the radiation field. We use a short-characteristics-based Gauss-Seidel acceleration scheme to compute radiative flux divergences for the energy equation. The effects of coherent scattering are tested by comparing the temperature stratification of three 3D time-dependent hydrodynamical atmosphere models of a solar-type star: without scattering, with continuum scattering only, and with bo...
3D MHD simulations of pellet injection and disruptions in tokamak plasmas
Nonlinear MHD simulation results of pellet injection show that MHD forces can accelerate large pellets, injected on the high field side of a tokamak, to the plasma center. Magnetic reconnection can produce a reverse shear q profile. Ballooning instability caused by pellets is also reduced by high field side injection. Studies are also reported of the current quench phase of disruptions, which can cause 3D halo currents and runaway electrons. (author)
3-D MHD Numerical Simulations of Cloud-Wind Interactions
Gregori, G.; Miniati, Francesco; Ryu, Dongsu; Jones, T. W.
2000-01-01
We present results from three-dimensional (3-D) numerical simulations investigating the magnetohydrodynamics of cloud-wind interactions. The initial cloud is spherical while the magnetic field is uniform and transverse to the cloud motion. A simplified analytical model that describes the magnetic energy evolution in front of the cloud is developed and compared with simulation results. In addition, it is found the interaction of the cloud with a magnetized interstellar medium (ISM) results in ...
Study of magnetic island using a 3D MHD equilibrium calculation code
Coupling the magnetic diagnostics and a 3D MHD equilibrium calculation code, the magnetic island is studied in the Large Helical Device (LHD) experiment. In an experiment, the collapse in the plasma core was observed in a configuration, which has large magnetic island produced by external perturbation coils. At the collapse, the temperature profile was flattened. This suggests the magnetic island evolved. The magnetic island was observed by the magnetic diagnostics. The magnetic diagnostics also suggests evolving the magnetic island. A 3D MHD equilibrium is calculated by the 3D MHD equilibrium code then signals of the magnetic diagnostics are simulated. Since the comparison of observed and calculated signals is comparable, the magnetic island in calculated equilibrium is similar to one of the experiment. (author)
3D MHD modeling of twisted coronal loops
Reale, F; Guarrasi, M; Mignone, A; Peres, G; Hood, A W; Priest, E R
2016-01-01
We perform MHD modeling of a single bright coronal loop to include the interaction with a non-uniform magnetic field. The field is stressed by random footpoint rotation in the central region and its energy is dissipated into heating by growing currents through anomalous magnetic diffusivity that switches on in the corona above a current density threshold. We model an entire single magnetic flux tube, in the solar atmosphere extending from the high-beta chromosphere to the low-beta corona through the steep transition region. The magnetic field expands from the chromosphere to the corona. The maximum resolution is ~30 km. We obtain an overall evolution typical of loop models and realistic loop emission in the EUV and X-ray bands. The plasma confined in the flux tube is heated to active region temperatures (~3 MK) after ~2/3 hr. Upflows from the chromosphere up to ~100 km/s fill the core of the flux tube to densities above 10^9 cm^-3. More heating is released in the low corona than the high corona and is finely ...
3D modelling of edge parallel flow asymmetries
The issue of parallel flows asymmetries in the edge plasma is tackled with a new first principle transport and turbulence code. TOKAM-3D is a 3D full-torus fluid code that can be used both in diffusive and turbulent regimes and covers either exclusively closed flux surfaces or both open and closed field lines in limiter geometry. Two independent mechanisms susceptible to lead to large amplitude asymmetric parallel flows are evidenced. Global ExB drifts coupled with the presence of the limiter break the poloidal symmetry and can generate large amplitude parallel flows even with poloidally uniform transport coefficients. On the other hand, turbulent transport in the edge exhibits a strong ballooning of the radial particle flux generating an up-down m = 1, n = 0 structure on the parallel velocity. The combination of both mechanisms in complete simulations leads to a poloidal and radial distribution of the parallel velocity comparable to experimental results.
3-D MHD Numerical Simulations of Cloud-Wind Interactions
Gregori, G; Ryu, D; Jones, T W; Miniati, Francesco; Ryu, Dongsu
2000-01-01
We present results from three-dimensional (3-D) numerical simulations investigating the magnetohydrodynamics of cloud-wind interactions. The initial cloud is spherical while the magnetic field is uniform and transverse to the cloud motion. A simplified analytical model that describes the magnetic energy evolution in front of the cloud is developed and compared with simulation results. In addition, it is found the interaction of the cloud with a magnetized interstellar medium (ISM) results in the formation of a highly structured magnetotail. The magnetic flux in the wake of the cloud organizes into flux ropes and a reconnection, current sheet is developed, as field lines of opposite polarity are brought close together near the symmetry axis. At the same time, magnetic pressure is strongly enhanced at the leading edge of the cloud from the stretching of the field lines that occurs there. This has an important dynamical effect on the subsequent evolution of the cloud, since some unstable modes tend to be strongl...
Parallel Processor for 3D Recovery from Optical Flow
Jose Hugo Barron-Zambrano
2009-01-01
Full Text Available 3D recovery from motion has received a major effort in computer vision systems in the recent years. The main problem lies in the number of operations and memory accesses to be performed by the majority of the existing techniques when translated to hardware or software implementations. This paper proposes a parallel processor for 3D recovery from optical flow. Its main feature is the maximum reuse of data and the low number of clock cycles to calculate the optical flow, along with the precision with which 3D recovery is achieved. The results of the proposed architecture as well as those from processor synthesis are presented.
Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver
Moustafa, Salli; Dutka Malen, Ivan; Plagne, Laurent; Ponçot, Angélique; Ramet, Pierre
2014-01-01
This paper describes the design and the performance of DOMINO, a 3D Cartesian SN solver that implements two nested levels of parallelism (multicore+SIMD) on shared memory computation nodes. DOMINO is written in C++, a multi-paradigm programming language that enables the use of powerful and generic parallel programming tools such as Intel TBB and Eigen. These two libraries allow us to combine multi-thread parallelism with vector operations in an efficient and yet portable way. As a result, DOM...
Parallel 3-D SN performance for DANTSYS/MPI on the Cray T3D
A data parallel version of the 3-D transport solver in DANTSYS has been in use on the SIMD CM-200's at LANL since 1994. This version typically obtains grind times of 150--200 nanoseconds on a 2,048 PE CM-200. The authors have now implemented a new message passing parallel version of DANTSYS, referred to as DANTSYS/MPI, on the 512 PE Cray T3D at Los Alamos. By taking advantage of the SPMD architecture of the Cray T3D, as well as its low latency communications network, they have managed to achieve grind times of less than 10 nanoseconds on real problems. DANTSYS/MPI is fully accelerated using DSA on both the inner and outer iterations. This paper describes the implementation of DANTSYS/MPI on the Cray T3D, and presents two simple performance models for the transport sweep which accurately predict the grind time as a function of the number of PE's and problem size, or scalability
3D hybrid and MHD/particle simulations of field-reversed configurations
A nonlinear 3D code in cylindrical geometry is being developed for the stability studies of FRC. Two numerical schemes have been implemented: a hybrid scheme with particle ions and fluid electrons, and MHD/particle scheme in which the background plasma is described by MHD equations. And energetic ions are treated via particle simulations. The MHD equations are advanced on a finite-difference mesh in a cylindrical coordinate system, while particle pushing is done on 3D Cartesian grids. Full ion dynamics is retained in order to include large-orbit effects (with s∼1), which are important for the tilt mode stabilization in FRC. Also, in contrast to the previous work, δf method is utilized to reduce numerical noise in the simulations. The code has been benchmarked against previous MHD simulation of tilting instability in FRC. It was found that rigid rotation reduces the growth rate, but does not stabilize the mode even for rotation rates equal to the Alfven time. Sheared rotation is found to be destabilizing for the velocity profile considered. Simulations with a fast ion beam with 1 % of the bulk ion density and s∼3 did not show a reduction in growth rate of the tilting instability. (author)
Trapping Solids at the Inner Edge of the Dead Zone: 3-D Global MHD Simulations
Dzyurkevich, Natalia; Flock, Mario; Turner, Neal J.; Klahr, Hubert; Henning, Thomas
2010-01-01
The poorly-ionized interior of the protoplanetary disk is the location where dust coagulation processes may be most efficient. However even here, planetesimal formation may be limited by the loss of solid material through radial drift, and by collisional fragmentation of the particles. Our aim is to investigate the possibility that solid particles are trapped at local pressure maxima in the dynamically evolving disk. We perform the first 3-D global non-ideal MHD calculations of the disk treat...
Parallel Optimization of 3D Cardiac Electrophysiological Model Using GPU
Yong Xia
2015-01-01
Full Text Available Large-scale 3D virtual heart model simulations are highly demanding in computational resources. This imposes a big challenge to the traditional computation resources based on CPU environment, which already cannot meet the requirement of the whole computation demands or are not easily available due to expensive costs. GPU as a parallel computing environment therefore provides an alternative to solve the large-scale computational problems of whole heart modeling. In this study, using a 3D sheep atrial model as a test bed, we developed a GPU-based simulation algorithm to simulate the conduction of electrical excitation waves in the 3D atria. In the GPU algorithm, a multicellular tissue model was split into two components: one is the single cell model (ordinary differential equation and the other is the diffusion term of the monodomain model (partial differential equation. Such a decoupling enabled realization of the GPU parallel algorithm. Furthermore, several optimization strategies were proposed based on the features of the virtual heart model, which enabled a 200-fold speedup as compared to a CPU implementation. In conclusion, an optimized GPU algorithm has been developed that provides an economic and powerful platform for 3D whole heart simulations.
A parallel sweeping preconditioner for heterogeneous 3D Helmholtz equations
Poulson, Jack; Engquist, Björn; Li, Siwei; Ying, Lexing
2012-01-01
A parallelization of a sweeping preconditioner for 3D Helmholtz equations without large cavities is introduced and benchmarked for several challenging velocity models. The setup and application costs of the sequential preconditioner are shown to be O({\\gamma}^2 N^{4/3}) and O({\\gamma} N log N), where {\\gamma}({\\omega}) denotes the modestly frequency-dependent number of grid points per Perfectly Matched Layer. Several computational and memory improvements are introduced relative to using black...
3D MHD Jet in a Non-Uniform Magnetic Field
Huang Hulin; Han Dong
2005-01-01
The purpose of this paper is to present a two-phase 3D magnetohydrodynamics (MHD) flow model that combines the volume of fluid (VOF) method with the technique derived from induced-magnetic-field equations for liquid metal free surface MHD-jet-flow. Analogy between the induced-magnetic-filed equation and the conventional computational fluid dynamics (CFD) equation is made, so that the equation can be conveniently accounted for by CFD. A penalty factor numerical method is introduced in order to force the local divergence-free condition of the magnetic fields and an extension of the void insulating calculation domain is applied to ensure that the induced-magnetic field at its boundaries is null. These simulation results for lithium liquid metal jets under magnetic field configurations of Magnetic Torus (Mtor) and National Spherical Torus Experiment (NSTX) outboard divertor have shown that three dimensional jet can not be annihilated by magnetic braking and its cross-section will deform in such a way that the momentum flux of the jet is conserved. 3D MHD effects from a magnetic field gradient cause return currents to interact with applied magnetic fields and produce unfavorable Lorentz forces.Under 3D applied non-uniform magnetic fields of the divertor, unfavorable Lorentz forces lead to a substantial change in flow pattern and a reduction in flow velocity, with the jet cross-section moving to one side of the jet space. These critical phenomena can not be revealed by 2D models.
Parallel acquisition of 3D-HA(CA)NH and 3D-HACACO spectra
Reddy, Jithender G.; Hosur, Ramakrishna V., E-mail: hosur@tifr.res.in [Tata Institute of Fundamental Research, Department of Chemical Sciences (India)
2013-06-15
We present here an NMR pulse sequence with 5 independent incrementable time delays within the frame of a 3-dimensional experiment, by incorporating polarization sharing and dual receiver concepts. This has been applied to directly record 3D-HA(CA)NH and 3D-HACACO spectra of proteins simultaneously using parallel detection of {sup 1}H and {sup 13}C nuclei. While both the experiments display intra-residue backbone correlations, the 3D-HA(CA)NH provides also sequential 'i - 1 {yields} i' correlation along the {sup 1}H{alpha} dimension. Both the spectra contain special peak patterns at glycine locations which serve as check points during the sequential assignment process. The 3D-HACACO spectrum contains, in addition, information on prolines and side chains of residues having H-C-CO network (i.e., {sup 1}H{beta}, {sup 13}C{beta} and {sup 13}CO{gamma} of Asp and Asn, and {sup 1}H{gamma}, {sup 13}C{gamma} and {sup 13}CO{delta} of Glu and Gln), which are generally absent in most conventional proton detected experiments.
Parallel acquisition of 3D-HA(CA)NH and 3D-HACACO spectra
We present here an NMR pulse sequence with 5 independent incrementable time delays within the frame of a 3-dimensional experiment, by incorporating polarization sharing and dual receiver concepts. This has been applied to directly record 3D-HA(CA)NH and 3D-HACACO spectra of proteins simultaneously using parallel detection of 1H and 13C nuclei. While both the experiments display intra-residue backbone correlations, the 3D-HA(CA)NH provides also sequential ‘i − 1 → i’ correlation along the 1Hα dimension. Both the spectra contain special peak patterns at glycine locations which serve as check points during the sequential assignment process. The 3D-HACACO spectrum contains, in addition, information on prolines and side chains of residues having H–C–CO network (i.e., 1Hβ, 13Cβ and 13COγ of Asp and Asn, and 1Hγ, 13Cγ and 13COδ of Glu and Gln), which are generally absent in most conventional proton detected experiments.
FISH: A 3D parallel MHD code for astrophysical applications
Kaeppeli, R; Scheidegger, S; Pen, U -L; Liebendörfer, M
2009-01-01
FISH is a fast and simple ideal magneto-hydrodynamics code that scales to ~10 000 processes for a Cartesian computational domain of ~1000^3 cells. The simplicity of FISH has been achieved by the rigorous application of the operator splitting technique, while second order accuracy is maintained by the symmetric ordering of the operators. Between directional sweeps, the three-dimensional data is rotated in memory so that the sweep is always performed in a cache-efficient way along the direction of contiguous memory. Hence, the code only requires a one-dimensional description of the conservation equations to be solved. This approach also enable an elegant novel parallelisation of the code that is based on persistent communications with MPI for cubic domain decomposition on machines with distributed memory. This scheme is then combined with an additional OpenMP parallelisation of different sweeps that can take advantage of clusters of shared memory. We document the detailed implementation of a second order TVD ad...
3D MHD free surface fluid flow simulation based on magnetic-field induction equations
The purpose of this paper is to present our recent efforts on 3D MHD model development and our results based on the technique derived from induced-magnetic-field equations. Two important features are utilized in our numerical method to obtain convergent solutions. First, a penalty factor is introduced in order to force the local divergence free condition of the magnetic fields. The second is that we extend the insulating wall thickness to ensure that the induced magnetic field at its boundaries is null. These simulation results for lithium film free surface flows under NSTX outboard mid-plane magnetic field configurations have shown that 3D MHD effects from a surface normal field gradient cause return currents to interact with surface normal fields and produce unfavorable MHD forces. This leads to a substantial change in flow pattern and a reduction in flow velocity, with most of the flow spilling over one side of the chute. These critical phenomena can not be revealed by 2D models. Additionally, a design which overcomes these undesired flow characteristics is obtained
Parallel PAB3D: Experiences with a Prototype in MPI
Guerinoni, Fabio; Abdol-Hamid, Khaled S.; Pao, S. Paul
1998-01-01
PAB3D is a three-dimensional Navier Stokes solver that has gained acceptance in the research and industrial communities. It takes as computational domain, a set disjoint blocks covering the physical domain. This is the first report on the implementation of PAB3D using the Message Passing Interface (MPI), a standard for parallel processing. We discuss briefly the characteristics of tile code and define a prototype for testing. The principal data structure used for communication is derived from preprocessing "patching". We describe a simple interface (COMMSYS) for MPI communication, and some general techniques likely to be encountered when working on problems of this nature. Last, we identify levels of improvement from the current version and outline future work.
Shared memory parallelism for 3D cartesian discrete ordinates solver
This paper describes the design and the performance of DOMINO, a 3D Cartesian SN solver that implements two nested levels of parallelism (multi-core + SIMD - Single Instruction on Multiple Data) on shared memory computation nodes. DOMINO is written in C++, a multi-paradigm programming language that enables the use of powerful and generic parallel programming tools such as Intel TBB and Eigen. These two libraries allow us to combine multi-thread parallelism with vector operations in an efficient and yet portable way. As a result, DOMINO can exploit the full power of modern multi-core processors and is able to tackle very large simulations, that usually require large HPC clusters, using a single computing node. For example, DOMINO solves a 3D full core PWR eigenvalue problem involving 26 energy groups, 288 angular directions (S16), 46*106 spatial cells and 1*1012 DoFs within 11 hours on a single 32-core SMP node. This represents a sustained performance of 235 GFlops and 40.74% of the SMP node peak performance for the DOMINO sweep implementation. The very high Flops/Watt ratio of DOMINO makes it a very interesting building block for a future many-nodes nuclear simulation tool. (authors)
Parallel FEM simulation of 3-D crack propagation
Full text: Crack propagation simulation is an important topic in many fields, e.g., aeronautical engineering, material sciences, and geophysics. This type of simulation requires a high computational power, mainly at three-dimensional mesh generation and structural analysis steps. These steps usually spend a large amount of computing time and machine resources. The main objective of this work is to provide a fast and accurate system for crack growth simulation in three-dimensional models. The main idea of the methodology presented is to parallelize mesh generation and structural analysis procedures, and to integrate these procedures into a computational environment able to perform automatic arbitrary crack propagation. A parallel mesh generation algorithm has been developed. This algorithm is capable of generating three-dimensional meshes of tetrahedral elements in arbitrary domains with one or multiple embedded cracks. A finite element method program called FEMOOP has been adapted to implement the parallel features. The parallel strategy to solve the set of linear equations is based on an element-by-element scheme in conjunction with a gradient iterative solution. A program called FRANC3D, which is completely integrated with other components of the system, performs crack propagation and geometry updates. The entire system is described in details and a set of parallel simulations of crack propagation are presented to show the reliability of the system. Refs. 4 (author)
3D Simulations of MHD Jet Propagation Through Uniform and Stratified External Environments
O'Neill, S. M.; Tregillis, I. L.; Jones, T. W.; Ryu, Dongsu
2005-01-01
We present a set of high-resolution 3D MHD simulations of steady light, supersonic jets, exploring the influence of jet Mach number and the ambient medium on jet propagation and energy deposition over long distances. The results are compared to simple self-similar scaling relations for the morphological evolution of jet-driven structures and to previously published 2D simulations. For this study we simulated the propagation of light jets with internal Mach numbers 3 and 12 to lengths exceedin...
Nanoflare statistics in an active region 3D MHD coronal model
Bingert, Sven
2012-01-01
Context. We investigate the statistics of the spatial and temporal distribution of the coronal heating in a three-dimensional magneto- hydrodynamical (3D MHD) model. The model describes the temporal evolution of the corona above an observed active region. The model is driven by photospheric granular motions which braid the magnetic field lines. This induces currents and their dissipation heats the plasma. We evaluate the transient heating as subsequent heating events and analyze their statistics. The results are then interpreted in the context of observed flare statistics and coronal heating mechanisms. Methods. To conduct the numerical experiment we use a high order finite difference code which solves the partial differential equations for the conservation of mass, the momentum and energy balance, and the induction equation. The energy balance includes the Spitzer heat conduction and the optical thin radiative loss in the corona. Results. The temporal and spatial distribution of the Ohmic heating in the 3D M...
Effect of magnetic perturbations on the 3D MHD self-organization of shaped tokamak plasmas
Bonfiglio, D; Veranda, M; Chacón, L; Escande, D F
2016-01-01
The effect of magnetic perturbations (MPs) on the helical self-organization of shaped tokamak plasmas is discussed in the framework of the nonlinear 3D MHD model. Numerical simulations performed in toroidal geometry with the \\textsc{pixie3d} code [L. Chac\\'on, Phys. Plasmas {\\bf 15}, 056103 (2008)] show that $n=1$ MPs significantly affect the spontaneous quasi-periodic sawtoothing activity of such plasmas. In particular, the mitigation of sawtooth oscillations is induced by $m/n=1/1$ and $2/1$ MPs. These numerical findings provide a confirmation of previous circular tokamak simulations, and are in agreement with tokamak experiments in the RFX-mod and DIII-D devices. Sawtooth mitigation via MPs has also been observed in reversed-field pinch simulations and experiments. The effect of MPs on the stochastization of the edge magnetic field is also discussed.
Capabilities of a Global 3D MHD Model for Monitoring Extremely Fast CMEs
Wu, C. C.; Plunkett, S. P.; Liou, K.; Socker, D. G.; Wu, S. T.; Wang, Y. M.
2015-12-01
Since the start of the space era, spacecraft have recorded many extremely fast coronal mass ejections (CMEs) which have resulted in severe geomagnetic storms. Accurate and timely forecasting of the space weather effects of these events is important for protecting expensive space assets and astronauts and avoiding communications interruptions. Here, we will introduce a newly developed global, three-dimensional (3D) magnetohydrodynamic (MHD) model (G3DMHD). The model takes the solar magnetic field maps at 2.5 solar radii (Rs) and intepolates the solar wind plasma and field out to 18 Rs using the algorithm of Wang and Sheeley (1990, JGR). The output is used as the inner boundary condition for a 3D MHD model. The G3DMHD model is capable of simulating (i) extremely fast CME events with propagation speeds faster than 2500 km/s; and (ii) multiple CME events in sequence or simultaneously. We will demonstrate the simulation results (and comparison with in-situ observation) for the fastest CME in record on 23 July 2012, the shortest transit time in March 1976, and the well-known historic Carrington 1859 event.
HPC parallel programming model for gyrokinetic MHD simulation
The 3-dimensional gyrokinetic PIC (particle-in-cell) code for MHD simulation, Gpic-MHD, was installed on SR16000 (“Plasma Simulator”), which is a scalar cluster system consisting of 8,192 logical cores. The Gpic-MHD code advances particle and field quantities in time. In order to distribute calculations over large number of logical cores, the total simulation domain in cylindrical geometry was broken up into NDD-r × NDD-z (number of radial decomposition times number of axial decomposition) small domains including approximately the same number of particles. The axial direction was uniformly decomposed, while the radial direction was non-uniformly decomposed. NRP replicas (copies) of each decomposed domain were used (“particle decomposition”). The hybrid parallelization model of multi-threads and multi-processes was employed: threads were parallelized by the auto-parallelization and NDD-r × NDD-z × NRP processes were parallelized by MPI (message-passing interface). The parallelization performance of Gpic-MHD was investigated for the medium size system of Nr × Nθ × Nz = 1025 × 128 × 128 mesh with 4.196 or 8.192 billion particles. The highest speed for the fixed number of logical cores was obtained for two threads, the maximum number of NDD-z, and optimum combination of NDD-r and NRP. The observed optimum speeds demonstrated good scaling up to 8,192 logical cores. (author)
Introducing ZEUS-MP A 3D, Parallel, Multiphysics Code for Astrophysical Fluid Dynamics
Norman, M L
2000-01-01
We describe ZEUS-MP: a Multi-Physics, Massively-Parallel, Message-Passing code for astrophysical fluid dynamics simulations in 3 dimensions. ZEUS-MP is a follow-on to the sequential ZEUS-2D and ZEUS-3D codes developed and disseminated by the Laboratory for Computational Astrophysics (lca.ncsa.uiuc.edu) at NCSA. V1.0 released 1/1/2000 includes the following physics modules: ideal hydrodynamics, ideal MHD, and self-gravity. Future releases will include flux-limited radiation diffusion, thermal heat conduction, two-temperature plasma, and heating and cooling functions. The covariant equations are cast on a moving Eulerian grid with Cartesian, cylindrical, and spherical polar coordinates currently supported. Parallelization is done by domain decomposition and implemented in F77 and MPI. The code is portable across a wide range of platforms from networks of workstations to massively parallel processors. Some parallel performance results are presented as well as an application to turbulent star formation.
3D Neutronic Analysis in MHD Calculations at ARIES-ST Fusion Reactors Systems
Hançerliogulları, Aybaba; Cini, Mesut
2013-10-01
In this study, we developed new models for liquid wall (FW) state at ARIES-ST fusion reactor systems. ARIES-ST is a 1,000 MWe fusion reactor system based on a low aspect ratio ST plasma. In this article, we analyzed the characteristic properties of magnetohydrodynamics (MHD) and heat transfer conditions by using Monte-Carlo simulation methods (ARIES Team et al. in Fusion Eng Des 49-50:689-695, 2000; Tillack et al. in Fusion Eng Des 65:215-261, 2003) . In fusion applications, liquid metals are traditionally considered to be the best working fluids. The working liquid must be a lithium-containing medium in order to provide adequate tritium that the plasma is self-sustained and that the fusion is a renewable energy source. As for Flibe free surface flows, the MHD effects caused by interaction with the mean flow is negligible, while a fairly uniform flow of thick can be maintained throughout the reactor based on 3-D MHD calculations. In this study, neutronic parameters, that is to say, energy multiplication factor radiation, heat flux and fissile fuel breeding were researched for fusion reactor with various thorium and uranium molten salts. Sufficient tritium amount is needed for the reactor to work itself. In the tritium breeding ratio (TBR) >1.05 ARIES-ST fusion model TBR is >1.1 so that tritium self-sufficiency is maintained for DT fusion systems (Starke et al. in Fusion Energ Des 84:1794-1798, 2009; Najmabadi et al. in Fusion Energ Des 80:3-23, 2006).
A novel code for numerical 3-D MHD studies of CME expansion
J. Kleimann
2009-03-01
Full Text Available A recent third-order, essentially non-oscillatory central scheme to advance the equations of single-fluid magnetohydrodynamics (MHD in time has been implemented into a new numerical code. This code operates on a 3-D Cartesian, non-staggered grid, and is able to handle shock-like gradients without producing spurious oscillations.
To demonstrate the suitability of our code for the simulation of coronal mass ejections (CMEs and similar heliospheric transients, we present selected results from test cases and perform studies of the solar wind expansion during phases of minimum solar activity. We can demonstrate convergence of the system into a stable Parker-like steady state for both hydrodynamic and MHD winds. The model is subsequently applied to expansion studies of CME-like plasma bubbles, and their evolution is monitored until a stationary state similar to the initial one is achieved. In spite of the model's (current simplicity, we can confirm the CME's nearly self-similar evolution close to the Sun, thus highlighting the importance of detailed modelling especially at small heliospheric radii.
Additionally, alternative methods to implement boundary conditions at the coronal base, as well as strategies to ensure a solenoidal magnetic field, are discussed and evaluated.
Quasi 3D ECE imaging system for study of MHD instabilities in KSTAR.
Yun, G S; Lee, W; Choi, M J; Lee, J; Kim, M; Leem, J; Nam, Y; Choe, G H; Park, H K; Park, H; Woo, D S; Kim, K W; Domier, C W; Luhmann, N C; Ito, N; Mase, A; Lee, S G
2014-11-01
A second electron cyclotron emission imaging (ECEI) system has been installed on the KSTAR tokamak, toroidally separated by 1/16th of the torus from the first ECEI system. For the first time, the dynamical evolutions of MHD instabilities from the plasma core to the edge have been visualized in quasi-3D for a wide range of the KSTAR operation (B0 = 1.7∼3.5 T). This flexible diagnostic capability has been realized by substantial improvements in large-aperture quasi-optical microwave components including the development of broad-band polarization rotators for imaging of the fundamental ordinary ECE as well as the usual 2nd harmonic extraordinary ECE. PMID:25430233
Quasi 3D ECE imaging system for study of MHD instabilities in KSTAR
Yun, G. S., E-mail: gunsu@postech.ac.kr; Choi, M. J.; Lee, J.; Kim, M.; Leem, J.; Nam, Y.; Choe, G. H. [Department of Physics, Pohang University of Science and Technology, Pohang 790-784 (Korea, Republic of); Lee, W.; Park, H. K. [Ulsan National Institute of Science and Technology, Ulsan 689-798 (Korea, Republic of); Park, H.; Woo, D. S.; Kim, K. W. [School of Electrical Engineering, Kyungpook National University, Daegu 702-701 (Korea, Republic of); Domier, C. W.; Luhmann, N. C. [Department of Electrical and Computer Engineering, University of California, Davis, California 95616 (United States); Ito, N. [KASTEC, Kyushu University, Kasuga-shi, Fukuoka 812-8581 (Japan); Mase, A. [Ube National College of Technology, Ube-shi, Yamaguchi 755-8555 (Japan); Lee, S. G. [National Fusion Research Institute, Daejeon 305-333 (Korea, Republic of)
2014-11-15
A second electron cyclotron emission imaging (ECEI) system has been installed on the KSTAR tokamak, toroidally separated by 1/16th of the torus from the first ECEI system. For the first time, the dynamical evolutions of MHD instabilities from the plasma core to the edge have been visualized in quasi-3D for a wide range of the KSTAR operation (B{sub 0} = 1.7∼3.5 T). This flexible diagnostic capability has been realized by substantial improvements in large-aperture quasi-optical microwave components including the development of broad-band polarization rotators for imaging of the fundamental ordinary ECE as well as the usual 2nd harmonic extraordinary ECE.
DPGL: The Direct3D9-based Parallel Graphics Library for Multi-display Environment
Zhen Liu; Jiao-Ying Shi
2007-01-01
The emergence of high performance 3D graphics cards has opened the way to PC clusters for high performance multidisplay environment. In order to exploit the rendering ability of PC clusters, we should design appropriate parallel rendering algorithms and parallel graphics library interfaces. Due to the rapid development of Direct3D, we bring forward DPGL, the Direct3D9-based parallel graphics library in D3DPR parallel rendering system, which implements Direct3D9 interfaces to support existing Direct3D9 application parallelization with no modification. Based on the parallelism analysis of Direct3D9 rendering pipeline, we briefly introduce D3DPR parallel rendering system. DPGL is the fundamental component of D3DPR. After presenting DPGL three layers architecture,we discuss the rendering resource interception and management. Finally, we describe the design and implementation of DPGL in detail,including rendering command interception layer, rendering command interpretation layer and rendering resource parallelization layer.
Scaling laws of coronal loops compared to a 3D MHD model of an Active Region
Bourdin, Philippe-A; Peter, Hardi
2016-01-01
Context. The structure and heating of coronal loops are investigated since decades. Established scaling laws relate fundamental quantities like the loop apex temperature, pressure, length, and the coronal heating. Aims. We test such scaling laws against a large-scale 3D MHD model of the Solar corona, which became feasible with nowadays high-performance computing. Methods. We drive an active region simulation a with photospheric observations and found strong similarities to the observed coronal loops in X-rays and EUV wavelength. A 3D reconstruction of stereoscopic observations showed that our model loops have a realistic spatial structure. We compare scaling laws to our model data extracted along an ensemble of field lines. Finally, we fit a new scaling law that represents well hot loops and also cooler structures, which was not possible before only based on observations. Results. Our model data gives some support for scaling laws that were established for hot and EUV-emissive coronal loops. For the RTV scali...
Skála, J.; Baruffa, F.; Büchner, J.; Rampp, M.
2015-08-01
Context. The numerical simulation of turbulence and flows in almost ideal astrophysical plasmas with large Reynolds numbers motivates the implementation of magnetohydrodynamical (MHD) computer codes with low resistivity. They need to be computationally efficient and scale well with large numbers of CPU cores, allow obtaining a high grid resolution over large simulation domains, and be easily and modularly extensible, for instance, to new initial and boundary conditions. Aims: Our aims are the implementation, optimization, and verification of a computationally efficient, highly scalable, and easily extensible low-dissipative MHD simulation code for the numerical investigation of the dynamics of astrophysical plasmas with large Reynolds numbers in three dimensions (3D). Methods: The new GOEMHD3 code discretizes the ideal part of the MHD equations using a fast and efficient leap-frog scheme that is second-order accurate in space and time and whose initial and boundary conditions can easily be modified. For the investigation of diffusive and dissipative processes the corresponding terms are discretized by a DuFort-Frankel scheme. To always fulfill the Courant-Friedrichs-Lewy stability criterion, the time step of the code is adapted dynamically. Numerically induced local oscillations are suppressed by explicit, externally controlled diffusion terms. Non-equidistant grids are implemented, which enhance the spatial resolution, where needed. GOEMHD3 is parallelized based on the hybrid MPI-OpenMP programing paradigm, adopting a standard two-dimensional domain-decomposition approach. Results: The ideal part of the equation solver is verified by performing numerical tests of the evolution of the well-understood Kelvin-Helmholtz instability and of Orszag-Tang vortices. The accuracy of solving the (resistive) induction equation is tested by simulating the decay of a cylindrical current column. Furthermore, we show that the computational performance of the code scales very
Flock, M.; Dzyurkevich, N.; Klahr, H.; Mignone, A.
2010-06-01
We assess the suitability of various numerical MHD algorithms for astrophysical accretion disk simulations with the PLUTO code. The well-studied linear growth of the magneto-rotational instability is used as the benchmark test for a comparison between the implementations within PLUTO and against the ZeusMP code. The results demonstrate the importance of using an upwind reconstruction of the electro-motive force (EMF) in the context of a constrained transport scheme, which is consistent with plane-parallel, grid-aligned flows. In contrast, constructing the EMF from the simple average of the Godunov fluxes leads to a numerical instability and the unphysical growth of the magnetic energy. We compare the results from 3D global calculations using different MHD methods against the analytical solution for the linear growth of the MRI, and discuss the effect of numerical dissipation. The comparison identifies a robust and accurate code configuration that is vital for realistic modeling of accretion disk processes.
3D relaxation MHD modeling with FOI-PERFECT code for electromagnetically driven HED systems
Wang, Ganghua; Duan, Shuchao; Xie, Weiping; Kan, Mingxian; Institute of Fluid Physics Collaboration
2015-11-01
One of the challenges in numerical simulations of electromagnetically driven high energy density (HED) systems is the existence of vacuum region. The electromagnetic part of the conventional model adopts the magnetic diffusion approximation (magnetic induction model). The vacuum region is approximated by artificially increasing the resistivity. On one hand the phase/group velocity is superluminal and hence non-physical in the vacuum region, on the other hand a diffusion equation with large diffusion coefficient can only be solved by implicit scheme. Implicit method is usually difficult to parallelize and converge. A better alternative is to solve the full electromagnetic equations for the electromagnetic part. Maxwell's equations coupled with the constitutive equation, generalized Ohm's law, constitute a relaxation model. The dispersion relation is given to show its transition from electromagnetic propagation in vacuum to resistive MHD in plasma in a natural way. The phase and group velocities are finite for this system. A better time stepping is adopted to give a 3rd full order convergence in time domain without the stiff relaxation term restriction. Therefore it is convenient for explicit & parallel computations. Some numerical results of FOI-PERFECT code are also given. Project supported by the National Natural Science Foundation of China (Grant No. 11172277,11205145).
Cooper, W. A.; Graves, J. P.; Duval, B. P.; Porte, L.; Reimerdes, H.; Sauter, O.; Tran, T.-M.
2015-12-01
> Novel free boundary magnetohydrodynamic equilibrium states with spontaneous three-dimensional (3-D) deformations of the plasma-vacuum interface are computed. The structures obtained look like saturated ideal external kink/peeling modes. Large edge pressure gradients yield toroidal mode number distortions when the edge bootstrap current is large and higher corrugations when this current is small. Linear ideal MHD stability analyses confirm the nonlinear saturated ideal kink equilibrium states produced and we can identify the Pfirsch-Schlüter current as the main linear instability driving mechanism when the edge pressure gradient is large. The dominant non-axisymmetric component of this Pfirsch-Schlüter current drives a near resonant helical parallel current density ribbon that aligns with the near vanishing magnetic shear region caused by the edge bootstrap current. This current ribbon is a manifestation of the outer mode previously found on JET (Solano 2010). We claim that the equilibrium corrugations describe structures that are commonly observed in quiescent H-mode tokamak discharges.
Turbulence and Steady Flows in 3D Global Stratified MHD Simulations of Accretion Disks
Flock, M; Klahr, H; Turner, N J; Henning, Th
2011-01-01
We present full 2 Pi global 3-D stratified MHD simulations of accretion disks. We interpret our results in the context of proto-planetary disks. We investigate the turbulence driven by the magneto-rotational instability (MRI) using the PLUTO Godunov code in spherical coordinates with the accurate and robust HLLD Riemann solver. We follow the turbulence for more than 1500 orbits at the innermost radius of the domain to measure the overall strength of turbulent motions and the detailed accretion flow pattern. We find that regions within two scale heights of the midplane have a turbulent Mach number of about 0.1 and a magnetic pressure two to three orders of magnitude less than the gas pressure, while outside three scale heights the magnetic pressure equals or exceeds the gas pressure and the turbulence is transonic, leading to large density fluctuations. The strongest large-scale density disturbances are spiral density waves, and the strongest of these waves has m=5. No clear meridional circulation appears in t...
3D MHD Simulations of Planet Migration in Turbulent Stratified Disks
Uribe, Ana; Flock, Mario; Henning, Thomas
2011-01-01
We performed 3D MHD simulations of planet migration in stratified disks using the Godunov code PLUTO, where the disk is turbulent due to the magnetorotational instability. We study the migration for planets with different planet-star mass ratios $q=M_{p}/M_{s}$. In agreement with previous studies, for the low-mass planet cases ($q=5\\times10^{-6}$ and $10^{-5}$), migration is dominated by random fluctuations in the torque. For a Jupiter-mass planet $(q=M_{p}/M_{s}=10^{-3}$ for $M_{s}=1M_{\\odot})$, we find a reduction of the magnetic stress inside the orbit of the planet and around the gap region. After an initial stage where the torque on the planet is positive, it reverses and we recover migration rates similar to those found in disks where the turbulent viscosity is modelled by an $\\alpha$ viscosity. For the intermediate-mass planets ($q=5\\times10^{-5}, 10^{-4}$ and $2\\times10^{-4}$) we find a new and so far unexpected behavior. In some cases they experience sustained and systematic outwards migration for th...
Trapping Solids at the Inner Edge of the Dead Zone: 3-D Global MHD Simulations
Dzyurkevich, Natalia; Turner, Neal J; Klahr, Hubert; Henning, Thomas
2010-01-01
The poorly-ionized interior of the protoplanetary disk is the location where dust coagulation processes may be most efficient. However even here, planetesimal formation may be limited by the loss of solid material through radial drift, and by collisional fragmentation of the particles. Our aim is to investigate the possibility that solid particles are trapped at local pressure maxima in the dynamically evolving disk. We perform the first 3-D global non-ideal MHD calculations of the disk treating the turbulence driven by the magneto-rotational instability. The domain contains an inner MRI-active region near the young star and an outer midplane dead zone, with the transition between the two modeled by a sharp increase in the magnetic diffusivity. The azimuthal magnetic fields generated in the active zone oscillate over time, changing sign about every 150 years. We thus observe the radial structure of the `butterfly pattern' seen previously in local shearing-box simulations. The mean magnetic field diffuses from...
Coronal energy input and dissipation in a solar active region 3D MHD model
Bourdin, Philippe-A; Peter, Hardi
2015-01-01
Context. We have conducted a 3D MHD simulation of the solar corona above an active region in full scale and high resolution, which shows coronal loops, and plasma flows within them, similar to observations. Aims. We want to find the connection between the photospheric energy input by field-line braiding with the coronal energy conversion by Ohmic dissipation of induced currents. Methods. To this end we compare the coronal energy input and dissipation within our simulation domain above different fields of view, e.g. for a small loops system in the active region (AR) core. We also choose an ensemble of field lines to compare, e.g., the magnetic energy input to the heating per particle along these field lines. Results. We find an enhanced Ohmic dissipation of currents in the corona above areas that also have enhanced upwards-directed Poynting flux. These regions coincide with the regions where hot coronal loops within the AR core are observed. The coronal density plays a role in estimating the coronal temperatur...
Radiative 3D MHD simulations of the spontaneous small-scale eruptions in the solar atmosphere
Kitiashvili, Irina N.
2015-08-01
Studying non-linear turbulent dynamics of the solar atmosphere is important for understanding mechanism of the solar and stellar brightness variations. High-resolution observations of the quiet Sun reveal ubiquitous distributions of high-speed jets, which are transport mass and energy into the solar corona and feeding the solar wind. However, the origin of these eruption events is still unknown. Using 3D realistic MHD numerical simulations we find that small-scale eruptions are produced by ubiquitous magnetized vortex tubes generated by the Sun's turbulent convection in subsurface layers. The swirling vortex tubes (resembling tornadoes) penetrate into the solar atmosphere, capture and stretch background magnetic field, and push the surrounding material up, generating shocks. Our simulations reveal complicated high-speed flow patterns and thermodynamic and magnetic structure in the erupting vortex tubes and shows that the eruptions are initiated in the subsurface layers and are driven by high-pressure gradients in the subphotosphere and photosphere and by the Lorentz force in the higher atmosphere layers. I will discuss about properties of these eruptions, their effects on brightness and spectral variations and comparison with observations.
Linearly perturbed MHD equilibria and 3D eddy current coupling via the control surface method
Portone, A.; Villone, F.; Liu, Y.; Albanese, R.; Rubinacci, G.
2008-08-01
In this paper, a coupling strategy based on the control surface concept is used to self-consistently couple linear MHD solvers to 3D codes for the eddy current computation of eddy currents in the metallic structures surrounding the plasma. The coupling is performed by assuming that the plasma inertia (and, with it, all Alfven wave-like phenomena) can be neglected on the time scale of interest, which is dictated by the relevant electromagnetic time of the metallic structures. As is shown, plasma coupling with the metallic structures results in perturbations to the inductance matrix operator. In particular, by adopting the Fourier decomposition in poloidal and toroidal modes, it turns out that each toroidal mode can be associated with a matrix (additively) perturbing the inductance matrix that commonly describes the magnetic coupling of currents in vacuum. In this way, the treatment of resistive wall modes instabilities of various toroidal mode numbers and their possible cross-talk through the currents induced in the metallic structures can be easily studied.
3D-MHD simulations of an accretion disk with star-disk boundary layer
Steinacker, A; Steinacker, Adriane; Papaloizou, John C.B.
2002-01-01
We present global 3D MHD simulations of geometrically thin but unstratified accretion disks in which a near Keplerian disk rotates between two bounding regions with initial rotation profiles that are stable to the MRI. The inner region models the boundary layer between the disk and an assumed more slowly rotating central, non magnetic star. We investigate the dynamical evolution of this system in response to initial vertical and toroidal fields imposed in a variety of domains contained within the near Keplerian disk. Cases with both non zero and zero net magnetic flux are considered and sustained dynamo activity found in runs for up to fifty orbital periods at the outer boundary of the near Keplerian disk. Simulations starting from fields with small radial scale and with zero net flux lead to the lowest levels of turbulence and smoothest variation of disk mean state variables. For our computational set up, average values of the Shakura & Sunyaev (1973) $\\alpha$ parameter in the Keplerian disk are typicall...
3D Tomography of MHD Fluctuations in the H-1NF Heliac
Haskey, S R; Seiwald, B; Howard, J
2014-01-01
A 3D tomographic reconstruction technique which does not rely on a set of radial basis functions is described for inversion of a set of limited-angle high-resolution 2D visible light emission projections (extended in the vertical and toroidal directions) of global MHD eigenmodes in the H-1NF heliac. This paper deals with some of the features and challenges that will arise in the application of tomographic imaging systems to fusion reactors, especially the strong shaping of optimised stellarator/heliotron configurations, and limited access in all types. The fluctuations are represented as a finite sum of Fourier modes characterised by toroidal and poloidal mode numbers having fixed amplitude and phase in a set of nested cylindrical flux volumes in Boozer space. The amplitudes and phases are calculated using iterative tomographic inversion techniques such as ART, SIRT and standard linear least-squares methods. The tomography is applied to synchronous camera images of singly charged carbon impurity ion emission ...
Parallel Hall effect from 3D single-component metamaterials
Kern, Christian; Kadic, Muamer; Wegener, Martin
2015-01-01
We propose a class of three-dimensional metamaterial architectures composed of a single doped semiconductor (e.g., n-Si) in air or vacuum that lead to unusual effective behavior of the classical Hall effect. Using an anisotropic structure, we numerically demonstrate a Hall voltage that is parallel---rather than orthogonal---to the external static magnetic-field vector ("parallel Hall effect"). The sign of this parallel Hall voltage can be determined by a structure parameter. Together with the...
Parallel Simulation of 3-D Turbulent Flow Through Hydraulic Machinery
徐宇; 吴玉林
2003-01-01
Parallel calculational methods were used to analyze incompressible turbulent flow through hydraulic machinery. Two parallel methods were used to simulate the complex flow field. The space decomposition method divides the computational domain into several sub-ranges. Parallel discrete event simulation divides the whole task into several parts according to their functions. The simulation results were compared with the serial simulation results and particle image velocimetry (PIV) experimental results. The results give the distribution and configuration of the complex vortices and illustrate the effectiveness of the parallel algorithms for numerical simulation of turbulent flows.
Parallel Hall effect from 3D single-component metamaterials
Kern, Christian; Wegener, Martin
2015-01-01
We propose a class of three-dimensional metamaterial architectures composed of a single doped semiconductor (e.g., n-Si) in air or vacuum that lead to unusual effective behavior of the classical Hall effect. Using an anisotropic structure, we numerically demonstrate a Hall voltage that is parallel---rather than orthogonal---to the external static magnetic-field vector ("parallel Hall effect"). The sign of this parallel Hall voltage can be determined by a structure parameter. Together with the previously demonstrated positive or negative orthogonal Hall voltage, we demonstrate four different sign combinations
Trapping solids at the inner edge of the dead zone: 3-D global MHD simulations
Dzyurkevich, N.; Flock, M.; Turner, N. J.; Klahr, H.; Henning, Th.
2010-06-01
Context. The poorly-ionized interior of the protoplanetary disk or “dead zone” is the location where dust coagulation processes may be most efficient. However even here, planetesimal formation may be limited by the loss of solid material through radial drift, and by collisional fragmentation of the particles. Both depend on the turbulent properties of the gas. Aims: Our aim here is to investigate the possibility that solid particles are trapped at local pressure maxima in the dynamically evolving disk. We perform the first 3-D global non-ideal magnetohydrodynamical (MHD) calculations of a section of the disk treating the turbulence driven by the magneto-rotational instability (MRI). Methods: We use the ZeusMP code with a fixed Ohmic resistivity distribution. The domain contains an inner MRI-active region near the young star and an outer midplane dead zone, with the transition between the two modeled by a sharp increase in the magnetic diffusivity. Results: The azimuthal magnetic fields generated in the active zone oscillate over time, changing sign about every 150 years. We thus observe the radial structure of the “butterfly pattern” seen previously in local shearing-box simulations. The mean magnetic field diffuses from the active zone into the dead zone, where the Reynolds stress nevertheless dominates, giving a residual α between 10-4 and 10-3. The greater total accretion stress in the active zone leads to a net reduction in the surface density, so that after 800 years an approximate steady state is reached in which a local radial maximum in the midplane pressure lies near the transition radius. We also observe the formation of density ridges within the active zone. Conclusions: The dead zone in our models possesses a mean magnetic field, significant Reynolds stresses and a steady local pressure maximum at the inner edge, where the outward migration of planetary embryos and the efficient trapping of solid material are possible.
A Parallel Sweeping Preconditioner for Heterogeneous 3D Helmholtz Equations
Poulson, Jack
2013-05-02
A parallelization of a sweeping preconditioner for three-dimensional Helmholtz equations without large cavities is introduced and benchmarked for several challenging velocity models. The setup and application costs of the sequential preconditioner are shown to be O(γ2N4/3) and O(γN logN), where γ(ω) denotes the modestly frequency-dependent number of grid points per perfectly matched layer. Several computational and memory improvements are introduced relative to using black-box sparse-direct solvers for the auxiliary problems, and competitive runtimes and iteration counts are reported for high-frequency problems distributed over thousands of cores. Two open-source packages are released along with this paper: Parallel Sweeping Preconditioner (PSP) and the underlying distributed multifrontal solver, Clique. © 2013 Society for Industrial and Applied Mathematics.
Parallel deterministic neutronics with AMR in 3D
Clouse, C.; Ferguson, J.; Hendrickson, C. [Lawrence Livermore National Lab., CA (United States)
1997-12-31
AMTRAN, a three dimensional Sn neutronics code with adaptive mesh refinement (AMR) has been parallelized over spatial domains and energy groups and runs on the Meiko CS-2 with MPI message passing. Block refined AMR is used with linear finite element representations for the fluxes, which allows for a straight forward interpretation of fluxes at block interfaces with zoning differences. The load balancing algorithm assumes 8 spatial domains, which minimizes idle time among processors.
3-D resistive MHD calculations for tokamak plasmas: beyond the simple reduced set of equations
Numerical studies of the resistive stability of tokamak plasmas in cylindrical geometry have been performed using: (1) the full set of resistive Magnetohydrodynamic (MHD) equations and (2) an extended version of the reduced set of resistive MHD equations including diamagnetic and electron temperature effects. In particular, the nonlinear interaction of tearing modes of many helicities has been investigated. The numerical results confirm many of the features uncovered previously using the simple reduced equations. (author)
Malapaka, Shiva Kumar; Mueller, Wolf-Christian [Max-Planck Institute for Plasma Physics, Boltzmannstrasse 2, D-85748 Garching bei Muenchen (Germany)
2013-09-01
Statistical properties of the Sun's photospheric turbulent magnetic field, especially those of the active regions (ARs), have been studied using the line-of-sight data from magnetograms taken by the Solar and Heliospheric Observatory and several other instruments. This includes structure functions and their exponents, flatness curves, and correlation functions. In these works, the dependence of structure function exponents ({zeta}{sub p}) of the order of the structure functions (p) was modeled using a non-intermittent K41 model. It is now well known that the ARs are highly turbulent and are associated with strong intermittent events. In this paper, we compare some of the observations from Abramenko et al. with the log-Poisson model used for modeling intermittent MHD turbulent flows. Next, we analyze the structure function data obtained from the direct numerical simulations (DNS) of homogeneous, incompressible 3D-MHD turbulence in three cases: sustained by forcing, freely decaying, and a flow initially driven and later allowed to decay (case 3). The respective DNS replicate the properties seen in the plots of {zeta}{sub p} against p of ARs. We also reproduce the trends and changes observed in intermittency in flatness and correlation functions of ARs. It is suggested from this analysis that an AR in the onset phase of a flare can be treated as a forced 3D-MHD turbulent system in its simplest form and that the flaring stage is representative of decaying 3D-MHD turbulence. It is also inferred that significant changes in intermittency from the initial onset phase of a flare to its final peak flaring phase are related to the time taken by the system to reach the initial onset phase.
Statistical properties of the Sun's photospheric turbulent magnetic field, especially those of the active regions (ARs), have been studied using the line-of-sight data from magnetograms taken by the Solar and Heliospheric Observatory and several other instruments. This includes structure functions and their exponents, flatness curves, and correlation functions. In these works, the dependence of structure function exponents (ζp) of the order of the structure functions (p) was modeled using a non-intermittent K41 model. It is now well known that the ARs are highly turbulent and are associated with strong intermittent events. In this paper, we compare some of the observations from Abramenko et al. with the log-Poisson model used for modeling intermittent MHD turbulent flows. Next, we analyze the structure function data obtained from the direct numerical simulations (DNS) of homogeneous, incompressible 3D-MHD turbulence in three cases: sustained by forcing, freely decaying, and a flow initially driven and later allowed to decay (case 3). The respective DNS replicate the properties seen in the plots of ζp against p of ARs. We also reproduce the trends and changes observed in intermittency in flatness and correlation functions of ARs. It is suggested from this analysis that an AR in the onset phase of a flare can be treated as a forced 3D-MHD turbulent system in its simplest form and that the flaring stage is representative of decaying 3D-MHD turbulence. It is also inferred that significant changes in intermittency from the initial onset phase of a flare to its final peak flaring phase are related to the time taken by the system to reach the initial onset phase
无
2009-01-01
An asynchronous and parallel time-marching method for three-dimensional (3D) time-dependent magnetohydrodynamic (MHD) simulation is used for large-scale solar wind simulation. It uses different local time steps in the corona and the heliosphere according to the local Courant-Friedrichs-Levy (CFL) conditions. The solar wind background with observed solar photospheric magnetic field as input is first presented. The simulation time for the background solar wind by using the asynchronous method is <1/6 of that by using the normal synchronous time-marching method with the same computation precision. Then, we choose the coronal mass ejection (CME) event of 13 November, 2003 as a test case. The time-dependent variations of the pressure and the velocity configured from a CME model at the inner boundary are applied to generate transient structures in order to study the dynamical interaction of a CME with the background solar wind flow between 1 and 230 Rs. This time-marching method is very effective in terms of computation time for large-scale 3D time-dependent numerical MHD problem. In this validation study, we find that this 3D MHD model, with the asynchronous and parallel time-marching method, provides a relatively satisfactory comparison with the ACE spacecraft obser- vations at L1 point.
Parallel processing for efficient 3D slope stability modelling
Marchesini, Ivan; Mergili, Martin; Alvioli, Massimiliano; Metz, Markus; Schneider-Muntau, Barbara; Rossi, Mauro; Guzzetti, Fausto
2014-05-01
We test the performance of the GIS-based, three-dimensional slope stability model r.slope.stability. The model was developed as a C- and python-based raster module of the GRASS GIS software. It considers the three-dimensional geometry of the sliding surface, adopting a modification of the model proposed by Hovland (1977), and revised and extended by Xie and co-workers (2006). Given a terrain elevation map and a set of relevant thematic layers, the model evaluates the stability of slopes for a large number of randomly selected potential slip surfaces, ellipsoidal or truncated in shape. Any single raster cell may be intersected by multiple sliding surfaces, each associated with a value of the factor of safety, FS. For each pixel, the minimum value of FS and the depth of the associated slip surface are stored. This information is used to obtain a spatial overview of the potentially unstable slopes in the study area. We test the model in the Collazzone area, Umbria, central Italy, an area known to be susceptible to landslides of different type and size. Availability of a comprehensive and detailed landslide inventory map allowed for a critical evaluation of the model results. The r.slope.stability code automatically splits the study area into a defined number of tiles, with proper overlap in order to provide the same statistical significance for the entire study area. The tiles are then processed in parallel by a given number of processors, exploiting a multi-purpose computing environment at CNR IRPI, Perugia. The map of the FS is obtained collecting the individual results, taking the minimum values on the overlapping cells. This procedure significantly reduces the processing time. We show how the gain in terms of processing time depends on the tile dimensions and on the number of cores.
Willensdorfer, M; Strumberger, E; Suttrop, W; Vanovac, B; Brida, D; Cavedon, M; Classen, I; Dunne, M; Fietz, S; Fischer, R; Kirk, A; Laggner, F M; Liu, Y Q; Odstrcil, T; Ryan, D A; Viezzer, E; Zohm, H; Luhmann, I C
2016-01-01
The plasma response from an external n = 2 magnetic perturbation field in ASDEX Upgrade has been measured using mainly electron cyclotron emission (ECE) diagnostics and a rigid rotating field. To interpret ECE and ECE-imaging (ECE-I) measurements accurately, forward modeling of the radiation transport has been combined with ray tracing. The measured data is compared to synthetic ECE data generated from a 3D ideal magnetohydrodynamics (MHD) equilibrium calculated by VMEC. The measured amplitudes of the helical displacement in the midplane are in reasonable agreement with the one from the synthetic VMEC diagnostics. Both exceed the vacuum field calculations and indicate the presence of an amplified kink response at the edge. Although the calculated magnetic structure of this edge kink peaks at poloidal mode numbers larger than the resonant components |m| > |nq|, the displacement measured by ECE-I is almost resonant |m| ~ |nq|. This is expected from ideal MHD in the proximity of rational surfaces. VMEC and MARS-...
A parallel multigrid-based preconditioner for the 3D heterogeneous high-frequency Helmholtz equation
We investigate the parallel performance of an iterative solver for 3D heterogeneous Helmholtz problems related to applications in seismic wave propagation. For large 3D problems, the computation is no longer feasible on a single processor, and the memory requirements increase rapidly. Therefore, parallelization of the solver is needed. We employ a complex shifted-Laplace preconditioner combined with the Bi-CGSTAB iterative method and use a multigrid method to approximate the inverse of the resulting preconditioning operator. A 3D multigrid method with 2D semi-coarsening is employed. We show numerical results for large problems arising in geophysical applications
Fast implementations of 3D PET reconstruction using vector and parallel programming techniques
Computationally intensive techniques that offer potential clinical use have arisen in nuclear medicine. Examples include iterative reconstruction, 3D PET data acquisition and reconstruction, and 3D image volume manipulation including image registration. One obstacle in achieving clinical acceptance of these techniques is the computational time required. This study focuses on methods to reduce the computation time for 3D PET reconstruction through the use of fast computer hardware, vector and parallel programming techniques, and algorithm optimization. The strengths and weaknesses of i860 microprocessor based workstation accelerator boards are investigated in implementations of 3D PET reconstruction
A Novel High-Order, Entropy Stable, 3D AMR MHD Solver with Guaranteed Positive Pressure
Derigs, Dominik; Gassner, Gregor J; Walch, Stefanie
2016-01-01
We describe a high-order numerical magnetohydrodynamics (MHD) solver built upon a novel non-linear entropy stable numerical flux function that supports eight travelling wave solutions. By construction the solver conserves mass, momentum, and energy and is entropy stable. The method is designed to treat the divergence-free constraint on the magnetic field in a similar fashion to a hyperbolic divergence cleaning technique. The solver described herein is especially well-suited for flows involving strong discontinuities. Furthermore, we present a new formulation to guarantee positivity of the pressure. We present the underlying theory and implementation of the new solver into the multi-physics, multi-scale adaptive mesh refinement (AMR) simulation code $\\texttt{FLASH}$ (http://flash.uchicago.edu). The accuracy, robustness and computational efficiency is demonstrated with a number of tests, including comparisons to available MHD implementations in $\\texttt{FLASH}$.
Virial theorem analysis of 3D numerical simulations of MHD self-gravitating turbulence
Shadmehri, Mohsen; Vazquez-Semadeni, Enrique; Ballesteros-Paredes, Javier
2001-01-01
We discuss the virial balance of all members of a cloud ensemble in numerical simulations of self-gravitating MHD turbulence. We first discuss the choice of reference frame for evaluating the terms entering the virial theorem (VT), concluding that the balance of each cloud should be measured in its own reference frame. We then report preliminary results suggesting that a) the clouds are far from virial equilibrium, with the ``geometric'' (time derivative) terms dominating the VT. b) The surfa...
A comparative study on 3-D solar wind structure observed by Ulysses and MHD simulation
FENG Xueshang; XIANG Changqing; ZHONG Dingkun; FAN Quanlin
2005-01-01
During Ulysses' first rapid pole-to-pole transit from September 1994 to June 1995, its observations showed that middle- or high-speed solar winds covered all latitudes except those between -20° and +20° near the ecliptic plane,where the velocity was 300-450 km/s. At poleward 40°,however, only fast solar winds at the speed of 700-870 km/s were observed. In addition, the transitions from low-speed wind to high-speed wind or vice versa were abrupt. In this paper, the large-scale structure of solar wind observed by Ulysses near solar minimum is simulated by using the three-dimensional numerical MHD model. The model combines TVD Lax-Friedrich scheme and MacCormack Ⅱ scheme and decomposes the calculation region into two regions: one from 1 to 22 Rs and the other from 18 Rs to 1 AU.Based on the observations of the solar photospheric magnetic field and an addition of the volumetric heating to MHD equations, the large-scale solar wind structure mentioned above is reproduced by using the three-dimensional MHD model and the numerical results are roughly consistent with Ulysses' observations. Our simulation shows that the initial magnetic field topology and the addition of volume heating may govern the bimodal structure of solar wind observed by Ulysses and also demonstrates that the three-dimensional MHD numerical model used here is efficient in modeling the large-scale solar wind structure.
ZHANG XianGuo; PU ZuYin; MA ZhiWei; ZHOU XuZhi
2008-01-01
A three-dimensional (3-D) Hall MHD simulation is carried out to study the roles of initial current carrier in the topology of magnetic field,the generation and distribuering the contribution of ions to the initial current,the topology of the obtained magnetic field turns to be more complex. In some cases,it is found that not only the traditional By quadrupole structure but also a reversal By quadrupole structure appears in the simulation box. This can explain the observational features near the diffusion region,which are inconsistent with the Hall MHD theory with the total initial current carried by electrons. Several other interesting features are also emerged. First,motions of electrons and ions are decoupled from each other in the small plasma region (Hall effect region) with a scale less than or comparable with the ion inertial length or ion skin depth di=c/ωp. In the non-Hall effect region,the global magnetic structure is shifted in +y direction under the influence of ions with initial y directional motion. However,in the Hall effect region,magnetic field lines are bent in -y direction,mainly controlled by the motion of electrons,then By is generated. Second,FACs emerge as a result of the appearance of By. Compared with the prior Hall MHD simulation results,the generated FACs shift in +y direction,
An Arbitrary Lagrangian-Eulerian Discretization of MHD on 3D Unstructured Grids
Rieben, R N; White, D A; Wallin, B K; Solberg, J M
2006-06-12
We present an arbitrary Lagrangian-Eulerian (ALE) discretization of the equations of resistive magnetohydrodynamics (MHD) on unstructured hexahedral grids. The method is formulated using an operator-split approach with three distinct phases: electromagnetic diffusion, Lagrangian motion, and Eulerian advection. The resistive magnetic dynamo equation is discretized using a compatible mixed finite element method with a 2nd order accurate implicit time differencing scheme which preserves the divergence-free nature of the magnetic field. At each discrete time step, electromagnetic force and heat terms are calculated and coupled to the hydrodynamic equations to compute the Lagrangian motion of the conducting materials. By virtue of the compatible discretization method used, the invariants of Lagrangian MHD motion are preserved in a discrete sense. When the Lagrangian motion of the mesh causes significant distortion, that distortion is corrected with a relaxation of the mesh, followed by a 2nd order monotonic remap of the electromagnetic state variables. The remap is equivalent to Eulerian advection of the magnetic flux density with a fictitious mesh relaxation velocity. The magnetic advection is performed using a novel variant of constrained transport (CT) that is valid for unstructured hexahedral grids with arbitrary mesh velocities. The advection method maintains the divergence free nature of the magnetic field and is second order accurate in regions where the solution is sufficiently smooth. For regions in which the magnetic field is discontinuous (e.g. MHD shocks) the method is limited using a novel variant of algebraic flux correction (AFC) which is local extremum diminishing (LED) and divergence preserving. Finally, we verify each stage of the discretization via a set of numerical experiments.
DANTSYS/MPI- a system for 3-D deterministic transport on parallel architectures
A data parallel version of the 3-D transport solver in DANTSYS has been in use on the SIMD CM-200s at LANL since 1994. This version typically obtains grind times of 150-200 nanoseconds on a 2048 PE CM-200. A new message passing parallel version of DANTSYS has been implemented referred to as DANTSYS/MPI, on the 512 PE Cray T3D at Los Alamos. By taking advantage of the SPMD architecture of the Cray T3D, as well as its low latency communications network, we have managed to achieve grind times of less than 10 nanoseconds on real problems. DANTSYS/MPI is fully accelerated using DSA on both the inner and outer iterations. The implementation is described of DANTSYS/MPI on the Cray T3D, and presents a simple performance model which accurately predicts the grind time as a function of the number of PE's and problem size, or scalableness. (author)
A novel high-order, entropy stable, 3D AMR MHD solver with guaranteed positive pressure
Derigs, Dominik; Winters, Andrew R.; Gassner, Gregor J.; Walch, Stefanie
2016-07-01
We describe a high-order numerical magnetohydrodynamics (MHD) solver built upon a novel non-linear entropy stable numerical flux function that supports eight travelling wave solutions. By construction the solver conserves mass, momentum, and energy and is entropy stable. The method is designed to treat the divergence-free constraint on the magnetic field in a similar fashion to a hyperbolic divergence cleaning technique. The solver described herein is especially well-suited for flows involving strong discontinuities. Furthermore, we present a new formulation to guarantee positivity of the pressure. We present the underlying theory and implementation of the new solver into the multi-physics, multi-scale adaptive mesh refinement (AMR) simulation code FLASH (http://flash.uchicago.edu)
A novel high-order, entropy stable, 3D AMR MHD solver with guaranteed positive pressure
Derigs, Dominik; Winters, Andrew R.; Gassner, Gregor J.; Walch, Stefanie
2016-07-01
We describe a high-order numerical magnetohydrodynamics (MHD) solver built upon a novel non-linear entropy stable numerical flux function that supports eight travelling wave solutions. By construction the solver conserves mass, momentum, and energy and is entropy stable. The method is designed to treat the divergence-free constraint on the magnetic field in a similar fashion to a hyperbolic divergence cleaning technique. The solver described herein is especially well-suited for flows involving strong discontinuities. Furthermore, we present a new formulation to guarantee positivity of the pressure. We present the underlying theory and implementation of the new solver into the multi-physics, multi-scale adaptive mesh refinement (AMR) simulation code FLASH (http://flash.uchicago.edu).
Parallel Isosurface Extraction for 3D Data Analysis Workflows in Distributed Environments
D'Agostino, Daniele; Clematis, Andrea; Gianuzzi, Vittoria
2011-01-01
Abstract In this paper we discuss the issues related to the development of efficient parallel implementations of the Marching Cubes algorithm, one of the most used methods for isosurface extraction, which is a fundamental operation for 3D data analysis and visualization. We present three possible parallelization strategies and we outline pros and cons of each of them, considering isosurface extraction as stand-alone operation or as part of a dynamic workflow. Our analysis shows tha...
2008-01-01
A three-dimensional (3-D) Hall MHD simulation is carried out to study the roles of initial current carrier in the topology of magnetic field, the generation and distribu- tion of field aligned currents (FACs), and the appearance of Alfvén waves. Consid- ering the contribution of ions to the initial current, the topology of the obtained magnetic field turns to be more complex. In some cases, it is found that not only the traditional By quadrupole structure but also a reversal By quadrupole structure appears in the simulation box. This can explain the observational features near the diffusion region, which are inconsistent with the Hall MHD theory with the total ini- tial current carried by electrons. Several other interesting features are also emerged. First, motions of electrons and ions are decoupled from each other in the small plasma region (Hall effect region) with a scale less than or comparable with the ion inertial length or ion skin depth di=c/ωp. In the non-Hall effect region, the global magnetic structure is shifted in +y direction under the influence of ions with initial y directional motion. However, in the Hall effect region, magnetic field lines are bent in ?y direction, mainly controlled by the motion of electrons, then By is generated. Second, FACs emerge as a result of the appearance of By. Compared with the prior Hall MHD simulation results, the generated FACs shift in +y direction, and hence the dawn-dusk symmetry is broken. Third, the Walén relation in our simulations is consistent with the Walén relation in Hall plasma, thus the presence of Alfvén wave is confirmed.
MHD and deep mixing in evolved stars. 1. 2D and 3D analytical models for the AGB
Nucci, M C
2014-01-01
The advection of thermonuclear ashes by magnetized domains emerging from near the H-shell was suggested to explain AGB star abundances. Here we verify this idea quantitatively through exact MHD models. Starting with a simple 2D geometry and in an inertia frame, we study plasma equilibria avoiding the complications of numerical simulations. We show that, below the convective envelope of an AGB star, variable magnetic fields induce a natural expansion, permitted by the almost ideal MHD conditions, in which the radial velocity grows as the second power of the radius. We then study the convective envelope, where the complexity of macro-turbulence allows only for a schematic analytical treatment. Here the radial velocity depends on the square root of the radius. We then verify the robustness of our results with 3D calculations for the velocity, showing that, for both the studied regions, the solution previously found can be seen as a planar section of a more complex behavior, in which anyway the average radial vel...
Non-twist map bifurcation of drift-lines and drift-island formation in saturated 3D MHD equilibria
Pfefferle, David; Cooper, Wilfred A.; Graves, Jonathan P.
2015-11-01
Based on non-canonical perturbation theory, guiding-centre drift equations are identified as perturbed magnetic field-line equations. The topology of passing-particle orbits, called drift-lines, is completely determined by the magnetic configuration. In axisymmetric tokamak fields, drift-lines lie on shifted flux-surfaces, called drift-surfaces. Field-lines and drift-lines are subject to island structures at rational surfaces only when a non-axisymmetric component is added. The picture is different in the case of 3D saturated MHD equilibrium like the helical core associated with a non-resonant internal kink mode. In assuming nested flux-surfaces, these bifurcated states, expected for a reversed q-profile with qmin close yet above unity and conveniently obtained in VMEC, feature integrable field-lines. The helical drift-lines however become resonant with the axisymmetric component in the region of qmin and spontaneously generate drift-islands. Due to the locally reversed sheared q-profile, the drift-island structure follows the bifurcation/reconnection mechanism of non-twist maps. This result provides a theoretical interpretation of NBI fast ion helical hot-spots in Long-Lived Modes as well as snake-like impurity density accumulation in internal MHD activity.
Rotation symmetry axes and the quality index in a 3D octahedral parallel robot manipulator system
Tanev, T. K.; Rooney, J.
2002-01-01
The geometry of a 3D octahedral parallel robot manipulator system is specified in terms of two rigid octahedral structures (the fixed and moving platforms) and six actuation legs. The symmetry of the system is exploited to determine the behaviour of (a new version of) the quality index for various motions. The main results are presented graphically.
A burnup corrected 3-D nodal depletion method for vector and parallel computer architectures
The 2- and 3-D nodal depletion code NOMAD-BC was parallelized and vectorized (3-D only). A 3-D, 2-cycle depletion problem was devised and successfully solved with the NOMAD-BC code in less than 35 seconds on two CPUs of a Cray X-MP/48. This shows a combined vectorization and parallelization speedup of 8.6. The same problem was solved on a 2-CPU 16 MHz SGI workstation in less than one hour, exhibiting a 1.78 speedup over the single processor solution on the same machine. It is shown in this work that complex and detailed burnup computations can be successfully optimized. In addition, the performance achieved demonstrates the possibility of obtaining results within very reasonable times, even on inexpensive workstations. Finally, the small CPU time requirements should make possible the routine evaluation of fuel cycles at great savings of the engineer's time. (author)
3D Multifluid MHD simulation for Uranus and Neptune: the seasonal variations of their magnetosphere
Cao, X.; Paty, C. S.
2015-12-01
The interaction between Uranus' intrinsic magnetic field and the solar wind is quite different from the magnetospheric interactions of other planets. Uranus' large obliquity, coupled with the fact that its dipole moment is off-centered and highly tilted relative to the rotation axis, leads to unique and seasonally dependent interaction geometries with the solar wind. We present results from adapting a multifluid MHD simulation to examine these seasonally dependent geometries in terms of the global magnetospheric structure, magnetopause and bow shock location, and magnetotail configuration. The Voyager 2 spacecraft encountered Uranus near solstice, and was able to observe the magnetic field structure and plasma characteristics of a twisted magnetotail [Behannon et al., 1987]. We use such magnetometer and plasma observations as a basis for benchmarking our simulations for the solstice scenario. Auroral observations made by the Hubble Space Telescope during equinox [Lamy et al.,2012] give some indication of the magnetospheric interaction with the solar wind. We also demonstrate the structural difference of the magnetosphere between solstice and equinox seasons. The magnetosphere at equinox is quite distinct due to the orientation and rotation of the magnetic axis relative to the solar wind direction.
A parallel algorithm for 3D particle tracking and Lagrangian trajectory reconstruction
Particle-tracking methods are widely used in fluid mechanics and multi-target tracking research because of their unique ability to reconstruct long trajectories with high spatial and temporal resolution. Researchers have recently demonstrated 3D tracking of several objects in real time, but as the number of objects is increased, real-time tracking becomes impossible due to data transfer and processing bottlenecks. This problem may be solved by using parallel processing. In this paper, a parallel-processing framework has been developed based on frame decomposition and is programmed using the asynchronous object-oriented Charm++ paradigm. This framework can be a key step in achieving a scalable Lagrangian measurement system for particle-tracking velocimetry and may lead to real-time measurement capabilities. The parallel tracking algorithm was evaluated with three data sets including the particle image velocimetry standard 3D images data set #352, a uniform data set for optimal parallel performance and a computational-fluid-dynamics-generated non-uniform data set to test trajectory reconstruction accuracy, consistency with the sequential version and scalability to more than 500 processors. The algorithm showed strong scaling up to 512 processors and no inherent limits of scalability were seen. Ultimately, up to a 200-fold speedup is observed compared to the serial algorithm when 256 processors were used. The parallel algorithm is adaptable and could be easily modified to use any sequential tracking algorithm, which inputs frames of 3D particle location data and outputs particle trajectories
3D Dynamics of Magnetopause Reconnection Using Hall-MHD Global Simulations
Maynard, K.; Germaschewski, K.; Raeder, J.; Bhattacharjee, A.
2011-12-01
Magnetic reconnection at Earth's magnetopause and in the magnetotail is of crucial importance for the dynamics of the global magnetosphere and space weather. Even though the plasma conditions in the magnetosphere are largely in the collisionless regime, most of the existing research using global computational models employ single-fluid magnetohydrodynamics (MHD) with artificial resistivity. Studies of reconnection in simplified, two-dimensional geometries have established that two-fluid and kinetic effects can dramatically alter dynamics and reconnection rates when compared with single-fluid models. These enhanced models also introduce particular signatures, for example a quadrupolar out-of-plane magnetic field component that has already been observed in space by satellite measurements. However, results from simplified geometries cannot be translated directly to the dynamics of three-dimensional magnetospheric reconnection. For instance, magnetic flux originating from the solar wind and arriving at the magnetopause can either reconnect or be advected around the magnetosphere. In this study, we use a new version of the OpenGGCM code that incorporates the Hall term in a Generalized Ohm's Law to study magnetopause reconnection under synthetic solar wind conditions and investigate how reconnection rates and dynamics of flux transfer events depend on the strength of the Hall term. The OpenGGCM, a global model of Earth's magnetosphere, has recently been ported to exploit modern computing architectures like the Cell processor and SIMD capabilities of conventional processors using an automatic code generator. These enhancements provide us with the performance needed to include the computationally expensive Hall physics.
Reiman, Allan H.
2016-07-01
In toroidal, magnetically confined plasmas, the heat and particle transport is strongly anisotropic, with transport along the field lines sufficiently strong relative to cross-field transport that the equilibrium pressure can generally be regarded as constant on the flux surfaces in much of the plasma. The regions near small magnetic islands, and those near the X-lines of larger islands, are exceptions, having a significant variation of the pressure within the flux surfaces. It is shown here that the variation of the equilibrium pressure within the flux surfaces in those regions has significant consequences for the pressure driven currents. It is further shown that the consequences are strongly affected by the symmetry of the magnetic field if the field is invariant under combined reflection in the poloidal and toroidal angles. (This symmetry property is called "stellarator symmetry.") In non-stellarator-symmetric equilibria, the pressure-driven currents have logarithmic singularities at the X-lines. In stellarator-symmetric MHD equilibria, the singular components of the pressure-driven currents vanish. These equilibria are to be contrasted with equilibria having B ṡ∇p =0 , where the singular components of the pressure-driven currents vanish regardless of the symmetry. They are also to be contrasted with 3D MHD equilibrium solutions that are constrained to have simply nested flux surfaces, where the pressure-driven current goes like 1 /x near rational surfaces, where x is the distance from the rational surface, except in the case of quasi-symmetric flux surfaces. For the purpose of calculating the pressure-driven currents near magnetic islands, we work with a closed subset of the MHD equilibrium equations that involves only perpendicular force balance, and is decoupled from parallel force balance. It is not correct to use the parallel component of the conventional MHD force balance equation, B ṡ∇p =0 , near magnetic islands. Small but nonzero values of B
Relativistic MHD simulations of core-collapse GRB jets: 3D instabilities and magnetic dissipation
Bromberg, Omer
2015-01-01
Relativistic jets naturally occur in astrophysical systems that involve accretion onto compact objects, such as core collapse of massive stars in gamma-ray bursts (GRBs) and accretion onto supermassive black holes in active galactic nuclei (AGN). It is generally accepted that these jets are powered electromagnetically, by the magnetised rotation of a central compact object. However, how they produce the observed emission and survive the propagation for many orders of magnitude in distance without being disrupted by current-driven non-axisymmetric instabilities is the subject of active debate. We carry out time-dependent 3D relativistic magnetohydrodynamic simulations of relativistic, Poynting flux dominated jets. The jets are launched self-consistently by the rotation of a strongly magnetised central compact object. This determines the natural degree of azimuthal magnetic field winding, a crucial factor that controls jet stability. We find that the jets are susceptible to two types of instability: (i) a globa...
An exact solution for the 3D MHD stagnation-point flow of a micropolar fluid
Borrelli, A.; Giantesio, G.; Patria, M. C.
2015-01-01
The influence of a non-uniform external magnetic field on the steady three dimensional stagnation-point flow of a micropolar fluid over a rigid uncharged dielectric at rest is studied. The total magnetic field is parallel to the velocity at infinity. It is proved that this flow is possible only in the axisymmetric case. The governing nonlinear partial differential equations are reduced to a system of ordinary differential equations by a similarity transformation, before being solved numerically. The effects of the governing parameters on the fluid flow and on the magnetic field are illustrated graphically and discussed.
Behaviour of magnetic islands in 3D MHD equilibria of helical devices
Magnetic island formation in 3D finite-β equilibria in the H-1 Heliac is studied by using the HINT code. It is found that the size of a dangerous island should increase with β but that destruction of the equilibrium at low β is avoided because the rotational transform evolves to exclude the rational surface concerned. At higher β there is evidence of near-resonant flux surface deformations which may lead to an equilibrium limit. A reconnected equilibrium at still higher β exhibits a double island structure which is similar to homoclinic phase portraits which have been observed after separatrix reconnection in Hamiltonian systems. The physical mechanisms of island formation in finite-β helical equilibria have been investigated. The HINT code predicts that the global effect to the Pfirsch-Schlueter currents can lead to self-healing of magnetic islands independent of whether or not the plasma is stable to resistive interchange modes. This result has been compared with the predictions of a boundary-layer analysis which has been extended to consider configurations with islands in the vacuum magnetic field. (author). 5 refs, 1 fig
Li, Yong Gang; Yang, Yang; Short, Michael P.; Ding, Ze Jun; Zeng, Zhi; Li, Ju
2015-12-01
SRIM-like codes have limitations in describing general 3D geometries, for modeling radiation displacements and damage in nanostructured materials. A universal, computationally efficient and massively parallel 3D Monte Carlo code, IM3D, has been developed with excellent parallel scaling performance. IM3D is based on fast indexing of scattering integrals and the SRIM stopping power database, and allows the user a choice of Constructive Solid Geometry (CSG) or Finite Element Triangle Mesh (FETM) method for constructing 3D shapes and microstructures. For 2D films and multilayers, IM3D perfectly reproduces SRIM results, and can be ∼102 times faster in serial execution and > 104 times faster using parallel computation. For 3D problems, it provides a fast approach for analyzing the spatial distributions of primary displacements and defect generation under ion irradiation. Herein we also provide a detailed discussion of our open-source collision cascade physics engine, revealing the true meaning and limitations of the “Quick Kinchin-Pease” and “Full Cascades” options. The issues of femtosecond to picosecond timescales in defining displacement versus damage, the limitation of the displacements per atom (DPA) unit in quantifying radiation damage (such as inadequacy in quantifying degree of chemical mixing), are discussed.
Gust Acoustics Computation with a Space-Time CE/SE Parallel 3D Solver
Wang, X. Y.; Himansu, A.; Chang, S. C.; Jorgenson, P. C. E.; Reddy, D. R. (Technical Monitor)
2002-01-01
The benchmark Problem 2 in Category 3 of the Third Computational Aero-Acoustics (CAA) Workshop is solved using the space-time conservation element and solution element (CE/SE) method. This problem concerns the unsteady response of an isolated finite-span swept flat-plate airfoil bounded by two parallel walls to an incident gust. The acoustic field generated by the interaction of the gust with the flat-plate airfoil is computed by solving the 3D (three-dimensional) Euler equations in the time domain using a parallel version of a 3D CE/SE solver. The effect of the gust orientation on the far-field directivity is studied. Numerical solutions are presented and compared with analytical solutions, showing a reasonable agreement.
Stiffness Analysis of 3-d.o.f. Overconstrained Translational Parallel Manipulators
Pashkevich, Anatoly; Wenger, Philippe
2008-01-01
The paper presents a new stiffness modelling method for overconstrained parallel manipulators, which is applied to 3-d.o.f. translational mechanisms. It is based on a multidimensional lumped-parameter model that replaces the link flexibility by localized 6-d.o.f. virtual springs. In contrast to other works, the method includes a FEA-based link stiffness evaluation and employs a new solution strategy of the kinetostatic equations, which allows computing the stiffness matrix for the overconstrained architectures and for the singular manipulator postures. The advantages of the developed technique are confirmed by application examples, which deal with comparative stiffness analysis of two translational parallel manipulators.
3D magnetospheric parallel hybrid multi-grid method applied to planet-plasma interactions
Leclercq, Ludivine; Modolo, Ronan; Leblanc, François; Hess, Sebastien; Mancini, Marco
2016-01-01
We present a new method to exploit multiple refinement levels within a 3D parallel hybrid model, developed to study planet-plasma interactions. This model is based on the hybrid formalism: ions are kinetically treated whereas electrons are considered as a inertia-less fluid. Generally, ions are represented by numerical particles whose size equals the volume of the cells. Particles that leave a coarse grid subsequently entering a refined region are split into particles whose volume corresponds...
A Parallel Implementation of the Mortar Element Method in 2D and 3D
Samake A.
2013-12-01
Full Text Available We present here the generic parallel computational framework in C++called Feel++for the mortar finite element method with the arbitrary number of subdomain partitions in 2D and 3D. An iterative method with block-diagonal preconditioners is used for solving the algebraic saddle-point problem arising from the finite element discretization. Finally we present a scalability study and the numerical results obtained using Feel++ library.
Edge-based electric field formulation in 3D CSEM simulations: A parallel approach
Castillo-Reyes, Octavio; de la Puente, Josep; Puzyrev, Vladimir; Cela, José M.
2015-01-01
This paper presents a parallel computing scheme for the data computation that arise when applying one of the most popular electromagnetic methods in exploration geophysics, namely, controlled-source electromagnetic (CSEM). The computational approach is based on linear edge finite element method in 3D isotropic domains. The total electromagnetic field is decomposed into primary and secondary electromagnetic field. The primary field is calculated analytically using an horizontal layered-e...
Spatial Parallelism of a 3D Finite Difference, Velocity-Stress Elastic Wave Propagation Code
MINKOFF,SUSAN E.
1999-12-09
Finite difference methods for solving the wave equation more accurately capture the physics of waves propagating through the earth than asymptotic solution methods. Unfortunately. finite difference simulations for 3D elastic wave propagation are expensive. We model waves in a 3D isotropic elastic earth. The wave equation solution consists of three velocity components and six stresses. The partial derivatives are discretized using 2nd-order in time and 4th-order in space staggered finite difference operators. Staggered schemes allow one to obtain additional accuracy (via centered finite differences) without requiring additional storage. The serial code is most unique in its ability to model a number of different types of seismic sources. The parallel implementation uses the MP1 library, thus allowing for portability between platforms. Spatial parallelism provides a highly efficient strategy for parallelizing finite difference simulations. In this implementation, one can decompose the global problem domain into one-, two-, and three-dimensional processor decompositions with 3D decompositions generally producing the best parallel speed up. Because i/o is handled largely outside of the time-step loop (the most expensive part of the simulation) we have opted for straight-forward broadcast and reduce operations to handle i/o. The majority of the communication in the code consists of passing subdomain face information to neighboring processors for use as ''ghost cells''. When this communication is balanced against computation by allocating subdomains of reasonable size, we observe excellent scaled speed up. Allocating subdomains of size 25 x 25 x 25 on each node, we achieve efficiencies of 94% on 128 processors. Numerical examples for both a layered earth model and a homogeneous medium with a high-velocity blocky inclusion illustrate the accuracy of the parallel code.
DANTSYS/MPI: a system for 3-D deterministic transport on parallel architectures
Baker, R.S.; Alcouffe, R.E.
1996-12-31
Since 1994, we have been using a data parallel form of our deterministic transport code DANTSYS to perform time-independent fixed source and eigenvalue calculations on the CM-200`s at Los Alamos National Laboratory (LANL). Parallelization of the transport sweep is obtained by using a 2-D spatial decomposition which retains the ability to invert the source iteration equation in a single iteration (i.e., the diagonal plane sweep). We have now implemented a message passing version of DANTSYS, referred to as DANTSYS/MPI, on the Cray T3D installed at Los Alamos in 1995. By taking advantage of the SPMD (Single Program, Multiple Data) architecture of the Cray T3D, as well as its low latency communications network, we have managed to achieve grind times (time to solve a single cell in phase space) of less than 10 nanoseconds on the 512 PE (Processing Element) T3D, as opposed to typical grind times of 150-200 nanoseconds on a 2048 PE CM-200, or 300-400 nanoseconds on a single PE of a Cray Y-MP. In addition, we have also parallelized the Diffusion Synthetic Accelerator (DSA) equations which are used to accelerate the convergence of the transport equation. DANTSYS/MPI currently runs on traditional Cray PVP`s and the Cray T3D, and it`s computational kernel (Sweep3D) has been ported to and tested on an array of SGI SMP`s (Symmetric Memory Processors), a network of IBM 590 workstations, an IBM SP2, and the Intel TFLOPs machine at Sandia National Laboratory. This paper describes the implementation of DANTSYS/MPI on the Cray T3D, and presents a simple performance model which accurately predicts the grind time as a function of the number of PE`s and problem size, or scalability. This paper also describes the parallel implementation and performance of the elliptic solver used in DANTSYS/MPI for solving the synthetic acceleration equations.
New adaptive differencing strategy in the PENTRAN 3-d parallel Sn code
It is known that three-dimensional (3-D) discrete ordinates (Sn) transport problems require an immense amount of storage and computational effort to solve. For this reason, parallel codes that offer a capability to completely decompose the angular, energy, and spatial domains among a distributed network of processors are required. One such code recently developed is PENTRAN, which iteratively solves 3-D multi-group, anisotropic Sn problems on distributed-memory platforms, such as the IBM-SP2. Because large problems typically contain several different material zones with various properties, available differencing schemes should automatically adapt to the transport physics in each material zone. To minimize the memory and message-passing overhead required for massively parallel Sn applications, available differencing schemes in an adaptive strategy should also offer reasonable accuracy and positivity, yet require only the zeroth spatial moment of the transport equation; differencing schemes based on higher spatial moments, in spite of their greater accuracy, require at least twice the amount of storage and communication cost for implementation in a massively parallel transport code. This paper discusses a new adaptive differencing strategy that uses increasingly accurate schemes with low parallel memory and communication overhead. This strategy, implemented in PENTRAN, includes a new scheme, exponential directional averaged (EDA) differencing
3-D electromagnetic plasma particle simulations on the Intel Delta parallel computer
A three-dimensional electromagnetic PIC code has been developed on the 512 node Intel Touchstone Delta MIMD parallel computer. This code is based on the General Concurrent PIC algorithm which uses a domain decomposition to divide the computation among the processors. The 3D simulation domain can be partitioned into 1-, 2-, or 3-dimensional sub-domains. Particles must be exchanged between processors as they move among the subdomains. The Intel Delta allows one to use this code for very-large-scale simulations (i.e. over 108 particles and 106 grid cells). The parallel efficiency of this code is measured, and the overall code performance on the Delta is compared with that on Cray supercomputers. It is shown that their code runs with a high parallel efficiency of ≥ 95% for large size problems. The particle push time achieved is 115 nsecs/particle/time step for 162 million particles on 512 nodes. Comparing with the performance on a single processor Cray C90, this represents a factor of 58 speedup. The code uses a finite-difference leap frog method for field solve which is significantly more efficient than fast fourier transforms on parallel computers. The performance of this code on the 128 node Cray T3D will also be discussed
Haberreiter, M; McIntosh, S; Wedemeyer-Boehm, S
2010-01-01
From the analysis of Dopplergrams in the K I 7699 A and Na I 5890 A spectral lines observed with the Magneto-Optical filter at Two Heights (MOTH) experiment during the austral summer in 2002-03 we find upward traveling waves in magnetic regions. Our analysis shows that the dispersion relation of these waves strongly depends on whether the wave is detected in the low-beta or high-beta regime. Moreover, the observed dispersion relation does not show the expected decrease of the acoustic cut-off frequency for the field guided slow magnetic wave. Instead, we detected an increase of the travel times below the acoustic cut-off frequency and at the same time a decrease of the travel time above it. To study the formation height of the spectral lines employed by MOTH in greater detail we are currently in the process of employing 3D MHD simulations carried out with CO5BOLD to perform NLTE spectral synthesis.
Description of a parallel, 3D, finite element, hydrodynamics-diffusion code
We describe a parallel, 3D, unstructured grid finite element, hydrodynamic diffusion code for inertial confinement fusion (ICF) applications and the ancillary software used to run it. The code system is divided into two entities, a controller and a stand-alone physics code. The code system may reside on different computers; the controller on the user s workstation and the physics code on a supercomputer. The physics code is composed of separate hydrodynamic, equation-of-state, laser energy deposition, heat conduction, and radiation transport packages and is parallelized for distributed memory architectures. For parallelization, a SPMD model is adopted; the domain is decomposed into a disjoint collection of sub-domains, one per processing element (PE). The PEs communicate using MPI. The code is used to simulate the hydrodynamic implosion of a spherical bubble
Parallel computation of 3-D Navier-Stokes flowfields for supersonic vehicles
Ryan, James S.; Weeratunga, Sisira
1993-01-01
Multidisciplinary design optimization of aircraft will require unprecedented capabilities of both analysis software and computer hardware. The speed and accuracy of the analysis will depend heavily on the computational fluid dynamics (CFD) module which is used. A new CFD module has been developed to combine the robust accuracy of conventional codes with the ability to run on parallel architectures. This is achieved by parallelizing the ARC3D algorithm, a central-differenced Navier-Stokes method, on the Intel iPSC/860. The computed solutions are identical to those from conventional machines. Computational speed on 64 processors is comparable to the rate on one Cray Y-MP processor and will increase as new generations of parallel computers become available.
Kolotilina, L.; Nikishin, A.; Yeremin, A. [and others
1994-12-31
The solution of large systems of linear equations is a crucial bottleneck when performing 3D finite element analysis of structures. Also, in many cases the reliability and robustness of iterative solution strategies, and their efficiency when exploiting hardware resources, fully determine the scope of industrial applications which can be solved on a particular computer platform. This is especially true for modern vector/parallel supercomputers with large vector length and for modern massively parallel supercomputers. Preconditioned iterative methods have been successfully applied to industrial class finite element analysis of structures. The construction and application of high quality preconditioners constitutes a high percentage of the total solution time. Parallel implementation of high quality preconditioners on such architectures is a formidable challenge. Two common types of existing preconditioners are the implicit preconditioners and the explicit preconditioners. The implicit preconditioners (e.g. incomplete factorizations of several types) are generally high quality but require solution of lower and upper triangular systems of equations per iteration which are difficult to parallelize without deteriorating the convergence rate. The explicit type of preconditionings (e.g. polynomial preconditioners or Jacobi-like preconditioners) require sparse matrix-vector multiplications and can be parallelized but their preconditioning qualities are less than desirable. The authors present results of numerical experiments with Factorized Sparse Approximate Inverses (FSAI) for symmetric positive definite linear systems. These are high quality preconditioners that possess a large resource of parallelism by construction without increasing the serial complexity.
Advanced quadratures and periodic boundary conditions in parallel 3D S{sub n} transport
Manalo, K.; Yi, C.; Huang, M.; Sjoden, G. [Nuclear and Radiological Engineering Program, G.W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, 770 State Street, Atlanta, GA 30332-0745 (United States)
2013-07-01
Significant updates in numerical quadratures have warranted investigation with 3D Sn discrete ordinates transport. We show new applications of quadrature departing from level symmetric (S{sub 2}o). investigating 3 recently developed quadratures: Even-Odd (EO), Linear-Discontinuous Finite Element - Surface Area (LDFE-SA), and the non-symmetric Icosahedral Quadrature (IC). We discuss implementation changes to 3D Sn codes (applied to Hybrid MOC-Sn TITAN and 3D parallel PENTRAN) that can be performed to accommodate Icosahedral Quadrature, as this quadrature is not 90-degree rotation invariant. In particular, as demonstrated using PENTRAN, the properties of Icosahedral Quadrature are suitable for trivial application using periodic BCs versus that of reflective BCs. In addition to implementing periodic BCs for 3D Sn PENTRAN, we implemented a technique termed 'angular re-sweep' which properly conditions periodic BCs for outer eigenvalue iterative loop convergence. As demonstrated by two simple transport problems (3-group fixed source and 3-group reflected/periodic eigenvalue pin cell), we remark that all of the quadratures we investigated are generally superior to level symmetric quadrature, with Icosahedral Quadrature performing the most efficiently for problems tested. (authors)
Schultz, Anthony [Nouvel Hopital Civil, Strasbourg University Hospital, Radiology Department, Strasbourg Cedex (France); Nouvel Hopital Civil, Service de Radiologie, Strasbourg Cedex (France); Caspar, Thibault [Nouvel Hopital Civil, Strasbourg University Hospital, Cardiology Department, Strasbourg Cedex (France); Schaeffer, Mickael [Nouvel Hopital Civil, Strasbourg University Hospital, Public Health and Biostatistics Department, Strasbourg Cedex (France); Labani, Aissam; Jeung, Mi-Young; El Ghannudi, Soraya; Roy, Catherine [Nouvel Hopital Civil, Strasbourg University Hospital, Radiology Department, Strasbourg Cedex (France); Ohana, Mickael [Nouvel Hopital Civil, Strasbourg University Hospital, Radiology Department, Strasbourg Cedex (France); Universite de Strasbourg / CNRS, UMR 7357, iCube Laboratory, Illkirch (France)
2016-06-15
To qualitatively and quantitatively compare different late gadolinium enhancement (LGE) sequences acquired at 3T with a parallel RF transmission technique. One hundred and sixty participants prospectively enrolled underwent a 3T cardiac MRI with 3 different LGE sequences: 3D Phase-Sensitive Inversion-Recovery (3D-PSIR) acquired 5 minutes after injection, 3D Inversion-Recovery (3D-IR) at 9 minutes and 3D-PSIR at 13 minutes. All LGE-positive patients were qualitatively evaluated both independently and blindly by two radiologists using a 4-level scale, and quantitatively assessed with measurement of contrast-to-noise ratio and LGE maximal surface. Statistical analyses were calculated under a Bayesian paradigm using MCMC methods. Fifty patients (70 % men, 56yo ± 19) exhibited LGE (62 % were post-ischemic, 30 % related to cardiomyopathy and 8 % post-myocarditis). Early and late 3D-PSIR were superior to 3D-IR sequences (global quality, estimated coefficient IR > early-PSIR: -2.37 CI = [-3.46; -1.38], prob(coef > 0) = 0 % and late-PSIR > IR: 3.12 CI = [0.62; 4.41], prob(coef > 0) = 100 %), LGE surface estimated coefficient IR > early-PSIR: -0.09 CI = [-1.11; -0.74], prob(coef > 0) = 0 % and late-PSIR > IR: 0.96 CI = [0.77; 1.15], prob(coef > 0) = 100 %. Probabilities for late PSIR being superior to early PSIR concerning global quality and CNR were over 90 %, regardless of the aetiological subgroup. In 3T cardiac MRI acquired with parallel RF transmission technique, 3D-PSIR is qualitatively and quantitatively superior to 3D-IR. (orig.)
Comparison of 3-D Synthetic Aperture Phased-Array Ultrasound Imaging and Parallel Beamforming
Rasmussen, Morten Fischer; Jensen, Jørgen Arendt
2014-01-01
This paper demonstrates that synthetic apertureimaging (SAI) can be used to achieve real-time 3-D ultra-sound phased-array imaging. It investigates whether SAI in-creases the image quality compared with the parallel beam-forming (PB) technique for real-time 3-D imaging. Data areobtained using both...... simulations and measurements with anultrasound research scanner and a commercially available 3.5-MHz 1024-element 2-D transducer array. To limit the probecable thickness, 256 active elements are used in transmit andreceive for both techniques. The two imaging techniques weredesigned for cardiac imaging, which...... requires sequences de-signed for imaging down to 15cm of depth and a frame rateof at least 20Hz. The imaging quality of the two techniquesis investigated through simulations as a function of depth andangle. SAI improved the full-width at half-maximum (FWHM) at low steering angles by 35%, and the 20-d...
Parallel Imaging of 3D Surface Profile with Space-Division Multiplexing
Hyung Seok Lee
2016-01-01
Full Text Available We have developed a modified optical frequency domain imaging (OFDI system that performs parallel imaging of three-dimensional (3D surface profiles by using the space division multiplexing (SDM method with dual-area swept sourced beams. We have also demonstrated that 3D surface information for two different areas could be well obtained in a same time with only one camera by our method. In this study, double field of views (FOVs of 11.16 mm × 5.92 mm were achieved within 0.5 s. Height range for each FOV was 460 µm and axial and transverse resolutions were 3.6 and 5.52 µm, respectively.
Parallel Imaging of 3D Surface Profile with Space-Division Multiplexing
Lee, Hyung Seok; Cho, Soon-Woo; Kim, Gyeong Hun; Jeong, Myung Yung; Won, Young Jae; Kim, Chang-Seok
2016-01-01
We have developed a modified optical frequency domain imaging (OFDI) system that performs parallel imaging of three-dimensional (3D) surface profiles by using the space division multiplexing (SDM) method with dual-area swept sourced beams. We have also demonstrated that 3D surface information for two different areas could be well obtained in a same time with only one camera by our method. In this study, double field of views (FOVs) of 11.16 mm × 5.92 mm were achieved within 0.5 s. Height range for each FOV was 460 µm and axial and transverse resolutions were 3.6 and 5.52 µm, respectively. PMID:26805840
A Parallelized 3D Particle-In-Cell Method With Magnetostatic Field Solver And Its Applications
Hsu, Kuo-Hsien; Chen, Yen-Sen; Wu, Men-Zan Bill; Wu, Jong-Shinn
2008-10-01
A parallelized 3D self-consistent electrostatic particle-in-cell finite element (PIC-FEM) code using an unstructured tetrahedral mesh was developed. For simulating some applications with external permanent magnet set, the distribution of the magnetostatic field usually also need to be considered and determined accurately. In this paper, we will firstly present the development of a 3D magnetostatic field solver with an unstructured mesh for the flexibility of modeling objects with complex geometry. The vector Poisson equation for magnetostatic field is formulated using the Galerkin nodal finite element method and the resulting matrix is solved by parallel conjugate gradient method. A parallel adaptive mesh refinement module is coupled to this solver for better resolution. Completed solver is then verified by simulating a permanent magnet array with results comparable to previous experimental observations and simulations. By taking the advantage of the same unstructured grid format of this solver, the developed PIC-FEM code could directly and easily read the magnetostatic field for particle simulation. In the upcoming conference, magnetron is simulated and presented for demonstrating the capability of this code.
Jung, Jaewoon; Kobayashi, Chigusa; Imamura, Toshiyuki; Sugita, Yuji
2016-03-01
Three-dimensional Fast Fourier Transform (3D FFT) plays an important role in a wide variety of computer simulations and data analyses, including molecular dynamics (MD) simulations. In this study, we develop hybrid (MPI+OpenMP) parallelization schemes of 3D FFT based on two new volumetric decompositions, mainly for the particle mesh Ewald (PME) calculation in MD simulations. In one scheme, (1d_Alltoall), five all-to-all communications in one dimension are carried out, and in the other, (2d_Alltoall), one two-dimensional all-to-all communication is combined with two all-to-all communications in one dimension. 2d_Alltoall is similar to the conventional volumetric decomposition scheme. We performed benchmark tests of 3D FFT for the systems with different grid sizes using a large number of processors on the K computer in RIKEN AICS. The two schemes show comparable performances, and are better than existing 3D FFTs. The performances of 1d_Alltoall and 2d_Alltoall depend on the supercomputer network system and number of processors in each dimension. There is enough leeway for users to optimize performance for their conditions. In the PME method, short-range real-space interactions as well as long-range reciprocal-space interactions are calculated. Our volumetric decomposition schemes are particularly useful when used in conjunction with the recently developed midpoint cell method for short-range interactions, due to the same decompositions of real and reciprocal spaces. The 1d_Alltoall scheme of 3D FFT takes 4.7 ms to simulate one MD cycle for a virus system containing more than 1 million atoms using 32,768 cores on the K computer.
A parallel sweeping preconditioner for high frequency heterogeneous 3D Helmholtz equations
Poulson, Jack; Fomel, Sergey; Li, Siwei; Ying, Lexing
2012-01-01
A parallelization of a recently introduced sweeping preconditioner for high frequency heterogeneous Helmholtz equations is presented along with experimental results for the full SEG/EAGE Overthrust seismic model at 30 Hz, using eight grid points per characteristic wavelength; to the best of our knowledge, this is the largest 3D Helmholtz calculation to date, and our algorithm only required fifteen minutes to complete on 8192 cores. While the setup and application costs of the sweeping preconditioner are trivially $\\Theta(N^{4/3})$ and $\\Theta(N \\log N)$, this paper provides strong empirical evidence that the number of iterations required for the convergence of GMRES equipped with the sweeping preconditioner is essentially independent of the frequency of the problem. Generalizations to time-harmonic Maxwell and linear-elastic wave equations are also briefly discussed since the techniques behind our parallelization are not specific to the Helmholtz equation.
Parallel 3D Finite Element Particle-in-Cell Simulations with Pic3P
Candel, A.; Kabel, A.; Lee, L.; Li, Z.; Ng, C.; Schussman, G.; Ko, K.; /SLAC; Ben-Zvi, I.; Kewisch, J.; /Brookhaven
2009-06-19
SLAC's Advanced Computations Department (ACD) has developed the parallel 3D Finite Element electromagnetic Particle-In-Cell code Pic3P. Designed for simulations of beam-cavity interactions dominated by space charge effects, Pic3P solves the complete set of Maxwell-Lorentz equations self-consistently and includes space-charge, retardation and boundary effects from first principles. Higher-order Finite Element methods with adaptive refinement on conformal unstructured meshes lead to highly efficient use of computational resources. Massively parallel processing with dynamic load balancing enables large-scale modeling of photoinjectors with unprecedented accuracy, aiding the design and operation of next-generation accelerator facilities. Applications include the LCLS RF gun and the BNL polarized SRF gun.
Three-dimensional parallel UNIPIC-3D code for simulations of high-power microwave devices
Wang, Jianguo; Chen, Zaigao; Wang, Yue; Zhang, Dianhui; Liu, Chunliang; Li, Yongdong; Wang, Hongguang; Qiao, Hailiang; Fu, Meiyan; Yuan, Yuan
2010-07-01
This paper introduces a self-developed, three-dimensional parallel fully electromagnetic particle simulation code UNIPIC-3D. In this code, the electromagnetic fields are updated using the second-order, finite-difference time-domain method, and the particles are moved using the relativistic Newton-Lorentz force equation. The electromagnetic field and particles are coupled through the current term in Maxwell's equations. Two numerical examples are used to verify the algorithms adopted in this code, numerical results agree well with theoretical ones. This code can be used to simulate the high-power microwave (HPM) devices, such as the relativistic backward wave oscillator, coaxial vircator, and magnetically insulated line oscillator, etc. UNIPIC-3D is written in the object-oriented C++ language and can be run on a variety of platforms including WINDOWS, LINUX, and UNIX. Users can use the graphical user's interface to create the complex geometric structures of the simulated HPM devices, which can be automatically meshed by UNIPIC-3D code. This code has a powerful postprocessor which can display the electric field, magnetic field, current, voltage, power, spectrum, momentum of particles, etc. For the sake of comparison, the results computed by using the two-and-a-half-dimensional UNIPIC code are also provided for the same parameters of HPM devices, the numerical results computed from these two codes agree well with each other.
3D Body Scanning Measurement System Associated with RF Imaging, Zero-padding and Parallel Processing
Kim Hyung Tae
2016-04-01
Full Text Available This work presents a novel signal processing method for high-speed 3D body measurements using millimeter waves with a general processing unit (GPU and zero-padding fast Fourier transform (ZPFFT. The proposed measurement system consists of a radio-frequency (RF antenna array for a penetrable measurement, a high-speed analog-to-digital converter (ADC for significant data acquisition, and a general processing unit for fast signal processing. The RF waves of the transmitter and the receiver are converted to real and imaginary signals that are sampled by a high-speed ADC and synchronized with the kinematic positions of the scanner. Because the distance between the surface and the antenna is related to the peak frequency of the conjugate signals, a fast Fourier transform (FFT is applied to the signal processing after the sampling. The sampling time is finite owing to a short scanning time, and the physical resolution needs to be increased; further, zero-padding is applied to interpolate the spectra of the sampled signals to consider a 1/m floating point frequency. The GPU and parallel algorithm are applied to accelerate the speed of the ZPFFT because of the large number of additional mathematical operations of the ZPFFT. 3D body images are finally obtained by spectrograms that are the arrangement of the ZPFFT in a 3D space.
3D Navier-Stokes Time Accurate Solutions Using Multipartitioning Parallel Computation Methodology
Zha, Ge-Cheng
1998-01-01
A parallel CFD code solving 3D time accurate Navier-Stokes equations with multipartitioning parallel Methodology is being developed in collaboration with Ohio State University within the Air Vehicle Directorate, at Wright Patterson Air Force Base. The advantage of the multipartitioning parallel method is that the domain decomposition will not introduce domain boundaries for the implicit operators. A ring structure data communication is employed so that the implicit time accurate method can be implemented for multi-processors with the same accuracy as for the single processor. No sub-iteration is needed at the domain boundaries. The code has been validated for some typical unsteady flows, which include Coutte Flow, flow passing a cylinder. The code now is being employed for a large scale time accurate wall jet transient flow computation. 'ne preliminary results are promising. The mesh has been refined to capture more details of the flow field. The mesh refinement computation is in progress and would be difficult to successfully implement without the parallel computation techniques used. A modified version of the code with more efficient inversion of the diagonalized block matrix is currently being tested.
Parallel CAE system for large-scale 3-D finite element analyses
This paper describes a new pre- and post-processing system for the automation of large-scale 3D finite element analyses. In the pre-processing stage, a geometry model lo be analyzed is defined by a user through an interactive operation with a 3D graphics editor. The analysis model is constructed by adding analysis conditions and a mesh refinement information lo the geometry model. The mesh refinement information, i.e. a nodal density distribution over the whole analysis domain is initially defined by superposing several locally optimum nodal patterns stored in the nodal pattern database of the system. Nodes and tetrahedral elements are generated using some computational geometry techniques whose processing speed is almost proportional to the total number of nodes. In the post-processing stage, scalar and vector values are evaluated at arbitrary points in the analysis domain, and displayed as equi-contours, vector lines, iso-surfaces, particle plots and realtime animation by means of scientific visualization techniques. The present system is also capable of mesh optimization. A posteriori error distribution over the whole analysis domain is obtained based on the simple error estimator proposed by Zienkiewicz and Zhu. The nodal density distribution to be used for mesh generation is optimized referring the obtained error distribution. Finally nodes and tetrahedral elements are re-generated. The present remeshing method is one of the global hr-version mesh adaptation methods. To deal with large-scale 3D finite element analyses in a reasonable computational time and memory requirement, a distributed/parallel processing technique is applied to some part of the present system. Fundamental performances of the present system are clearly demonstrated through 3D thermal conduction analyses. (author)
Design and verification of an ultra-precision 3D-coordinate measuring machine with parallel drives
Bos, Edwin; Moers, Ton; van Riel, Martijn
2015-08-01
An ultra-precision 3D coordinate measuring machine (CMM), the TriNano N100, has been developed. In our design, the workpiece is mounted on a 3D stage, which is driven by three parallel drives that are mutually orthogonal. The linear drives support the 3D stage using vacuum preloaded (VPL) air bearings, whereby each drive determines the position of the 3D stage along one translation direction only. An exactly constrained design results in highly repeatable machine behavior. Furthermore, the machine complies with the Abbé principle over its full measurement range and the application of parallel drives allows for excellent dynamic behavior. The design allows a 3D measurement uncertainty of 100 nanometers in a measurement range of 200 cubic centimeters. Verification measurements using a Gannen XP 3D tactile probing system on a spherical artifact show a standard deviation in single point repeatability of around 2 nm in each direction.
Recent progress in 3D EM/EM-PIC simulation with ARGUS and parallel ARGUS
ARGUS is an integrated, 3-D, volumetric simulation model for systems involving electric and magnetic fields and charged particles, including materials embedded in the simulation region. The code offers the capability to carry out time domain and frequency domain electromagnetic simulations of complex physical systems. ARGUS offers a boolean solid model structure input capability that can include essentially arbitrary structures on the computational domain, and a modular architecture that allows multiple physics packages to access the same data structure and to share common code utilities. Physics modules are in place to compute electrostatic and electromagnetic fields, the normal modes of RF structures, and self-consistent particle-in-cell (PIC) simulation in either a time dependent mode or a steady state mode. The PIC modules include multiple particle species, the Lorentz equations of motion, and algorithms for the creation of particles by emission from material surfaces, injection onto the grid, and ionization. In this paper, we present an updated overview of ARGUS, with particular emphasis given in recent algorithmic and computational advances. These include a completely rewritten frequency domain solver which efficiently treats lossy materials and periodic structures, a parallel version of ARGUS with support for both shared memory parallel vector (i.e. CRAY) machines and distributed memory massively parallel MIMD systems, and numerous new applications of the code
3-D readout-electronics packaging for high-bandwidth massively paralleled imager
Kwiatkowski, Kris; Lyke, James
2007-12-18
Dense, massively parallel signal processing electronics are co-packaged behind associated sensor pixels. Microchips containing a linear or bilinear arrangement of photo-sensors, together with associated complex electronics, are integrated into a simple 3-D structure (a "mirror cube"). An array of photo-sensitive cells are disposed on a stacked CMOS chip's surface at a 45.degree. angle from light reflecting mirror surfaces formed on a neighboring CMOS chip surface. Image processing electronics are held within the stacked CMOS chip layers. Electrical connections couple each of said stacked CMOS chip layers and a distribution grid, the connections for distributing power and signals to components associated with each stacked CSMO chip layer.
The new Exponential Directional Iterative (EDI) 3-D Sn scheme for parallel adaptive differencing
The new Exponential Directional Iterative (EDI) discrete ordinates (Sn) scheme for 3-D Cartesian Coordinates is presented. The EDI scheme is a logical extension of the positive, efficient Exponential Directional Weighted (EDW) Sn scheme currently used as the third level of the adaptive spatial differencing algorithm in the PENTRAN parallel discrete ordinates solver. Here, the derivation and advantages of the EDI scheme are presented; EDI uses EDW-rendered exponential coefficients as initial starting values to begin a fixed point iteration of the exponential coefficients. One issue that required evaluation was an iterative cutoff criterion to prevent the application of an unstable fixed point iteration; although this was needed in some cases, it was readily treated with a default to EDW. Iterative refinement of the exponential coefficients in EDI typically converged in fewer than four fixed point iterations. Moreover, EDI yielded more accurate angular fluxes compared to the other schemes tested, particularly in streaming conditions. Overall, it was found that the EDI scheme was up to an order of magnitude more accurate than the EDW scheme on a given mesh interval in streaming cases, and is potentially a good candidate as a fourth-level differencing scheme in the PENTRAN adaptive differencing sequence. The 3-D Cartesian computational cost of EDI was only about 20% more than the EDW scheme, and about 40% more than Diamond Zero (DZ). More evaluation and testing are required to determine suitable upgrade metrics for EDI to be fully integrated into the current adaptive spatial differencing sequence in PENTRAN. (author)
Rastogi, Richa; Srivastava, Abhishek; Khonde, Kiran; Sirasala, Kirannmayi M.; Londhe, Ashutosh; Chavhan, Hitesh
2015-07-01
This paper presents an efficient parallel 3D Kirchhoff depth migration algorithm suitable for current class of multicore architecture. The fundamental Kirchhoff depth migration algorithm exhibits inherent parallelism however, when it comes to 3D data migration, as the data size increases the resource requirement of the algorithm also increases. This challenges its practical implementation even on current generation high performance computing systems. Therefore a smart parallelization approach is essential to handle 3D data for migration. The most compute intensive part of Kirchhoff depth migration algorithm is the calculation of traveltime tables due to its resource requirements such as memory/storage and I/O. In the current research work, we target this area and develop a competent parallel algorithm for post and prestack 3D Kirchhoff depth migration, using hybrid MPI+OpenMP programming techniques. We introduce a concept of flexi-depth iterations while depth migrating data in parallel imaging space, using optimized traveltime table computations. This concept provides flexibility to the algorithm by migrating data in a number of depth iterations, which depends upon the available node memory and the size of data to be migrated during runtime. Furthermore, it minimizes the requirements of storage, I/O and inter-node communication, thus making it advantageous over the conventional parallelization approaches. The developed parallel algorithm is demonstrated and analysed on Yuva II, a PARAM series of supercomputers. Optimization, performance and scalability experiment results along with the migration outcome show the effectiveness of the parallel algorithm.
In situ patterned micro 3D liver constructs for parallel toxicology testing in a fluidic device.
Skardal, Aleksander; Devarasetty, Mahesh; Soker, Shay; Hall, Adam R
2015-09-01
3D tissue models are increasingly being implemented for drug and toxicology testing. However, the creation of tissue-engineered constructs for this purpose often relies on complex biofabrication techniques that are time consuming, expensive, and difficult to scale up. Here, we describe a strategy for realizing multiple tissue constructs in a parallel microfluidic platform using an approach that is simple and can be easily scaled for high-throughput formats. Liver cells mixed with a UV-crosslinkable hydrogel solution are introduced into parallel channels of a sealed microfluidic device and photopatterned to produce stable tissue constructs in situ. The remaining uncrosslinked material is washed away, leaving the structures in place. By using a hydrogel that specifically mimics the properties of the natural extracellular matrix, we closely emulate native tissue, resulting in constructs that remain stable and functional in the device during a 7-day culture time course under recirculating media flow. As proof of principle for toxicology analysis, we expose the constructs to ethyl alcohol (0-500 mM) and show that the cell viability and the secretion of urea and albumin decrease with increasing alcohol exposure, while markers for cell damage increase. PMID:26355538
Jiang, Chaowei; Wu, S T; Hu, Qiang
2012-01-01
We apply a data-driven MHD model to investigate the three-dimensional (3D) magnetic field of NOAA active region (AR) 11117 around the time of a C-class confined flare occurred on 2010 October 25. The MHD model, based on the spacetime conservation-element and solution-element (CESE) scheme, is designed to focus on the magnetic-field evolution and to consider a simplified solar atomsphere with finite plasma $\\beta$. Magnetic vector-field data derived from the observations at the photoshpere is inputted directly to constrain the model. Assuming that the dynamic evolution of the coronal magnetic field can be approximated by successive equilibria, we solve a time sequence of MHD equilibria basing on a set of vector magnetograms for AR 11117 taken by the Helioseismic and Magnetic Imager (HMI) on board the {\\it Solar Dynamic Observatory (SDO)} around the time of flare. The model qualitatively reproduces the basic structures of the 3D magnetic field, as supported by the visual similarity between the field lines and t...
Flock, M; Klahr, H; Mignone, A
2009-01-01
We employ the PLUTO code for computational astrophysics to assess and compare the validity of different numerical algorithms on simulations of the magneto-rotational instability in 3D accretion disks. In particular we stress on the importance of using a consistent upwind reconstruction of the electro-motive force (EMF) when using the constrained transport (CT) method to avoid the onset of numerical instabilities. We show that the electro-motive force (EMF) reconstruction in the classical constrained transport (CT) method for Godunov schemes drives a numerical instability. The well-studied linear growth of magneto-rotational instability (MRI) is used as a benchmark for an inter-code comparison of PLUTO and ZeusMP. We reproduce the analytical results for linear MRI growth in 3D global MHD simulations and present a robust and accurate Godunov code which can be used for 3D accretion disk simulations in curvilinear coordinate systems.
Application of the SDD-CMFD acceleration method to parallel 3-D MOC transport
In this paper the spatial domain decomposed coarse mesh finite difference (SDD-CMFD) method is applied as an acceleration technique to a parallel implementation of the 3-D method of characteristics (MOC) for a series of problems to assess the effectiveness of the method for practical applications. The SDD-CMFD method assumes the problem domain is divided into independent parallelizable sweep regions globally linked within the framework of a CMFD-like system. Results obtained with the MPACT code are examined for three problems. The first analysis is of multi-dimensional, 1-group, infinite homogeneous media problems that compare the numerically-measured rate of convergence to that predicted by the 1-D Fourier analysis performed in previous work. It is observed that the rate of convergence of the numerical experiments has similar behavior to that predicted by the Fourier analysis for variations of optical thickness in the coarse cell and spatial subdomain. However, the rate of convergence is measured to be slightly less than that predicted by Fourier analysis. The algorithm is applied to the Takeda 3-D neutron transport benchmark, and compared to a standard source iteration. In the analysis of this problem, the method is observed to speed up convergence, significantly reducing the number of outer iterations by a factor of nearly 20x and reducing the overall run time by a factor of about 10x. Finally, the method is applied to a realistic PWR assembly, which is observed to converge in 7 outer iterations, a factor of 150x less than source iteration, using the SDD-CMFD acceleration method, and have an estimated speedup of ∼34x over conventional source iteration. (author)
3D magnetospheric parallel hybrid multi-grid method applied to planet-plasma interactions
Leclercq, L.; Modolo, R.; Leblanc, F.; Hess, S.; Mancini, M.
2016-03-01
We present a new method to exploit multiple refinement levels within a 3D parallel hybrid model, developed to study planet-plasma interactions. This model is based on the hybrid formalism: ions are kinetically treated whereas electrons are considered as a inertia-less fluid. Generally, ions are represented by numerical particles whose size equals the volume of the cells. Particles that leave a coarse grid subsequently entering a refined region are split into particles whose volume corresponds to the volume of the refined cells. The number of refined particles created from a coarse particle depends on the grid refinement rate. In order to conserve velocity distribution functions and to avoid calculations of average velocities, particles are not coalesced. Moreover, to ensure the constancy of particles' shape function sizes, the hybrid method is adapted to allow refined particles to move within a coarse region. Another innovation of this approach is the method developed to compute grid moments at interfaces between two refinement levels. Indeed, the hybrid method is adapted to accurately account for the special grid structure at the interfaces, avoiding any overlapping grid considerations. Some fundamental test runs were performed to validate our approach (e.g. quiet plasma flow, Alfven wave propagation). Lastly, we also show a planetary application of the model, simulating the interaction between Jupiter's moon Ganymede and the Jovian plasma.
Chien-Lun Hou; Hao-Ting Lin; Mao-Hsiung Chiang
2011-01-01
In this paper, a stereo vision 3D position measurement system for a three-axial pneumatic parallel mechanism robot arm is presented. The stereo vision 3D position measurement system aims to measure the 3D trajectories of the end-effector of the robot arm. To track the end-effector of the robot arm, the circle detection algorithm is used to detect the desired target and the SAD algorithm is used to track the moving target and to search the corresponding target location along the conjugate epip...
Hao-Ting Lin; Mao-Hsiung Chiang
2011-01-01
This study aimed to develop a novel 3D parallel mechanism robot driven by three vertical-axial pneumatic actuators with a stereo vision system for path tracking control. The mechanical system and the control system are the primary novel parts for developing a 3D parallel mechanism robot. In the mechanical system, a 3D parallel mechanism robot contains three serial chains, a fixed base, a movable platform and a pneumatic servo system. The parallel mechanism are designed and analyzed first for ...
Wakefield Simulation of CLIC PETS Structure Using Parallel 3D Finite Element Time-Domain Solver T3P
Candel, A.; Kabel, A.; Lee, L.; Li, Z.; Ng, C.; Schussman, G.; Ko, K.; /SLAC; Syratchev, I.; /CERN
2009-06-19
In recent years, SLAC's Advanced Computations Department (ACD) has developed the parallel 3D Finite Element electromagnetic time-domain code T3P. Higher-order Finite Element methods on conformal unstructured meshes and massively parallel processing allow unprecedented simulation accuracy for wakefield computations and simulations of transient effects in realistic accelerator structures. Applications include simulation of wakefield damping in the Compact Linear Collider (CLIC) power extraction and transfer structure (PETS).
Design and verification of an ultra-precision 3D-coordinate measuring machine with parallel drives
An ultra-precision 3D coordinate measuring machine (CMM), the TriNano N100, has been developed. In our design, the workpiece is mounted on a 3D stage, which is driven by three parallel drives that are mutually orthogonal. The linear drives support the 3D stage using vacuum preloaded (VPL) air bearings, whereby each drive determines the position of the 3D stage along one translation direction only. An exactly constrained design results in highly repeatable machine behavior. Furthermore, the machine complies with the Abbé principle over its full measurement range and the application of parallel drives allows for excellent dynamic behavior. The design allows a 3D measurement uncertainty of 100 nanometers in a measurement range of 200 cubic centimeters. Verification measurements using a Gannen XP 3D tactile probing system on a spherical artifact show a standard deviation in single point repeatability of around 2 nm in each direction. (paper)
Christopher D. Dharmaraj
2009-01-01
Full Text Available Three-dimensional Oximetric Electron Paramagnetic Resonance Imaging using the Single Point Imaging modality generates unpaired spin density and oxygen images that can readily distinguish between normal and tumor tissues in small animals. It is also possible with fast imaging to track the changes in tissue oxygenation in response to the oxygen content in the breathing air. However, this involves dealing with gigabytes of data for each 3D oximetric imaging experiment involving digital band pass filtering and background noise subtraction, followed by 3D Fourier reconstruction. This process is rather slow in a conventional uniprocessor system. This paper presents a parallelization framework using OpenMP runtime support and parallel MATLAB to execute such computationally intensive programs. The Intel compiler is used to develop a parallel C++ code based on OpenMP. The code is executed on four Dual-Core AMD Opteron shared memory processors, to reduce the computational burden of the filtration task significantly. The results show that the parallel code for filtration has achieved a speed up factor of 46.66 as against the equivalent serial MATLAB code. In addition, a parallel MATLAB code has been developed to perform 3D Fourier reconstruction. Speedup factors of 4.57 and 4.25 have been achieved during the reconstruction process and oximetry computation, for a data set with 23×23×23 gradient steps. The execution time has been computed for both the serial and parallel implementations using different dimensions of the data and presented for comparison. The reported system has been designed to be easily accessible even from low-cost personal computers through local internet (NIHnet. The experimental results demonstrate that the parallel computing provides a source of high computational power to obtain biophysical parameters from 3D EPR oximetric imaging, almost in real-time.
Dharmaraj, Christopher D; Thadikonda, Kishan; Fletcher, Anthony R; Doan, Phuc N; Devasahayam, Nallathamby; Matsumoto, Shingo; Johnson, Calvin A; Cook, John A; Mitchell, James B; Subramanian, Sankaran; Krishna, Murali C
2009-01-01
Three-dimensional Oximetric Electron Paramagnetic Resonance Imaging using the Single Point Imaging modality generates unpaired spin density and oxygen images that can readily distinguish between normal and tumor tissues in small animals. It is also possible with fast imaging to track the changes in tissue oxygenation in response to the oxygen content in the breathing air. However, this involves dealing with gigabytes of data for each 3D oximetric imaging experiment involving digital band pass filtering and background noise subtraction, followed by 3D Fourier reconstruction. This process is rather slow in a conventional uniprocessor system. This paper presents a parallelization framework using OpenMP runtime support and parallel MATLAB to execute such computationally intensive programs. The Intel compiler is used to develop a parallel C++ code based on OpenMP. The code is executed on four Dual-Core AMD Opteron shared memory processors, to reduce the computational burden of the filtration task significantly. The results show that the parallel code for filtration has achieved a speed up factor of 46.66 as against the equivalent serial MATLAB code. In addition, a parallel MATLAB code has been developed to perform 3D Fourier reconstruction. Speedup factors of 4.57 and 4.25 have been achieved during the reconstruction process and oximetry computation, for a data set with 23 x 23 x 23 gradient steps. The execution time has been computed for both the serial and parallel implementations using different dimensions of the data and presented for comparison. The reported system has been designed to be easily accessible even from low-cost personal computers through local internet (NIHnet). The experimental results demonstrate that the parallel computing provides a source of high computational power to obtain biophysical parameters from 3D EPR oximetric imaging, almost in real-time. PMID:19672315
Sofronov, I.D.; Voronin, B.L.; Butnev, O.I. [VNIIEF (Russian Federation)] [and others
1997-12-31
The aim of the work performed is to develop a 3D parallel program for numerical calculation of gas dynamics problem with heat conductivity on distributed memory computational systems (CS), satisfying the condition of numerical result independence from the number of processors involved. Two basically different approaches to the structure of massive parallel computations have been developed. The first approach uses the 3D data matrix decomposition reconstructed at temporal cycle and is a development of parallelization algorithms for multiprocessor CS with shareable memory. The second approach is based on using a 3D data matrix decomposition not reconstructed during a temporal cycle. The program was developed on 8-processor CS MP-3 made in VNIIEF and was adapted to a massive parallel CS Meiko-2 in LLNL by joint efforts of VNIIEF and LLNL staffs. A large number of numerical experiments has been carried out with different number of processors up to 256 and the efficiency of parallelization has been evaluated in dependence on processor number and their parameters.
Chien-Lun Hou
2011-02-01
Full Text Available In this paper, a stereo vision 3D position measurement system for a three-axial pneumatic parallel mechanism robot arm is presented. The stereo vision 3D position measurement system aims to measure the 3D trajectories of the end-effector of the robot arm. To track the end-effector of the robot arm, the circle detection algorithm is used to detect the desired target and the SAD algorithm is used to track the moving target and to search the corresponding target location along the conjugate epipolar line in the stereo pair. After camera calibration, both intrinsic and extrinsic parameters of the stereo rig can be obtained, so images can be rectified according to the camera parameters. Thus, through the epipolar rectification, the stereo matching process is reduced to a horizontal search along the conjugate epipolar line. Finally, 3D trajectories of the end-effector are computed by stereo triangulation. The experimental results show that the stereo vision 3D position measurement system proposed in this paper can successfully track and measure the fifth-order polynomial trajectory and sinusoidal trajectory of the end-effector of the three- axial pneumatic parallel mechanism robot arm.
Bristeau, Marie-Odile; Glowinski, Roland; Périaux, Jacques; Rossi, Tuomo
1999-01-01
We consider the scattering problem for 3-D electromagnetic harmonic waves. The time-domain Maxwell's equations are solved and Exact Controllability methods improve the convergence of the solutions to the time-periodic ones for nonconvex obstacles. A least-squares formulation solved by a preconditioned conjugate gradient is introduced. The discretization is achieved in time by a centered finite difference scheme and in space by Lagrange finite elements. Numerical results for 3-D nonconvex scat...
ud-Doula, Asif; Owocki, Stanley P; Petit, Veronique; Townsend, Richard H D
2012-01-01
We present the first fully 3D MHD simulation for magnetic channeling and confinement of a radiatively driven, massive-star wind. The specific parameters are chosen to represent the prototypical slowly rotating magnetic O star \\theta^1 Ori C, for which centrifugal and other dynamical effects of rotation are negligible. The computed global structure in latitude and radius resembles that found in previous 2D simulations, with unimpeded outflow along open field lines near the magnetic poles, and a complex equatorial belt of inner wind trapping by closed loops near the stellar surface, giving way to outflow above the Alfv\\'{e}n radius. In contrast to this previous 2D work, the 3D simulation described here now also shows how this complex structure fragments in azimuth, forming distinct clumps of closed loop infall within the Alfv\\'{e}n radius, transitioning in the outer wind to radial spokes of enhanced density with characteristic azimuthal separation of $15-20 \\degr$. Applying these results in a 3D code for line r...
Haberreiter, M.; Guerreiro, N.; Hansteen, V. H.; Schmutz, W. K.
2015-12-01
The physical mechanism that heats the solar corona is one of the still open science questions in solar physics. One of the proposed mechanism for coronal heating are nanoflares. To investigate their role in coronal heating we study the properties of the small-scale heating events in the solar atmosphere using 3D MHD simulations. We present a method to identify and track these heating events in time which allows us to study their life time, energy, and spectral signatures. These spectal signatures will be compared with available spectrosopic observations obtained with IRIS and SUMER. Ultimately, these results will be important for the coordinated scientific exploitation of SPICE and EUI along with other instruments onboard Solar Orbiter to address the coronal heating problem.
Characterization of a parallel-beam CCD optical-CT apparatus for 3D radiation dosimetry
Krstajic, Nikola; Doran, Simon J.
2007-07-01
3D measurement of optical attenuation is of interest in a variety of fields of biomedical importance, including spectrophotometry, optical projection tomography (OPT) and analysis of 3D radiation dosimeters. Accurate, precise and economical 3D measurements of optical density (OD) are a crucial step in enabling 3D radiation dosimeters to enter wider use in clinics. Polymer gels and Fricke gels, as well as dosimeters not based around gels, have been characterized for 3D dosimetry over the last two decades. A separate problem is the verification of the best readout method. A number of different imaging modalities (magnetic resonance imaging (MRI), optical CT, x-ray CT and ultrasound) have been suggested for the readout of information from 3D dosimeters. To date only MRI and laser-based optical CT have been characterized in detail. This paper describes some initial steps we have taken in establishing charge coupled device (CCD)-based optical CT as a viable alternative to MRI for readout of 3D radiation dosimeters. The main advantage of CCD-based optical CT over traditional laser-based optical CT is a speed increase of at least an order of magnitude, while the simplicity of its architecture would lend itself to cheaper implementation than both MRI and laser-based optical CT if the camera itself were inexpensive enough. Specifically, we study the following aspects of optical metrology, using high quality test targets: (i) calibration and quality of absorbance measurements and the camera requirements for 3D dosimetry; (ii) the modulation transfer function (MTF) of individual projections; (iii) signal-to-noise ratio (SNR) in the projection and reconstruction domains; (iv) distortion in the projection domain, depth-of-field (DOF) and telecentricity. The principal results for our current apparatus are as follows: (i) SNR of optical absorbance in projections is better than 120:1 for uniform phantoms in absorbance range 0.3 to 1.6 (and better than 200:1 for absorbances 1.0 to
Signatures of small-scale heating events in EUV spectral lines as modeled from 3D MHD simulations
Guerreiro, Nuno; Haberreiter, Margit; Hansteen, Viggo; Curdt, Werner; Schmutz, Werner
2014-05-01
We aim at understanding the implications of small scale heating events in the solar atmosphere for the variations of the solar spectral irradiance. We present a technique for identification and characterization of these events in 3D simulations of the solar atmosphere. An accurate property determination of these events in time and space will help us to understand how spectral lines, in particular in the EUV, respond to them and which kind of spectral signatures one would expect to find in observations as from SOHO/SUMER and eventually from future space missions, as for example observations by SPICE on board Solar Orbiter.
Parallel Adaptive Computation of Blood Flow in a 3D ``Whole'' Body Model
Zhou, M.; Figueroa, C. A.; Taylor, C. A.; Sahni, O.; Jansen, K. E.
2008-11-01
Accurate numerical simulations of vascular trauma require the consideration of a larger portion of the vasculature than previously considered, due to the systemic nature of the human body's response. A patient-specific 3D model composed of 78 connected arterial branches extending from the neck to the lower legs is constructed to effectively represent the entire body. Recently developed outflow boundary conditions that appropriately represent the downstream vasculature bed which is not included in the 3D computational domain are applied at 78 outlets. In this work, the pulsatile blood flow simulations are started on a fairly uniform, unstructured mesh that is subsequently adapted using a solution-based approach to efficiently resolve the flow features. The adapted mesh contains non-uniform, anisotropic elements resulting in resolution that conforms with the physical length scales present in the problem. The effects of the mesh resolution on the flow field are studied, specifically on relevant quantities of pressure, velocity and wall shear stress.
A first 3D parallel diffusion solver based on a mixed dual finite element approximation
This paper presents a new extension of the mixed dual finite element approximation of the diffusion equation in rectangular geometry. The mixed dual formulation has been extended in order to take into account discontinuity conditions. The iterative method is based on an alternating direction method which uses the current as unknown. This method is parallelizable and have very fast convergence properties. Some results for a 3D calculation on the CRAY computer are presented. (orig.)
Compensation of errors in robot machining with a parallel 3D-piezo compensation mechanism
Schneider, Ulrich; Drust, Manuel; Puzik, Arnold; Verl, Alexander
2013-01-01
This paper proposes an approach for a 3D-Piezo Compensation Mechanism unit that is capable of fast and accurate adaption of the spindle position to enhance machining by robots. The mechanical design is explained which focuses on low mass, good stiffness and high bandwidth in order to allow compensating for errors beyond the bandwidth of the robot. In addition to previous works [7] and [9], an advanced actuation design is presented enabling movements in three translational axes allowing a work...
BioFVM: an efficient, parallelized diffusive transport solver for 3-D biological simulations
Ghaffarizadeh, Ahmadreza; Friedman, Samuel H.; Macklin, Paul
2015-01-01
Motivation: Computational models of multicellular systems require solving systems of PDEs for release, uptake, decay and diffusion of multiple substrates in 3D, particularly when incorporating the impact of drugs, growth substrates and signaling factors on cell receptors and subcellular systems biology. Results: We introduce BioFVM, a diffusive transport solver tailored to biological problems. BioFVM can simulate release and uptake of many substrates by cell and bulk sources, diffusion and de...
Wang, S.; De Hoop, M. V.; Xia, J.; Li, X.
2011-12-01
We consider the modeling of elastic seismic wave propagation on a rectangular domain via the discretization and solution of the inhomogeneous coupled Helmholtz equation in 3D, by exploiting a parallel multifrontal sparse direct solver equipped with Hierarchically Semi-Separable (HSS) structure to reduce the computational complexity and storage. In particular, we are concerned with solving this equation on a large domain, for a large number of different forcing terms in the context of seismic problems in general, and modeling in particular. We resort to a parsimonious mixed grid finite differences scheme for discretizing the Helmholtz operator and Perfect Matched Layer boundaries, resulting in a non-Hermitian matrix. We make use of a nested dissection based domain decomposition, and introduce an approximate direct solver by developing a parallel HSS matrix compression, factorization, and solution approach. We cast our massive parallelization in the framework of the multifrontal method. The assembly tree is partitioned into local trees and a global tree. The local trees are eliminated independently in each processor, while the global tree is eliminated through massive communication. The solver for the inhomogeneous equation is a parallel hybrid between multifrontal and HSS structure. The computational complexity associated with the factorization is almost linear with the size of the Helmholtz matrix. Our numerical approach can be compared with the spectral element method in 3D seismic applications.
Parallel load balancing strategy for Volume-of-Fluid methods on 3-D unstructured meshes
Jofre, Lluís; Borrell, Ricard; Lehmkuhl, Oriol; Oliva, Assensi
2015-02-01
Volume-of-Fluid (VOF) is one of the methods of choice to reproduce the interface motion in the simulation of multi-fluid flows. One of its main strengths is its accuracy in capturing sharp interface geometries, although requiring for it a number of geometric calculations. Under these circumstances, achieving parallel performance on current supercomputers is a must. The main obstacle for the parallelization is that the computing costs are concentrated only in the discrete elements that lie on the interface between fluids. Consequently, if the interface is not homogeneously distributed throughout the domain, standard domain decomposition (DD) strategies lead to imbalanced workload distributions. In this paper, we present a new parallelization strategy for general unstructured VOF solvers, based on a dynamic load balancing process complementary to the underlying DD. Its parallel efficiency has been analyzed and compared to the DD one using up to 1024 CPU-cores on an Intel SandyBridge based supercomputer. The results obtained on the solution of several artificially generated test cases show a speedup of up to ∼12× with respect to the standard DD, depending on the interface size, the initial distribution and the number of parallel processes engaged. Moreover, the new parallelization strategy presented is of general purpose, therefore, it could be used to parallelize any VOF solver without requiring changes on the coupled flow solver. Finally, note that although designed for the VOF method, our approach could be easily adapted to other interface-capturing methods, such as the Level-Set, which may present similar workload imbalances.
Parallel 3-D particle-in-cell modelling of charged ultrarelativistic beam dynamics
Boronina, Marina A.; Vshivkov, Vitaly A.
2015-12-01
> ) in supercolliders. We use the 3-D set of Maxwell's equations for the electromagnetic fields, and the Vlasov equation for the distribution function of the beam particles. The model incorporates automatically the longitudinal effects, which can play a significant role in the cases of super-high densities. We present numerical results for the dynamics of two focused ultrarelativistic beams with a size ratio 10:1:100. The results demonstrate high efficiency of the proposed computational methods and algorithms, which are applicable to a variety of problems in relativistic plasma physics.
Schultz, A.
2010-12-01
3D forward solvers lie at the core of inverse formulations used to image the variation of electrical conductivity within the Earth's interior. This property is associated with variations in temperature, composition, phase, presence of volatiles, and in specific settings, the presence of groundwater, geothermal resources, oil/gas or minerals. The high cost of 3D solutions has been a stumbling block to wider adoption of 3D methods. Parallel algorithms for modeling frequency domain 3D EM problems have not achieved wide scale adoption, with emphasis on fairly coarse grained parallelism using MPI and similar approaches. The communications bandwidth as well as the latency required to send and receive network communication packets is a limiting factor in implementing fine grained parallel strategies, inhibiting wide adoption of these algorithms. Leading Graphics Processor Unit (GPU) companies now produce GPUs with hundreds of GPU processor cores per die. The footprint, in silicon, of the GPU's restricted instruction set is much smaller than the general purpose instruction set required of a CPU. Consequently, the density of processor cores on a GPU can be much greater than on a CPU. GPUs also have local memory, registers and high speed communication with host CPUs, usually through PCIe type interconnects. The extremely low cost and high computational power of GPUs provides the EM geophysics community with an opportunity to achieve fine grained (i.e. massive) parallelization of codes on low cost hardware. The current generation of GPUs (e.g. NVidia Fermi) provides 3 billion transistors per chip die, with nearly 500 processor cores and up to 6 GB of fast (DDR5) GPU memory. This latest generation of GPU supports fast hardware double precision (64 bit) floating point operations of the type required for frequency domain EM forward solutions. Each Fermi GPU board can sustain nearly 1 TFLOP in double precision, and multiple boards can be installed in the host computer system. We
Wei-Fan Chen; Hsin-Yi Lai; Cha'o-Kuang Chen
2012-01-01
The velocity profile and pressure gradient of an unsteady state unidirectional MHD flow of Voigt fluids moving between two parallel surfaces under magnetic field effects are solved by the Laplace transform method. The flow motion between parallel surfaces is induced by a prescribed inlet volume flow rate that varies with time. Four cases of different inlet volume flow rates are considered in this study including (1) constant acceleration piston motion, (2) suddenly started flow, (3) linear ac...
Simulation of the 3D viscoelastic free surface flow by a parallel corrected particle scheme
Jin-Lian, Ren; Tao, Jiang
2016-02-01
In this work, the behavior of the three-dimensional (3D) jet coiling based on the viscoelastic Oldroyd-B model is investigated by a corrected particle scheme, which is named the smoothed particle hydrodynamics with corrected symmetric kernel gradient and shifting particle technique (SPH_CS_SP) method. The accuracy and stability of SPH_CS_SP method is first tested by solving Poiseuille flow and Taylor-Green flow. Then the capacity for the SPH_CS_SP method to solve the viscoelastic fluid is verified by the polymer flow through a periodic array of cylinders. Moreover, the convergence of the SPH_CS_SP method is also investigated. Finally, the proposed method is further applied to the 3D viscoelastic jet coiling problem, and the influences of macroscopic parameters on the jet coiling are discussed. The numerical results show that the SPH_CS_SP method has higher accuracy and better stability than the traditional SPH method and other corrected SPH method, and can improve the tensile instability. Project supported by the Natural Science Foundation of Jiangsu Province, China (Grant Nos. BK20130436 and BK20150436) and the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, China (Grant No. 15KJB110025).
Chu, Chunlei
2009-01-01
The major performance bottleneck of the parallel Fourier method on distributed memory systems is the network communication cost. In this study, we investigate the potential of using non‐blocking all‐to‐all communications to solve this problem by overlapping computation and communication. We present the runtime comparison of a 3D seismic modeling problem with the Fourier method using non‐blocking and blocking calls, respectively, on a Linux cluster. The data demonstrate that a performance improvement of up to 40% can be achieved by simply changing blocking all‐to‐all communication calls to non‐blocking ones to introduce the overlapping capability. A 3D reverse‐time migration result is also presented as an extension to the modeling work based on non‐blocking collective communications.
High-Performance Computation of Distributed-Memory Parallel 3D Voronoi and Delaunay Tessellation
Peterka, Tom; Morozov, Dmitriy; Phillips, Carolyn
2014-11-14
Computing a Voronoi or Delaunay tessellation from a set of points is a core part of the analysis of many simulated and measured datasets: N-body simulations, molecular dynamics codes, and LIDAR point clouds are just a few examples. Such computational geometry methods are common in data analysis and visualization; but as the scale of simulations and observations surpasses billions of particles, the existing serial and shared-memory algorithms no longer suffice. A distributed-memory scalable parallel algorithm is the only feasible approach. The primary contribution of this paper is a new parallel Delaunay and Voronoi tessellation algorithm that automatically determines which neighbor points need to be exchanged among the subdomains of a spatial decomposition. Other contributions include periodic and wall boundary conditions, comparison of our method using two popular serial libraries, and application to numerous science datasets.
Calibration of 3-d.o.f. Translational Parallel Manipulators Using Leg Observations
Pashkevich, Anatoly; Wenger, Philippe; Gomolitsky, Roman
2009-01-01
The paper proposes a novel approach for the geometrical model calibration of quasi-isotropic parallel kinematic mechanisms of the Orthoglide family. It is based on the observations of the manipulator leg parallelism during motions between the specific test postures and employs a low-cost measuring system composed of standard comparator indicators attached to the universal magnetic stands. They are sequentially used for measuring the deviation of the relevant leg location while the manipulator moves the TCP along the Cartesian axes. Using the measured differences, the developed algorithm estimates the joint offsets and the leg lengths that are treated as the most essential parameters. Validity of the proposed calibration technique is confirmed by the experimental results.
Large-scale Parallel Unstructured Mesh Computations for 3D High-lift Analysis
Mavriplis, Dimitri J.; Pirzadeh, S.
1999-01-01
A complete "geometry to drag-polar" analysis capability for the three-dimensional high-lift configurations is described. The approach is based on the use of unstructured meshes in order to enable rapid turnaround for complicated geometries that arise in high-lift configurations. Special attention is devoted to creating a capability for enabling analyses on highly resolved grids. Unstructured meshes of several million vertices are initially generated on a work-station, and subsequently refined on a supercomputer. The flow is solved on these refined meshes on large parallel computers using an unstructured agglomeration multigrid algorithm. Good prediction of lift and drag throughout the range of incidences is demonstrated on a transport take-off configuration using up to 24.7 million grid points. The feasibility of using this approach in a production environment on existing parallel machines is demonstrated, as well as the scalability of the solver on machines using up to 1450 processors.
Multiscale simulation of mixing processes using 3D-parallel, fluid-structure interaction techniques
Valette, Rudy; Vergnes, Bruno; Coupez, Thierry
2008-01-01
International audience This work focuses on the development of a general finite element code, called Ximex®, devoted to the three-dimensional direct simulation of mixing processes of complex fluids. The code is based on a simplified fictitious domain method coupled with a "level-set" approach to represent the rigid moving boundaries, such as screws and rotors, as well as free surfaces. These techniques, combined with the use of parallel computing, allow computing the time-dependent flow of...
Task-parallel implementation of 3D shortest path raytracing for geophysical applications
Giroux, Bernard; Larouche, Benoît
2013-04-01
This paper discusses two variants of the shortest path method and their parallel implementation on a shared-memory system. One variant is designed to perform raytracing in models with stepwise distributions of interval velocity while the other is better suited for continuous velocity models. Both rely on a discretization scheme where primary nodes are located at the corners of cuboid cells and where secondary nodes are found on the edges and sides of the cells. The parallel implementations allow raytracing concurrently for different sources, providing an attractive framework for ray-based tomography. The accuracy and performance of the implementations were measured by comparison with the analytic solution for a layered model and for a vertical gradient model. Mean relative error less than 0.2% was obtained with 5 secondary nodes for the layered model and 9 secondary nodes for the gradient model. Parallel performance depends on the level of discretization refinement, on the number of threads, and on the problem size, with the most determinant variable being the level of discretization refinement (number of secondary nodes). The results indicate that a good trade-off between speed and accuracy is achieved with the number of secondary nodes equal to 5. The programs are written in C++ and rely on the Standard Template Library and OpenMP.
A new ray-tracing scheme for 3D diffuse radiation transfer on highly parallel architectures
Tanaka, Satoshi; Okamoto, Takashi; Hasegawa, Kenji
2014-01-01
We present a new numerical scheme to solve the transfer of diffuse radiation on three-dimensional mesh grids which is efficient on processors with highly parallel architecture such as recently popular GPUs and CPUs with multi- and many-core architectures. The scheme is based on the ray-tracing method and the computational cost is proportional to $N_{\\rm m}^{5/3}$ where $N_{\\rm m}$ is the number of mesh grids, and is devised to compute the radiation transfer along each light-ray completely in parallel with appropriate grouping of the light-rays. We find that the performance of our scheme scales well with the number of adopted CPU cores and GPUs, and also that our scheme is nicely parallelized on a multi-node system by adopting the multiple wave front scheme, and the performance scales well with the amount of the computational resources. As numerical tests to validate our scheme and to give a physical criterion for the angular resolution of our ray-tracing scheme, we perform several numerical simulations of the...
Hybrid shared/distributed parallelism for 3D characteristics transport solvers
In this paper, we will present a new hybrid parallel model for solving large-scale 3-dimensional neutron transport problems used in nuclear reactor simulations. Large heterogeneous reactor problems, like the ones that occurs when simulating Candu cores, have remained computationally intensive and impractical for routine applications on single-node or even vector computers. Based on the characteristics method, this new model is designed to solve the transport equation after distributing the calculation load on a network of shared memory multi-processors. The tracks are either generated on the fly at each characteristics sweep or stored in sequential files. The load balancing is taken into account by estimating the calculation load of tracks and by distributing batches of uniform load on each node of the network. Moreover, the communication overhead can be predicted after benchmarking the latency and bandwidth using appropriate network test suite. These models are useful for predicting the performance of the parallel applications and to analyze the scalability of the parallel systems. (authors)
A new ray-tracing scheme for 3D diffuse radiation transfer on highly parallel architectures
Tanaka, Satoshi; Yoshikawa, Kohji; Okamoto, Takashi; HASEGAWA, Kenji
2014-01-01
We present a new numerical scheme to solve the transfer of diffuse radiation on three-dimensional mesh grids which is efficient on processors with highly parallel architecture such as recently popular GPUs and CPUs with multi- and many-core architectures. The scheme is based on the ray-tracing method and the computational cost is proportional to $N_{\\rm m}^{5/3}$ where $N_{\\rm m}$ is the number of mesh grids, and is devised to compute the radiation transfer along each light-ray completely in ...
3D parallel-detection microwave tomography for clinical breast imaging
Epstein, N. R., E-mail: nepstein@ucalgary.ca [Schulich School of Engineering, University of Calgary, 2500 University Dr. NW, Calgary, Alberta T2N 1N4 (Canada); Meaney, P. M. [Thayer School of Engineering, Dartmouth College, 14 Engineering Dr., Hanover, New Hampshire 03755 (United States); Paulsen, K. D. [Thayer School of Engineering, Dartmouth College, 14 Engineering Dr., Hanover, New Hampshire 03755 (United States); Department of Radiology, Geisel School of Medicine, Dartmouth College, Hanover, New Hampshire 03755 (United States); Norris Cotton Cancer Center, Dartmouth Hitchcock Medical Center, Lebanon, New Hampshire 03756 (United States); Advanced Surgical Center, Dartmouth Hitchcock Medical Center, Lebanon, New Hampshire 03756 (United States)
2014-12-15
A biomedical microwave tomography system with 3D-imaging capabilities has been constructed and translated to the clinic. Updates to the hardware and reconfiguration of the electronic-network layouts in a more compartmentalized construct have streamlined system packaging. Upgrades to the data acquisition and microwave components have increased data-acquisition speeds and improved system performance. By incorporating analog-to-digital boards that accommodate the linear amplification and dynamic-range coverage our system requires, a complete set of data (for a fixed array position at a single frequency) is now acquired in 5.8 s. Replacement of key components (e.g., switches and power dividers) by devices with improved operational bandwidths has enhanced system response over a wider frequency range. High-integrity, low-power signals are routinely measured down to −130 dBm for frequencies ranging from 500 to 2300 MHz. Adequate inter-channel isolation has been maintained, and a dynamic range >110 dB has been achieved for the full operating frequency range (500–2900 MHz). For our primary band of interest, the associated measurement deviations are less than 0.33% and 0.5° for signal amplitude and phase values, respectively. A modified monopole antenna array (composed of two interwoven eight-element sub-arrays), in conjunction with an updated motion-control system capable of independently moving the sub-arrays to various in-plane and cross-plane positions within the illumination chamber, has been configured in the new design for full volumetric data acquisition. Signal-to-noise ratios (SNRs) are more than adequate for all transmit/receive antenna pairs over the full frequency range and for the variety of in-plane and cross-plane configurations. For proximal receivers, in-plane SNRs greater than 80 dB are observed up to 2900 MHz, while cross-plane SNRs greater than 80 dB are seen for 6 cm sub-array spacing (for frequencies up to 1500 MHz). We demonstrate accurate
The linear Boltzmann transport equation (BTE) is an integro-differential equation arising in deterministic models of neutral and charged particle transport. In slab (one-dimensional Cartesian) geometry and certain higher-dimensional cases, Diffusion Synthetic Acceleration (DSA) is known to be an effective algorithm for the iterative solution of the discretized BTE. Fourier and asymptotic analyses have been applied to various idealizations (e.g., problems on infinite domains with constant coefficients) to obtain sharp bounds on the convergence rate of DSA in such cases. While DSA has been shown to be a highly effective acceleration (or preconditioning) technique in one-dimensional problems, it has been observed to be less effective in higher dimensions. This is due in part to the expense of solving the related diffusion linear system. We investigate here the effectiveness of a parallel semicoarsening multigrid (SMG) solution approach to DSA preconditioning in several three dimensional problems. In particular, we consider the algorithmic and implementation scalability of a parallel SMG-DSA preconditioner on several types of test problems
Parallel unstructured mesh optimisation for 3D radiation transport and fluids modelling
In this paper we describe the theory and application of a parallel mesh optimisation procedure to obtain self-adapting finite element solutions on unstructured tetrahedral grids. The optimisation procedure adapts the tetrahedral mesh to the solution of a radiation transport or fluid flow problem without sacrificing the integrity of the boundary (geometry), or internal boundaries (regions) of the domain. The objective is to obtain a mesh which has both a uniform interpolation error in any direction and the element shapes are of good quality. This is accomplished with use of a non-Euclidean (anisotropic) metric which is related to the Hessian of the solution field. Appropriate scaling of the metric enables the resolution of multi-scale phenomena as encountered in transient incompressible fluids and multigroup transport calculations. The resulting metric is used to calculate element size and shape quality. The mesh optimisation method is based on a series of mesh connectivity and node position searches of the landscape defining mesh quality which is gauged by a functional. The mesh modification thus fits the solution field(s) in an optimal manner. The parallel mesh optimisation/adaptivity procedure presented in this paper is of general applicability. We illustrate this by applying it to a transient CFD (computational fluid dynamics) problem. Incompressible flow past a cylinder at moderate Reynolds numbers is modelled to demonstrate that the mesh can follow transient flow features. (authors)
A spherical harmonics research code (DANTE) has been developed which is compatible with parallel computer architectures. DANTE provides 3-D, multi-material, deterministic, transport capabilities using an arbitrary finite element mesh. The linearized Boltzmann transport equation is solved in a second order self-adjoint form utilizing a Galerkin finite element spatial differencing scheme. The core solver utilizes a preconditioned conjugate gradient algorithm. Other distinguishing features of the code include options for discrete-ordinates and simplified spherical harmonics angular differencing, an exact Marshak boundary treatment for arbitrarily oriented boundary faces, in-line matrix construction techniques to minimize memory consumption, and an effective diffusion based preconditioner for scattering dominated problems. Algorithm efficiency is demonstrated for a massively parallel SIMD architecture (CM-5), and compatibility with MPP multiprocessor platforms or workstation clusters is anticipated
3D interconnect architecture for high-bandwidth massively paralleled imager
The proton radiography group at LANL is developing a fast (5x106 frames/s or 5 megaframe/s) multi-frame imager for use in dynamic radiographic experiments with high-energy protons. The mega-pixel imager will acquire and process a burst of 32 frames captured at inter-frame time ∼200 ns. Real time signal processing and storage requirements for entire frames, of rapidly acquired pixels impose severe demands on the space available for the electronics in a standard monolithic approach. As such, a 3D arrangement of detector and circuit elements is under development. In this scheme, the readout integrated circuits (ROICs) are stacked vertically (like playing cards) into a cube configuration. Another die, a fully depleted pixel photo-diode focal plane array (FPA), is bump bonded to one of the edge surfaces formed by the resulting ROIC cube. Recently, an assembly of the proof-of-principle test cube and sensor has been completed
3D interconnect architecture for high-bandwidth massively paralleled imager
Kwiatkowski, K. E-mail: krisk@lanl.gov; Lyke, J.C.; Wojnarowski, R.J.; Beche, J.-F.; Fillion, R.; Kapusta, C.; Millaud, J.; Saia, R.; Wilke, M.D
2003-08-21
The proton radiography group at LANL is developing a fast (5x10{sup 6} frames/s or 5 megaframe/s) multi-frame imager for use in dynamic radiographic experiments with high-energy protons. The mega-pixel imager will acquire and process a burst of 32 frames captured at inter-frame time {approx}200 ns. Real time signal processing and storage requirements for entire frames, of rapidly acquired pixels impose severe demands on the space available for the electronics in a standard monolithic approach. As such, a 3D arrangement of detector and circuit elements is under development. In this scheme, the readout integrated circuits (ROICs) are stacked vertically (like playing cards) into a cube configuration. Another die, a fully depleted pixel photo-diode focal plane array (FPA), is bump bonded to one of the edge surfaces formed by the resulting ROIC cube. Recently, an assembly of the proof-of-principle test cube and sensor has been completed.
Awatsuji, Yasuhiro; Xia, Peng; Wang, Yexin; Matoba, Osamu
2016-03-01
Digital holography is a technique of 3D measurement of object. The technique uses an image sensor to record the interference fringe image containing the complex amplitude of object, and numerically reconstructs the complex amplitude by computer. Parallel phase-shifting digital holography is capable of accurate 3D measurement of dynamic object. This is because this technique can reconstruct the complex amplitude of object, on which the undesired images are not superimposed, form a single hologram. The undesired images are the non-diffraction wave and the conjugate image which are associated with holography. In parallel phase-shifting digital holography, a hologram, whose phase of the reference wave is spatially and periodically shifted every other pixel, is recorded to obtain complex amplitude of object by single-shot exposure. The recorded hologram is decomposed into multiple holograms required for phase-shifting digital holography. The complex amplitude of the object is free from the undesired images is reconstructed from the multiple holograms. To validate parallel phase-shifting digital holography, a high-speed parallel phase-shifting digital holography system was constructed. The system consists of a Mach-Zehnder interferometer, a continuous-wave laser, and a high-speed polarization imaging camera. Phase motion picture of dynamic air flow sprayed from a nozzle was recorded at 180,000 frames per second (FPS) have been recorded by the system. Also phase motion picture of dynamic air induced by discharge between two electrodes has been recorded at 1,000,000 FPS, when high voltage was applied between the electrodes.
This paper deals with 3D MHD modelling of the behaviour of a tetrafluoromethane (CF4) plasma arc in a batch reactor under peculiar conditions of low current (0.35 A) and very high pressure (50 atm). The first part of the manuscript presents results for a horizontal configuration of the reactor, as is undertaken experimentally. The model has led to the understanding of the instabilities observed experimentally for such unusual operating conditions. The curved shape of the arc and the sliding of the anodic arc root along the electrode have been revealed to be the source of the experimental instabilities. The latter part of the manuscript investigates the effect of two vertical configurations of the reactor; with a cathode at the top and cathode at the bottom to overcome the instabilities. In these reactor configurations, the arc is much more stable and stays centred in the middle of the electrodes. These configurations are more suitable for the stability of the arc discharge, but have to be verified experimentally. (paper)
Implementation of a 3D plasma particle-in-cell code on a MIMD parallel computer
A three-dimensional plasma particle-in-cell (PIC) code has been implemented on the Intel Delta MIMD parallel supercomputer using the General Concurrent PIC algorithm. The GCPIC algorithm uses a domain decomposition to divide the computation among the processors: A processor is assigned a subdomain and all the particles in it. Particles must be exchanged between processors as they move. Results are presented comparing the efficiency for 1-, 2- and 3-dimensional partitions of the three dimensional domain. This algorithm has been found to be very efficient even when a large fraction (e.g. 30%) of the particles must be exchanged at every time step. On the 512-node Intel Delta, up to 125 million particles have been pushed with an electrostatic push time of under 500 nsec/particle/time step
A Case Study of a Hybrid Parallel 3D Surface Rendering Graphics Architecture
Holten-Lund, Hans Erik; Madsen, Jan; Pedersen, Steen
1997-01-01
This paper presents a case study in the design strategy used inbuilding a graphics computer, for drawing very complex 3Dgeometric surfaces. The goal is to build a PC based computer systemcapable of handling surfaces built from about 2 million triangles, andto be able to render a perspective view...... of these on a computer displayat interactive frame rates, i.e. processing around 50 milliontriangles per second. The paper presents a hardware/softwarearchitecture called HPGA (Hybrid Parallel Graphics Architecture) whichis likely to be able to carry out this task. The case study focuses ontechniques to increase...... the clock frequency as well as the parallelismof the system. This paper focuses on the back-end graphics pipeline,which is responsible for rasterizing triangles.%with a practically linear increase in performance. A pure software implementation of the proposed architecture iscurrently able to process 300...
Parallel CFD simulation of flow in a 3D model of vibrating human vocal folds
Šidlof, Petr; Horáček, Jaromír; Řidký, V.
2013-01-01
Roč. 80, č. 1 (2013), s. 290-300. ISSN 0045-7930 R&D Projects: GA ČR(CZ) GAP101/11/0207 Institutional research plan: CEZ:AV0Z20760514 Keywords : numerical simulation * vocal folds * glottal airflow * inite volume method * parallel CFD Subject RIV: BI - Acoustics Impact factor: 1.532, year: 2013 http://www.sciencedirect.com/science?_ob=ArticleListURL&_method=list&_ArticleListID=-268060849&_sort=r&_st=13&view=c&_acct=C000034318&_version=1&_urlVersion=0&_userid=640952&md5=7c5b5539857ee9a02af5e690585b3126&searchtype=a
Hybrid Characteristics: 3D radiative transfer for parallel adaptive mesh refinement hydrodynamics
Rijkhorst, E J; Dubey, A; Mellema, G R; Rijkhorst, Erik-Jan; Plewa, Tomasz; Dubey, Anshu; Mellema, Garrelt
2005-01-01
We have developed a three-dimensional radiative transfer method designed specifically for use with parallel adaptive mesh refinement hydrodynamics codes. This new algorithm, which we call hybrid characteristics, introduces a novel form of ray tracing that can neither be classified as long, nor as short characteristics, but which applies the underlying principles, i.e. efficient execution through interpolation and parallelizability, of both. Primary applications of the hybrid characteristics method are radiation hydrodynamics problems that take into account the effects of photoionization and heating due to point sources of radiation. The method is implemented in the hydrodynamics package FLASH. The ionization, heating, and cooling processes are modelled using the DORIC ionization package. Upon comparison with the long characteristics method, we find that our method calculates the column density with a similarly high accuracy and produces sharp and well defined shadows. We show the quality of the new algorithm ...
A parallel block multi-level preconditioner for the 3D incompressible Navier-Stokes equations
The development of robust and efficient algorithms for both steady-state simulations and fully implicit time integration of the Navier-Stokes equations is an active research topic. To be effective, the linear subproblems generated by these methods require solution techniques that exhibit robust and rapid convergence. In particular, they should be insensitive to parameters in the problem such as mesh size, time step, and Reynolds number. In this context, we explore a parallel preconditioner based on a block factorization of the coefficient matrix generated in an Oseen nonlinear iteration for the primitive variable formulation of the system. The key to this preconditioner is the approximation of a certain Schur complement operator by a technique first proposed by Kay, Loghin, and Wathen [SIAM J. Sci. Comput., 2002] and Silvester, Elman, Kay, and Wathen [J. Comput. Appl. Math. 128 (2001) 261]. The resulting operator entails subsidiary computations (solutions of pressure Poisson and convection-diffusion subproblems) that are similar to those required for decoupled solution methods; however, in this case these solutions are applied as preconditioners to the coupled Oseen system. One important aspect of this approach is that the convection-diffusion and Poisson subproblems are significantly easier to solve than the entire coupled system, and a solver can be built using tools developed for the subproblems. In this paper, we apply smoothed aggregation algebraic multigrid to both subproblems. Previous work has focused on demonstrating the optimality of these preconditioners with respect to mesh size on serial, two-dimensional, steady-state computations employing geometric multi-grid methods; we focus on extending these methods to large-scale, parallel, three-dimensional, transient and steady-state simulations employing algebraic multigrid (AMG) methods. Our results display nearly optimal convergence rates for steady-state solutions as well as for transient solutions over a
3D Profile Filter Algorithm Based on Parallel Generalized B-spline Approximating Gaussian
REN Zhiying; GAO Chenghui; SHEN Ding
2015-01-01
Currently, the approximation methods of the Gaussian filter by some other spline filters have been developed. However, these methods are only suitable for the study of one-dimensional filtering, when these methods are used for three-dimensional filtering, it is found that a rounding error and quantization error would be passed to the next in every part. In this paper, a new and high-precision implementation approach for Gaussian filter is described, which is suitable for three-dimensional reference filtering. Based on the theory of generalized B-spline function and the variational principle, the transmission characteristics of a digital filter can be changed through the sensitivity of the parameters (t1, t2), and which can also reduce the rounding error and quantization error by the filter in a parallel form instead of the cascade form. Finally, the approximation filter of Gaussian filter is obtained. In order to verify the feasibility of the new algorithm, the reference extraction of the conventional methods are also used and compared. The experiments are conducted on the measured optical surface, and the results show that the total calculation by the new algorithm only requires 0.07 s for 480´480 data points;the amplitude deviation between the reference of the parallel form filter and the Gaussian filter is smaller;the new method is closer to the characteristic of the Gaussian filter through the analysis of three-dimensional roughness parameters, comparing with the cascade generalized B-spline approximating Gaussian. So the new algorithm is also efficient and accurate for the implementation of Gaussian filter in the application of surface roughness measurement.
A 3D MPI-Parallel GPU-accelerated framework for simulating ocean wave energy converters
Pathak, Ashish; Raessi, Mehdi
2015-11-01
We present an MPI-parallel GPU-accelerated computational framework for studying the interaction between ocean waves and wave energy converters (WECs). The computational framework captures the viscous effects, nonlinear fluid-structure interaction (FSI), and breaking of waves around the structure, which cannot be captured in many potential flow solvers commonly used for WEC simulations. The full Navier-Stokes equations are solved using the two-step projection method, which is accelerated by porting the pressure Poisson equation to GPUs. The FSI is captured using the numerically stable fictitious domain method. A novel three-phase interface reconstruction algorithm is used to resolve three phases in a VOF-PLIC context. A consistent mass and momentum transport approach enables simulations at high density ratios. The accuracy of the overall framework is demonstrated via an array of test cases. Numerical simulations of the interaction between ocean waves and WECs are presented. Funding from the National Science Foundation CBET-1236462 grant is gratefully acknowledged.
Borazjani, Iman; Ge, Liang; Le, Trung; Sotiropoulos, Fotis
2013-04-01
We develop an overset-curvilinear immersed boundary (overset-CURVIB) method in a general non-inertial frame of reference to simulate a wide range of challenging biological flow problems. The method incorporates overset-curvilinear grids to efficiently handle multi-connected geometries and increase the resolution locally near immersed boundaries. Complex bodies undergoing arbitrarily large deformations may be embedded within the overset-curvilinear background grid and treated as sharp interfaces using the curvilinear immersed boundary (CURVIB) method (Ge and Sotiropoulos, Journal of Computational Physics, 2007). The incompressible flow equations are formulated in a general non-inertial frame of reference to enhance the overall versatility and efficiency of the numerical approach. Efficient search algorithms to identify areas requiring blanking, donor cells, and interpolation coefficients for constructing the boundary conditions at grid interfaces of the overset grid are developed and implemented using efficient parallel computing communication strategies to transfer information among sub-domains. The governing equations are discretized using a second-order accurate finite-volume approach and integrated in time via an efficient fractional-step method. Various strategies for ensuring globally conservative interpolation at grid interfaces suitable for incompressible flow fractional step methods are implemented and evaluated. The method is verified and validated against experimental data, and its capabilities are demonstrated by simulating the flow past multiple aquatic swimmers and the systolic flow in an anatomic left ventricle with a mechanical heart valve implanted in the aortic position. PMID:23833331
Koldan, Jelena; Puzyrev, Vladimir; de la Puente, Josep; Houzeaux, Guillaume; Cela, José María
2014-06-01
We present an elaborate preconditioning scheme for Krylov subspace methods which has been developed to improve the performance and reduce the execution time of parallel node-based finite-element (FE) solvers for 3-D electromagnetic (EM) numerical modelling in exploration geophysics. This new preconditioner is based on algebraic multigrid (AMG) that uses different basic relaxation methods, such as Jacobi, symmetric successive over-relaxation (SSOR) and Gauss-Seidel, as smoothers and the wave front algorithm to create groups, which are used for a coarse-level generation. We have implemented and tested this new preconditioner within our parallel nodal FE solver for 3-D forward problems in EM induction geophysics. We have performed series of experiments for several models with different conductivity structures and characteristics to test the performance of our AMG preconditioning technique when combined with biconjugate gradient stabilized method. The results have shown that, the more challenging the problem is in terms of conductivity contrasts, ratio between the sizes of grid elements and/or frequency, the more benefit is obtained by using this preconditioner. Compared to other preconditioning schemes, such as diagonal, SSOR and truncated approximate inverse, the AMG preconditioner greatly improves the convergence of the iterative solver for all tested models. Also, when it comes to cases in which other preconditioners succeed to converge to a desired precision, AMG is able to considerably reduce the total execution time of the forward-problem code-up to an order of magnitude. Furthermore, the tests have confirmed that our AMG scheme ensures grid-independent rate of convergence, as well as improvement in convergence regardless of how big local mesh refinements are. In addition, AMG is designed to be a black-box preconditioner, which makes it easy to use and combine with different iterative methods. Finally, it has proved to be very practical and efficient in the
Gainullin, I. K.; Sonkin, M. A.
2015-03-01
A parallelized three-dimensional (3D) time-dependent Schrodinger equation (TDSE) solver for one-electron systems is presented in this paper. The TDSE Solver is based on the finite-difference method (FDM) in Cartesian coordinates and uses a simple and explicit leap-frog numerical scheme. The simplicity of the numerical method provides very efficient parallelization and high performance of calculations using Graphics Processing Units (GPUs). For example, calculation of 106 time-steps on the 1000ṡ1000ṡ1000 numerical grid (109 points) takes only 16 hours on 16 Tesla M2090 GPUs. The TDSE Solver demonstrates scalability (parallel efficiency) close to 100% with some limitations on the problem size. The TDSE Solver is validated by calculation of energy eigenstates of the hydrogen atom (13.55 eV) and affinity level of H- ion (0.75 eV). The comparison with other TDSE solvers shows that a GPU-based TDSE Solver is 3 times faster for the problems of the same size and with the same cost of computational resources. The usage of a non-regular Cartesian grid or problem-specific non-Cartesian coordinates increases this benefit up to 10 times. The TDSE Solver was applied to the calculation of the resonant charge transfer (RCT) in nanosystems, including several related physical problems, such as electron capture during H+-H0 collision and electron tunneling between H- ion and thin metallic island film.
Odelu Ojjela; Naresh Kumar, N.
2016-01-01
The objective of the present study is to investigate the first-order chemical reaction and Soret and Dufour effects on an incompressible MHD combined free and forced convection heat and mass transfer of a micropolar fluid through a porous medium between two parallel plates. Assume that there are a periodic injection and suction at the lower and upper plates. The nonuniform temperature and concentration of the plates are assumed to be varying periodically with time. A suitable similarity trans...
Ma, Yingliang; Saetzler, Kurt
2008-01-01
In this paper we describe a novel 3D subdivision strategy to extract the surface of binary image data. This iterative approach generates a series of surface meshes that capture different levels of detail of the underlying structure. At the highest level of detail, the resulting surface mesh generated by our approach uses only about 10% of the triangles in comparison to the marching cube algorithm (MC) even in settings were almost no image noise is present. Our approach also eliminates the so-called "staircase effect" which voxel based algorithms like the MC are likely to show, particularly if non-uniformly sampled images are processed. Finally, we show how the presented algorithm can be parallelized by subdividing 3D image space into rectilinear blocks of subimages. As the algorithm scales very well with an increasing number of processors in a multi-threaded setting, this approach is suited to process large image data sets of several gigabytes. Although the presented work is still computationally more expensive than simple voxel-based algorithms, it produces fewer surface triangles while capturing the same level of detail, is more robust towards image noise and eliminates the above-mentioned "staircase" effect in anisotropic settings. These properties make it particularly useful for biomedical applications, where these conditions are often encountered. PMID:17993710
Wei-Fan Chen
2012-01-01
Full Text Available The velocity profile and pressure gradient of an unsteady state unidirectional MHD flow of Voigt fluids moving between two parallel surfaces under magnetic field effects are solved by the Laplace transform method. The flow motion between parallel surfaces is induced by a prescribed inlet volume flow rate that varies with time. Four cases of different inlet volume flow rates are considered in this study including (1 constant acceleration piston motion, (2 suddenly started flow, (3 linear acceleration piston motion, and (4 oscillatory piston motion. The solution for each case is elaborately derived, and the results of associated velocity profile and pressure gradients are presented in analytical forms.
Jia, Xuanji; Zhou, Yong
2015-09-01
We prove that a weak solution (u, b) to the MHD equations is smooth on (0, T ] if \\text{M}\\in {{L}α}≤ft(0,T;{{L}γ}≤ft({{{R}}3}\\right)\\right) with 2/α +3/γ =2 , 1≤slant α definition below). As we will explain later, this kind of regularity criteria is more likely to capture the nature of the coupling effects between the fluid velocity and the magnetic field in the evolution of the MHD flows. Moreover, the condition on \\text{M} is scaling invariant, i.e. it is of Ladyzhenskaya-Prodi-Serrin type.
1 - Description of program or function: PARTISN (Parallel, Time-Dependent SN) is the evolutionary successor to CCC-0547/DANTSYS. User input and cross section formats are very similar to that of DANTSYS. The linear Boltzmann transport equation is solved for neutral particles using the deterministic (SN) method. Both the static (fixed source or eigenvalue) and time-dependent forms of the transport equation are solved in forward or adjoint mode. Vacuum, reflective, periodic, white, or inhomogeneous boundary conditions are solved. General anisotropic scattering and inhomogeneous sources are permitted. PARTISN solves the transport equation on orthogonal (single level or block-structured AMR) grids in 1-D (slab, two-angle slab, cylindrical, or spherical), 2-D (X-Y, R-Z, or R-T) and 3-D (X-Y-Z or R-Z-T) geometries. 2 - Methods:PARTISN numerically solves the multigroup form of the neutral-particle Boltzmann transport equation. The discrete-ordinates form of approximation is used for treating the angular variation of the particle distribution. For curvilinear geometries, diamond differencing is used for angular discretization. The spatial discretizations may be either low-order (diamond difference or Adaptive Weighted Diamond Difference (AWDD)) or higher-order (linear discontinuous or exponential discontinuous). Negative fluxes are eliminated by a local set-to-zero-and-correct algorithm for the diamond case (DD/STZ). Time differencing is Crank-Nicholson (diamond), also with a set-to-zero fix-up scheme. Both inner and outer iterations can be accelerated using the diffusion synthetic acceleration method, or transport synthetic acceleration can be used to accelerate the inner iterations. The diffusion solver uses either the conjugate gradient or multigrid method. Chebyshev acceleration of the fission source is used. The angular source terms may be treated either via standard PN expansions or Galerkin scattering. An option is provided for strictly positive scattering sources
Koldan, Jelena
2013-01-01
The growing significance, technical development and employment of electromagnetic (EM) methods in exploration geophysics have led to the increasing need for reliable and fast techniques of interpretation of 3-D EM data sets acquired in complex geological environments. The first and most important step to creating an inversion method is the development of a solver for the forward problem. In order to create an efficient, reliable and practical 3-D EM inversion, it is necessary to have a 3-D EM...
Large Scale Earth’s Bow Shock with Northern IMF as Simulated by PIC Code in Parallel with MHD Model
Suleiman Baraka
2016-06-01
In this paper, we propose a 3D kinetic model (particle-in-cell,PIC) for the description of the large scale Earth’s bow shock. Theproposed version is stable and does not require huge or extensive computerresources. Because PIC simulations work with scaled plasma andfield parameters, we also propose to validate our code by comparing itsresults with the available MHD simulations under same scaled solar wind(SW) and (IMF) conditions. We report new results from the two models.In both codes the Earth’s bow shock position is found to be $\\approx 14.8 R_{E} $along the Sun–Earth line, and $\\approx 29 R_{E} $ on the dusk side. Those findingsare consistent with past in \\textit{situ} observations. Both simulations reproducethe theoretical jump conditions at the shock. However, the PIC codedensity and temperature distributions are inflated and slightly shifted sunwardwhen compared to the MHD results. Kinetic electron motions andreflected ions upstream may cause this sunward shift. Species distributionsin the foreshock region are depicted within the transition of theshock (measured $ \\approx $ 2 $ c/\\omega_{pi} $ for $ \\Theta_{Bn}=90^{o}$ and $M_{MS}=4.7 $) and in thedownstream. The size of the foot jump in the magnetic field at the shock ismeasured to be ($1.7 c/ \\omega_{pi} $). In the foreshocked region, the thermal velocityis found equal to 213 km s^{−1} at 15R_{E} and is equal to 63 km s^{-1} at12 R_{E} (magnetosheath region). Despite the large cell size of the currentversion of the PIC code, it is powerful to retain macrostructure of planetsmagnetospheres in very short time, thus it can be used for pedagogicaltest purposes. It is also likely complementary with MHD to deepen ourunderstanding of the large scale magnetosphere.
Large Scale Earth's Bow Shock with Northern IMF as Simulated by PIC Code in Parallel with MHD Model
Baraka, Suleiman
2016-06-01
In this paper, we propose a 3D kinetic model (particle-in-cell, PIC) for the description of the large scale Earth's bow shock. The proposed version is stable and does not require huge or extensive computer resources. Because PIC simulations work with scaled plasma and field parameters, we also propose to validate our code by comparing its results with the available MHD simulations under same scaled solar wind (SW) and (IMF) conditions. We report new results from the two models. In both codes the Earth's bow shock position is found to be ≈14.8 R E along the Sun-Earth line, and ≈29 R E on the dusk side. Those findings are consistent with past in situ observations. Both simulations reproduce the theoretical jump conditions at the shock. However, the PIC code density and temperature distributions are inflated and slightly shifted sunward when compared to the MHD results. Kinetic electron motions and reflected ions upstream may cause this sunward shift. Species distributions in the foreshock region are depicted within the transition of the shock (measured ≈2 c/ ω pi for Θ Bn = 90° and M MS = 4.7) and in the downstream. The size of the foot jump in the magnetic field at the shock is measured to be (1.7 c/ ω pi ). In the foreshocked region, the thermal velocity is found equal to 213 km s-1 at 15 R E and is equal to 63 km s -1 at 12 R E (magnetosheath region). Despite the large cell size of the current version of the PIC code, it is powerful to retain macrostructure of planets magnetospheres in very short time, thus it can be used for pedagogical test purposes. It is also likely complementary with MHD to deepen our understanding of the large scale magnetosphere.
Large Scale Earth's Bow Shock with Northern IMF as simulated by PIC code in parallel with MHD model
Baraka, Suleiman M
2016-01-01
In this paper, we propose a 3D kinetic model (Particle-in-Cell PIC ) for the description of the large scale Earth's bow shock. The proposed version is stable and does not require huge or extensive computer resources. Because PIC simulations work with scaled plasma and field parameters, we also propose to validate our code by comparing its results with the available MHD simulations under same scaled Solar wind ( SW ) and ( IMF ) conditions. We report new results from the two models. In both codes the Earth's bow shock position is found to be ~14.8 RE along the Sun-Earth line, and ~ 29 RE on the dusk side. Those findings are consistent with past in situ observations. Both simulations reproduce the theoretical jump conditions at the shock. However, the PIC code density and temperature distributions are inflated and slightly shifted sunward when compared to the MHD results. Kinetic electron motions and reflected ions upstream may cause this sunward shift. Species distributions in the foreshock region are depicted...
3D Equilibrium Reconstructions in DIII-D
Lao, L. L.; Ferraro, N. W.; Strait, E. J.; Turnbull, A. D.; King, J. D.; Hirshman, H. P.; Lazarus, E. A.; Sontag, A. C.; Hanson, J.; Trevisan, G.
2013-10-01
Accurate and efficient 3D equilibrium reconstruction is needed in tokamaks for study of 3D magnetic field effects on experimentally reconstructed equilibrium and for analysis of MHD stability experiments with externally imposed magnetic perturbations. A large number of new magnetic probes have been recently installed in DIII-D to improve 3D equilibrium measurements and to facilitate 3D reconstructions. The V3FIT code has been in use in DIII-D to support 3D reconstruction and the new magnetic diagnostic design. V3FIT is based on the 3D equilibrium code VMEC that assumes nested magnetic surfaces. V3FIT uses a pseudo-Newton least-square algorithm to search for the solution vector. In parallel, the EFIT equilibrium reconstruction code is being extended to allow for 3D effects using a perturbation approach based on an expansion of the MHD equations. EFIT uses the cylindrical coordinate system and can include the magnetic island and stochastic effects. Algorithms are being developed to allow EFIT to reconstruct 3D perturbed equilibria directly making use of plasma response to 3D perturbations from the GATO, MARS-F, or M3D-C1 MHD codes. DIII-D 3D reconstruction examples using EFIT and V3FIT and the new 3D magnetic data will be presented. Work supported in part by US DOE under DE-FC02-04ER54698, DE-FG02-95ER54309 and DE-AC05-06OR23100.
MHD flow and heat transfer in a rarefied gas in a rotating parallel plate channel
An exact analysis of MHD flow of a rarefied gas in a rotating plane channel is presented for the velocity field, induced magnetic field and temperature field. Axial and transverse components of the velocity field, induced magnetic field and the function affecting the temperature field are shown on graphs. The numerical values of the axial and transverse skin-friction components, axial and transverse components of the mass flux and the function affecting the rate of heat transfer are entered in Tables. The results are discussed. (Auth.)
Mohammad H. Yazdi
2011-12-01
Full Text Available This paper presents a new design of open parallel microchannels embedded within a permeable continuous moving surface due to reduction of exergy losses in magnetohydrodynamic (MHD flow at a prescribed surface temperature (PST. The entropy generation number is formulated by an integral of the local rate of entropy generation along the width of the surface based on an equal number of microchannels and no-slip gaps interspersed between those microchannels. The velocity, the temperature, the velocity gradient and the temperature gradient adjacent to the wall are substituted into this equation resulting from the momentum and energy equations obtained numerically by an explicit Runge-Kutta (4, 5 formula, the Dormand-Prince pair and shooting method. The entropy generation number, as well as the Bejan number, for various values of the involved parameters of the problem are also presented and discussed in detail.
Odelu Ojjela
2016-01-01
Full Text Available The objective of the present study is to investigate the first-order chemical reaction and Soret and Dufour effects on an incompressible MHD combined free and forced convection heat and mass transfer of a micropolar fluid through a porous medium between two parallel plates. Assume that there are a periodic injection and suction at the lower and upper plates. The nonuniform temperature and concentration of the plates are assumed to be varying periodically with time. A suitable similarity transformation is used to reduce the governing partial differential equations into nonlinear ordinary differential equations and then solved numerically by the quasilinearization method. The fluid flow and heat and mass transfer characteristics for various parameters are analyzed in detail and shown in the form of graphs. It is observed that the concentration of the fluid decreases whereas the temperature of the fluid enhances with the increasing of chemical reaction and Soret and Dufour parameters.
Ishak Hashim
2013-11-01
Full Text Available The present study examines embedded open parallel microchannels within a micropatterned permeable surface for reducing entropy generation in MHD fluid flow in microscale systems. A local similarity solution for the transformed governing equations is obtained. The governing partial differential equations along with the boundary conditions are first cast into a dimensionless form and then the reduced ordinary differential equations are solved numerically via the Dormand-Prince pair and shooting method. The dimensionless entropy generation number is formulated by an integral of the local rate of entropy generation along the width of the surface based on an equal number of microchannels and no-slip gaps interspersed between those microchannels. Finally, the entropy generation numbers, as well as the Bejan number, are investigated. It is seen that surface-embedded microchannels can successfully reduce entropy generation in the presence of an applied magnetic field.
Alireza AZIMI
2014-07-01
Full Text Available In this paper the velocity fields associated with the two-dimensional unsteady magnetohydrodynamic (MHD flow of a viscous fluid between moving parallel plates have been investigated. The governing Navier-Stokes equations for the flow are reduced to a fourth order nonlinear ordinary differential equation. The Homotopy Perturbation Method (HPM and Reconstruction of Variational Iteration Method (RVIM have been used to achieve analytical solutions. The obtained approximate results have been compared with numerical ones and results from pervious works in some cases. It has been shown that the current study is accurate and validated and can be used for other nonlinear cases.doi:10.14456/WJST.2014.70
Parallel GRISYS/Power Challenge System Version 1.0 and 3D Prestack Depth Migration Package
Zhao Zhenwen
1995-01-01
@@ Based on the achievements and experience of seismic data parallel processing made in the past years by Beijing Global Software Corporation (GS) of CNPC, Parallel GRISYS/Power Challenge seismic data processing system version 1.0 has been cooperatively developed and integrated on the Power Challenge computer by GS, SGI (USA) and Shuangyuan Company of Academia Sinica.
Gabriele Jost
2010-01-01
Full Text Available Today most systems in high-performance computing (HPC feature a hierarchical hardware design: shared-memory nodes with several multi-core CPUs are connected via a network infrastructure. When parallelizing an application for these architectures it seems natural to employ a hierarchical programming model such as combining MPI and OpenMP. Nevertheless, there is the general lore that pure MPI outperforms the hybrid MPI/OpenMP approach. In this paper, we describe the hybrid MPI/OpenMP parallelization of IR3D (Incompressible Realistic 3-D code, a full-scale real-world application, which simulates the environmental effects on the evolution of vortices trailing behind control surfaces of underwater vehicles. We discuss performance, scalability and limitations of the pure MPI version of the code on a variety of hardware platforms and show how the hybrid approach can help to overcome certain limitations.
Kaldestad, Knut B.; Haddadin, Sami; Belder, Rico; Hovland, Geir; Anisi, David A.
2014-01-01
In this paper we present an experimental study on real-time collision avoidance with potential ﬁelds that are based on 3D point cloud data and processed on the Graphics Processing Unit (GPU). The virtual forces from the potential ﬁelds serve two purposes. First, they are used for changing the reference trajectory. Second they are projected to and applied on torque control level for generating according nullspace behavior together with a Cartesian impedance main control ...
The author's goal is to provide a physical understanding of the ideal MHD model which includes: (1) a basic description of the model, (2) a derivation starting from a more fundamental kinetic model, and (3) a discussion of its range of validity. The ideal MHD model is a single-fluid model that describes the effects of magnetic geometry on the macroscopic equilibrium and stability properties of fusion plasmas. The model is derived in a straight forward manner by forming the mass, momentum, and energy moments of the Boltzmann equation. The moment equations reduce to ideal MHD with the introduction of three critical assumptions: high collisionality, small ion gyro radius, and small resistivity. An analysis of the validity conditions shows that the collision-dominated assumption is never satisfied in plasmas of fusion interest. The remaining two conditions are satisfied by a wide margin. A careful examination of the collision-dominated assumption shows that those particular parts of ideal MHD treated inaccurately (i.e., the parallel momentum and energy equations), play little, if any practical role in MHD equilibrium and stability. These equations primarily describe compression and expansion of a plasma whereas most MHD instabilities involve incompressible motions. The model is incorrect only where it does not matter. This realization leads to the introduction of a modified MHD model known as collisionless MHD which makes predictions nearly identical to collision-dominated assumption. It is thus valid for plasmas of fusion interest. The derivation follows from an analysis of single-particle guiding center motion in a collisionless plasma and the subsequent closure of the system by the heuristic assumption that the motions of interest are incompressible
Hybrid MPI+OpenMP parallelization of an FFT-based 3D Poisson solver with one periodic direction
Gorobets, Andrei; Trias Miquel, Francesc Xavier; Borrell Pol, Ricard; Lehmkuhl Barba, Oriol; Oliva Llena, Asensio
2011-01-01
This work is devoted to the development of efficient parallel algorithms for the direct numerical simulation (DNS) of incompressible flows on modern supercomputers. In doing so, a Poisson equation needs to be solved at each time-step to project the velocity field onto a divergence-free space. Due to the non-local nature of its solution, this elliptic system is the part of the algorithm that is most difficult to parallelize. The Poisson solver presented here is restricted to problems with o...
The finite element-based Continuum Damage Mechanics (CDM) software DAMAGE XXX has been developed: to model high-temperature creep damage initiation, evolution and crack growth in 3-D engineering components; and, to run on parallel computer architectures. The driver has been to achieve computational speed through computer parallelism. The development and verification of the software have been carried out using uni-axial crosswelded testpieces in which the plane of symmetry of the V-weld preparation is orthogonal to the tensile loading axis. The welds were manufactured using 0.5Cr-0.5Mo-0.25V ferritic parent steel, and a matching 2.25Cr-1Mo ferritic steel weld filler metal. The Heat Affected Zones (HAZ) of welds were assumed to be divided into three sub-regions: Coarse grained-HAZ (CG-HAZ); Refined grained-HAZ (R-HAZ); and, the inter-critical HAZ regions (Type IV-HAZ). Constitutive equations and associated parameters are summarised for weld, CG-HAZ, R-HAZ, Type IV-HAZ, and parent materials, at 575, 590, and 600 deg. C. These are used to make finite element-based predictions of crossweld testpiece lifetimes and failure modes using the newly developed 3-D parallel computer software, and independent 2-D serial software, at an average minimum cross-section stress of 69.5 MPa. Crossweld testpiece analyses, done using the newly developed 3-D parallel software, have been verified using independent results of 2-D serial software; and, of laboratory experiments.
Recent 3D hybrid simulation of a plasma current-carrying column revealed two regimes of sausage and kink instability development. In the first regime, with small Hall parameter, development of instabilities leads to appearance of large-scale axial perturbations and eventually to the bending of the plasma column. In the second regime, with five times larger Hall parameter, small-scale perturbations dominated and no bending of the plasma column was observed. Simulation results are compared to recent experimental data, including laser probing, x-ray spectroscopy and time-gated x-ray imaging during wire array implosions at NTF
Castillo-Reyes, Octavio; de la Puente, Josep; Puzyrev, Vladimir; Cela, José M.
2015-01-01
This paper deals with the most relevant parallel and numerical issues that arise when applying the Edge Element Method in the solution of electromagnetic problems in exploration geophysics. In this sense, in recent years the application of land and marine controlled-source electromagnetic (CSEM) surveys has gained tremendous interest among the offshore exploration community. This method is especially significant in detecting hydrocarbon in shallow/deep waters. On the other hand, in Finite Ele...
Bulovyatov, Alexander
2010-01-01
The band structure computation turns into solving a family of Maxwell eigenvalue problems on the periodicity domain. The discretization is done by the finite element method with special higher order H(curl)- and H1-conforming modified elements. The eigenvalue problem is solved by a preconditioned iterative eigenvalue solver with a projection onto the divergence-free vector fields. As a preconditioner we use the parallel multigrid method with a special Hiptmair smoother.
Koldan, Jelena; Puzyrev, Vladimir; de la Puente, Josep; Houzeaux, Guillaume; José M. Cela
2014-01-01
We present an elaborate preconditioning scheme for Krylov subspace methods which has been developed to improve the performance and reduce the execution time of parallel node-based finite-element solvers for three-dimensional electromagnetic numerical modelling in exploration geophysics. This new preconditioner is based on algebraic multigrid that uses different basic relaxation methods, such as Jacobi, symmetric successive over-relaxation and Gauss-Seidel, as smoothers and the wav...
Aftosmis, M. J.; Berger, M. J.; Murman, S. M.; Kwak, Dochan (Technical Monitor)
2002-01-01
The proposed paper will present recent extensions in the development of an efficient Euler solver for adaptively-refined Cartesian meshes with embedded boundaries. The paper will focus on extensions of the basic method to include solution adaptation, time-dependent flow simulation, and arbitrary rigid domain motion. The parallel multilevel method makes use of on-the-fly parallel domain decomposition to achieve extremely good scalability on large numbers of processors, and is coupled with an automatic coarse mesh generation algorithm for efficient processing by a multigrid smoother. Numerical results are presented demonstrating parallel speed-ups of up to 435 on 512 processors. Solution-based adaptation may be keyed off truncation error estimates using tau-extrapolation or a variety of feature detection based refinement parameters. The multigrid method is extended to for time-dependent flows through the use of a dual-time approach. The extension to rigid domain motion uses an Arbitrary Lagrangian-Eulerlarian (ALE) formulation, and results will be presented for a variety of two- and three-dimensional example problems with both simple and complex geometry.
Kressler, Bryan; Spincemaille, Pascal; Prince, Martin R; Wang, Yi
2006-09-01
Time-resolved 3D MRI with high spatial and temporal resolution can be achieved using spiral sampling and sliding-window reconstruction. Image reconstruction is computationally intensive because of the need for data regridding, a large number of temporal phases, and multiple RF receiver coils. Inhomogeneity blurring correction for spiral sampling further increases the computational work load by an order of magnitude, hindering the clinical utility of spiral trajectories. In this work the reconstruction time is reduced by a factor of >40 compared to reconstruction using a single processor. This is achieved by using a cluster of 32 commercial off-the-shelf computers, commodity networking hardware, and readily available software. The reconstruction system is demonstrated for time-resolved spiral contrast-enhanced (CE) peripheral MR angiography (MRA), and a reduction of reconstruction time from 80 min to 1.8 min is achieved. PMID:16892189
Heat Transfer on Steady MHD rotating flow through porous medium in a parallel plate channel
Dr. G. Prabhakara Rao,; M. Naga Sasikala
2015-01-01
We discussed the combined effects of radiative heat transfer and a transverse magnetic field on steady rotating flow of an electrically conducting optically thin fluid through a porous medium in a parallel plate channel and non-uniform temperatures at the walls. The analytical solutions are obtained from coupled nonlinear partial differential equations for the problem. The computational results are discussed quantitatively with the aid of the dimensionless parameters entering in t...
Heat Transfer on Steady MHD rotating flow through porous medium in a parallel plate channel
Dr. G. Prabhakara Rao,
2015-04-01
Full Text Available We discussed the combined effects of radiative heat transfer and a transverse magnetic field on steady rotating flow of an electrically conducting optically thin fluid through a porous medium in a parallel plate channel and non-uniform temperatures at the walls. The analytical solutions are obtained from coupled nonlinear partial differential equations for the problem. The computational results are discussed quantitatively with the aid of the dimensionless parameters entering in the solution.
Sohail NADEEM; Masood, Sadaf; Mehmood, Rashid; Sadiq, Muhammad Adil
2015-01-01
The present analysis deals with flow and heat transfer aspects of a micropolar nanofluid between two horizontal parallel plates in a rotating system. The governing partial differential equations for momentum, energy, micro rotation and nano-particles concentration are presented. Similarity transformations are utilized to convert the system of partial differential equations into system of ordinary differential equations. The reduced equations are solved analytically with the help of optimal ho...
Sung, Chul
2013-08-01
Accurate estimation of neuronal count and distribution is central to the understanding of the organization and layout of cortical maps in the brain, and changes in the cell population induced by brain disorders. High-throughput 3D microscopy techniques such as Knife-Edge Scanning Microscopy (KESM) are enabling whole-brain survey of neuronal distributions. Data from such techniques pose serious challenges to quantitative analysis due to the massive, growing, and sparsely labeled nature of the data. In this paper, we present a scalable, incremental learning algorithm for cell body detection that can address these issues. Our algorithm is computationally efficient (linear mapping, non-iterative) and does not require retraining (unlike gradient-based approaches) or retention of old raw data (unlike instance-based learning). We tested our algorithm on our rat brain Nissl data set, showing superior performance compared to an artificial neural network-based benchmark, and also demonstrated robust performance in a scenario where the data set is rapidly growing in size. Our algorithm is also highly parallelizable due to its incremental nature, and we demonstrated this empirically using a MapReduce-based implementation of the algorithm. We expect our scalable, incremental learning approach to be widely applicable to medical imaging domains where there is a constant flux of new data. © 2013 IEEE.
Ervik, Åsmund; Müller, Bernhard
2014-01-01
To leverage the last two decades' transition in High-Performance Computing (HPC) towards clusters of compute nodes bound together with fast interconnects, a modern scalable CFD code must be able to efficiently distribute work amongst several nodes using the Message Passing Interface (MPI). MPI can enable very large simulations running on very large clusters, but it is necessary that the bulk of the CFD code be written with MPI in mind, an obstacle to parallelizing an existing serial code. In this work we present the results of extending an existing two-phase 3D Navier-Stokes solver, which was completely serial, to a parallel execution model using MPI. The 3D Navier-Stokes equations for two immiscible incompressible fluids are solved by the continuum surface force method, while the location of the interface is determined by the level-set method. We employ the Portable Extensible Toolkit for Scientific Computing (PETSc) for domain decomposition (DD) in a framework where only a fraction of the code needs to be a...
A 3D point-kernel multiple scatter model for parallel-beam SPECT based on a gamma-ray buildup factor
A three-dimensional (3D) point-kernel multiple scatter model for point spread function (PSF) determination in parallel-beam single-photon emission computed tomography (SPECT), based on a dose gamma-ray buildup factor, is proposed. This model embraces nonuniform attenuation in a voxelized object of imaging (patient body) and multiple scattering that is treated as in the point-kernel integration gamma-ray shielding problems. First-order Compton scattering is done by means of the Klein-Nishina formula, but the multiple scattering is accounted for by making use of a dose buildup factor. An asset of the present model is the possibility of generating a complete two-dimensional (2D) PSF that can be used for 3D SPECT reconstruction by means of iterative algorithms. The proposed model is convenient in those situations where more exact techniques are not economical. For the proposed model's testing purpose calculations (for the point source in a nonuniform scattering object for parallel beam collimator geometry), the multiple-order scatter PSF generated by means of the proposed model matched well with those using Monte Carlo (MC) simulations. Discrepancies are observed only at the exponential tails mostly due to the high statistic uncertainty of MC simulations in this area, but not because of the inappropriateness of the model
A 3D point-kernel multiple scatter model for parallel-beam SPECT based on a gamma-ray buildup factor
Marinkovic, Predrag; Ilic, Radovan; Spaic, Rajko
2007-09-01
A three-dimensional (3D) point-kernel multiple scatter model for point spread function (PSF) determination in parallel-beam single-photon emission computed tomography (SPECT), based on a dose gamma-ray buildup factor, is proposed. This model embraces nonuniform attenuation in a voxelized object of imaging (patient body) and multiple scattering that is treated as in the point-kernel integration gamma-ray shielding problems. First-order Compton scattering is done by means of the Klein-Nishina formula, but the multiple scattering is accounted for by making use of a dose buildup factor. An asset of the present model is the possibility of generating a complete two-dimensional (2D) PSF that can be used for 3D SPECT reconstruction by means of iterative algorithms. The proposed model is convenient in those situations where more exact techniques are not economical. For the proposed model's testing purpose calculations (for the point source in a nonuniform scattering object for parallel beam collimator geometry), the multiple-order scatter PSF generated by means of the proposed model matched well with those using Monte Carlo (MC) simulations. Discrepancies are observed only at the exponential tails mostly due to the high statistic uncertainty of MC simulations in this area, but not because of the inappropriateness of the model.
Nadeem, Sohail; Masood, Sadaf; Mehmood, Rashid; Sadiq, Muhammad Adil
2015-01-01
The present analysis deals with flow and heat transfer aspects of a micropolar nanofluid between two horizontal parallel plates in a rotating system. The governing partial differential equations for momentum, energy, micro rotation and nano-particles concentration are presented. Similarity transformations are utilized to convert the system of partial differential equations into system of ordinary differential equations. The reduced equations are solved analytically with the help of optimal homotopy analysis method (OHAM). Analytical solutions for velocity, temperature, micro-rotation and concentration profiles are expressed graphically against various emerging physical parameters. Physical quantities of interest such as skin friction co-efficient, local heat and local mass fluxes are also computed both analytically and numerically through mid-point integration scheme. It is found that both the solutions are in excellent agreement. Local skin friction coefficient is found to be higher for the case of strong concentration i.e. n=0, as compared to the case of weak concentration n=0.50. Influence of strong and weak concentration on Nusselt and Sherwood number appear to be similar in a quantitative sense. PMID:26046637
Sohail Nadeem
Full Text Available The present analysis deals with flow and heat transfer aspects of a micropolar nanofluid between two horizontal parallel plates in a rotating system. The governing partial differential equations for momentum, energy, micro rotation and nano-particles concentration are presented. Similarity transformations are utilized to convert the system of partial differential equations into system of ordinary differential equations. The reduced equations are solved analytically with the help of optimal homotopy analysis method (OHAM. Analytical solutions for velocity, temperature, micro-rotation and concentration profiles are expressed graphically against various emerging physical parameters. Physical quantities of interest such as skin friction co-efficient, local heat and local mass fluxes are also computed both analytically and numerically through mid-point integration scheme. It is found that both the solutions are in excellent agreement. Local skin friction coefficient is found to be higher for the case of strong concentration i.e. n=0, as compared to the case of weak concentration n=0.50. Influence of strong and weak concentration on Nusselt and Sherwood number appear to be similar in a quantitative sense.
Dong, C.; Bougher, S. W.; Ma, Y.; Toth, G.; Lee, Y.; Nagy, A. F.; Tenishev, V.; Pawlowski, D. J.; Meng, X.; Combi, M. R.
2013-12-01
The study of the solar wind interaction with Mars upper atmosphere/ionosphere has triggered a great of interest in recent years. Among the large number of topics in this research area, the investigation of ion escape fluxes has become increasingly important due to its potential impact on the long-term evolution of Mars atmosphere (e.g., loss of water) over its history. In the present work, we adopt the 3-D Mars cold neutral atmosphere profiles (0~300 km) from the newly developed and validated Mars Global Ionosphere Thermosphere Model (M-GITM) and the 3-D hot oxygen profiles (100km~5RM) from the exosphere Monte Carlo model Adaptive Mesh Particle Simulator (AMPS). We apply these 3-D model outputs fields into the 3-D BATS-R-US Mars multi-fluid MHD model (100km~20RM) that can better simulate the interplay between Mars upper atmosphere and solar wind by considering the dynamics of individual ion species. The multi-fluid model solves separate continuity, momentum and energy equations for each ion species (H+, O+, O2+, CO2+). The M-GITM model together with the AMPS exosphere model take into account the effects of solar cycle and seasonal variations on both cold and hot neutral atmospheres, allowing us to investigate the corresponding effects on the Mars upper atmosphere ion escape by using a one-way coupling approach, i.e., both the M-GITM and AMPS model outputs are used as the inputs for the multi-fluid model and M-GITM is used as input into the AMPS exosphere model. The calculations are carried out for selected cases with different nominal solar wind, solar cycle and crustal field orientation conditions. This work has the potential to provide predictions of ion escape rates for comparison to future data to be returned by the MAVEN primary mission (2014-2016) and thereby improve our understanding of present day escape processes. Acknowledgments: The work presented here was supported by NASA grants NNH10CC04C, NNX09AL26G, NSF grant ATM-0535811.
Li, Shengtai [Los Alamos National Laboratory; Li, Hui [Los Alamos National Laboratory
2012-06-14
sensitive to the position of the planet, we adopt the corotating frame that allows the planet moving only in radial direction if only one planet is present. This code has been extensively tested on a number of problems. For the earthmass planet with constant aspect ratio h = 0.05, the torque calculated using our code matches quite well with the the 3D linear theory results by Tanaka et al. (2002). The code is fully parallelized via message-passing interface (MPI) and has very high parallel efficiency. Several numerical examples for both fixed planet and moving planet are provided to demonstrate the efficacy of the numerical method and code.
Detman, T. R.; Intriligator, D. S.; Dryer, M.; Sun, W.; Deehr, C. S.; Intriligator, J.
2012-01-01
We describe our 3-D, time ]dependent, MHD solar wind model that we recently modified to include the physics of pickup protons from interstellar neutral hydrogen. The model has a time-dependent lower boundary condition, at 0.1 AU, that is driven by source surface map files through an empirical interface module. We describe the empirical interface and its parameter tuning to maximize model agreement with background (quiet) solar wind observations at ACE. We then give results of a simulation study of the famous Halloween 2003 series of solar events. We began with shock inputs from the Fearless Forecast real ]time shock arrival prediction study, and then we iteratively adjusted input shock speeds to obtain agreement between observed and simulated shock arrival times at ACE. We then extended the model grid to 5.5 AU and compared those simulation results with Ulysses observations at 5.2 AU. Next we undertook the more difficult tuning of shock speeds and locations to get matching shock arrival times at both ACE and Ulysses. Then we ran this last case again with neutral hydrogen density set to zero, to identify the effect of pickup ions. We show that the speed of interplanetary shocks propagating from the Sun to Ulysses is reduced by the effects of pickup protons. We plan to make further improvements to the model as we continue our benchmarking process to 10 AU, comparing our results with Cassini observations, and eventually on to 100 AU, comparing our results with Voyager 1 and 2 observations.
High-Fidelity RF Gun Simulations with the Parallel 3D Finite Element Particle-In-Cell Code Pic3P
Candel, A; Kabel, A.; Lee, L.; Li, Z.; Limborg, C.; Ng, C.; Schussman, G.; Ko, K.; /SLAC
2009-06-19
SLAC's Advanced Computations Department (ACD) has developed the first parallel Finite Element 3D Particle-In-Cell (PIC) code, Pic3P, for simulations of RF guns and other space-charge dominated beam-cavity interactions. Pic3P solves the complete set of Maxwell-Lorentz equations and thus includes space charge, retardation and wakefield effects from first principles. Pic3P uses higher-order Finite Elementmethods on unstructured conformal meshes. A novel scheme for causal adaptive refinement and dynamic load balancing enable unprecedented simulation accuracy, aiding the design and operation of the next generation of accelerator facilities. Application to the Linac Coherent Light Source (LCLS) RF gun is presented.
Tramm, John R.; Gunow, Geoffrey; He, Tim; Smith, Kord S.; Forget, Benoit; Siegel, Andrew R.
2016-05-01
In this study we present and analyze a formulation of the 3D Method of Characteristics (MOC) technique applied to the simulation of full core nuclear reactors. Key features of the algorithm include a task-based parallelism model that allows independent MOC tracks to be assigned to threads dynamically, ensuring load balancing, and a wide vectorizable inner loop that takes advantage of modern SIMD computer architectures. The algorithm is implemented in a set of highly optimized proxy applications in order to investigate its performance characteristics on CPU, GPU, and Intel Xeon Phi architectures. Speed, power, and hardware cost efficiencies are compared. Additionally, performance bottlenecks are identified for each architecture in order to determine the prospects for continued scalability of the algorithm on next generation HPC architectures.
DeJong, Andrew
Numerical models of fluid-structure interaction have grown in importance due to increasing interest in environmental energy harvesting, airfoil-gust interactions, and bio-inspired formation flying. Powered by increasingly powerful parallel computers, such models seek to explain the fundamental physics behind the complex, unsteady fluid-structure phenomena. To this end, a high-fidelity computational model based on the high-order spectral difference method on 3D unstructured, dynamic meshes has been developed. The spectral difference method constructs continuous solution fields within each element with a Riemann solver to compute the inviscid fluxes at the element interfaces and an averaging mechanism to compute the viscous fluxes. This method has shown promise in the past as a highly accurate, yet sufficiently fast method for solving unsteady viscous compressible flows. The solver is monolithically coupled to the equations of motion of an elastically mounted 3-degree of freedom rigid bluff body undergoing flow-induced lift, drag, and torque. The mesh is deformed using 4 methods: an analytic function, Laplace equation, biharmonic equation, and a bi-elliptic equation with variable diffusivity. This single system of equations -- fluid and structure -- is advanced through time using a 5-stage, 4th-order Runge-Kutta scheme. Message Passing Interface is used to run the coupled system in parallel on up to 240 processors. The solver is validated against previously published numerical and experimental data for an elastically mounted cylinder. The effect of adding an upstream body and inducing wake galloping is observed.
3D MHD Simulations of Spheromak Compression
Stuber, James E.; Woodruff, Simon; O'Bryan, John; Romero-Talamas, Carlos A.; Darpa Spheromak Team
2015-11-01
The adiabatic compression of compact tori could lead to a compact and hence low cost fusion energy system. The critical scientific issues in spheromak compression relate both to confinement properties and to the stability of the configuration undergoing compression. We present results from the NIMROD code modified with the addition of magnetic field coils that allow us to examine the role of rotation on the stability and confinement of the spheromak (extending prior work for the FRC). We present results from a scan in initial rotation, from 0 to 100km/s. We show that strong rotational shear (10km/s over 1cm) occurs. We compare the simulation results with analytic scaling relations for adiabatic compression. Work performed under DARPA grant N66001-14-1-4044.
Kordy, M.; Wannamaker, P.; Maris, V.; Cherkaev, E.; Hill, G.
2016-01-01
We have developed an algorithm, which we call HexMT, for 3-D simulation and inversion of magnetotelluric (MT) responses using deformable hexahedral finite elements that permit incorporation of topography. Direct solvers parallelized on symmetric multiprocessor (SMP), single-chassis workstations with large RAM are used throughout, including the forward solution, parameter Jacobians and model parameter update. In Part I, the forward simulator and Jacobian calculations are presented. We use first-order edge elements to represent the secondary electric field (E), yielding accuracy O(h) for E and its curl (magnetic field). For very low frequencies or small material admittivities, the E-field requires divergence correction. With the help of Hodge decomposition, the correction may be applied in one step after the forward solution is calculated. This allows accurate E-field solutions in dielectric air. The system matrix factorization and source vector solutions are computed using the MKL PARDISO library, which shows good scalability through 24 processor cores. The factorized matrix is used to calculate the forward response as well as the Jacobians of electromagnetic (EM) field and MT responses using the reciprocity theorem. Comparison with other codes demonstrates accuracy of our forward calculations. We consider a popular conductive/resistive double brick structure, several synthetic topographic models and the natural topography of Mount Erebus in Antarctica. In particular, the ability of finite elements to represent smooth topographic slopes permits accurate simulation of refraction of EM waves normal to the slopes at high frequencies. Run-time tests of the parallelized algorithm indicate that for meshes as large as 176 × 176 × 70 elements, MT forward responses and Jacobians can be calculated in ˜1.5 hr per frequency. Together with an efficient inversion parameter step described in Part II, MT inversion problems of 200-300 stations are computable with total run times
Santasusana, Miquel; Irazábal, Joaquín; Oñate, Eugenio; Carbonell, Josep Maria
2016-07-01
In this work, we present a new methodology for the treatment of the contact interaction between rigid boundaries and spherical discrete elements (DE). Rigid body parts are present in most of large-scale simulations. The surfaces of the rigid parts are commonly meshed with a finite element-like (FE) discretization. The contact detection and calculation between those DE and the discretized boundaries is not straightforward and has been addressed by different approaches. The algorithm presented in this paper considers the contact of the DEs with the geometric primitives of a FE mesh, i.e. facet, edge or vertex. To do so, the original hierarchical method presented by Horner et al. (J Eng Mech 127(10):1027-1032, 2001) is extended with a new insight leading to a robust, fast and accurate 3D contact algorithm which is fully parallelizable. The implementation of the method has been developed in order to deal ideally with triangles and quadrilaterals. If the boundaries are discretized with another type of geometries, the method can be easily extended to higher order planar convex polyhedra. A detailed description of the procedure followed to treat a wide range of cases is presented. The description of the developed algorithm and its validation is verified with several practical examples. The parallelization capabilities and the obtained performance are presented with the study of an industrial application example.
Pathak, Ashish; Raessi, Mehdi
2014-11-01
We present a 3D MPI-parallel, GPU-accelerated computational tool that captures the interaction between a moving rigid body and two-fluid flows. Although the immediate application is the study of ocean wave energy converters (WECs), the model was developed at a general level and can be used in other applications. Solving the full Navier-Stokes equations, the model is able to capture non-linear effects, including wave-breaking and fluid-structure interaction, that have significant impact on WEC performance. To transport mass and momentum, we use a consistent scheme that can handle large density ratios (e.g. air/water). We present a novel reconstruction scheme for resolving three-phase (solid-liquid-gas) cells in the volume-of-fluid context, where the fluid interface orientation is estimated via a minimization procedure, while imposing a contact angle. The reconstruction allows for accurate mass and momentum transport in the vicinity of three-phase cells. The fast-fictitious-domain method is used for capturing the interaction between a moving rigid body and two-fluid flow. The pressure Poisson solver is accelerated using GPUs in the MPI framework. We present results of an array of test cases devised to assess the performance and accuracy of the computational tool.
Athena3D: Flux-conservative Godunov-type algorithm for compressible magnetohydrodynamics
Hawley, John; Simon, Jake; Stone, James; Gardiner, Thomas; Teuben, Peter
2015-05-01
Written in FORTRAN, Athena3D, based on Athena (ascl:1010.014), is an implementation of a flux-conservative Godunov-type algorithm for compressible magnetohydrodynamics. Features of the Athena3D code include compressible hydrodynamics and ideal MHD in one, two or three spatial dimensions in Cartesian coordinates; adiabatic and isothermal equations of state; 1st, 2nd or 3rd order reconstruction using the characteristic variables; and numerical fluxes computed using the Roe scheme. In addition, it offers the ability to add source terms to the equations and is parallelized based on MPI.
A Fast MHD Code for Gravitationally Stratified Media using Graphical Processing Units: SMAUG
M. K. Griffiths; V. Fedun; R.Erdélyi
2015-03-01
Parallelization techniques have been exploited most successfully by the gaming/graphics industry with the adoption of graphical processing units (GPUs), possessing hundreds of processor cores. The opportunity has been recognized by the computational sciences and engineering communities, who have recently harnessed successfully the numerical performance of GPUs. For example, parallel magnetohydrodynamic (MHD) algorithms are important for numerical modelling of highly inhomogeneous solar, astrophysical and geophysical plasmas. Here, we describe the implementation of SMAUG, the Sheffield Magnetohydrodynamics Algorithm Using GPUs. SMAUG is a 1–3D MHD code capable of modelling magnetized and gravitationally stratified plasma. The objective of this paper is to present the numerical methods and techniques used for porting the code to this novel and highly parallel compute architecture. The methods employed are justified by the performance benchmarks and validation results demonstrating that the code successfully simulates the physics for a range of test scenarios including a full 3D realistic model of wave propagation in the solar atmosphere.
MHD simulations on an unstructured mesh
Two reasons for using an unstructured computational mesh are adaptivity, and alignment with arbitrarily shaped boundaries. Two codes which use finite element discretization on an unstructured mesh are described. FEM3D solves 2D and 3D RMHD using an adaptive grid. MH3D++, which incorporates methods of FEM3D into the MH3D generalized MHD code, can be used with shaped boundaries, which might be 3D
The problem of unsteady conducting viscous flow of n-immiscible and incompressible fluids, occupying equal heights between parallel plates under the influence of periodic pressure gradient superposed on the steady flow has been studied. Expressions for velocity distributions for n-fluids have been obtained. The velocity distributions have been shown graphically against nondimensional distance in the case of two fluids in particular. (auth.)
KHEM CHAND
2011-01-01
The heat transfer and hydromagnetic boundary layer flow of an electrically conducting viscous ,incompressible fluid over a continuous flat surface moving in a parallel free stream is investigated. The porous infinite surface is subjected to a slightly sinusoidal transverse suction velocity distribution. The flow becomes three dimensional due to this type of suction velocity without taking into account the induced magnetic field; the mathematical analysis is presented for the hydromagnetic lam...
Oberholzer, K.; Romaneehsen, B.; Kunz, P.; Thelen, M.; Kreitner, K.F. [Klinik fuer Radiologie, Johannes Gutenberg-Univ. Mainz (Germany); Kramm, T. [Klinik fuer Herz-, Thorax- und Gefaesschirurgie, Johannes Gutenberg-Univ. Mainz (Germany)
2004-04-01
Purpose: Comparison of two different types of contrast-enhanced 3D-MR angiography (CE-MRA) with integrated parallel acquisition technique (iPAT) in patients with chronic-thromboembolic pulmonary hypertension (CTEPH) and evaluation whether sagittal acquisition with higher resolution and minimized acquisition time is superior to common coronal orientation. Materials and Methods: CE-MRA was performed on 15 patients with CTEPH preoperatively and on 10 patients also postoperatively, while 5 other patients received only a postoperative MRA. All 30 MR studies with one coronal and two sagittal acquisitions were blindly evaluated and compared. The resolution of coronal and sagittal MRA was 1.3 x 0.6 x 1.4 mm{sup 3} and 1.2 x 1.2 x 1.2 mm{sup 3}, and acquisition time 20 and 17 sec (iPAT factor 2, GRAPPA), respectively. Image quality, coverage of the pulmonary arteries, delineation of patent segmental and subsegmental vessels and pathological findings were assessed. A total of 1980 vessels were evaluated. Results: Sagittal 3D-MRA was superior in overall image quality and complete coverage of the vessels compared to coronal MRA, 18% of subsegmental and 4.3% of segmental arteries as well as 1.1% of the lobar vessels were not covered by coronal acquisition. Only 0.5% of sagittal subsegments were missed. The number of depicted patent segmental and subsegmental arteries was higher in sagittal MRA (460 vs 489 and 573 vs. 649, respectively), the total difference of patent vessels was 105. Sagittal MRA revealed more pathological findings in segmental arteries (especially thrombotic material and stenoses). (orig.) [German] Ziel: Vergleich zweier kontrastmittelverstaerkter MR-Angiographie-Techniken der Pulmonalarterien mit integrierter paralleler Akquisitionstechnik (iPAT) bei Patienten mit chronisch-thromboembolischer pulmonaler Hypertonie (CTEPH), Ueberpruefung der Hypothese, dass mit sagittaler Datenaufnahme eine bessere Bildqualitaet und Detailerkennbarkeit durch hoehere Aufloesung
Gabriele Jost; Bob Robins
2010-01-01
Today most systems in high-performance computing (HPC) feature a hierarchical hardware design: shared-memory nodes with several multi-core CPUs are connected via a network infrastructure. When parallelizing an application for these architectures it seems natural to employ a hierarchical programming model such as combining MPI and OpenMP. Nevertheless, there is the general lore that pure MPI outperforms the hybrid MPI/OpenMP approach. In this paper, we describe the hybrid MPI/OpenMP paralleliz...
We present a numerical algorithm for simulating the spinodal decomposition described by the three dimensional Cahn–Hilliard–Cook (CHC) equation, which is a fourth-order stochastic partial differential equation with a noise term. The equation is discretized in space and time based on a fully implicit, cell-centered finite difference scheme, with an adaptive time-stepping strategy designed to accelerate the progress to equilibrium. At each time step, a parallel Newton–Krylov–Schwarz algorithm is used to solve the nonlinear system. We discuss various numerical and computational challenges associated with the method. The numerical scheme is validated by a comparison with an explicit scheme of high accuracy (and unreasonably high cost). We present steady state solutions of the CHC equation in two and three dimensions. The effect of the thermal fluctuation on the spinodal decomposition process is studied. We show that the existence of the thermal fluctuation accelerates the spinodal decomposition process and that the final steady morphology is sensitive to the stochastic noise. We also show the evolution of the energies and statistical moments. In terms of the parallel performance, it is found that the implicit domain decomposition approach scales well on supercomputers with a large number of processors
Powerful supercomputers are available today. MBC-1000M is one of Russian supercomputers that may be used by distant way access. Programs LUCKY and LUCKYC were created to work for multi-processors systems. These programs have algorithms created especially for these computers and used MPI (message passing interface) service for exchanges between processors. LUCKY may resolved shielding tasks by multigroup discreet ordinate method. LUCKYC may resolve critical tasks by same method. Only XYZ orthogonal geometry is available. Under little space steps to approximate discreet operator this geometry may be used as universal one to describe complex geometrical structures. Cross section libraries are used up to P8 approximation by Legendre polynomials for nuclear data in GIT format. Programming language is Fortran-90. 'Vector' processors may be used that lets get a time profit up to 30 times. But unfortunately MBC-1000M has not these processors. Nevertheless sufficient value for efficiency of parallel calculations was obtained under 'space' (LUCKY) and 'space and energy' (LUCKYC) paralleling. AUTOCAD program is used to control geometry after a treatment of input data. Programs have powerful geometry module, it is a beautiful tool to achieve any geometry. Output results may be processed by graphic programs on personal computer. (authors)
Zheng, Xiang
2015-03-01
We present a numerical algorithm for simulating the spinodal decomposition described by the three dimensional Cahn-Hilliard-Cook (CHC) equation, which is a fourth-order stochastic partial differential equation with a noise term. The equation is discretized in space and time based on a fully implicit, cell-centered finite difference scheme, with an adaptive time-stepping strategy designed to accelerate the progress to equilibrium. At each time step, a parallel Newton-Krylov-Schwarz algorithm is used to solve the nonlinear system. We discuss various numerical and computational challenges associated with the method. The numerical scheme is validated by a comparison with an explicit scheme of high accuracy (and unreasonably high cost). We present steady state solutions of the CHC equation in two and three dimensions. The effect of the thermal fluctuation on the spinodal decomposition process is studied. We show that the existence of the thermal fluctuation accelerates the spinodal decomposition process and that the final steady morphology is sensitive to the stochastic noise. We also show the evolution of the energies and statistical moments. In terms of the parallel performance, it is found that the implicit domain decomposition approach scales well on supercomputers with a large number of processors. © 2015 Elsevier Inc.
NIF Ignition Target 3D Point Design
Jones, O; Marinak, M; Milovich, J; Callahan, D
2008-11-05
We have developed an input file for running 3D NIF hohlraums that is optimized such that it can be run in 1-2 days on parallel computers. We have incorporated increasing levels of automation into the 3D input file: (1) Configuration controlled input files; (2) Common file for 2D and 3D, different types of capsules (symcap, etc.); and (3) Can obtain target dimensions, laser pulse, and diagnostics settings automatically from NIF Campaign Management Tool. Using 3D Hydra calculations to investigate different problems: (1) Intrinsic 3D asymmetry; (2) Tolerance to nonideal 3D effects (e.g. laser power balance, pointing errors); and (3) Synthetic diagnostics.
Lucas, Laurent; Loscos, Céline
2013-01-01
While 3D vision has existed for many years, the use of 3D cameras and video-based modeling by the film industry has induced an explosion of interest for 3D acquisition technology, 3D content and 3D displays. As such, 3D video has become one of the new technology trends of this century.The chapters in this book cover a large spectrum of areas connected to 3D video, which are presented both theoretically and technologically, while taking into account both physiological and perceptual aspects. Stepping away from traditional 3D vision, the authors, all currently involved in these areas, provide th
Beane, Andy
2012-01-01
The essential fundamentals of 3D animation for aspiring 3D artists 3D is everywhere--video games, movie and television special effects, mobile devices, etc. Many aspiring artists and animators have grown up with 3D and computers, and naturally gravitate to this field as their area of interest. Bringing a blend of studio and classroom experience to offer you thorough coverage of the 3D animation industry, this must-have book shows you what it takes to create compelling and realistic 3D imagery. Serves as the first step to understanding the language of 3D and computer graphics (CG)Covers 3D anim
The driver linac of the proposed Rare Isotope Accelerator (RIA) requires a great variety of high intensity, high charge state ion beams. In order to design and to optimize the low energy beamline optics of the RIA front end,we have developed a new parallel three-dimensional model to simulate the low energy, multi-species ion beam formation and transport from the ECR ion source extraction region to the focal plane of the analyzing magnet. A multisection overlapped computational domain has been used to break the original transport system into a number of each subsystem, macro-particle tracking is used to obtain the charge density distribution in this subdomain. The three-dimensional Poisson equation is solved within the subdomain and particle tracking is repeated until the solution converges. Two new Poisson solvers based on a combination of the spectral method and the multigrid method have been developed to solve the Poisson equation in cylindrical coordinates for the beam extraction region and in the Frenet-Serret coordinates for the bending magnet region. Some test examples and initial applications will also be presented
Self-consistent stationary MHD shear flows in the solar atmosphere as electric field generators
Nickeler, D H; Wiegelmann, T; Kraus, M
2014-01-01
Magnetic fields and flows in coronal structures, for example, in gradual phases in flares, can be described by 2D and 3D magnetohydrostatic (MHS) and steady magnetohydrodynamic (MHD) equilibria. Within a physically simplified, but exact mathematical model, we study the electric currents and corresponding electric fields generated by shear flows. Starting from exact and analytically calculated magnetic potential fields, we solveid the nonlinear MHD equations self-consistently. By applying a magnetic shear flow and assuming a nonideal MHD environment, we calculated an electric field via Faraday's law. The formal solution for the electromagnetic field allowed us to compute an expression of an effective resistivity similar to the collisionless Speiser resistivity. We find that the electric field can be highly spatially structured, or in other words, filamented. The electric field component parallel to the magnetic field is the dominant component and is high where the resistivity has a maximum. The electric field ...
Nonlinear evolution of MHD instabilities
A 3-D nonlinear MHD computer code was used to study the time evolution of internal instabilities. Velocity vortex cells are observed to persist into the nonlinear evolution. Pressure and density profiles convect around these cells for a weak localized instability, or convect into the wall for a strong instability. (U.S.)
The direct use of enlarged subsets of mathematically exact equations of change in moments of the velocity distribution function, each equation corresponding to one of the macroscopic variables to be retained, produces extended MHD models. The first relevant level of closure provides 'ten moment' equations in the density ρ, velocity v, scalar pressure p, and the traceless component of the pressure tensor t. The next 'thirteen moment' level also includes the thermal flux vector q, and further extended MHD models could be developed by including even higher level basic equations of change. Explicit invariant forms for the tensor t and the heat flux vector defining q follow from their respective basic equations of change. Except in the neighbourhood of a magnetic null, in magnetised plasma these forms may be resolved into known sums of their parallel, cross (or transverse) and perpendicular components. Parallel viscosity in an electron-ion plasma is specifically discussed. (author)
Morrison, P. J.; Abdelhamid, H. M.; Grasso, D.; Hazeltine, R. D.; Lingam, M.; Tassi, E.
2015-11-01
Over the years various reduced fluid models have been obtained for modeling plasmas, with the goal of capturing important physics while maintaining computability. Such models have included the physics contained in various generalizations of Ohm's law, including Hall drift and electron inertia. In a recent publication it was shown that full 3D extended MHD is a Hamiltonian system by finding its noncanonical Poisson bracket. Subsequently, this bracket was shown to be derivable from that for Hall MHD by a series of remarkable transformations, which greatly simplifies the proof of the Jacobi identity and allows one to immediately obtain generalizations of the helicity and cross helicity. In this poster we use this structure to obtain exact reduced fluid models with the effects of full two-fluid theory. Results of numerical computations of collisionless reconnection using an exact reduced 4-field model will be presented and analytical comparisons of mode structure of previous reduced models will be made.
D. Pletinckx
2012-09-01
Full Text Available The current 3D hype creates a lot of interest in 3D. People go to 3D movies, but are we ready to use 3D in our homes, in our offices, in our communication? Are we ready to deliver real 3D to a general public and use interactive 3D in a meaningful way to enjoy, learn, communicate? The CARARE project is realising this for the moment in the domain of monuments and archaeology, so that real 3D of archaeological sites and European monuments will be available to the general public by 2012. There are several aspects to this endeavour. First of all is the technical aspect of flawlessly delivering 3D content over all platforms and operating systems, without installing software. We have currently a working solution in PDF, but HTML5 will probably be the future. Secondly, there is still little knowledge on how to create 3D learning objects, 3D tourist information or 3D scholarly communication. We are still in a prototype phase when it comes to integrate 3D objects in physical or virtual museums. Nevertheless, Europeana has a tremendous potential as a multi-facetted virtual museum. Finally, 3D has a large potential to act as a hub of information, linking to related 2D imagery, texts, video, sound. We describe how to create such rich, explorable 3D objects that can be used intuitively by the generic Europeana user and what metadata is needed to support the semantic linking.
This book explains modeling of solid works 3D and application of 3D CAD/CAM. The contents of this book are outline of modeling such as CAD and 2D and 3D, solid works composition, method of sketch, writing measurement fixing, selecting projection, choosing condition of restriction, practice of sketch, making parts, reforming parts, modeling 3D, revising 3D modeling, using pattern function, modeling necessaries, assembling, floor plan, 3D modeling method, practice floor plans for industrial engineer data aided manufacturing, processing of CAD/CAM interface.