Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel simulation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,477 records · Page 82

Revisiting Parallel Cyclic Reduction and Parallel Prefix-Based Algorithms for Block Tridiagonal System of Equations

Simulations that require solutions of block tridiagonal systems of equations rely on fast parallel solvers for runtime efficiency. Leading parallel solvers that are highly effective for general systems of equations, dense or sparse, are limited in scalability when applied to block tridiagonal systems. This paper presents scalability results as well as detailed analyses of two parallel solvers that exploit the special structure of block tridiagonal matrices to deliver superior performance, often by orders of magnitude. A rigorous analysis of their relative parallel runtimes is shown to reveal the existence of a critical block size that separates the parameter space spanned by the number of block rows, the block size and the processor count, into distinct regions that favor one or the other of the two solvers. Dependence of this critical block size on the above parameters as well as on machine-specific constants is established. These formal insights are supported by empirical results on up to 2,048 cores of a Cray XT4 system. To the best of our knowledge, this is the highest reported scalability for parallel block tridiagonal solvers to date.

Seal, Sudip K↗

First-Principles Grand-Canonical Simulations of Water Adsorption in Proton-Exchanged Zeolites

Water appears by design or as impurities in many important reactive systems. For those catalyzed by porous solid acids, such as widely used zeolites, experimentally quantifying the amount or elucidating the structure of adsorbed water clusters at reaction conditions is challenging, while computational studies (e.g., first-principles molecular dynamics simulations) often need to assume the loading to examine solvation effects. Furthermore, we perform first-principles grand-canonical simulations to predict water adsorption to H-ZSM-5 zeolites under specified experimental conditions. Presampling with inexpensive force fields and a pool-based parallelization algorithm are used to improve simulation efficiency, while molecular dynamics is used to sample configurations involving hydronium species. We observe that H + exchange dramatically increases the hydrophilicity of zeolite MFI and an appreciable amount of water is present at very low relative humidities. At all conditions examined, the zeolitic protons are found to dissociate readily from the surface basic sites and become mobile by participating in the hydrogen-bonded chains of adsorbed water molecules.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Reinforcement Learning for Load-balanced Parallel Particle Tracing

We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems. Our method combines three novel components: (1) a work donation algorithm, (2) a high-order workload estimation model, and (3) a communication cost model. First, we design an RL-based work donation algorithm. Our algorithm monitors workloads of processes and creates RL agents to donate data blocks and particles from high-workload processes to low-workload processes to minimize program execution time. The agents learn the donation strategy on the fly based on reward and cost functions designed to consider processes' workload changes and data transfer costs of donation actions. Second, we propose a workload estimation model, helping RL agents estimate the workload distribution of processes in future computations. Third, we design a communication cost model that considers both block and particle data exchange costs, helping RL agents make effective decisions with minimized communication costs. We demonstrate that our algorithm adapts to different flow behaviors in large-scale fluid dynamics, ocean, and weather simulation data. Our algorithm improves parallel particle tracing performance in terms of parallel efficiency, load balance, and costs of I/O and communication for evaluations with up to 16,384 processors.

Distributed and parallel particle tracing↗

Particle Acceleration in Relativistic Jets due to Weibel Instability

Shock acceleration is an ubiquitous phenomenon in astrophysical plasmas. Plasma waves and their associated instabilities (e.g., the Buneman instability, two-streaming instability, and the Weibel instability) created in the shocks are responsible for particle (electron, positron, and ion) acceleration. Using a 3-D relativistic electromagnetic particle (REMP) code, we have investigated particle acceleration associated with a relativistic jet front propagating through an ambient plasma with and without initial magnetic fields. We find only small differences in the results between no ambient and weak ambient magnetic fields. Simulations show that the Weibel instability created in the collisionless shock front accelerates particles perpendicular and parallel to the jet propagation direction. The simulation results show that this instability is responsible for generating and amplifying highly nonuniform, small-scale magnetic fields, which contribute to the electron s transverse deflection behind the jet head. The jitter radiation (Medvedev 2000) from deflected electrons has different properties than synchrotron radiation which is calculated in a uniform magnetic field. This jitter radiation may be important to understanding the complex time evolution and/or spectral structure in gamma-ray bursts, relativistic jets, and supernova remnants.

Nishikawa, K.↗

NUMERICAL SIMULATION OF THREE-DIMENSIONAL ASYMMETRIC RECONNECTION AND APPLICATION TO A PHYSICAL MECHANISM OF PENUMBRAL MICROJETS

Three-dimensional (3D) component reconnection, where reconnecting field lines are not perfectly anti-parallel, is studied with a 3D magnetohydrodynamic simulation. In particular, we consider the asymmetry of the field strength of the reconnecting field lines. As the asymmetry increases, the generated reconnection jet tends to be parallel to stronger field lines. This is because weaker field lines have higher gas pressure in the initial equilibrium, and hence the gas pressure gradient along the reconnected field lines is generated, which accelerates the field-aligned plasma flow. This mechanism may explain penumbral microjets and other types of jets that are parallel to magnetic field lines.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

A general CFD framework for fault-resilient simulations based on multi-resolution information fusion

We develop a general CFD framework for multi-resolution simulations to target multiscale problems but also resilience in exascale simulations, where faulty processors may lead to gappy, in space-time, simulated fields. We combine approximation theory and domain decomposition together with statistical learning techniques, e.g. coKriging, to estimate boundary conditions and minimize communications by performing independent parallel runs. To demonstrate this new simulation approach, we consider two benchmark problems. First, we solve the heat equation (a) on a small number of spatial “patches” distributed across the domain, simulated by finite differences at fine resolution and (b) on the entire domain simulated at very low resolution, thus fusing multi-resolution models to obtain the final answer. Second, we simulate the flow in a lid-driven cavity in an analogous fashion, by fusing finite difference solutions obtained with fine and low resolution assuming gappy data sets. We investigate the influence of various parameters for this framework, including the correlation kernel, the size of a buffer employed in estimating boundary conditions, the coarseness of the resolution of auxiliary data, and the communication frequency across different patches in fusing the information at different resolution levels. In addition to its robustness and resilience, the new framework can be employed to generalize previous multiscale approaches involving heterogeneous discretizations or even fundamentally different flow descriptions, e.g. in continuum-atomistic simulations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Spatial decomposition of structured grids for nuclear reactor simulations

Spatial decomposition methods based on graph partitioning are developed and implemented in the high fidelity neutron transport code MPACT. These graph-based spatial decomposition methods are more general than previous decomposition methods and typically provide better load balance and reduced runtimes due to their improved parallel efficiency. Correlations are drawn between simulation runtime and the balance of the partition for 2D simulations. Comparisons are made using partition balance metrics for different decomposition schemes in 2D and 3D simulations. Finally, for typical ranges of subdomains, graph-based partitioning methods offer significant reductions to runtimes. However, for highly decomposed problems, these graph-based methods may decrease convergence rates, thus reducing parallel efficiency compared to older methods.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Implementation of Active Sites in DSMC to Capture Pitting of Oxidizing Carbon Materials

In this work we demonstrate a newly developed capability to capture pitting of carbon fibers in DSMC simulations, specifically using the Stochastic PArallel Rarefied-gas Time-accurate Analyzer (SPARTA) code. State-of-the-art reactive surface models in DSMC compute collision dependent carbon consumption rates (usually through desorption of CO) based on a set of surface reactions that has been derived from molecular beam experiments. The reactivity on each carbon surface element is constant in those models, such that the carbon surface recedes uniformly as a result of ablation. However, it is well known that in reality the carbon surface has locally different reaction rates due to the presence of defects at the atomic scale. These defective sites have a much higher reactivity than the average sites (2-3 orders of magnitude) and are first to react during ablation leading to its removal. This causes all the neighboring atoms to be defective and increase their reactivity, thus leading to the localized carbon removal around these ”active” sites. In this manner, these highly reactive defective sites serve as nucleation sites for the formation and growth of etch pits with potentially detrimental effects on the structural integrity. Recently a detailed surface chemistry framework was developed in SPARTA, capable of incorporating various reaction mechanisms such as adsorption, desorption, Eley-Rideal (ER) and Langmuir-Hinshelwood (LH) mechanisms. Within this framework, we have implemented the capability of a single surface having multiple site sets with different reactivities. Using this feature, we can simulate the presence of active sites on carbon surfaces, whose reactivity is much greater than an average site as a result of defects. We have implemented the active site fraction as a property of surface elements within SPARTA, which is directly proportional to the local reactivity of each surface element. By introducing an initial distribution of the active site fraction across the carbon surface, and propagating it in a manner that mimics the evolution of real reacting carbon surfaces, we are able to capture the formation and growth of etch pits as a result of surface consumption reactions such as oxidation.

DSMC↗

Implementation of active sites to capture pitting of oxidizing carbon materials in DSMC.

In this work we demonstrate a newly developed capability to capture pitting of carbon fibers in DSMC simulations, specifically using the Stochastic PArallel Rarefied-gas Time-accurate Analyzer (SPARTA) code [1]. State-of-the-art reactive surface models in DSMC compute collision dependent carbon consumption rates (usually through desorption of CO) based on a set of surface reactions that has been derived from molecular beam experiments [2]. The reactivity on each carbon surface element is constant in those models, such that the carbon surface recedes uniformly as a result of ablation. However, it is well known that in reality the carbon surface has locally different reaction rates due to the presence of defects at the atomic scale [3]. These defective sites have a much higher reactivity than the average sites (2-3 orders of magnitude) and are first to react during ablation leading to its removal. This causes all the neighboring atoms to be defective and increase their reactivity, thus leading to the localized carbon removal around these ”active” sites (as shown in Fig. 1). In this manner, these highly reactive defective sites serve as nucleation sites for the formation and growth of etch pits with potentially detrimental effects on the structural integrity. Recently a detailed surface chemistry framework was developed in SPARTA, capable of incorporating various reaction mechanisms such as adsorption, desorption, Eley-Rideal (ER) and Langmuir-Hinshelwood (LH) mechanisms [4]. Within this framework, we have implemented the capability of a single surface having multiple site sets with different reactivities. Using this feature, we can simulate the presence of active sites on carbon surfaces, whose reactivity is much greater than an average site as a result of defects. We have implemented the active site fraction as a property of surface elements within SPARTA, which is directly proportional to the local reactivity of each surface element. By introducing an initial distribution of the active site fraction across the carbon surface, and propagating it in a manner that mimics the evolution of real reacting carbon surfaces, we are able to capture the formation and growth of etch pits as a result of surface consumption reactions such as oxidation.

DSMC↗

Mixed augmented variational formulation (MAVF) for lower hybrid full-wave calculations

In the continuation of the works led in cylindrical geometry, a full toroidal description for an arbitrary poloidal cross-section of the plasma has been developed. For simulation purpose a mixed augmented variational formulation (MAVF), which is particularly well suited for solving Maxwell equations, is considered. The discretization of the MAVF is carried out using Taylor-Hood P2-iso-P1 finite elements. This formulation provide a natural implementation for parallel processing, a particularly important aspect when simulations for plasmas of large size must be considered. Details on the specific application of the MAVF to the LH problem are presented, as well as the structure of the corresponding matrices. A first application to a realistic small tokamak configuration is considered.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

GPU simulation of nonlinear propagation of dual band ultrasound pulse complexes

In a new method of ultrasound imaging, called SURF imaging, dual band pulse complexes composed of overlapping low frequency (LF) and high frequency (HF) pulses are transmitted, where the frequency ratio LF:HF ∼ 1 : 20, and the relative bandwidth of both pulses are ∼ 50 − 70%. The LF pulse length is hence ∼ 20 times the HF pulse length. The LF pulse is used to nonlinearly manipulate the material elasticity observed by the co-propagating HF pulse. This produces nonlinear interaction effects that give more information on the propagation of the pulse complex. Due to the large difference in frequency and pulse length between the LF and the HF pulses, we have developed a dual level simulation where the LF pulse propagation is first simulated independent of the HF pulse, using a temporal sampling frequency matched to the LF pulse. A separate equation for the HF pulse is developed, where the the presimulated LF pulse modifies the propagation velocity. The equations are adapted to parallel processing in a GPU, where nonlinear simulations of a typical HF beam of 10 MHz down to 40 mm is done in ∼ 2 secs in a standard GPU. This simulation is hence very useful for studying the manipulation effect of the LF pulse on the HF pulse.

42 ENGINEERING↗

Implementation and Characterization of Three-Dimensional Particle-in-Cell Codes on Multiple-Instruction-Multiple-Data Massively Parallel Supercomputers

A three-dimensional electrostatic particle-in-cell (PIC) plasma simulation code has been developed on coarse-grain distributed-memory massively parallel computers with message passing communications. Our implementation is the generalization to three-dimensions of the general concurrent particle-in-cell (GCPIC) algorithm. In the GCPIC algorithm, the particle computation is divided among the processors using a domain decomposition of the simulation domain. In a three-dimensional simulation, the domain can be partitioned into one-, two-, or three-dimensional subdomains ("slabs," "rods," or "cubes") and we investigate the efficiency of the parallel implementation of the push for all three choices. The present implementation runs on the Intel Touchstone Delta machine at Caltech; a multiple-instruction-multiple-data (MIMD) parallel computer with 512 nodes. We find that the parallel efficiency of the push is very high, with the ratio of communication to computation time in the range 0.3%-10.0%. The highest efficiency (> 99%) occurs for a large, scaled problem with 64(sup 3) particles per processing node (approximately 134 million particles of 512 nodes) which has a push time of about 250 ns per particle per time step. We have also developed expressions for the timing of the code which are a function of both code parameters (number of grid points, particles, etc.) and machine-dependent parameters (effective FLOP rate, and the effective interprocessor bandwidths for the communication of particles and grid points). These expressions can be used to estimate the performance of scaled problems--including those with inhomogeneous plasmas--to other parallel machines once the machine-dependent parameters are known.

Lyster, P. M.↗

Reduced model simulations of the scrape-off-layer heat-flux width and comparison with experiment

Reduced model simulations of turbulence in the edge and scrape-off-layer (SOL) region of a spherical torus or tokamak plasma are employed to address the physics of the scrape-off-layer heat flux width. The simulation model is an electrostatic two-dimensional fluid turbulence model, applied in the plane perpendicular to the magnetic field at the outboard midplane of the torus. The model contains curvature-driven-interchange modes, sheath losses, and both perpendicular turbulent diffusive and convective (blob) transport. These transport processes compete with classical parallel transport to set the SOL width. Midplane SOL profiles of density, temperature and parallel heat flux are obtained from the simulation and compared with experimental results from the National Spherical Torus Experiment (NSTX) to study the scaling of the heat flux width with power and plasma current. It is concluded that midplane turbulence is the main contributor to the SOL heat flux width for the low power H-mode discharges studied, while additional physics is required to explain the plasma current scaling of the SOL heat flux width observed experimentally in higher power discharges. Intermittent separatrix spanning convective cells are found to be the main mechanism that sets the near-SOL width in the simulations. The roles of sheared flows and blob trapping vs. emission are discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Self-optimized construction of transition rate matrices from accelerated atomistic simulations with Bayesian uncertainty quantification

Here, a massively parallel method to build large transition rate matrices from temperature-accelerated molecular dynamics trajectories is presented. Bayesian Markov model analysis is used to estimate the expected residence time in the known state space, providing crucial uncertainty quantification for higher-scale simulation schemes such as kinetic Monte Carlo or cluster dynamics. The estimators are additionally used to optimize where exploration is performed and the degree of temperature acceleration on the fly, giving an autonomous, optimal procedure to explore the state space of complex systems. The method is tested against exactly solvable models and used to explore the dynamics of C15 interstitial defects in iron. Our uncertainty quantification scheme allows for accurate modeling of the evolution of these defects over timescales of several seconds.

36 MATERIALS SCIENCE↗

Parallel machine architecture and compiler design facilities

The objective is to provide an integrated simulation environment for studying and evaluating various issues in designing parallel systems, including machine architectures, parallelizing compiler techniques, and parallel algorithms. The status of Delta project (which objective is to provide a facility to allow rapid prototyping of parallelized compilers that can target toward different machine architectures) is summarized. Included are the surveys of the program manipulation tools developed, the environmental software supporting Delta, and the compiler research projects in which Delta has played a role.

Kuck, David J.↗

Verification and source-position error analysis of film reconstruction techniques used in the brachytherapy planning systems

A method was presented that employs standard linac QA tools to verify the accuracy of film reconstruction algorithms used in the brachytherapy planning system. Verification of reconstruction techniques is important as suggested in the ESTRO booklet 8: ''The institution should verify the full process of any reconstruction technique employed clinically.'' Error modeling was also performed to analyze seed-position errors. The ''isocentric beam checker'' device was used in this work. It has a two-dimensional array of steel balls embedded on its surface. The checker was placed on the simulator couch with its center ball coincident with the simulator isocenter, and one axis of its cross marks parallel to the axis of gantry rotation. The gantry of the simulator was rotated to make the checker behave like a three-dimensional array of balls. Three algorithms used in the ABACUS treatment planning system: orthogonal film, 2-films-with-variable-angle, and 3-films-with-variable-angle were tested. After exposing and digitizing the films, the position of each steel ball on the checker was reconstructed and compared to its true position, which can be accurately calculated. The results showed that the error is dependent on the object-isocenter distance, but not the magnification of the object. The averaged errors were less than 1 mm within the tolerance level defined by Roueet al. [''The EQUAL-ESTRO audit on geometric reconstruction techniques in brachytherapy,'' Radiother. Oncol. 78, 78-83 (2006)]. However, according to the error modeling, the theoretical error would be greater than 2 mm if the objects were located more than 20 cm away from the isocenter with a 0.5 deg. reading error of the gantry and collimator angles. Thus, in addition to carefully performing the QA of the gantry and collimator angle indicators, it is suggested that the patient, together with the applicators or seeds inside, should be placed close to the isocenter as much as possible. This method could be used to test the reconstruction techniques of any planning system, and the most suitable one can be chosen for clinical use.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Role of Reynolds stress and toroidal momentum transport in the dynamics of internal transport barriers

We study the interplay between intrinsic rotation and internal transport barrier (ITB) dynamics through the dynamic change of the parallel Reynolds stress. Global flux-driven gyrofluid simulations are used for this study. In particular, we investigate the role of parallel velocity gradient instability (PVGI) in the ITB formation and the back transition. It is found that the excitation of PVGI is followed by a change in the Reynolds stress which drives a momentum redistribution. This significantly influences E Multiplication-Sign B shear evolution and subsequent ITB dynamics. Nonlocal interactions among fluctuations are also observed during the PVGI excitation, resulting in turbulence suppression at the ITB.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Advancements in real-time engine simulation technology

The approaches used to develop real-time engine simulations are reviewed. Both digital and hybrid (analog and digital) techniques are discussed and specific examples of each are cited. These approaches are assessed from the standpoint of their usefulness for digital engine control development. A number of NASA-sponsored simulation research activities, aimed at exploring real-time simulation techniques, are described. These include the development of a microcomputer-based, parallel processor system for real-time engine simulation.

Szuch, J. R.↗