Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed parallelization”

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 1,423 records · Page 79

Strategic planning for disaster recovery with stochastic last mile distribution

This paper considers the single commodity allocation problem (SCAP) for disaster recovery, a fundamental problem faced by all populated areas. SCAPs are complex stochastic optimization problems that combine resource allocation, warehouse routing, and parallel fleet routing. Moreover, these problems must be solved under tight runtime constraints to be practical in real-world disaster situations. This paper formalizes the specification of SCAPs and introduces a novel multi-stage hybrid-optimization algorithm that utilizes the strengths of mixed integer programming, constraint programming, and large neighborhood search. The algorithm was validated on hurricane disaster scenarios generated by Los Alamos National Laboratory using state-of-the-art disaster simulation tools and is deployed to aid federal organizations in the US.

97 MATHEMATICS AND COMPUTING↗

Parallel peak pruning for scalable SMP contour tree computation

As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. Here in this paper, we report the first shared SMP algorithm for fully parallel contour tree computation, withfor-mal guarantees of O(lgnlgt) parallel steps and O(n lgn) work, and implementations with up to 10x parallel speed up in OpenMP and up to 50x speed up in NVIDIA Thrust.

97 MATHEMATICS AND COMPUTING↗

A Many-Task Parallel Approach for Multiscale Simulations of Subsurface Flow and Reactive Transport

Continuum-scale models have long been used to study subsurface flow, transport, and reactions but lack the ability to resolve processes that are governed by pore-scale mixing. Recently, pore-scale models, which explicitly resolve individual pores and soil grains, have been developed to more accurately model pore-scale phenomena, particularly reaction processes that are controlled by local mixing. However, pore-scale models are prohibitively expensive for modeling application-scale domains. This motivates the use of a hybrid multiscale approach in which continuum- and pore-scale codes are coupled either hierarchically or concurrently within an overall simulation domain (time and space). This approach is naturally suited to an adaptive, loosely-coupled many-task methodology with three potential levels of concurrency. Each individual code (pore- and continuum-scale) can be implemented in parallel; multiple semi-independent instances of the pore-scale code are required at each time step providing a second level of concurrency; and Monte Carlo simulations of the overall system to represent uncertainty in material property distributions provide a third level of concurrency. We have developed a hybrid multiscale model of a mixing-controlled reaction in a porous medium wherein the reaction occurs only over a limited portion of the domain. Loose, minimally-invasive coupling of pre-existing parallel continuum- and pore-scale codes has been accomplished by an adaptive script-based workflow implemented in the Swift workflow system. We describe here the methods used to create the model system, adaptively control multiple coupled instances of pore- and continuum-scale simulations, and maximize the scalability of the overall system. We present results of numerical experiments conducted on NERSC supercomputing systems; our results demonstrate that loose many-task coupling provides a scalable solution for multiscale subsurface simulations with minimal overhead.

high performance computing↗

miniVite: A Graph Analytics Benchmarking Tool for Massively Parallel Systems

Benchmarking of high performance computing sys-tems can help provide critical insights for ef?cient design of computing systems and software applications. Although a large number of tools for benchmarking exist, there is a lack of rep-resentative benchmarks for the class of irregular computations as exempli?ed by graph analytics. In this paper, we propose miniVite as a representative graph analytics benchmark tool to test a variety of distributed-memory systems. Graph clustering, popularly known as community detection, is a prototypical graph operation used in numerous scienti?c computing and analytics applications. The goal of clustering is to partition a graph into clusters (or communities) such that each cluster consists of vertices that are densely connected within the cluster and sparsely connected to the rest of the graph. Modu-larity optimization is a popular technique for identifying clusters in a graph. Ef?cient parallelization of modularity optimization-based algorithms is challenging. One successful approach was conceived in Vite, a distributed-memory implementation of the Louvain algorithm that incorporates several heuristics. We introduce miniVite as a representative but simpli?ed variant of Vite, to serve as a prototypical graph analytics benchmarking tool. Unlike other graph-based methods such as breadth-?rst search and betweenness centrality, miniVite represents highly complex computational patterns stressing a variety of system features, which can provide crucial insight for co-design of future computing systems.

community detection, parallel, MPI↗

Studying Catalytically Viable Single-Crystalline Metal Oxide Nanorods Using Synchrotron-Based Scanning Hard X-ray Microscopy

Synchrotron-based scanning hard X-ray microscopy (SHXM) was used to extract localized chemical and structural information within a system of model alkaline earth-metal tungstate nanorods, characterized by multiple chemical configurations. Specifically, we have highlighted the practical ability of SHXM to probe chemically distinctive nanoscale species, consisting of (i) chemically doped versus (ii) solid solution-state nanorods of comparable dimension, synthesized using a template-directed method under ambient conditions. Indeed, we show that SHXM can be used to map out elemental distributions within individual anisotropic nanorods with nanoscale resolution, coupled with chemical sensitivity and specificity. Complementary electrochemical results suggest the possibility of using these nanorods as support materials for electro-oxidation reactions within an acidic electrolyte medium. Our structural and chemical composition results have been corroborated using parallel lines of inquiry involving scanning electron microscopy, transmission electron microscopy, energy-dispersive X-ray spectroscopy, X-ray diffraction, and X-ray photoelectron spectroscopy. Furthermore, these measurements confirmed the relatively even and uniform distribution of the expected, individual elements within all of the nanorod samples tested.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Coupling Big Data Analytics and Reactive Transport Modeling for Cost-effective Groundwater Monitoring - 17163

This study presents an innovative approach for sustainable and cost-effective groundwater monitoring. This approach takes advantage of recent advances in various technologies: (1) in situ autonomous sensors, (2) big data analytics, and (3) parallel high-performance computing for flow and reactive transport modeling. In situ sensors are used to periodically measure the key variables (such as pH, redox potential, electrical conductivity, and groundwater level), which control contaminant mobility and the plume spatial and temporal distribution. Based on a limited number of groundwater sampling, the data analytics methods-data mining and machine learning-allow us to identify and quantify the correlations between the in situ-measured variables and contaminant concentrations, and also to detect significant changes associated with the plume mobility. In addition, a state-of-the-art parallel numerical flow and reactive transport simulator Amanzi, and uncertainty quantification software Agni are used to provide an improved physical and mechanistic understanding of the contaminated groundwater system behavior, and to predict the long-term plume distribution for optimizing and adapting the monitoring strategy. Amanzi and Agni were developed as part of the Advanced Simulation Capability for Environmental Management (ASCEM) program of the DOE Office of Environmental Management. Such modeling is critical, particularly, for assessing the impact of climate change and associated hydrological shifts. The developed approach is expected to significantly reduce the groundwater sampling frequency and associated cost. In addition, the real-time information on plume mobility serves as an early warning system, improving the resiliency of contaminated or potentially contaminated sites. We demonstrate this approach using as an example the Savannah River Site (SRS) F-Area, where groundwater is contaminated by various radionuclides, including uranium, tritium and technetium. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Multidimensional Vlasov–Poisson Simulations with High-order Monotonicity- and Positivity-preserving Schemes

We develop new numerical schemes for Vlasov–Poisson equations with high-order accuracy. Our methods are based on a spatially monotonicity-preserving (MP) scheme and are modified suitably so that the positivity of the distribution function is also preserved. We adopt an efficient semi-Lagrangian time integration scheme that is more accurate and computationally less expensive than the three-stage TVD Runge–Kutta integration. We apply our spatially fifth- and seventh-order schemes to a suite of simulations of collisionless self-gravitating systems and electrostatic plasma simulations, including linear and nonlinear Landau damping in one dimension and Vlasov–Poisson simulations in a six-dimensional phase space. The high-order schemes achieve a significantly improved accuracy in comparison with the third-order positive-flux-conserved scheme adopted in our previous study. With the semi-Lagrangian time integration, the computational cost of our high-order schemes does not significantly increase, but remains roughly the same as that of the third-order scheme. Vlasov–Poisson simulations on 128{sup 3}×128{sup 3} mesh grids have been successfully performed on a massively parallel computer.

79 ASTRONOMY AND ASTROPHYSICS↗

Designing a Distributed Systems Architecture Testbed for Real-Time Power Grid Systems

Power engineers who are striving to improve real-time attribute of power grid applications are ill equipped with software engineering methods and tools that allow them to rigorously evaluate their designs, taken into account data communication, geographic locations, and high performance computing capacity. This paper presents a technical approach to designing a testbed for embedding real-time monitoring and computation functionalities into the power grid system. The approach focuses on integrating the parallel computational models with the data management infrastructure for near-real time power grid state estimation. We study and summarize various forces and requirements that drive the design decisions in the distributed systems architecture. Given the continental scale of the power grid, it is important for the testbed to be extensible and scalable within a complex topology of physical entities, controlled by an overlaid network of power utilities and regulatory balancing authorities. This paper outlines the technical steps, and software toolkits to develop this testbed.

99 GENERAL AND MISCELLANEOUS↗

SU-E-T-531: Performance Evaluation of Multithreaded Geant4 for Proton Therapy Dose Calculations in a High Performance Computing Facility

Purpose: To evaluate the efficiency of multithreaded Geant4 (Geant4-MT, version 10.0) for proton Monte Carlo dose calculations using a high performance computing facility. Methods: Geant4-MT was used to calculate 3D dose distributions in 1×1×1 mm3 voxels in a water phantom and patient's head with a 150 MeV proton beam covering approximately 5×5 cm2 in the water phantom. Three timestamps were measured on the fly to separately analyze the required time for initialization (which cannot be parallelized), processing time of individual threads, and completion time. Scalability of averaged processing time per thread was calculated as a function of thread number (1, 100, 150, and 200) for both 1M and 50 M histories. The total memory usage was recorded. Results: Simulations with 50 M histories were fastest with 100 threads, taking approximately 1.3 hours and 6 hours for the water phantom and the CT data, respectively with better than 1.0 % statistical uncertainty. The calculations show 1/N scalability in the event loops for both cases. The gains from parallel calculations started to decrease with 150 threads. The memory usage increases linearly with number of threads. No critical failures were observed during the simulations. Conclusion: Multithreading in Geant4-MT decreased simulation time in proton dose distribution calculations by a factor of 64 and 54 at a near optimal 100 threads for water phantom and patient's data respectively. Further simulations will be done to determine the efficiency at the optimal thread number. Considering the trend of computer architecture development, utilizing Geant4-MT for radiotherapy simulations is an excellent cost-effective alternative for a distributed batch queuing system. However, because the scalability depends highly on simulation details, i.e., the ratio of the processing time of one event versus waiting time to access for the shared event queue, a performance evaluation as described is recommended.

60 APPLIED LIFE SCIENCES↗

2-dimensional ion velocity distributions measured by laser-induced fluorescence above a radio-frequency biased silicon wafer

The dynamics of ions traversing sheaths in low temperature plasmas are important to the formation of the ion energy distribution incident onto surfaces during microelectronics fabrication. Ion dynamics have been measured using laser-induced fluorescence (LIF) in the sheath above a 30 cm diameter, 2.2 MHz-biased silicon wafer in a commercial inductively coupled plasma processing reactor. The velocity distribution of argon ions was measured at thousands of positions above and radially along the surface of the wafer by utilizing a planar laser sheet from a pulsed, tunable dye laser. Velocities were measured both parallel and perpendicular to the wafer over an energy range of 0.4–600 eV. The resulting fluorescence was recorded using a fast CCD camera, which provided resolution of 0.4 mm in space and 30 ns in time. Data were taken at eight different phases during the 2.2 MHz cycle. The ion velocity distributions (IVDs) in the sheath were found to be spatially non-uniform near the edge of the wafer and phase-dependent as a function of height. Several cm above the wafer the IVD is Maxwellian and independent of phase. Experimental results were compared with simulations. The experimental time-averaged ion energy distribution function as a function of height compare favorably with results from the computer model.

36 MATERIALS SCIENCE↗

Modeling the performance and cost of lithium-ion batteries for electric-drive vehicles.

This report details the Battery Performance and Cost model (BatPaC) developed at Argonne National Laboratory for lithium-ion battery packs used in automotive transportation. The model designs the battery for a specified power, energy, and type of vehicle battery. The cost of the designed battery is then calculated by accounting for every step in the lithium-ion battery manufacturing process. The assumed annual production level directly affects each process step. The total cost to the original equipment manufacturer calculated by the model includes the materials, manufacturing, and warranty costs for a battery produced in the year 2020 (in 2010 US$). At the time this report is written, this calculation is the only publically available model that performs a bottom-up lithium-ion battery design and cost calculation. Both the model and the report have been publically peer-reviewed by battery experts assembled by the U.S. Environmental Protection Agency. This report and accompanying model include changes made in response to the comments received during the peer-review. The purpose of the report is to document the equations and assumptions from which the model has been created. A user of the model will be able to recreate the calculations and perhaps more importantly, understand the driving forces for the results. Instructions for use and an illustration of model results are also presented. Almost every variable in the calculation may be changed by the user to represent a system different from the default values pre-entered into the program. The distinct advantage of using a bottom-up cost and design model is that the entire power-to-energy space may be traversed to examine the correlation between performance and cost. The BatPaC model accounts for the physical limitations of the electrochemical processes within the battery. Thus, unrealistic designs are penalized in energy density and cost, unlike cost models based on linear extrapolations. Additionally, the consequences on cost and energy density from changes in cell capacity, parallel cell groups, and manufacturing capabilities are easily assessed with the model. New proposed materials may also be examined to translate bench-scale values to the design of full-scale battery packs providing realistic energy densities and prices to the original equipment manufacturer. The model will be openly distributed to the public in the year 2011. Currently, the calculations are based in a Microsoft{reg_sign} Office Excel spreadsheet. Instructions are provided for use; however, the format is admittedly not user-friendly. A parallel development effort has created an alternate version based on a graphical user-interface that will be more intuitive to some users. The version that is more user-friendly should allow for wider adoption of the model.

25 ENERGY STORAGE↗

Fast and Accurate Support Vector Machines on Large Scale Systems

Support Vector Machines (SVM) is a supervised Machine Learning and Data Mining (MLDM) algorithm, which has become ubiquitous largely due to its high accuracy and obliviousness to dimensionality. The objective of SVM is to find an optimal boundary --- also known as hyperplane --- which separates the samples (examples in a dataset) of different classes by a maximum margin. Usually, very few samples contribute to the definition of the boundary. However, existing parallel algorithms use the entire dataset for finding the boundary, which is sub-optimal for performance reasons. In this paper, we propose a novel distributed memory algorithm to eliminate the samples which do not contribute to the boundary definition in SVM. We propose several heuristics, which range from early (aggressive) to late (conservative) elimination of the samples, such that the overall time for generating the boundary is reduced considerably. In a few cases, a sample may be eliminated (shrunk) pre-emptively --- potentially resulting in an incorrect boundary. We propose a scalable approach to synchronize the necessary data structures such that the proposed algorithm maintains its accuracy. We consider the necessary trade-offs of single/multiple synchronization using in-depth time-space complexity analysis. We implement the proposed algorithm using MPI and compare it with libsvm--- de facto sequential SVM software --- which we enhance with OpenMP for multi-core/many-core parallelism. Our proposed approach shows excellent efficiency using up to 4096 processes on several large datasets such as UCI HIGGS Boson dataset and Offending URL dataset.

Vishnu, Abhinav↗

Planar Collisionless Shock Simulations with the Semi-implicit Particle-in-cell Model FLEKS

This study investigates the applicability of the semi-implicit particle-in-cell code FLexible Exascale Kinetic Simulator (FLEKS) to heliospheric shock simulations. We examine one- and two-dimensional local planar shock simulations, initialized using MHD states with upstream conditions representative of plasmas in the hypersonic, β ∼ 1 regime, for both quasi-perpendicular and quasi-parallel configurations. The refined algorithm in FLEKS proves robust, enabling accurate shock simulations with a grid resolution on the order of the electron inertial length d e . Our simulations successfully capture key shock features, including shock structures (foot, ramp, overshoot, and undershoot), upstream and downstream waves (fast magnetosonic, whistler, Alfvén ion-cyclotron, and mirror modes), and non-Maxwellian particle distributions. Crucially, we find that at least two spatial dimensions are critical for accurately reproducing downstream-wave physics in quasi-perpendicular shocks and capturing the complex dynamics of quasi-parallel shocks, including surface rippling, shocklets, short, large-amplitude magnetic structures, magnetic reconnection, and jets. Furthermore, our parameter studies demonstrate the impact of mass ratio and grid resolution on shock physics. This work provides valuable guidance for selecting appropriate physical and numerical parameters for shock simulations using a semi-implicit PIC method, paving the way for incorporating kinetic shock processes into large-scale collisionless plasma simulations with the MHD-AEPIC model.

plasma astrophysics↗

Unraveling the Formation Region and Frequency of Chorus Spectral Gaps

Abstract The present study addresses two basic questions related to banded chorus waves in the Earth’s magnetosphere: 1) are chorus spectral gaps formed near the equatorial source region or during propagation away from the equator? and 2) why are chorus spectral gaps usually located below 0.5 f ce ( f ce : electron gyro‐frequency)? By analyzing Van Allen Probes data, we demonstrate that chorus spectral gaps are observed in the source region where chorus waves propagate both in the parallel and anti‐parallel directions to the magnetic field. Chorus spectral gaps below 0.5 f ce are associated with electron parallel acceleration at energies above the equatorial Landau resonant energies. We explain that initially generated chorus waves quickly isotropize the electron distribution through Landau resonant acceleration, and the isotropization occurs for higher energies at higher latitudes. The isotropized population, after returning to the magnetic equator, leads to a chorus gap typically below 0.5 f ce by suppressing wave excitation.

Li, Jinxing↗

Role of Intersections in Fracture Connectivity

Networks of intersecting fractures often provide the flow paths through subsurface reservoirs. Assessing network connectivity is challenging because fracture intersections compose a vanishingly small fraction of the network void volume. In this paper, motivated by 3D X-ray imaging of the simplest element of fracture network, that is, two orthogonal fractures, we perform a percolation and finite-size scaling analysis to study the connectivity provided by fracture intersections. The conditions when an intersection enhances connectivity across a sample depend on spatial correlations in the fracture aperture distributions, on the stress state, and on the direction of flow. Here we consider three flow directions: (a) across intersections, (b) parallel to intersections and (c) around corners. For (a), intersections provide minimal enhancement of connectivity because they contribute little additional void area. For (b), intersections increase the probability of a connected path near threshold by enabling 3D connected pathways that are not possible in parallel fractures. Flow around corners, (c), is fundamentally the result of the intersection connecting two fractures in series and spatial correlations are broken around corners, suppressing the connectivity relative to (a). When the connected fractures are stressed equally, a joint percolation threshold emerges that continues to have scale invariance. However, when the fractures are stressed unequally, the system has mixed percolation without clearly defined percolation thresholds. In all cases, percolation probabilities are found to be scale dependent which has important consequences for the connectivity of larger fracture networks composed of the fundamental element studied here.

02 PETROLEUM↗

Results of the implementation on a mock-up of the full 3dB hybrid matching option of the ITER ICRH system

Each of the two ICRH antennas for ITER must couple 20MW to the plasma in the 40-55MHz band via an array of 24 radiating shorted straps fed by four generators. The matching system must provide automatic matching control on the mean load provided by the plasma and be resilient (parallel {Gamma}{sub G} parallel <0.2) to a wide range of fast antenna load excursions occurring in ELMy plasmas. Furthermore, good control of the current distribution in the strap array must be possible for the various heating and current drive scenarios. Two load resilient matching options have been considered for ITER: the 4 'Conjugate-T'(CT) and the 4 hybrids ones, the first being presently considered as a back-up option. Automatic control of these 2 options has been developed, and tested for optimization on a low-powered scaled mock-up. Successful implementation of the simultaneous feedback control of 11 actuators for the matching of the 4 CT and for the control of the toroidal phasing has already been achieved. The matching and the array current control of the 3dB hybrid option are provided by simultaneous feedback control of the decouplers and double stub tuners (in total 23 actuators) and this has also been successfully achieved for the full array. The paper discusses the circuit implementation and presents the obtained results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Mechanisms underpinning the ultrahigh piezoelectricity in Sm-doped 0.705Pb(Mg 1/3 Nb 2/3 )O 3 -0.295PbTiO 3 : Temperature-induced metastable local structure and field-induced polarization rotation

The solid solution of (100 – x )%Pb(Mg 1/3 Nb 2/3 )O 3 - x %PbTiO 3 (PMN- x PT) exhibits ultrahigh piezoelectric and dielectric properties near the morphotropic phase boundary compositions and, as such, has been extensively studied in recent years. Recently, 2.5 mol. % Sm-doped PMN-29PT polycrystalline ceramics were reported to possess the highest piezoelectric coefficients (~1500 pC/N) among all reported piezoceramics, but the atomic-scale mechanisms for such high piezoelectric properties are not yet clear. Here, in situ X-ray diffraction and X-ray total scattering measurements during the application of an electric field, together with in situ total scattering measurement at different temperatures, were conducted for 2.5 mol. % Sm-doped PMN-29.5PT (2.5Sm-PMN-29.5PT). Both the largest field-induced strain and the piezoelectric response were found in the crystallites oriented with their &#12296 100 &#12297 PC directions parallel to the applied field. The local Pb displacement was analyzed using the reverse Monte Carlo method based on the pair distribution functions at different temperatures, where a temperature-induced directional change of Pb displacement was observed. Based on the experimental observations, a field-induced polarization rotation is suggested to be the dominant mechanism for the ultrahigh piezoelectricity of the 2.5Sm-PMN-29.5PT ceramic, while the ease of polarization rotation is possibly attributed to the temperature-induced metastable local monoclinic symmetries with their polar axes close to &#12296 111 &#12297 PC .

36 MATERIALS SCIENCE↗

THE ACCELERATION OF THERMAL PROTONS AT PARALLEL COLLISIONLESS SHOCKS: THREE-DIMENSIONAL HYBRID SIMULATIONS

We present three-dimensional hybrid simulations of collisionless shocks that propagate parallel to the background magnetic field to study the acceleration of protons that forms a high-energy tail on the distribution. We focus on the initial acceleration of thermal protons and compare it with results from one-dimensional simulations. We find that for both one- and three-dimensional simulations, particles that end up in the high-energy tail of the distribution later in the simulation gained their initial energy right at the shock. This confirms previous results but is the first to demonstrate this using fully three-dimensional fields. The result is not consistent with the ''thermal leakage'' model. We also show that the gyrocenters of protons in the three-dimensional simulation can drift away from the magnetic field lines on which they started due to the removal of ignorable coordinates that exist in one- and two-dimensional simulations. Our study clarifies the injection problem for diffusive shock acceleration.

79 ASTRONOMY AND ASTROPHYSICS↗