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 955 records · Page 53

Parallel phase model : a programming model for high-end parallel machines with manycores.

This paper presents a parallel programming model, Parallel Phase Model (PPM), for next-generation high-end parallel machines based on a distributed memory architecture consisting of a networked cluster of nodes with a large number of cores on each node. PPM has a unified high-level programming abstraction that facilitates the design and implementation of parallel algorithms to exploit both the parallelism of the many cores and the parallelism at the cluster level. The programming abstraction will be suitable for expressing both fine-grained and coarse-grained parallelism. It includes a few high-level parallel programming language constructs that can be added as an extension to an existing (sequential or parallel) programming language such as C; and the implementation of PPM also includes a light-weight runtime library that runs on top of an existing network communication software layer (e.g. MPI). Design philosophy of PPM and details of the programming abstraction are also presented. Several unstructured applications that inherently require high-volume random fine-grained data accesses have been implemented in PPM with very promising results.

99 GENERAL AND MISCELLANEOUS↗

Microtearing modes in tokamak discharges

Microtearing modes (MTMs) have been identified as a source of significant electron thermal transport in tokamak discharges. In order to describe the evolution of these discharges, it is necessary to improve the prediction of electron thermal transport. This can be accomplished by utilizing a model for transport driven by MTMs in whole device predictive modeling codes. The objective of this paper is to develop the dispersion relation that governs the MTM driven transport. A unified fluid/kinetic approach is used in the development of a nonlinear dispersion relation for MTMs. The derivation includes the effects of electrostatic and magnetic fluctuations, arbitrary electron-ion collisionality, electron temperature and density gradients, magnetic curvature, and the effects associated with the parallel propagation vector. An iterative nonlinear approach is used to calculate the distribution function employed in obtaining the nonlinear parallel current and the nonlinear dispersion relation. The third order nonlinear effects in magnetic fluctuations are included, and the influence of third order effects on a multi-wave system is considered. An envelope equation for the nonlinear microtearing modes in the collision dominant limit is introduced in order to obtain the saturation level. In the limit that the mode amplitude does not vary along the field line, slab geometry, and strong collisionality, the fluid dispersion relation for nonlinear microtearing modes is found to agree with the kinetic dispersion relation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Towards Flange-to-Flange Turbopump Simulations for Liquid Rocket Engines

The primary objective of this research is to support the design of liquid rocket systems for the Advanced Space Transportation System. Since the space launch systems in the near future are likely to rely on liquid rocket engines, increasing the efficiency and reliability of the engine components is an important task. One of the major problems in the liquid rocket engine is to understand fluid dynamics of fuel and oxidizer flows from the fuel tank to plume. Understanding the flow through the entire turbopump geometry through numerical simulation will be of significant value toward design. This will help to improve safety of future space missions. One of the milestones of this effort is to develop, apply and demonstrate the capability and accuracy of 3D CFD methods as efficient design analysis tools on high performance computer platforms. The development of the MPI and MLP versions of the INS3D code is currently underway. The serial version of INS3D code is a multidimensional incompressible Navier-Stokes solver based on overset grid technology. INS3D-MPI is based on the explicit massage-passing interface across processors and is primarily suited for distributed memory systems. INS3D-MLP is based on multi-level parallel method and is suitable for distributed-shared memory systems. For the entire turbopump simulations, moving boundary capability and an efficient time-accurate integration methods are build in the flow solver. To handle the geometric complexity and moving boundary problems, overset grid scheme is incorporated with the solver that new connectivity data will be obtained at each time step. The Chimera overlapped grid scheme allows subdomains move relative to each other, and provides a great flexibility when the boundary movement creates large displacements. The performance of the two time integration schemes for time-accurate computations is investigated. For an unsteady flow which requires small physical time step, the pressure projection method was found to be computationally efficient since it does not require any subiterations procedure. It was observed that the artificial compressibility method requires a fast convergence scheme at each physical time step in order to satisfy incompressibility condition. This was obtained by using a GMRES-ILU(0) solver in our computations. When a line-relaxation scheme was used, the time accuracy was degraded and time-accurate computations became very expensive. The current geometry for the LOX boost turbopump has various rotating and stationary components, such as inducer, stators, kicker, hydrolic turbine, where the flow is extremely unsteady. Figure 1 shows the geometry and computed surface pressure of the inducer. The inducer and the hydrolic turbine rotate in different rotational speed.

Kiris, Cetin↗

HPC formulations of optimization algorithms for tensor completion

Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often accomplished via low-rank sparse tensor factorization, a computationally expensive non-convex optimization problem which has only recently been studied in the context of parallel computing. In this work, we study three optimization algorithms that have been successfully applied to tensor completion: alternating least squares (ALS), stochastic gradient descent (SGD), and coordinate descent (CCD++). We explore opportunities for parallelism on shared- and distributed-memory systems and address challenges such as memory- and operation-efficiency, load balance, cache locality, and communication. Among our advancements are a communication-efficient CCD++ algorithm, an ALS algorithm rich in level-3 BLAS routines, and an SGD algorithm which combines stratification with asynchronous communication. Furthermore, we show that introducing randomization during ALS and CCD++ can accelerate convergence. We evaluate our parallel formulations on a variety of real datasets on a modern supercomputer and demonstrate speedups through 16384 cores. Further, these improvements reduce time-to-solution from hours to seconds on real-world datasets. We show that after our optimizations, ALS is advantageous on parallel systems of small-to-moderate scale, while both ALS and CCD++ provide the lowest time-to-solution on large-scale distributed systems.

97 MATHEMATICS AND COMPUTING↗

Nonlinear Dynamics of Mirror Instability Revisited

A nonlinear dynamics of the mirror modes near the instability threshold is revisited. It is shown that the major saturation is provided by modification of the velocity distribution function in the vicinity of small parallel ion velocities. The final relaxation scenario is based on almost resonant particle interaction with mirror modes. The saturated plasma state can be considered as a magnetic counterpart to electrostatic Bernstein-Greene-Kruskal modes. Our analytical model is verified by relevant numerical simulations. Test particle and PIC simulations indeed show that it is a modification of distribution function at small parallel velocities that results in fading away of free energy driving mirror mode. The physical similarity of the mirror and Weibel instabilities is demonstrated. The multipoint satellite measurements in space plasma can be used to validate a proposed scenario.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Heating and acceleration of ions in nonresonant Alfvenic turbulence

Nonlinear scattering of protons and alpha particles during the dissipation of the finite amplitude, low-frequency Alfvenic turbulence is studied. The process discussed here is not the coherent scattering and acceleration, as those often treated in the past studies, but is an incoherent process in which it is essential that the Alfvenic turbulence has a broadband spectrum. The presence of such an Alfvenic turbulence is widely recognized observationally both in the solar corona and in the solar wind. Numerical results suggest that, although there is no apparent sign of the occurrence of any parametric instabilities, the ions are heated efficiently by the nonlinear Landau damping, i.e., trapping and phase mixing by Alfven wave packets which are generated by beating of finite amplitude Alfven waves. The heating occurs both in the parallel and in the perpendicular directions, and the ion distribution function which is asymmetric with respect to the parallel velocity is produced. Eventual perpendicular energy of ions is much influenced by the spectrum and polarization of the given Alfvenic turbulence since the turbulence initially possess transverse energy as specified by Walen's relation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Distributed Louvain Algorithm for Graph Community Detection

In most real-world networks, the nodes/vertices tend to be organized into tightly-knit modules known as communities or clusters, such that nodes within a community are more likely to be “related” to one another than they are to the rest of the network. The goodness of partitioning into communities is typically measured using a well known measure called modularity. However, modularity optimization is an NP-complete problem. In 2008, Blondel, et al. introduced a multi-phase, iterative heuristic for modularity optimization, called the Louvain method. Owing to its speed and ability to yield high quality communities, the Louvain method continues to be one of the most widely used tools for serial community detection. In this paper, we present the design of a distributed memory implementation of the Louvain algorithm for parallel community detection. Our approach begins with an arbitrarily partitioned distributed graph input, and employs several heuristics to speedup the computation of the different steps of the Louvain algorithm. We evaluate our implementation and its different variants using real-world networks from various application domains (including internet, biology, social networks). Our MPI+OpenMP implementation yields about 7x speedup (on 4K processes) for soc-friendster network (1.8B edges) over a state-of-the-art shared-memory multicore implementation (on 64 threads), without compromising output quality. Furthermore, our distributed implementation was able to process a larger graph (uk-2007; 3.3B edges) in 32 seconds on 1K cores (64 nodes) of NERSC Cori, when the state-of-the-art shared-memory implementation failed to run due to insufficient memory on a single Cori node containing 128 GB.

High performance computing, graph algorithms, Dist↗

Enabling the High Level Synthesis of Data Analytics Accelerators

Conventional High Level Synthesis (HLS) tools mainly tar- get compute intensive kernels typical of digital signal pro- cessing applications. We are developing techniques and ar- chitectural templates to enable HLS of data analytics appli- cations. These applications are memory intensive, present fine-grained, unpredictable data accesses, and irregular, dy- namic task parallelism. We discuss an architectural tem- plate based around a distributed controller to efficiently ex- ploit thread level parallelism. We present a memory in- terface that supports parallel memory subsystems and en- ables implementing atomic memory operations. We intro- duce a dynamic task scheduling approach to efficiently ex- ecute heavily unbalanced workload. The templates are val- idated by synthesizing queries from the Lehigh University Benchmark (LUBM), a well know SPARQL benchmark.

Data Analytics↗

A parallel dynamic load balancing algorithm for 3-D adaptive unstructured grids

Adaptive local grid refinement and coarsening results in unequal distribution of workload among the processors of a parallel system. A novel method for balancing the load in cases of dynamically changing tetrahedral grids is developed. The approach employs local exchange of cells among processors in order to redistribute the load equally. An important part of the load balancing algorithm is the method employed by a processor to determine which cells within its subdomain are to be exchanged. Two such methods are presented and compared. The strategy for load balancing is based on the Divide-and-Conquer approach which leads to an efficient parallel algorithm. This method is implemented on a distributed-memory MIMD system.

Vidwans, A.↗

Kinetic Properties of the Neutral Solar Wind

Charge-exchange collisions between the solar wind protons and interstellar hydrogen produce a distinctive population of neutral hydrogen streaming radially at nearly the solar-wind speed. This tenuous population, known as the neutral solar wind (NSW) is thought to play a key role in the appearance of the Interplanetary Boundary EXplorer ribbon, a bright circular band in the sky that is the source of neutral hydrogen with energies near 1 keV. According to the leading model of the ribbon, the velocity distribution of NSW hydrogen is imparted on the pickup ions (PUIs) generated via charge exchange with the interstellar protons beyond the heliopause, and in this way controls the stability of the resulting ring distribution of PUIs against hydromagnetic wave generation. In this paper, we examine the velocity distributions of the NSW atoms in the heliosphere and the outer heliosheath regions by following the phase-space trajectories of the Boltzmann equation. It is demonstrated that these distributions are highly anisotropic, with the parallel (radial) temperature greatly exceeding the perpendicular temperature. Ions picked up near 90° from the anisotropic NSW would form a stable ring distribution capable of generating the ribbon flux. We also discuss a second population of neutrals born in charge transfer collisions with interstellar PUIs, the so-called neutralized pickup ion (NPI) component. Their high thermal velocities translate into large parallel velocity spread of the daughter ribbon PUIs, which would adversely affect plasma stability in local interstellar space.

79 ASTRONOMY AND ASTROPHYSICS↗

Ground surface temperature reconstructions: Using in situ estimates for thermal conductivity acquired with a fiber-optic distributed thermal perturbation sensor

We have developed a borehole methodology to estimate formation thermal conductivity in situ with a spatial resolution of one meter. In parallel with a fiber-optic distributed temperature sensor (DTS), a resistance heater is deployed to create a controlled thermal perturbation. The transient thermal data is inverted to estimate the formation's thermal conductivity. We refer to this instrumentation as a Distributed Thermal Perturbation Sensor (DTPS), given the distributed nature of the DTS measurement technology. The DTPS was deployed in permafrost at the High Lake Project Site (67 degrees 22 minutes N, 110 degrees 50 minutes W), Nunavut, Canada. Based on DTPS data, a thermal conductivity profile was estimated along the length of a wellbore. Using the thermal conductivity profile, the baseline geothermal profile was then inverted to estimate a ground surface temperature history (GSTH) for the High Lake region. The GSTH exhibits a 100-year long warming trend, with a present-day ground surface temperature increase of 3.0 {+-} 0.8 C over the long-term average.

54 ENVIRONMENTAL SCIENCES↗

A Recursive Hypergraph Bipartitioning Framework for Reducing Bandwidth and Latency Costs Simultaneously

Intelligent partitioning models are commonly used for efficient parallelization of irregular applications on distributed systems. These models usually aim to minimize a single communication cost metric, which is either related to communication volume or message count. However, both volume- and message-related metrics should be taken into account during partitioning for a more efficient parallelization. There are only a few works that consider both of them and they usually address each in separate phases of a two-phase approach. In this work, we propose a recursive hypergraph bipartitioning framework that reduces the total volume and total message count in a single phase. In this framework, the standard hypergraph models, nets of which already capture the bandwidth cost, are augmented with message nets. The message nets encode the message count so that minimizing conventional cutsize captures the minimization of bandwidth and latency costs together. Our model provides a more accurate representation of the overall communication cost by incorporating both the bandwidth and the latency components into the partitioning objective. The use of the widely-adopted successful recursive bipartitioning framework provides the flexibility of using any existing hypergraph partitioner. In conclusion, the experiments on instances from different domains show that our model on the average achieves up to 52 percent reduction in total message count and hence results in 29 percent reduction in parallel running time compared to the model that considers only the total volume.

97 MATHEMATICS AND COMPUTING↗

Modulational instability of electromagnetic electron-cyclotron wave packets in the magnetosphere with non-Maxwellian electron distribution

The satellite observations of the magnetosphere in the low-frequency ion dynamics revealed several facts: (1) localized structures for electric field signal parallel to the magnetic field; (2) anisotropy for the electron velocity distribution such that T{sub perpendicular}<<T{sub parallel}; and (3) non-Maxwellian distribution function for the electrons. Based on these evidences, a nonlinear model is presented to develop the electromagnetic electron-cyclotron (EMEC) theory to the non-Maxwellian plasmas. Then, the modulational instability analysis of EMEC waves is investigated.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Transverse momentum-dependent parton distribution functions in lattice QCD

A fundamental structural property of the nucleon is the distribution of quark momenta, both parallel as well as perpendicular to its propagation. Experimentally, this information is accessible via selected processes such as semi-inclusive deep inelastic scattering (SIDIS) and the Drell-Yan process (DY), which can be parametrized in terms of transversemomentum-dependent parton distributions (TMDs). On the other hand, these distribution functions can be extracted from nucleon matrix elements of a certain class of bilocal quark operators in which the quarks are connected by a staple-shaped Wilson line serving to incorporate initial state (DY) or final state (SIDIS) interactions. A scheme for evaluating such matrix elements within lattice QCD is developed. This requires casting the calculation in a particular Lorentz frame, which is facilitated by a parametrization of the matrix elements in terms of invariant amplitudes. Exploratory results are presented for the time-reversal odd Sivers and Boer-Mulders transverse momentum shifts.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Electron velocity space hole modes

In space plasmas the local electron distribution is formed by ballistic motion from different source regions. Since electrons with positive and negative parallel (v-parallel) velocities have different sources and experience different interactions with the large-scale electromagnetic fields, the electron distribution function near v-parallel = 0 should possess considerable structure, including the possibility of velocity space holes, i.e., regions where the phase space density is zero, and sharp discontinuities. A particular hole distribution, which may occur upstream of slow shocks in the distant geomagnetic tail, is shown to support a nonstandard plasma wave mode with frequencies between the ion and electron plasma frequencies and parallel phase speed above the ion, but well below the electron, thermal speed. The hole mode can be destabilized by a positive slope in the low parallel velocity electron distribution, and the growth rate is strongly enhanced if the electron parallel temperature exceeds the perpendicular temperature; the mode can also be excited by a hot, fast ion beam. The hole modes exist only for a narrow range of propagation angles about the magnetic field direction.

Coroniti, Ferdinand V.↗

CAST: Contraction Algorithm for Symmetric Tensors

Tensor contractions represent the most compute-intensive core kernels in ab initio computational quantum chemistry and nuclear physics. Symmetries in these tensor contractions makes them difficult to load balance and scale to large distributed systems. In this paper, we develop an efficient and scalable algorithm to contract symmetric tensors. We introduce a novel approach that avoids data redistribution in contracting symmetric tensors while also avoiding redundant storage and maintaining load balance. We present experimental results on two parallel supercomputers for several symmetric contractions that appear in the CCSD quantum chemistry method. We also present a novel approach to tensor redistribution that can take advantage of parallel hyperplanes when the initial distribution has replicated dimensions, and use collective broadcast when the final distribution has replicated dimensions, making the algorithm very efficient.

distributed memory↗