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 181 records · Page 10

A composite grid solver for conjugate heat transfer in fluid-structure systems

We describe a numerical method for modeling temperature-dependent fluid flow coupled to heat transfer in solids. This approach to conjugate heat transfer can be used to compute transient and steady state solutions to a wide range of fluid-solid systems in complex two- and three-dimensional geometry. Fluids are modeled with the temperature-dependent incompressible Navier-Stokes equations using the Boussinesq approximation. Solids with heat transfer are modeled with the heat equation. Appropriate interface equations are applied to couple the solutions across different domains. The computational region is divided into a number of sub-domains corresponding to fluid domains and solid domains. There may be multiple fluid domains and multiple solid domains. Each fluid or solid sub-domain is discretized with an overlapping grid. The entire region is associated with a composite grid which is the union of the overlapping grids for the sub-domains. A different physics solver (fluid solver or solid solver) is associated with each sub-domain. A higher-level multi-domain solver manages the entire solution process. We propose and analyze some centered discrete approximations to the interface equations that have some desirable stability properties. The coupled interface equations may be solved directly when using explicit time-stepping methods in the sub-domains, resulting in a strongly coupled approach. The stability of the interface treatment in this case is independent of the relative sizes of the material properties in the two domains with the time-step only depending on the usual von Neumann conditions for each sub-domain. For implicit time-stepping methods we solve the interface equations in a weakly coupled fashion to avoid forming a coupled implicit system across all sub-domains. The convergence of this approach does depend on the relative sizes of the thermal conductivities and diffusivities. We analyze different iteration strategies for solving these implicit equations including the use of mixed (Robin) approximations at the interface. Numerical results are presented to illustrate the method. The accuracy of the technique is verified using the method of analytic solutions and by computing the solution to some heat exchanger problems where the exact solution is known. The technique is also applied to the modeling of an inertial-confinement-fusion hohlraum target and the flow of coolant past an hexagonal array of heated fuel rods. The multi-domain solver runs in parallel on distributed memory computers and some parallel results are provided.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Scalable parallel distance field construction for large-scale applications

Computing distance fields is fundamental to many scientific and engineering applications. Distance fields can be used to direct analysis and reduce data. In this paper, we present a highly scalable method for computing 3D distance fields on massively parallel distributed-memory machines. Anew distributed spatial data structure, named parallel distance tree, is introduced to manage the level sets of data and facilitate surface tracking overtime, resulting in significantly reduced computation and communication costs for calculating the distance to the surface of interest from any spatial locations. Our method supports several data types and distance metrics from real-world applications. We demonstrate its efficiency and scalability on state-of-the-art supercomputers using both large-scale volume datasets and surface models. We also demonstrate in-situ distance field computation on dynamic turbulent flame surfaces for a petascale combustion simulation. In conclusion, our work greatly extends the usability of distance fields for demanding applications.

97 MATHEMATICS AND COMPUTING↗

Parallel Nonnegative CP Decomposition of Dense Tensors

The CP tensor decomposition is a low-rank approximation of a tensor. We present a distributed-memory parallel algorithm and implementation of an alternating optimization method for computing a CP decomposition of dense tensors that can enforce nonnegativity of the computed low-rank factors. The principal task is to parallelize the Matricized-Tensor Times Khatri-Rao Product (MTTKRP) bottleneck subcomputation. The algorithm is computation efficient, using dimension trees to avoid redundant computation across MTTKRPs within the alternating method. Our approach is also communication efficient, using a data distribution and parallel algorithm across a multidimensional processor grid that can be tuned to minimize communication. We benchmark our software on synthetic as well as hyperspectral image and neuroscience dynamic functional connectivity data, demonstrating that our algorithm scales well to 100s of nodes (up to 4096 cores) and is faster and more general than the currently available parallel software.

Ballard, Grey↗

Lowering entry barriers to developing custom simulators of distributed applications and platforms with SimGrid

Researchers in parallel and distributed computing (PDC) often resort to simulation because experiments conducted using a simulator can be for arbitrary experimental scenarios, are less resource-, labor-, and time-consuming than their real-world counterparts, and are perfectly repeatable and observable. Many frameworks have been developed to ease the development of PDC simulators, and these frameworks provide different levels of accuracy, scalability, versatility, extensibility, and usability. Further, the SimGrid framework has been used by many PDC researchers to produce a wide range of simulators for over two decades. Its popularity is due to a large emphasis placed on accuracy, scalability, and versatility, and is in spite of shortcomings in terms of extensibility and usability. Although SimGrid provides sensible simulation models for the common case, it was difficult for users to extend these models to meet domain-specific needs. Furthermore, SimGrid only provided relatively low-level simulation abstractions, making the implementation of a simulator of a complex system a labor-intensive undertaking. In this work we describe developments in the last decade that have contributed to vastly improving extensibility and usability, thus lowering or removing entry barriers for users to develop custom SimGrid simulators.

97 MATHEMATICS AND COMPUTING↗

Asynchronous distributed-memory task-parallel algorithm for compressible flows on unstructured 3D Eulerian grids

Here, we discuss the implementation of a finite element method, used to numerically solve the Euler equations of compressible flows, using an asynchronous runtime system (RTS). The algorithm is implemented for distributed-memory machines, using stationary unstructured 3D meshes, combining data-, and task-parallelism on top of the Charm++ RTS. Charm++’s execution model is asynchronous by default, allowing arbitrary overlap of computation and communication. Task-parallelism allows scheduling parts of an algorithm independently of, or dependent on, each other. Built-in automatic load balancing enables continuous redistribution of computational load by migration of work units based on real-time CPU load measurement. The RTS also features automatic checkpointing, fault tolerance, resilience against hardware failure, and supports power-, and energy-aware computation. We demonstrate scalability up to 25 x 10 9 cells at $\mathscr{O}$10 4 compute cores and the benefits of automatic load balancing for irregular workloads. The full source code with documentation is available at https://quinoacomputing.org.

42 ENGINEERING↗

Experimental Investigation of Low-Frequency Distributed Acoustic Sensor Responses to Two Parallel Propagating Fractures

Low-frequency distributed acoustic sensing (LF-DAS) is a diagnostic tool for hydraulic fracture propagation with far-field monitoring using fiber optic sensors. LF-DAS senses strain rate variation caused by stress field change due to fracture propagation. Fiber optic sensors are installed in the monitoring wells in the vicinity of a fractured well. From the strain responses, fracture propagation can be evaluated. To understand subsurface conditions with multiple propagating fractures, a laboratory-scale hydraulic fracture experiment was performed simulating the LF-DAS response to fracture propagation with embedded distributed optical fiber strain sensors under these conditions. The experiment was performed using a transparent cube of epoxy with two parallel radial initial flaws centered in the cube. Fluid was injected into the sample to generate fractures along the initial flaws. The experiment used distributed high-definition fiber optic strain sensors with tight spatial resolutions. The sensors were embedded at two different locations on opposite sides of the initial flaws, serving as observation/monitoring locations. We also employed finite element modeling to numerically solve the linear elastic equations of equilibrium continuity and stress–strain relationships. The measured strains from the experiment were compared to simulation results from the finite element model. The experimentally derived strain and strain-rate waterfall plots from this study show the responses to both fractures propagating, while the fracture at the lower position took most of the fluid during the experiment. Interestingly, a fracture first began propagating from the upper flaw of the two flaws, but once the lower fracture was initiated, it grew much faster than the upper fracture. Both fibers were intercepted by the lower fracture, further verifying the strain signature as a fracture is approaching and intersecting an offset fiber.

Chemistry↗

The relation between reconnected flux, the parallel electric field, and the reconnection rate in a three-dimensional kinetic simulation of magnetic reconnection

We investigate the distribution of parallel electric fields and their relationship to the location and rate of magnetic reconnection in a large particle-in-cell simulation of 3D turbulent magnetic reconnection with open boundary conditions. The simulation's guide field geometry inhibits the formation of simple topological features such as null points. Therefore, we derive the location of potential changes in magnetic connectivity by finding the field lines that experience a large relative change between their endpoints, i.e., the quasi-separatrix layer. We find a good correspondence between the locus of changes in magnetic connectivity or the quasi-separatrix layer and the map of large gradients in the integrated parallel electric field (or quasi-potential). Furthermore, we investigate the distribution of the parallel electric field along the reconnecting field lines. We find the reconnection rate is controlled by only the low-amplitude, zeroth and first–order trends in the parallel electric field while the contribution from fluctuations of the parallel electric field, such as electron holes, is negligible. The results impact the determination of reconnection sites and reconnection rates in models and in situ spacecraft observations of 3D turbulent reconnection. It is difficult through direct observation to isolate the loci of the reconnection parallel electric field amidst the large amplitude fluctuations. However, we demonstrate that a positive slope of the running sum of the parallel electric field along the field line as a function of field line length indicates where reconnection is occurring along the field line.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Alfvénic oscillations of the electron distribution function: Linear theory and experimental measurements

Wave propagation can be an accurate method for determining material properties. High frequency whistler mode waves (0.7 < ω/|Ω{sub ce}| < 1) in an overdense plasma (ω{sub pe} > |Ω{sub ce}|) are damped primarily by Doppler-shifted electron cyclotron resonance. A kinetic description of whistler mode propagation parallel to the background magnetic field shows that damping is proportional to the parallel electron distribution function. This property enables an experimental determination of the parallel electron distribution function using a measurement of whistler mode wave absorption. The whistler mode wave absorption diagnostic uses this technique on UCLA’s Large Plasma Device (LaPD) to measure the distribution of high energy electrons (5 − 10v{sub te}) with 0.1% precision. The accuracy is limited by systematic effects that need to be considered carefully. Ongoing research uses this diagnostic to investigate the effect of inertial Alfvén waves on the electron distribution function. Results presented here verify experimentally the linear effects of inertial Alfvén waves on the reduced electron distribution function, a necessary step before nonlinear physics can be tested. Ongoing experiments with the whistler mode wave absorption diagnostic are making progress toward the first direct detection of electrons nonlinearly accelerated by inertial Alfvén waves, a process believed to play an important role in auroral generation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Structure of 30 Mg explored via in-beam γ-ray spectroscopy

In the island of inversion, ground states of neutron-rich sd-shell nuclei exhibit strong admixtures of intruder configurations from the fp shell. The nucleus 30 Mg, located at the boundary of the island of inversion, serves as a cornerstone to track the structural evolution as one approaches this region. Spin-parity assignments for excited states in 30 Mg, especially negative-parity levels, have yet to be established. In the present work, the nuclear structure of 30Mg was investigated by in-beam gamma-ray spectroscopy mainly focusing on firm spin-parity determinations. High-intensity rare-isotope beams of 31 Mg, 32 Mg, 34 Si, and 35 P bombarded a Be target to induce nucleon removal reactions populating states in 30 Mg. Gamma rays were detected by the state-of-the-art gamma-ray tracking array GRETINA. For the direct one-neutron removal reaction, final-state exclusive cross sections and parallel momentum distributions were deduced. Multi-nucleon removal reactions from different projectiles were exploited to gain complementary information. With the aid of the parallel momentum distributions, an updated level scheme with revised spin-parity assignments was constructed. Spectroscopic factors associated with each state were also deduced. Results were confronted with large-scale shell-model calculations using two different effective interactions, showing excellent agreement with the present level scheme. Furthermore, a marked difference in the spectroscopic factors indicates that the full delineation of the transition into the island of inversion remains a challenge for theoretical models.

20 ≤ A ≤ 38↗

Parallel PIPS-SBB: multi-level parallelism for stochastic mixed-integer programs

PIPS-SBB is a distributed-memory parallel solver with a scalable data distribution paradigm. It is designed to solve MIPs with a dual-block angular structure, which is characteristic of deterministic-equivalent Stochastic Mixed-Integer Programs (SMIPs). In this paper, we present two different parallelizations of Branch & Bound (B&B), implementing both as extensions of PIPS-SBB, thus adding an additional layer of parallelism. In the first of the proposed frameworks, PIPS-PSBB, the coordination and load-balancing of the different optimization workers is done in a decentralized fashion. This new framework is designed to ensure all available cores are processing the most promising parts of the B&B tree. The second, ug[PIPS-SBB,MPI], is a parallel implementation using the Ubiquity Generator (UG), a universal framework for parallelizing B&B tree search that has been sucessfully applied to other MIP solvers. We show the effects of leveraging multiple levels of parallelism in potentially improving scaling performance beyond thousands of cores.

97 MATHEMATICS AND COMPUTING↗

Towards Flexible Exascale Stream Processing System Simulation

Stream processing is an important emerging computational model for performing complex operations on and across multi-source, high-volume, unpredictable dataflows. We present Flow, a platform for parallel and distributed stream processing system simulation that provides a flexible modeling environment for analyzing stream processing applications. The Flow stream processing system simulator is a high-performance, scalable simulator that automatically parallelizes chunks of the model space and incurs near-zero synchronization overhead for acyclic stream application graphs. We show promising parallel and distributed event rates exceeding 149 million events per second on a cluster with 512 processor cores.

99 GENERAL AND MISCELLANEOUS↗

Two-Nucleon Knockout Spectroscopy at the Limits of Nuclear Stability

Sudden single-nucleon removal reactions from fast radioactive beams are now key to studies of the structure of rare isotopes. The sensitivity of the heavy residue's parallel momentum distribution to the orbital angular momentum of the removed nucleon is a crucial feature with a high spectroscopic value. Two-nucleon removal reactions provide experimental reach toward the rarest nuclear species. We show that the residue parallel momentum distributions in these reactions offer a clear spectroscopic signal of the angular momentum of the pair of nucleons removed, and thus of the residue final state spins and spectroscopy. Our formalism is applied successfully to new final-state-inclusive measurements of like-nucleon pair removal reactions to states in neutron-rich {sup 36}Mg and neutron-deficient {sup 20}Mg. We also confront a new final-state-exclusive decomposition of two-proton knockout data to states in neutron-rich {sup 26}Ne.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Improved hydrogeophysical characterization and monitoring through parallel modeling and inversion of time-domain resistivity andinduced-polarization data

Electrical geophysical methods have found wide use in the growing discipline of hydrogeophysics, both for characterizing the electrical properties of the subsurface, and for monitoring subsurface processes in terms of the spatiotemporal changes in subsurface conductivity, chargeability, and source currents they govern. Current multichannel and multielectrode data collections systems are able to collect large amounts of data in relatively short periods of time. However, practitioners are often unable to fully utilize these large data sets and the information they contain due to the processing limitations of standard desktop computers. This limitation can be addressed by utilizing the storage and processing capabilities of high-performance parallel computing environments. We present a parallel distributed-memory forward and inverse modeling algorithm for analyzing resistivity and time-domain induced polarization data. The primary components of the parallel computations include distributed computation of the pole solutions in forward mode, distributed storage and computation of the Jacobian matrix in inverse mode, and parallel execution of the inverse equation solver. We demonstrate the corresponding parallel code for three efforts: (1) resistivity characterization of the Hanford 300 Area Integrated Field Research Challenge site in Hanford, WA; (2) resistivity characterization of a volcanic island in the southern Tyrrhenian Sea in Italy; and (3) resistivity and IP monitoring of biostimulation at a superfund site in Brandywine, MD. Inverse analysis of each of these data sets would be limited (or impossible) in a standard serial computing environment which underscores the need for high-performance computing to fully utilize the potential of electrical geophysical methods in hydrogeophysical applications.

Hanford IFRC↗

Improved hydrogeophysical characterization and monitoring through parallel modeling and inversion of time-domain resistivity and induced-polarization data

Electrical geophysical methods have found wide use in the growing discipline of hydrogeophysics, both for characterizing the electrical properties of the subsurface, and for monitoring subsurface processes in terms of the spatiotemporal changes in subsurface conductivity, chargeability, and source currents they govern. Current multichannel and multielectrode data collections systems are able to collect large amounts of data in relatively short periods of time. However, practitioners are often unable to fully utilize these large data sets and the information they contain due to the processing limitations of standard desktop computers. This limitation can be addressed by utilizing the storage and processing capabilities of high-performance parallel computing environments. We present a parallel distributed-memory forward and inverse modeling algorithm for analyzing resistivity and time-domain induced polarization data. The primary components of the parallel computations include distributed computation of the pole solutions in forward mode, distributed storage and computation of the Jacobian matrix in inverse mode, and parallel execution of the inverse equation solver. We demonstrate the corresponding parallel code for three efforts: (1) resistivity characterization of the Hanford 300 Area Integrated Field Research Challenge site in Hanford, WA; (2) resistivity characterization of a volcanic island in the southern Tyrrhenian Sea in Italy; and (3) resistivity and IP monitoring of biostimulation at a superfund site in Brandywine, MD. Inverse analysis of each of these data sets would be limited (or impossible) in a standard serial computing environment which underscores the need for high-performance computing to fully utilize the potential of electrical geophysical methods in hydrogeophysical applications.

58 GEOSCIENCES↗

Distributed control system for parallel-connected DC boost converters

The disclosed invention is a distributed control system for operating a DC bus fed by disparate DC power sources that service a known or unknown load. The voltage sources vary in v-i characteristics and have time-varying, maximum supply capacities. Each source is connected to the bus via a boost converter, which may have different dynamic characteristics and power transfer capacities, but are controlled through PWM. The invention tracks the time-varying power sources and apportions their power contribution while maintaining the DC bus voltage within the specifications. A central digital controller solves the steady-state system for the optimal duty cycle settings that achieve a desired power supply apportionment scheme for a known or predictable DC load. A distributed networked control system is derived from the central system that utilizes communications among controllers to compute a shared estimate of the unknown time-varying load through shared bus current measurements and bus voltage measurements.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Highly scalable distributed-memory sparse triangular solution algorithms.

This paper presents a highly efficient distributed-memory parallel sparse triangular solver. The triangular solution phase is often performed following factorization phase in the sparse linear solvers and has become increasingly computa­tionally expensive for direct solvers with many right hand sides (RHSs) or preconditioned iterative solvers. However, the low arithmetic intensity and sequential nature of the triangular solve algorithm pose performance challenges for its large-scale distributed-memory parallelization. In this work, we propose several strategies to enhance scalability of an algorithm with 2D block cyclic process layout. First, an asynchronous binary-tree-based communication scheme implemented via non-blocking MPI functions is leveraged to broadcast partial solutions and reduce partial updates among a subset of processes for each block column and row of the triangular matrix, respectively. This scheme reduces message latency, improves communication load balance and significantly accelerates asynchronous execution of the triangular solve. In addition, efficient BLAS operations and threading implementations are exploited to accelerate local computations and further reduce process idle time. The proposed strategies are implemented in SuperLU_DIST and numerical experiments show up to 4.4x improvement with one right-hand side and up to 6.1x improvement with 50 right- hand sides on 4096 processes, compared to the current release. This is the first time that sparse triangular solution is demonstrated strong scaling on more than 4000 cores.

Liu, Yang↗

Reaction theories for exotic nuclei

This contribution discusses two important dynamical effects in the scattering of exotic beams. The first part deals proton breakup. The Coulomb interactions between the core and the target and the proton and the target are treated to all orders, including also the full multipole expansion of the Coulomb potential. The dynamics of proton Coulomb breakup is compared to that of an equivalent neutron of larger binding energy in order to elucidate the differences with the well understood neutron breakup mechanism. With respect to nuclear breakup it is found that a proton behaves exactly as a neutron of larger binding energy. The extra 'effective energy' is due to the combined core-target Coulomb barrier. In Coulomb breakup we distinguish the effect of the core-target Coulomb potential (called recoil effect), with respect to which the proton behaves again as a more bound neutron, from the direct proton-target Coulomb potential. The latter gives cross sections about an order of magnitude larger than the recoil term. The two effects give rise to complicated interferences in the parallel momentum distributions. They are instead easily separable in the proton angular distributions which are therefore suggested as a very useful observable for future experimental studies. The second part has to do with the dynamics of one-neutron and one-proton removal from unstable nuclei with large asymmetry {Delta}S S{sub n}-S{sub p} in the separation energies and incident energies below 80 MeV/nucleon. Strong non-sudden effects are observed in the case of deeply-bound-nucleon removal. The corresponding parallel momentum distributions exhibit an abrupt cutoff at high momentum that corresponds to an energy threshold occurring when the incident energy per particle is of comparable magnitude as the nucleon separation energy.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Fast and Scalable Implementations of Influence Maximization Algorithms

The Influence Maximization problem has been extensively studied in the past decade because of its practical applications in finding the key influencers in social networks. Due to the hardness of the underlying problem, existing algorithms have tried to trade off practical efficiency with approximation guarantees. However, even such approximate solutions take several hours of compute time on modest sized real world inputs. On the other hand, there is a lack of effective parallel and distributed algorithms to solve this problem. In this paper, we present efficient parallel algorithms for multithreaded and distributed systems to solve the influence maximization with approximation guarantee. Our algorithms extend state-of-the-art sequential approach based on computing reverse reachability sets. We present a detailed experimental evaluation, and analyze their performance and their sensitivity to input parameters, using real world inputs. Our experimental results demonstrate significant speedup on parallel architectures. We further show a speedup of up to 586X relative to the state-of-the-art sequential baseline using 1024 nodes of a supercomputer at far greater accuracy and twice the seed set size. To the best of our knowledge, this is the first effort in parallelizing the influence maximization operation at scale.

Minutoli, Marco↗