Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parallel, scaling”

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 901 records · Page 50

New Insight into Short-Wavelength Solar Wind Fluctuations from Vlasov Theory

The nature of solar wind (SW) turbulence below the proton gyroscale is a topic that is being investigated extensively nowadays, both theoretically and observationally. Although recent observations gave evidence of the dominance of kinetic Alfven waves (KAWs) at sub-ion scales with omega < omega(sub ci), other studies suggest that the KAW mode cannot carry the turbulence cascade down to electron scales and that the whistler mode (i.e., omega > omega (sub ci)) is more relevant. Here, we study key properties of the short-wavelength plasma modes under limited, but realistic, SW conditions, Typically Beta(sub i) approx. > Beta (sub e) ∼ 1 and for high oblique angles of propagation 80 deg <= Theta (sub kB) < 90 deg as observed from the Cluster spacecraft data. The linear properties of the plasma modes under these conditions are poorly known, which contrasts with the well-documented cold plasma limit and/or moderate oblique angles of propagation (Theta (sub kB) < 80 deg). Based on linear solutions of the Vlasov kinetic theory, we discuss the relevance of each plasma mode (fast, Bernstein, KAW, whistler) in carrying the energy cascade down to electron scales. We show, in particular, that the shear Alfven mode (known in the magnetohydrodynamic limit) extends at scales kappa rho (sub i) approx. > 1 to frequencies either larger or smaller than omega (sub ci), depending on the anisotropy kappa (parallel )/ kappa(perpendicular). This extension into small scales is more readily called whistler (omega > omega (sub ci)) or KAW (omega < omega (sub ci)) although the mode is essentially the same. This contrasts with the well-accepted idea that the whistler branch always develops as a continuation at high frequencies of the fast magnetosonic mode. We show, furthermore, that the whistler branch is more damped than the KAW one, which makes the latter the more relevant candidate to carry the energy cascade down to electron scales. We discuss how these new findings may facilitate resolution of the controversy concerning the nature of the small-scale turbulence, and we discuss the implications for present and future spacecraft wave measurements in the SW.

waves↗

MetaStrider: Architectures for Scalable Memory-centric Reduction of Sparse Data Streams

Reduction is an operation performed on the values of two or more key-value pairs that share the same key. Reduction of sparse data streams finds application in a wide variety of domains such as data and graph analytics, cybersecurity, machine learning, and HPC applications. However, these applications exhibit low locality of reference, rendering traditional architectures and data representations inefficient. This article presents MetaStrider, a significant algorithmic and architectural enhancement to the state-of-the-art, SuperStrider. Furthermore, these enhancements enable a variety of parallel, memory-centric architectures that we propose, resulting in demonstrated performance that scales near-linearly with available memory-level parallelism.

97 MATHEMATICS AND COMPUTING↗

Extreme-scale EV charging infrastructure planning for last-mile delivery using high-performance parallel computing

Here, this paper addresses stochastic charger location and allocation problems under queue congestion for last-mile delivery using electric vehicles (EVs). The objective is to decide where to open charging stations and how many chargers of each type to install, subject to budgetary and waiting-time constraints. We formulate the problem as a mixed-integer non-linear program, where each station-charger pair is modeled as a multiserver queue with stochastic arrivals and service times to capture the notion of waiting in fleet operations. The model is extremely large, with billions of variables and constraints for a typical metropolitan area; even loading the model in solver memory is difficult, let alone solving it. To address this challenge, we develop a Lagrangian-based dual decomposition framework that decomposes the problem by station and leverages parallelization on high-performance computing systems, where the subproblems are solved by using a cutting plane method and their solutions are collected at the master level. We also develop a three-step rounding heuristic to transform the fractional subproblem solutions into feasible integral solutions. Computational experiments on data from the Chicago metropolitan area with hundreds of thousands of households and thousands of candidate stations show that our approach produces high-quality solutions in cases where existing exact methods cannot even load the model in memory. We also analyze various policy scenarios, demonstrating that combining existing depots with newly built stations under multiagency collaboration substantially reduces costs and congestion. These findings offer a scalable and efficient framework for developing sustainable large-scale EV charging networks.

Capacity allocation↗

Large-scale structure after COBE: Peculiar velocities and correlations of cold dark matter halos

Large N-body simulations on parallel supercomputers allow one to simultaneously investigate large-scale structure and the formation of galactic halos with unprecedented resolution. Our study shows that the masses as well as the spatial distribution of halos on scales of tens of megaparsecs in a cold dark matter (CDM) universe with the spectrum normalized to the anisotropies detected by Cosmic Background Explorer (COBE) is compatible with the observations. We also show that the average value of the relative pairwise velocity dispersion sigma(sub v) - used as a principal argument against COBE-normalized CDM models-is significantly lower for halos than for individual particles. When the observational methods of extracting sigma(sub v) are applied to the redshift catalogs obtained from the numerical experiments, estimates differ significantly between different observation-sized samples and overlap observational estimates obtained following the same procedure.

Zurek, Wojciech H.↗

Parallel adaptive mesh refinement within the PUMAA3D Project

To enable the solution of large-scale applications on distributed memory architectures, we are designing and implementing parallel algorithms for the fundamental tasks of unstructured mesh computation. In this paper, we discuss efficient algorithms developed for two of these tasks: parallel adaptive mesh refinement and mesh partitioning. The algorithms are discussed in the context of two-dimensional finite element solution on triangular meshes, but are suitable for use with a variety of element types and with h- or p-refinement. Results demonstrating the scalability and efficiency of the refinement algorithm and the quality of the mesh partitioning are presented for several test problems on the Intel DELTA.

Freitag, Lori↗

Three-Dimensional High-Lift Analysis Using a Parallel Unstructured Multigrid Solver

A directional implicit unstructured agglomeration multigrid solver is ported to shared and distributed memory massively parallel machines using the explicit domain-decomposition and message-passing approach. Because the algorithm operates on local implicit lines in the unstructured mesh, special care is required in partitioning the problem for parallel computing. A weighted partitioning strategy is described which avoids breaking the implicit lines across processor boundaries, while incurring minimal additional communication overhead. Good scalability is demonstrated on a 128 processor SGI Origin 2000 machine and on a 512 processor CRAY T3E machine for reasonably fine grids. The feasibility of performing large-scale unstructured grid calculations with the parallel multigrid algorithm is demonstrated by computing the flow over a partial-span flap wing high-lift geometry on a highly resolved grid of 13.5 million points in approximately 4 hours of wall clock time on the CRAY T3E.

Mavriplis, Dimitri J.↗

Implementation of Parallel Adaptive-Krylov Exponential Solvers for Stiff Problems

Recently exponential integrators have been receiving increased attention as a means of solving large stiff systems of ODEs. Preliminary performance analysis demonstrated that exponential integrators hold promise compared to state-of-the-art implicit methods. However, much work remains to be done to understand in detail possible computational advantages these methods may offer in practice. This is particularly true for supercomputer-scale problems as there has been very little work on parallelizing exponential methods. In this paper we describe an implementation of a suite of parallel exponential solvers. Additionally, we present some performance tests on four stiff benchmark problems of a particular adaptive-Krylov exponential propagation iterative Runge--Kutta (EPIRK) method from the suite, and compare efficiency with the Newton--Krylov implicit solver CVODE.

97 MATHEMATICS AND COMPUTING↗

Parallel Anisotropic Unstructured Grid Adaptation

Computational Fluid Dynamics (CFD) has become critical to the design and analysis of aerospace vehicles. Parallel grid adaptation that resolves multiple scales with anisotropy is identified as one of the challenges in the CFD Vision 2030 Study to increase the capacity and capability of CFD simulation. The Study also cautions that computer architectures are undergoing a radical change and dramatic increases in algorithm concurrency will be required to exploit full performance. This paper reviews four different methods to parallel anisotropic grid generation. They cover both ends of the spectrum: (i) using existing state-of-the-art software optimized for a single core and modifying it for parallel platforms and (ii) designing and implementing scalable software with incomplete, but rapidly maturating functionality. A brief overview for each grid adaptation system is presented in the context of a telescopic approach for multilevel concurrency. These methods employ different approaches to enable parallel execution, which provides a unique opportunity to illustrate the relative behavior of each approach. Qualitative and quantitative metric evaluations are used to draw lessons for future developments in this critical area for parallel CFD simulation.

Tsolakis, Christos↗

DeepClone: Lightweight State Replication of Deep Learning Models for Data Parallel Training

Training modern deep neural network (DNN) models involves complex workflows triggered by model exploration, sensitivity analysis, explainability, etc. A key primitive in this context is the ability to clone a model training instance, i.e. “fork” the training process in a potentially different direction, which enables comparisons of different evolution paths using variations of training data and model parameters. However, in a quest improve the training throughput, a mix of data parallel, model parallel, pipeline parallel and layer-wise parallel approaches are making the problem of cloning highly complex. In this paper, we explore the problem of efficient cloning under such circumstances. To this end, we leverage several properties of data-parallel training and layer-wise parallelism to design DeepClone, a cloning approach based on augmenting the execution graph to gain direct access to tensors, which are then sharded and reconstructed asynchronously in order to minimize runtime overhead, standby duration, readiness duration. Compared with state-of-art approaches, DeepClone shows orders of magnitude improvement for several classes of DNN models.

data-parallel training↗

F3D Image Processing and Analysis for Many - and Multi-core Platforms

F3D is written in OpenCL, so it achieve[sic] platform-portable parallelism on modern mutli-core CPUs and many-core GPUs. The interface and mechanims to access F3D core are written in Java as a plugin for Fiji/ImageJ to deliver several key image-processing algorithms necessary to remove artifacts from micro-tomography data. The algorithms consist of data parallel aware filters that can efficiently utilizes[sic] resources and can work on out of core datasets and scale efficiently across multiple accelerators. Optimizing for data parallel filters, streaming out of core datasets, and efficient resource and memory and data managements over complex execution sequence of filters greatly expedites any scientific workflow with image processing requirements. F3D performs several different types of 3D image processing operations, such as non-linear filtering using bilateral filtering and/or median filtering and/or morphological operators (MM). F3D gray-level MM operators are one-pass constant time methods that can perform morphological transformations with a line-structuring element oriented in discrete directions. Additionally, MM operators can be applied to gray-scale images, and consist of two parts: (a) a reference shape or structuring element, which is translated over the image, and (b) a mechanism, or operation, that defines the comparisons to be performed between the image and the structuring element. This tool provides a critical component within many complex pipelines such as those for performing automated segmentation of image stacks. F3D is also called a "descendent" of Quant-CT, another software we developed in the past. These two modules are to be integrated in a next version. Further details were reported in: D.M. Ushizima, T. Perciano, H. Krishnan, B. Loring, H. Bale, D. Parkinson, and J. Sethian. Structure recognition from high-resolution images of ceramic composites. IEEE International Conference on Big Data, October 2014.

Source record↗

F3D Image Processing and Analysis for Many - and Multi-core Platforms

F3D is written in OpenCL, so it achieve[sic] platform-portable parallelism on modern mutli-core CPUs and many-core GPUs. The interface and mechanims to access F3D core are written in Java as a plugin for Fiji/ImageJ to deliver several key image-processing algorithms necessary to remove artifacts from micro-tomography data. The algorithms consist of data parallel aware filters that can efficiently utilizes[sic] resources and can work on out of core datasets and scale efficiently across multiple accelerators. Optimizing for data parallel filters, streaming out of core datasets, and efficient resource and memory and data managements over complex execution sequence of filters greatly expedites any scientific workflow with image processing requirements. F3D performs several different types of 3D image processing operations, such as non-linear filtering using bilateral filtering and/or median filtering and/or morphological operators (MM). F3D gray-level MM operators are one-pass constant time methods that can perform morphological transformations with a line-structuring element oriented in discrete directions. Additionally, MM operators can be applied to gray-scale images, and consist of two parts: (a) a reference shape or structuring element, which is translated over the image, and (b) a mechanism, or operation, that defines the comparisons to be performed between the image and the structuring element. This tool provides a critical component within many complex pipelines such as those for performing automated segmentation of image stacks. F3D is also called a "descendent" of Quant-CT, another software we developed in the past. These two modules are to be integrated in a next version. Further details were reported in: D.M. Ushizima, T. Perciano, H. Krishnan, B. Loring, H. Bale, D. Parkinson, and J. Sethian. Structure recognition from high-resolution images of ceramic composites. IEEE International Conference on Big Data, October 2014.

Source record↗

On the inward drift of runaway electrons during the plateau phase of runaway current

The well observed inward drift of current carrying runaway electrons during runaway plateau phase after disruption is studied by considering the phase space dynamic of runaways in a large aspect ratio toroidal system. We consider the case where the toroidal field is unperturbed and the toroidal symmetry of the system is preserved. The balance between the change in canonical angular momentum and the input of mechanical angular momentum in such a system requires runaways to drift horizontally in configuration space for any given change in momentum space. The dynamic of this drift can be obtained by integrating the modified Euler-Lagrange equation over one bounce time. It is then found that runaway electrons will always drift inward as long as they are decelerating. This drift motion is essentially non-linear, since the current is carried by runaways themselves, and any runaway drift relative to the magnetic axis will cause further displacement of the axis itself. A simplified analytical model is constructed to describe such inward drift both in the ideal wall case and no wall case, and the runaway current center displacement as a function of parallel momentum variation is obtained. The time scale of such displacement is estimated by considering effective radiation drag, which shows reasonable agreement with the observed displacement time scale. Furthermore, this indicates that the phase space dynamic studied here plays a major role in the horizontal displacement of runaway electrons during plateau phase. (C) 2016 AIP Publishing LLC.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Collaborative Research: Continuous Dynamic Grid Adaptation in a Global Atmospheric Model - Application and Refinement

This project had goals of advancing the performance capabilities of the numerical general circulation model EULAG and using it to produce a fully operational atmospheric global climate model (AGCM) that can employ either static or dynamic grid stretching for targeted phenomena. The resulting AGCM combined EULAG's advanced dynamics core with the "physics" of the NCAR Community Atmospheric Model (CAM). Effort discussed below shows how we improved model performance and tested both EULAG and the coupled CAM-EULAG in several ways to demonstrate the grid stretching and ability to simulate very well a wide range of scales, that is, multi-scale capability. We leveraged our effort through interaction with an international EULAG community that has collectively developed new features and applications of EULAG, which we exploited for our own work summarized here. Overall, the work contributed to over 40 peer-reviewed publications and over 70 conference/workshop/seminar presentations, many of them invited. 3a. EULAG Advances EULAG is a non-hydrostatic, parallel computational model for all-scale geophysical flows. EULAG's name derives from its two computational options: EULerian (flux form) or semi-LAGrangian (advective form). The model combines nonoscillatory forward-in-time (NFT) numerical algorithms with a robust elliptic Krylov solver. A signature feature of EULAG is that it is formulated in generalized time-dependent curvilinear coordinates. In particular, this enables grid adaptivity. In total, these features give EULAG novel advantages over many existing dynamical cores. For EULAG itself, numerical advances included refining boundary conditions and filters for optimizing model performance in polar regions. We also added flexibility to the model's underlying formulation, allowing it to work with the pseudo-compressible equation set of Durran in addition to EULAG's standard anelastic formulation. Work in collaboration with others also extended the demonstrated range of validity of soundproof models, showing that they are more broadly applicable than some had previously thought. Substantial testing of EULAG included application and extension of the Jablonowski-Williamson baroclinic wave test - an archetype of planetary weather - and further analysis of multi-scale interactions arising from collapse of temperature fronts in both the baroclinic wave test and simulations of the Held-Suarez idealized climate. These analyses revealed properties of atmospheric gravity waves not seen in previous work and further demonstrated the ability of EULAG to simulate realistic behavior over several orders of magnitude of length scales. Additional collaborative work enhanced capability for modeling atmospheric flows with adaptive moving meshes and demonstrated the ability of EULAG to move into petascale computing. 3b. CAM-EULAG Advances We have developed CAM-EULAG in collaboration with former project postdoc, now University of Cape Town Assistant Professor, Babatunde Abiodun. Initial study documented good model performance in aqua-planet simulations. In particular, we showed that the grid adaptivity (stretching) implemented in CAM-EULAG allows higher resolution in selected regions without causing anomalous behavior such as spurious wave reflection. We then used the stretched-grid version to analyze simulated extreme precipitation events in West Africa, comparing the precipitation and event environment with observed behavior. The model simulates fairly well the spatial scale and the interannual and intraseasonal variability of the extreme events, although its extreme precipitation intensity is weaker than observed. In addition, both observations and the simulations show possible forcing of extreme events by African easterly waves. 3c. Other Contributions Through our collaborations, we have made contributions to a wide range of outcomes. For research focused on terrestrial behavior, these have included (1) upwind schemes for gas dynamics, (2) a nonlinear perspective on the dynamics of the Madden-Julian Oscillation, (3) numerical realism of thermal convection, (4) extreme precipitation processes, (5) unstructured meshes, (6) porous-media analogies for simulating flow in urban environments, (7) Monge-Ampere enhancements of semi-Lagrangian methods and (8) further extensions of the generality of EULAG applications to geophysical problems. The generality of EULAG for multi-scale flow was also demonstrated through solar applications. Simulations of solar magnetohydrodynamics showed that EULAG produces the solar cycle fairly well. Although the model's solar cycle is significantly longer than observed, it shows remarkable agreement with observations in features of spatial evolution. These efforts in environments that are extreme from a geophysical perspective have helped to establish the robustness of EULAG as an all-scale code for geophysical applications.

54 ENVIRONMENTAL SCIENCES↗

Adaptive Control and Scaling Approach for the Emulation of Dynamic Sub-scale Torque Loads

Previous research by the authors proposed a control and scaling approach for emulating dynamic sub-scale torque loads. This approach produced an emulation controller that successfully regulated the dynamic behavior of a sub-scale electro-mechanical system intended to be a dynamical representation of the sub-scale turboelectric powertrain of a single-aisle commercial aircraft. The sub-scale system provides an environment without turbomachinery or rotors for the initial testing of electrified aircraft propulsion (EAP) control algorithms as they would be applied to a full-scale EAP system. The sub-scale turbomachinery/rotor torque loads were produced by electric machines (EMs) driven by the control and scaling approach, a full-scale turboelectric powertrain model, and an advanced EAP control algorithm. Although successfully tested, this approach produces an emulation controller that does not guarantee asymptotic stability. Modifying the original control law and integrating adaptive control techniques into the emulation controller allows the designer to guarantee asymptotic stability. This paper introduces the idea behind the emulation controller modifications, derives the controller, proves asymptotic stability, describes the implementation of the controller on a sub-scale electro-mechanical system intended to represent a parallel hybrid-electric turbofan engine, and describes the testing of a full-scale advanced EAP control algorithm. The turbofan engine and emulation controller performance are compared to results obtained using the previous, non-adaptive control and scaling approach.

adaptive↗

Adaptive Control and Scaling Approach for the Emulation of Dynamic Subscale Torque Loads

Previous research by the authors proposed a control and scaling approach for emulating dynamic sub-scale torque loads. This approach produced an emulation controller that successfully regulated the dynamic behavior of a sub-scale electro-mechanical system intended to be a dynamical representation of the sub-scale turboelectric powertrain of a single-aisle commercial aircraft. The sub-scale system provides an environment without turbomachinery or rotors for the initial testing of electrified aircraft propulsion (EAP) control algorithms as they would be applied to a full-scale EAP system. The sub-scale turbomachinery/rotor torque loads were produced by electric machines (EMs) driven by the control and scaling approach, a full-scale turboelectric powertrain model, and an advanced EAP control algorithm. Although successfully tested, this approach produces an emulation controller that does not guarantee asymptotic stability. Modifying the original control law and integrating adaptive control techniques into the emulation controller allows the designer to guarantee asymptotic stability. This paper introduces the idea behind the emulation controller modifications, derives the controller, proves asymptotic stability, describes the implementation of the controller on a sub-scale electro-mechanical system intended to represent a parallel hybrid-electric turbofan engine, and describes the testing of a full-scale advanced EAP control algorithm. The turbofan engine and emulation controller performance are compared to results obtained using the previous, non-adaptive control and scaling approach.

adaptive↗

Supporting HEP Data as the Exascale Era Approaches

We describe our work on the use of HPC data formats and storage technologies to efficiently describe, store and access High Energy Physics (HEP) data. In the HEP community, important data sets are large, currently at the scale of tens of PiB, and are expected to grow dramatically in the next decade. These data require different data representations—ranging from complex C++ objects to tabular data—that are used at the many varied stages of data analysis. Traditionally, these data have been stored in large collections of files at each stage. This approach does not scale well on HPC resources. To obtain good scalability, without requiring that analysts have parallel programming expertise, our work stresses the use of HPCoptimized tools and implicit data-parallelism. We describe data organization and the performance and scaling of data processing using examples from three HEP experiments (LArIAT, NOvA and DUNE), and for three different stages of analysis. We compare the performance of our HPC-oriented solutions to the traditional HEP approaches.

Buchanan, Norman↗

3D nanolithography with metalens arrays and spatially adaptive illumination

The growing demand for advanced materials, miniaturized devices and integrated microsystems calls for the reliable fabrication of complex, multiscale, three-dimensional (3D) architectures, a need increasingly addressed through light-based and laser-based processes. However, owing to the field-of-view (FOV) limitations of conventional imaging optics, existing 3D laser nanofabrication techniques face fundamental challenges in throughput, proximity error and stitching defects on the path to scaling. Here, in this study, we present a scalable 3D nanofabrication platform that uses a metalens-generated focal spot array to parallelize two-photon lithography (TPL) beyond centimetre-scale write field areas. Metalenses are ideally suited for producing submicron-scale focal spots for high-throughput nanolithography, as they uniquely feature large numerical apertures (NAs), immersion media compatibility and large-scale manufacturability. We experimentally demonstrate a printing system that uses a 12-cm 2 metalens array to produce more than 120,000 cooperative focal spots, corresponding to a throughput exceeding 10 8 voxels s −1 . By programmatically patterning the focal spot array using a spatial light modulator (SLM), an adaptive parallel printing strategy is developed for precise greyscale linewidth modulation and choreographed printing of semiperiodic and fully aperiodic 3D geometries. We demonstrate parallel printing of replicated microstructures (>50 M microparticles per day), centimetre-scale 3D architectures with feature sizes down to 113 nm, and photonic and mechanical metamaterials. This work demonstrates the potential of 3D nanolithography towards wafer-scale production, showing how TPL could be used at scale for applications in microelectronics, biomedicine, quantum technology and high-energy laser targets.

Materials science↗