Search NASA⌕ Search

SEARCH · Search NASA

Results for “edge computer”

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 721 records · Page 40

Approximate Inverse Chain Preconditioner: Iteration Count Case Study for Spectral Support Solvers

As the growing availability of computational power slows, there has been an increasing reliance on algorithmic advances. However, faster algorithms alone will not necessarily bridge the gap in allowing computational scientists to study problems at the edge of scientific discovery in the next several decades. Often, it is necessary to simplify or precondition solvers to accelerate the study of large systems of linear equations commonly seen in a number of scientific fields. Preconditioning a problem to increase efficiency is often seen as the best approach; yet, preconditioners which are fast, smart, and efficient do not always exist. Following the progress of [1], we present a new preconditioner for symmetric diagonally dominant (SDD) systems of linear equations. These systems are common in certain PDEs, network science, and supervised learning among others. Based on spectral support graph theory, this new preconditioner builds off of the work of [2], computing and applying a V-cycle chain of approximate inverse matrices. This preconditioner approach is both algebraic in nature as well as hierarchically-constrained depending on the condition number of the system to be solved. Due to its generation of an Approximate Inverse Chain of matrices, we refer to this as the AIC preconditioner. We further accelerate the AIC preconditioner by utilizing precomputations to simplify setup and multiplications in the con-text of an iterative Krylov-subspace solver. While these iterative solvers can greatly reduce solution time, the number of iterations can grow large quickly in the absence of good preconditioners. Initial results for the AIC preconditioner have shown a very large reduction in iteration counts for SDD systems as compared to standard preconditioners such as Incomplete Cholesky (ICC) and Multigrid (MG). We further show significant reduction in iteration counts against the more advanced Combinatorial Multigrid (CMG) preconditioner. We have further developed no-fill sparsification techniques to ensure that the computational cost of applying the AIC preconditioner does not grow prohibitively large as the depth of the V-cycle grows for systems with larger condition numbers. Our numerical results have shown that these sparsifiers maintain the sparsity structure of our system while also displaying significant reductions in iteration counts.1 2

97 MATHEMATICS AND COMPUTING↗

Approximate Inverse Chain Preconditioner: Iteration Count Case Study for Spectral Support Solvers

As the growing availability of computational power slows, there has been an increasing reliance on algorithmic advances. However, faster algorithms alone will not necessarily bridge the gap in allowing computational scientists to study problems at the edge of scientific discovery in the next several decades. Often, it is necessary to simplify or precondition solvers to accelerate the study of large systems of linear equations commonly seen in a number of scientific fields. Preconditioning a problem to increase efficiency is often seen as the best approach; yet, preconditioners which are fast, smart, and efficient do not always exist. Following the progress of [1], we present a new preconditioner for symmetric diagonally dominant (SDD) systems of linear equations. These systems are common in certain PDEs, network science, and supervised learning among others. Based on spectral support graph theory, this new preconditioner builds off of the work of [2], computing and applying a V-cycle chain of approximate inverse matrices. This preconditioner approach is both algebraic in nature as well as hierarchically-constrained depending on the condition number of the system to be solved. Due to its generation of an Approximate Inverse Chain of matrices, we refer to this as the AIC preconditioner. We further accelerate the AIC preconditioner by utilizing precomputations to simplify setup and multiplications in the con-text of an iterative Krylov-subspace solver. While these iterative solvers can greatly reduce solution time, the number of iterations can grow large quickly in the absence of good preconditioners. Initial results for the AIC preconditioner have shown a very large reduction in iteration counts for SDD systems as compared to standard preconditioners such as Incomplete Cholesky (ICC) and Multigrid (MG). We further show significant reduction in iteration counts against the more advanced Combinatorial Multigrid (CMG) preconditioner. We have further developed no-fill sparsification techniques to ensure that the computational cost of applying the AIC preconditioner does not grow prohibitively large as the depth of the V-cycle grows for systems with larger condition numbers. Our numerical results have shown that these sparsifiers maintain the sparsity structure of our system while also displaying significant reductions in iteration counts.1 2

97 MATHEMATICS AND COMPUTING↗

PANDORA: A Parallel Dendrogram Construction Algorithm for Single Linkage Clustering on GPU

This paper introduces Pandora, a parallel algorithm for computing dendrograms, the hierarchical cluster trees for single linkage clustering (SLC). Current parallel approaches construct dendrograms by partitioning a minimum spanning tree and removing edges. However, they struggle with skewed, hard-to-parallelize real-world dendrograms. Consequently, computing dendrograms is the sequential bottleneck in HDBSCAN*[21], a popular SLC variant. Pandora uses recursive tree contraction to address this limitation. Pandora contracts nodes to construct progressively smaller trees. It computes the smallest contracted dendrogram and expands it by inserting contracted edges. This recursive strategy is highly parallel, skew-independent, work-optimal, and well-suited for GPUs and multicores. We develop a performance portable implementation of Pandora in Kokkos[31] and evaluate its performance on multicore CPUs and multi-vendor GPUs (e.g., Nvidia, AMD) for dendrogram construction in HDBSCAN*. Multithreaded Pandora is 2.2x faster than the current best-multithreaded implementation. Our GPU version achieves 6-20x speedup on AMD GPUs and 10-37x on NVIDIA GPUs over multithreaded Pandora. Pandora removes HDBSCAN*’s sequential bottleneck, greatly boosting efficiency, particularly with GPUs.

Sao, Piyush↗

Distributed, Intelligent Edge-Sensing for a Smarter Grid

The electric grid is undergoing major transformations and developments resulting in unprecedented levels of volatility, uncertainty, and stress on grid infrastructure. Smart sensors and methods aiding in advanced visibility and situational awareness are key for tackling these issues. In this work, a decentralized architecture is proposed, where sensing, local computation and control capability are embedded in the edge devices, communicating with a set of trusted 'data mules' in a 'delay-tolerant' manner, while functioning autonomously. This system has been designed and implemented as an overall platform – called Global Asset Monitoring, Management and Analytics (GAMMA) Platform intended to provide the backbone for a global array of sensors and actuators. Further, as a building block for advanced current sensing solutions, a smart, low-cost ‘clip-on’ current sensor based on PCB-embedded Rogowski coil has been developed. The sensor hosts a novel signal conditioning stage allowing an 'auto-tuning' feature, resulting in a universal current sensor design for measuring a wide range of currents, including faults for smart grid applications. Finally, the research proposes a method to instrument and monitor key parameters for the most common electric utility asset – the pole-top distribution transformer. The work done in this research enables scalable, edge-intelligent sensing solutions for monitoring grid infrastructure, allowing utility operators to gain advanced visibility in an economical way.

Kulkarni, Shreyas Bhalchandra↗

TU-FG-201-04: Computer Vision in Autonomous Quality Assurance of Linear Accelerators

Purpose: Routine quality assurance (QA) of linear accelerators represents a critical and costly element of a radiation oncology center. Recently, a system was developed to autonomously perform routine quality assurance on linear accelerators. The purpose of this work is to extend this system and contribute computer vision techniques for obtaining quantitative measurements for a monthly multi-leaf collimator (MLC) QA test specified by TG-142, namely leaf position accuracy, and demonstrate extensibility for additional routines. Methods: Grayscale images of a picket fence delivery on a radioluminescent phosphor coated phantom are captured using a CMOS camera. Collected images are processed to correct for camera distortions, rotation and alignment, reduce noise, and enhance contrast. The location of each MLC leaf is determined through logistic fitting and a priori modeling based on knowledge of the delivered beams. Using the data collected and the criteria from TG-142, a decision is made on whether or not the leaf position accuracy of the MLC passes or fails. Results: The locations of all MLC leaf edges are found for three different picket fence images in a picket fence routine to 0.1mm/1pixel precision. The program to correct for image alignment and determination of leaf positions requires a runtime of 21– 25 seconds for a single picket, and 44 – 46 seconds for a group of three pickets on a standard workstation CPU, 2.2 GHz Intel Core i7. Conclusion: MLC leaf edges were successfully found using techniques in computer vision. With the addition of computer vision techniques to the previously described autonomous QA system, the system is able to quickly perform complete QA routines with minimal human contribution.

60 APPLIED LIFE SCIENCES↗

Downstream Effects on Orbiter Leeside Flow Separation for Hypersonic Flows

Discrepancies between experiment and computation for shuttle leeside flow separation, which came to light in the Columbia accident investigation, are resolved. Tests were run in the Langley Research Center 20-Inch Hypersonic CF4 Tunnel with a baseline orbiter model and two extended trailing edge models. The extended trailing edges altered the wing leeside separation lines, moving the lines toward the fuselage, proving that wing trailing edge modeling does affect the orbiter leeside flow. Computations were then made with a wake grid. These calculations more closely matched baseline experiments. Thus, the present findings demonstrate that it is imperative to include the wake flow domain in CFD calculations in order to accurately predict leeside flow separation for hypersonic vehicles at high angles of attack.

Buck, Gregory M.↗

Effect of Dynamic Rolling Oscillations on Twin Tail Buffet Response

The effect of dynamic rolling oscillations of delta-wing/twin-tail configuration on twin-tail buffet response is investigated. The computational model consists of a sharp-edged delta wing of aspect ratio one and swept-back flexible twin tail with taper ratio of 0.23. The configuration model is statically pitched at 30 deg. angle of attack and then forced to oscillate in roll around the symmetry axis at a constant amplitude of 4 deg. and reduced frequency of pi and 2(pi). The freestream Mach number and Reynolds number are 0.3 and 1.25 million, respectively. This multidisciplinary problem is solved using three sets of equations on a dynamic multi-block grid structure. The first set is the unsteady, full Navier-Stokes equations, the second set is the aeroelastic equations for coupled bending and torsion vibrations of the tails, and the third set is the grid-displacement equations. The configuration is investigated for inboard position of the twin tails which corresponds to a separation distance between the twin tails of 33% wing span. The computed results are compared with the results of stationary configuration, which previously have been validated using experimental data. The results conclusively showed that the rolling oscillations of the configuration have led to higher loads, higher deflections, and higher excitation peaks than those of the stationary configuration. Moreover, increasing the reduced frequency has led to higher loads and excitation peaks and lower bending and torsion deflections and acceleration.

Sheta, Essam F.↗

Efficient, Predictive Tomography of Multi-Qubit Quantum Processors

After decades of R&D, quantum computers comprising more than 2 qubits are appearing. If this progress is to continue, the research community requires a capability for precise characterization (“tomography”) of these enlarged devices, which will enable benchmarking, improvement, and finally certification as mission-ready. As world leaders in characterization -- our gate set tomography (GST) method is the current state of the art – the project team is keenly aware that every existing protocol is either (1) catastrophically inefficient for more than 2 qubits, or (2) not rich enough to predict device behavior. GST scales poorly, while the popular randomized benchmarking technique only measures a single aggregated error probability. This project explored a new insight: that the combinatorial explosion plaguing standard GST could be avoided by using an ansatz of few-qubit interactions to build a complete, efficient model for multi-qubit errors. We developed this approach, prototyped it, and tested it on a cutting-edge quantum processor developed by Rigetti Quantum Computing (RQC), a US-based startup. We implemented our new models within Sandia’s PyGSTi open-source code, and tested them experimentally on the RQC device by probing crosstalk. We found two major results: first, our schema worked and is viable for further development; second, while the Rigetti device is indeed a “real” 8-qubit quantum processor, its behavior fluctuated significantly over time while we were experimenting with it and this drift made it difficult to fit our models of crosstalk to the data.

97 MATHEMATICS AND COMPUTING↗

Globus service enhancements for exascale applications and facilities

Many extreme-scale applications require the movement of large quantities of data to, from, and among leadership computing facilities, as well as other scientific facilities and the home institutions of facility users. These applications, particularly when leadership computing facilities are involved, can touch upon edge cases (e.g., terabyte files) that had not been a focus of previous Globus optimization work, which had emphasized rather the movement of many smaller (megabyte to gigabyte) files. We report here on how automated client-driven chunking can be used to accelerate both the movement of large files and the integrity checking operations that have proven to be essential for large data transfers. In conclusion, we present detailed performance studies that provide insights into the benefits of these modifications in a range of file transfer scenarios.

97 MATHEMATICS AND COMPUTING↗

Vortical Flow Prediction Using an Adaptive Unstructured Grid Method

A computational fluid dynamics (CFD) method has been employed to compute vortical flows around slender wing/body configurations. The emphasis of the paper is on the effectiveness of an adaptive grid procedure in "capturing" concentrated vortices generated at sharp edges or flow separation lines of lifting surfaces flying at high angles of attack. The method is based on a tetrahedral unstructured grid technology developed at the NASA Langley Research Center. Two steady-state, subsonic, inviscid and Navier-Stokes flow test cases are presented to demonstrate the applicability of the method for solving practical vortical flow problems. The first test case concerns vortex flow over a simple 65 delta wing with different values of leading-edge radius. Although the geometry is quite simple, it poses a challenging problem for computing vortices originating from blunt leading edges. The second case is that of a more complex fighter configuration. The superiority of the adapted solutions in capturing the vortex flow structure over the conventional unadapted results is demonstrated by comparisons with the wind-tunnel experimental data. The study shows that numerical prediction of vortical flows is highly sensitive to the local grid resolution and that the implementation of grid adaptation is essential when applying CFD methods to such complicated flow problems.

Pirzadeh, Shahyar Z.↗

Vortical Flow Prediction using an Adaptive Unstructured Grid Method

A computational fluid dynamics (CFD) method has been employed to compute vortical flows around slender wing/body configurations. The emphasis of the paper is on the effectiveness of an adaptive grid procedure in "capturing" concentrated vortices generated at sharp edges or flow separation lines of lifting surfaces flying at high angles of attack. The method is based on a tetrahedral unstructured grid technology developed at the NASA Langley Research Center. Two steady-state, subsonic, inviscid and Navier-Stokes flow test cases are presented to demonstrate the applicability of the method for solving vortical flow problems. The first test case concerns vortex flow over a simple 65 delta wing with different values of leading-edge radius. Although the geometry is quite simple, it poses a challenging problem for computing vortices originating from blunt leading edges. The second case is that of a more complex fighter configuration. The superiority of the adapted solutions in capturing the vortex flow structure over the conventional unadapted results is demonstrated by comparisons with the wind-tunnel experimental data. The study shows that numerical prediction of vortical flows is highly sensitive to the local grid resolution and that the implementation of grid adaptation is essential when applying CFD methods to such complicated flow problems.

Pirzadeh, Shahyar Z.↗

Edge localized linear ideal magnetohydrodynamic instability studies in an extended-magnetohydrodynamic code

A linear benchmark between the linear ideal MHD stability codes ELITE [H. R. Wilson et al., Phys. Plasmas 9, 1277 (2002)], GATO [L. Bernard et al., Comput. Phys. Commun. 24, 377 (1981)], and the extended nonlinear magnetohydrodynamic (MHD) code, NIMROD [C. R. Sovinec et al.., J. Comput. Phys. 195, 355 (2004)] is undertaken for edge-localized (MHD) instabilities. Two ballooning-unstable, shifted-circle tokamak equilibria are compared where the stability characteristics are varied by changing the equilibrium plasma profiles. The equilibria model an H-mode plasma with a pedestal pressure profile and parallel edge currents. For both equilibria, NIMROD accurately reproduces the transition to instability (the marginally unstable mode), as well as the ideal growth spectrum for a large range of toroidal modes (n=1-20). The results use the compressible MHD model and depend on a precise representation of 'ideal-like' and 'vacuumlike' or 'halo' regions within the code. The halo region is modeled by the introduction of a Lundquist-value profile that transitions from a large to a small value at a flux surface location outside of the pedestal region. To model an ideal-like MHD response in the core and a vacuumlike response outside the transition, separate criteria on the plasma and halo Lundquist values are required. For the benchmarked equilibria the critical Lundquist values are 10{sup 8} and 10{sup 3} for the ideal-like and halo regions, respectively. Notably, this gives a ratio on the order of 10{sup 5}, which is much larger than experimentally measured values using T{sub e} values associated with the top of the pedestal and separatrix. Excellent agreement with ELITE and GATO calculations are made when sharp boundary transitions in the resistivity are used and a small amount of physical dissipation is added for conditions very near and below marginal ideal stability.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Stress Concentration Around an Open Circular Hole in a Plate Subjected to Bending Normal to the Plane of the Plate

An aluminum-alloy plate containing an open circular hole of diameter large compared with the thickness of the plate was subjected to bending forces normal to the plane of the plate. Deflection and strain measurements were taken for two different loads. Stress concentrations occurred at the edge of the hole and the maximum stresses were tangential to the hole at the ends of the transverse diameter. The maximum stress at the edge of the hole was 1.59 times the computed stress on the net section and 1.85 times the computed stress in a solid plate of the same dimensions subjected to the same bending forces. The maximum deflections were about 20 percent greater than the corresponding deflection for a solid plate of the same size subjected to the same bending forces. The smallest edge distance was equal to 2-1/2 times the diameter of the hole and the stress concentration on this side of the hole was the same as on the side where the edge distance was about 4-1/2 diameters. A theoretical analysis of the problem shows that, for an aluminum plate of infinite width, the stress concentration at the edge of the hole would be 1.87 times the stress in a solid plate, which is substantially the same relation obtained for the plate tested.

Dumont, C↗

Framework Application for Core Edge Transport Simulation (FACETS)

The FACETS (Framework Application for Core-Edge Transport Simulations) project of Scientific Discovery through Advanced Computing (SciDAC) Program was aimed at providing a high-fidelity whole-tokamak modeling for the U.S. magnetic fusion energy program and ITER through coupling separate components for each of the core region, edge region, and wall, with realistic plasma particles and power sources and turbulent transport simulation. The project also aimed at developing advanced numerical algorithms, efficient implicit coupling methods, and software tools utilizing the leadership class computing facilities under Advanced Scientific Computing Research (ASCR). The FACETS project was conducted by a multi-discipline, multi-institutional teams, the Lead PI was J.R. Cary (Tech-X Corp.). In the FACETS project, the Applied Plasma Theory Group at the MAE Department of UCSD developed the Wall and Plasma-Surface Interaction (WALLPSI) module, performed its validation against experimental data, and integrated it into the developed framework. WALLPSI is a one-dimensional, coarse grained, reaction/advection/diffusion code applied to each material boundary cell in the common modeling domain for a tokamak. It incorporates an advanced model for plasma particle transport and retention in the solid matter of plasma facing components, simulation of plasma heat power load handling, calculation of erosion/deposition, and simulation of synergistic effects in strong plasma-wall coupling.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Summer Proceedings 2018: The Center for Computing Research at Sandia National Laboratories

The Center for Computing Research (CCR) at Sandia National Laboratories organizes an active and productive summer program each year, in coordination with the Computer Science Research Institute (CSRI) and Cyber Engineering Research Institute (CERI). CERI focuses on open, exploratory research in cyber security in partnership with academia, industry, and government, and provides collaborators an accessible portal to Sandia's cybersecurity experts and facilities. Moreover, CERI provides an environment for visionary, threat-informed research on national cyber challenges. CSRI brings university faculty and students to Sandia National Laboratories for focused collaborative research on DOE computer and computational science problems. CSRI provides a mechanism by which university researchers learn about problems in computer and computational science at DOE Laboratories. Participants conduct leading - edge research, interact with scientists and engineers at the laboratories, and help transfer the results of their research to programs at the labs.

97 MATHEMATICS AND COMPUTING↗

HDBind: encoding of molecular structure with hyperdimensional binary representations

Traditional methods for identifying “hit” molecules from a large collection of potential drug-like candidates rely on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have a significant limitation in that they require exceptional computing capabilities for even relatively small collections of molecules. Increasingly large and complex state-of-the-art deep learning approaches have gained popularity with the promise to improve the productivity of drug design, notorious for its numerous failures. However, as deep learning models increase in their size and complexity, their acceleration at the hardware level becomes more challenging. Hyperdimensional Computing (HDC) has recently gained attention in the computer hardware community due to its algorithmic simplicity relative to deep learning approaches. The HDC learning paradigm, which represents data with high-dimension binary vectors, allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas (computer vision, bioinformatics, mass spectrometery, remote sensing, edge devices, etc.). To the best of our knowledge, our work is the first to consider HDC for the task of fast and efficient screening of modern drug-like compound libraries. We also propose the first HDC graph-based encoding methods for molecular data, demonstrating consistent and substantial improvement over previous work. We compare our approaches to alternative approaches on the well-studied MoleculeNet dataset and the recently proposed LIT-PCBA dataset derived from high quality PubChem assays. We demonstrate our methods on multiple target hardware platforms, including Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs), showing at least an order of magnitude improvement in energy efficiency versus even our smallest neural network baseline model with a single hidden layer. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools. We make our code publicly available at https://github.com/LLNL/hdbind.

59 BASIC BIOLOGICAL SCIENCES↗

Climatic clustering and longitudinal analysis with impacts on food, bioenergy, and pandemics

Predicted growth in world population will put unparalleled stress on the need for sustainable energy and global food production, as well as increase the likelihood of future pandemics. In this work, we identify high-resolution environmental zones in the context of a changing climate and predict longitudinal processes relevant to these challenges. We do this using exhaustive vector comparison methods that measure the climatic similarity between all locations on earth at high geospatial resolution relative to global-scale analyses. The results are captured as networks, in which edges between geolocations are defined if their historical climate similarities exceed a threshold. We apply Markov clustering and our novel Correlation of Correlations method to the resulting climatic networks, which provides unprecedented agglomerative and longitudinal views of climatic relationships across the globe. The methods performed here resulted in the fastest (9.37x10 18 operations/sec) and one of the largest (168.7x10 21 operations) scientific computations ever performed, with more than 100 quadrillion edges considered for a single climatic network. Our climatic analysis reveals areas of the world experiencing rapid environmental changes, which can have important implications for global carbon fluxes and zoonotic spillover events. Correlation and network analyses of this kind are widely applicable across computational and predictive biology domains, including systems biology, ecology, carbon cycles, biogeochemistry, and zoonosis research.

59 BASIC BIOLOGICAL SCIENCES↗

A first-principle calculation of the XANES spectrum of Cu{sup 2+} in water

The progress in high performance computing we are witnessing today offers the possibility of accurate electron density calculations of systems in realistic physico-chemical conditions. In this paper, we present a strategy aimed at performing a first-principle computation of the low energy part of the X-ray Absorption Spectroscopy (XAS) spectrum based on the density functional theory calculation of the electronic potential. To test its effectiveness, we apply the method to the computation of the X-ray absorption near edge structure part of the XAS spectrum in the paradigmatic, but simple case of Cu{sup 2+} in water. In order to keep into account the effect of the metal site structure fluctuations in determining the experimental signal, the theoretical spectrum is evaluated as the average over the computed spectra of a statistically significant number of simulated metal site configurations. The comparison of experimental data with theoretical calculations suggests that Cu{sup 2+} lives preferentially in a square-pyramidal geometry. The remarkable success of this approach in the interpretation of XAS data makes us optimistic about the possibility of extending the computational strategy we have outlined to the more interesting case of molecules of biological relevance bound to transition metal ions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗