Search NASA⌕ Search

SEARCH · Search NASA

Results for “Vectorized algorithm”

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 541 records · Page 30

Epigraph hemagglutinin vaccine induces broad cross-reactive immunity against swine H3 influenza virus

Influenza A virus infection in swine impacts the agricultural industry in addition to its zoonotic potential. Here, we utilize epigraph, a computational algorithm, to design a universal swine H3 influenza vaccine. The epigraph hemagglutinin proteins are delivered using an Adenovirus type 5 vector and are compared to a wild type hemagglutinin and the commercial inactivated vaccine, FluSure. In mice, epigraph vaccination leads to significant cross-reactive antibody and T-cell responses against a diverse panel of swH3 isolates. Epigraph vaccination also reduces weight loss and lung viral titers in mice after challenge with three divergent swH3 viruses. Vaccination studies in swine, the target species for this vaccine, show stronger levels of cross-reactive antibodies and T-cell responses after immunization with the epigraph vaccine compared to the wild type and FluSure vaccines. In both murine and swine models, epigraph vaccination shows superior cross-reactive immunity that should be further investigated as a universal swH3 vaccine.

59 BASIC BIOLOGICAL SCIENCES↗

Evaluating and Optimizing OpenCL Base64 Data Unpacking Kernel with FPGA

Development of applications using OpenCL targeting FPGAs is an emerging approach on heterogeneous computing systems. This paper uses the data unpacking algorithm in Base64 encoding as a case study to present programming and optimization techniques, and experimental results of the OpenCL-based implementations on an FPGA. We explain the algorithm and evaluate the performance of the kernel implementations with Intel's FPGA OpenCL SDK. The experimental results show kernel vectorization and duplication are two optimization techniques that can improve the kernel performance. The performance of kernel duplication is also closely related to the local work size. Our experiment shows 16-lane vectorization increases the bandwidth by a factor of 2 to 10 for large input data sizes. Moreover, the performance of kernel duplication using 16 compute units is 40% to 1.5% less than that of kernel vectorization depending on the input size. Tuning the local work size can improve the kernel performance by a factor of 3 to 23. For this kernel, using local memory is not an effective technique to improve the kernel performance because input data is not reused. A combination of vectorization and duplication achieves the highest performance of 12.3 GiB/s. Compared to an Intel Xeon E5 CPU and an Nvidia Tesla K80 GPU, the performance of the kernel on the Arria 10 FPGA is 6.7X faster than the CPU and 3X slower than the GPU. The performance per watt on the FPGA is 20.5X higher than the CPU and 1.19X lower than the GPU.

Base64 Encoding↗

Superconducting Hyperdimensional Associative Memory Circuit for Scalable Machine Learning

Here we propose a generalized architecture for the first rapid-single-flux-quantum (RSFQ) associative memory circuit. The circuit employs hyperdimensional computing (HDC), a machine learning (ML) paradigm utilizing vectors with dimensionality in the thousands to represent information. HDC designs have small memory footprints, simple computations, and simple training algorithms compared to superconducting neural network accelerators (SNNAs), making them a better option for scalable SFQ machine learning (ML) solutions. The proposed superconducting HDC (SHDC) circuit uses entirely on-chip RSFQ memory which is tightly integrated with logic, operates at 33.3 GHz, is applicable to general ML tasks, and is manufacturable at practically useful scales given current SFQ fabrication limits. Tailored to a language recognition task, SHDC consists of ~ 2-20 M Josephson junctions (JJs) and consumes up to three times less power than an analogous CMOS HDC circuit while achieving 78-84% higher throughput. SHDC is capable of outperforming the state of the art RSFQ SNNA, SuperNPU, by 48-99% for all benchmark NN architectures tested while occupying up to 90% less area and consuming up to nine times less power. To the best of the authors' knowledge, SHDC is currently the only superconducting ML approach feasible at practically useful scales for real-world ML tasks and capable of online learning.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

SU-F-R-46: Predicting Distant Failure in Lung SBRT Using Multi-Objective Radiomics Model

Purpose: To predict distant failure in lung stereotactic body radiation therapy (SBRT) in early stage non-small cell lung cancer (NSCLC) by using a new multi-objective radiomics model. Methods: Currently, most available radiomics models use the overall accuracy as the objective function. However, due to data imbalance, a single object may not reflect the performance of a predictive model. Therefore, we developed a multi-objective radiomics model which considers both sensitivity and specificity as the objective functions simultaneously. The new model is used to predict distant failure in lung SBRT using 52 patients treated at our institute. Quantitative imaging features of PET and CT as well as clinical parameters are utilized to build the predictive model. Image features include intensity features (9), textural features (12) and geometric features (8). Clinical parameters for each patient include demographic parameters (4), tumor characteristics (8), treatment faction schemes (4) and pretreatment medicines (6). The modelling procedure consists of two steps: extracting features from segmented tumors in PET and CT; and selecting features and training model parameters based on multi-objective. Support Vector Machine (SVM) is used as the predictive model, while a nondominated sorting-based multi-objective evolutionary computation algorithm II (NSGA-II) is used for solving the multi-objective optimization. Results: The accuracy for PET, clinical, CT, PET+clinical, PET+CT, CT+clinical, PET+CT+clinical are 71.15%, 84.62%, 84.62%, 85.54%, 82.69%, 84.62%, 86.54%, respectively. The sensitivities for the above seven combinations are 41.76%, 58.33%, 50.00%, 50.00%, 41.67%, 41.67%, 58.33%, while the specificities are 80.00%, 92.50%, 90.00%, 97.50%, 92.50%, 97.50%, 97.50%. Conclusion: A new multi-objective radiomics model for predicting distant failure in NSCLC treated with SBRT was developed. The experimental results show that the best performance can be obtained by combining all features.

60 APPLIED LIFE SCIENCES↗

WE-AB-202-09: Feasibility and Quantitative Analysis of 4DCT-Based High Precision Lung Elastography

Purpose: The purpose of this project is to derive high precision elastography measurements from 4DCT lung scans to facilitate the implementation of elastography in a radiotherapy context. Methods: 4DCT scans of the lungs were acquired, and breathing stages were subsequently registered to each other using an optical flow DIR algorithm. The displacement of each voxel gleaned from the registration was taken to be the ground-truth deformation. These vectors, along with the 4DCT source datasets, were used to generate a GPU-based biomechanical simulation that acted as a forward model to solve the inverse elasticity problem. The lung surface displacements were applied as boundary constraints for the model-guided lung tissue elastography, while the inner voxels were allowed to deform according to the linear elastic forces within the model. A biomechanically-based anisotropic convergence magnification technique was applied to the inner voxels in order to amplify the subtleties of the interior deformation. Solving the inverse elasticity problem was accomplished by modifying the tissue elasticity and iteratively deforming the biomechanical model. Convergence occurred when each voxel was within 0.5 mm of the ground-truth deformation and 1 kPa of the ground-truth elasticity distribution. To analyze the feasibility of the model-guided approach, we present the results for regions of low ventilation, specifically, the apex. Results: The maximum apical boundary expansion was observed to be between 2 and 6 mm. Simulating this expansion within an apical lung model, it was observed that 100% of voxels converged within 0.5 mm of ground-truth deformation, while 91.8% converged within 1 kPa of the ground-truth elasticity distribution. A mean elasticity error of 0.6 kPa illustrates the high precision of our technique. Conclusion: By utilizing 4DCT lung data coupled with a biomechanical model, high precision lung elastography can be accurately performed, even in low ventilation regions of the lungs. This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No. DGE-1144087.

60 APPLIED LIFE SCIENCES↗

Domi

Domi (Greek for "structure") is a Trilinos package that provides support for multi-dimensional data arrays distributed over multiple processors of a high performance computing system. The software supports data arrays of arbitrary number of dimensions mapped to a multi-dimensional grid of processors. Domi provides local access to the data, as well as the ability to compute global quantities such as norms, maxima and minima. Data arrays can be constructed with boundary and communication padding, necessary for finite difference algorithms, and provides high-level methods for communicating data between processors to update these buffers. The distributed maps and vectors in Domi can be converted to the equivalent data structures in Epetra and Tpetra (both of which assume unstructured data), using view semantics when appropriate, for use with other Trilinos solvers.

Spotz, WilliamF.↗

Orbital Motion of the Wide Planetary-mass Companion GSC 6214-210 b: No Evidence for Dynamical Scattering

Direct-imaging exoplanet surveys have discovered a class of 5–20 M{sub Jup} substellar companions at separations >100 au from their host stars, which present a challenge to planet and star formation models. Detailed analysis of the orbital architecture of these systems can provide constraints on possible formation mechanisms, including the possibility that they were dynamically ejected onto a wide orbit. We present astrometry for the wide planetary-mass companion GSC 6214-210 b (240 au; ≈14 M{sub Jup}) obtained using NIRC2 with adaptive optics at the Keck telescope over 10 years. Our measurements achieved astrometric uncertainties of ≈1 mas per epoch. We determined a relative motion of 1.12 ± 0.15 mas yr{sup −1} (0.61 ± 0.09 km s{sup −1}), the first detection of orbital motion for this companion. We compute the minimum periastron for the companion due to our measured velocity vector and derive constraints on the orbital parameters through our modified implementation of the Orbits for the Impatient rejection sampling algorithm. We find that close periastron orbits, which could indicate that the companion was dynamically scattered, are present in our posterior but have low likelihoods. For all orbits in our posterior, we assess the detectability of close-in companions that could have scattered GSC 6214-210 b from a closer orbit, and find that most potential scatterers would have been detected in previous imaging. We conclude that formation at small orbital separation and subsequent dynamical scattering through interaction with another potential close-in object is an unlikely formation pathway for this companion. We also update stellar and substellar properties for the system using the new parallax from Gaia DR2.

79 ASTRONOMY AND ASTROPHYSICS↗

Domi

Domi (Greek for "structure") is a Trilinos package that provides support for multi-dimensional data arrays distributed over multiple processors of a high performance computing system. The software supports data arrays of arbitrary number of dimensions mapped to a multi-dimensional grid of processors. Domi provides local access to the data, as well as the ability to compute global quantities such as norms, maxima and minima. Data arrays can be constructed with boundary and communication padding, necessary for finite difference algorithms, and provides high-level methods for communicating data between processors to update these buffers. The distributed maps and vectors in Domi can be converted to the equivalent data structures in Epetra and Tpetra (both of which assume unstructured data), using view semantics when appropriate, for use with other Trilinos solvers.

Spotz, William F.↗

A Themodynamically Consistent Fractional Visco-Elasto-Plastic Model with Memory-Dependent Damage for Anomalous Materials

We develop a thermodynamically consistent, fractional visco-elastoplastic model coupled with damage for anomalous materials. The model utilizes Scott-Blair rheological elements for both visco- elastic/plastic parts. The constitutive equations are obtained through Helmholtz free-energy potentials for Scott-Blair elements, together with a memory-dependent fractional yield function and dissipation inequalities. A memory-dependent Lemaitre-type damage is introduced through fractional damage energy release rates. For time-fractional integration of the resulting nonlinear system of equations, we develop a first-order semi-implicit fractional return-mapping algorithm. We also develop a finite-difference discretization for the fractional damage energy release rate, which results into Hankel-type matrix-vector operations for each time-step, allowing us to reduce the computational complexity from O(N 3 ) to O(N 2 ) through the use of Fast Fourier Transforms. Our numerical results demonstrate that the fractional orders for visco-elasto-plasticity play a crucial role in damage evolution, due to the competition between the anomalous plastic slip and bulk damage energy release rates.

36 MATERIALS SCIENCE↗

Studying Z/γ*+Jet Production in proton-antiproton collisions at √s = 1.96 TeV

The production of jets in association with a Z/γ* boson is an example of an important class of processes at hadron colliders, namely vector boson + jet (V + jet) production. Comparisons of measurements of this class of processes with theory predictions constitute an important, fundamental test of the Standard Model of particle physics, and of the theory of QCD in particular. While having a smaller cross section than other V +jet processes, Z/γ*(→ e + e - ) + jets production, with Z/γ* {yields} e + e - /μ + μ - , has a distinct experimental signature allowing for measurements characterized by low backgrounds and a direct, precise measurement of the properties of the decay products of the Z/γ* boson. In this thesis, several new measurements of the properties of jets produced in association with a Z/γ* boson in p$\bar{p}$ collisions at √s = 1.96 TeV are presented. The cross section for Z/γ*(→ e + e - ) + N jet production (N ≤ 3) is measured, differential in the transverse momentum of the Nth jet in the event, normalized to the inclusive Z/γ* cross section. Also, the cross section for Z/γ*(→e + e - ) + N jets (N ≥ 1) is measured, differential in the difference in azimuthal angle between the di-electron system and any jet in the event, normalized to unity. The data used in the measurements were collected by the D0 experiment located at the Tevatron Collider of the Fermi National Accelerator Laboratory and correspond to an integrated luminosity of 1.04 fb -1 . The measured jet transverse momentum spectra are compared with the predictions of perturbative calculations at the next-to-leading order in the strong coupling constant. Given the low sensitivity of the calculations to model parameters, these comparisons represent a stringent test of perturbative QCD. One of the main goals currently being pursued in particle physics is the discovery of the only particle predicted by the Standard Model which has so far no been detected experimentally, namely the Higgs boson. It is assumed that the ATLAS and CMS experiments located at the Large Hadron Collider (LHC), a proton-proton collider at √s = 14 TeV, will be able to detect the Higgs boson, or rule out its existence, within the next few years. The collisions delivered by the LHC will also be used to perform a long range of searches for other new particles, for instance particles predicted by models based on the principle of supersymmetry. The associated production of vector bosons with jets has relatively large production rates at the LHC and can produce a long list of different final states which can include charged leptons, missing transverse energy, as well as light- and heavy-flavour jets. This makes V + jet production a major source of background events to many searches for new particles. Most techniques used for estimating the expected number of background events to searches rely on passing the stable final-state particles of simulated hadron collisions generated using a so-called event generator code, through a simulation of the experimental detector system. The development of event generators which are capable of reliably predicting the properties of jets produced in association with a core process, e.g. the production of a vector boson, has been the subject of a large amount of research activity during the last ten years. These efforts have led to the appearance of the CKKW and MLM algorithms which are implemented in several event generators, among them SHERPA and ALPGEN + PYTHIA. The large data sample collected by the D0 experiment during Run II offers an excellent opportunity for validating these new event generators against experimental measurements of V + jet production. As argued above, the Z/γ*(→ e + e - ) + jets process offers the combination of a clean experimental signature and large production rates, making it the process of choice for these studies.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Computing rank‐revealing factorizations of matrices stored out‐of‐core

This paper describes efficient algorithms for computing rank-revealing factorizations of matrices that are too large to fit in main memory (RAM), and must instead be stored on slow external memory devices such as disks (out-of-core or out-of-memory). Traditional algorithms for computing rank-revealing factorizations (such as the column pivoted QR factorization and the singular value decomposition) are very communication intensive as they require many vector-vector and matrix-vector operations, which become prohibitively expensive when data is not in RAM. Randomization allows to reformulate new methods so that large contiguous blocks of the matrix are processed in bulk. The paper describes two distinct methods. The first is a blocked version of column pivoted Householder QR, organized as a “left-looking” method to minimize the number of the expensive write operations. The second method results employs a UTV factorization. It is organized as an algorithm-by-blocks to overlap computations and I/O operations. As it incorporates power iterations, it is much better at revealing the numerical rank. Numerical experiments on several computers demonstrate that the new algorithms are almost as fast when processing data stored on slow memory devices as traditional algorithms are for data stored in RAM.

97 MATHEMATICS AND COMPUTING↗

Streamline Integration Using MPI-Hybrid Parallelism on a Large Multicore Architecture

Streamline computation in a very large vector field data set represents a significant challenge due to the nonlocal and data-dependent nature of streamline integration. In this paper, we conduct a study of the performance characteristics of hybrid parallel programming and execution as applied to streamline integration on a large, multicore platform. With multicore processors now prevalent in clusters and supercomputers, there is a need to understand the impact of these hybrid systems in order to make the best implementation choice. We use two MPI-based distribution approaches based on established parallelization paradigms, parallelize over seeds and parallelize over blocks, and present a novel MPI-hybrid algorithm for each approach to compute streamlines. Our findings indicate that the work sharing between cores in the proposed MPI-hybrid parallel implementation results in much improved performance and consumes less communication and I/O bandwidth than a traditional, nonhybrid distributed implementation.

97 MATHEMATICS AND COMPUTING↗

Highly Excited and Exotic Meson Spectrum from Dynamical Lattice QCD

Using a new quark-field construction algorithm and a large variational basis of operators, we extract a highly excited isovector meson spectrum on dynamical anisotropic lattices. We show how carefully constructed operators can be used to reliably identify the continuum spin of extracted states, overcoming the reduced cubic symmetry of the lattice. Using this method we extract, with confidence, excited states, states with exotic quantum numbers (0{sup +-}, 1{sup -+}, and 2{sup +-}), and states of high spin, including, for the first time in lattice QCD, spin-four states.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Deep learning has surged in popularity and proven to be effective for various artificial intelligence applications including information extraction from cancer pathology reports. Since word representation is a core unit that enables deep learning algorithms to understand words and be able to perform NLP, this representation must include as much information as possible to help these algorithms achieve high classification performance. Therefore, in this work in addition to the distributional information of words in large sized corpora, we use UMLS vocabulary resources to enrich the vector space representation of words with the semantic relations between words. These resources provide many terminologies pertaining to cancer. The refined word embeddings are used with a convolutional neural (CNN) model to extract four data elements from cancer pathology reports; ICD-O-3 tumor topography codes, tumor laterality, behavior, and histological grade. We observed that using UMLS vocabulary resources to enrich word embeddings of CNN models consistently outperformed CNN models without pre-training word embeddings and even with pre-trained word embeddings on a domain specific corpus across all four tasks. The results show marginal improvement on the laterality task, but a significant improvement on the other tasks, especially for the macro-f score. Specifically, the improvements are 3%, 13%, and 15% for tumor site, histological grade, and behavior tasks, respectively. This approach is encouraging to enrich word embeddings with more clinical data resources to be used for information abstraction tasks from clinical pathology reports.

Alawad, Mohammed↗

Explicit time integration of the stiff chemical Langevin equations using computational singular perturbation

A stable explicit time-scale splitting algorithm for stiff chemical Langevin equations (CLEs) is developed, based on the concept of computational singular perturbation. The drift term of the CLE is projected onto basis vectors that span the fast and slow subdomains. The corresponding fast modes exhaust quickly, in the mean sense, and the system state then evolves, with a mean drift controlled by slow modes, on a random manifold. The drift-driven time evolution of the state due to fast exhausted modes is modeled algebraically as an exponential decay process, while that due to slow drift modes and diffusional processes is integrated explicitly. This enables time integration step sizes much larger than those required by typical explicit numerical methods for stiff stochastic differential equations. The algorithm is motivated and reported on, and extensive numerical experiments are conducted to illustrate its accuracy and stability with a number of model systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

SPECTRAL METHODS FOR TIME-DEPENDENT STUDIES OF ACCRETION FLOWS. III. THREE-DIMENSIONAL, SELF-GRAVITATING, MAGNETOHYDRODYNAMIC DISKS

Accretion disks are three-dimensional, turbulent, often self-gravitating, magnetohydrodynamic (MHD) flows, which can be modeled with numerical simulations. In this paper, we present a new algorithm that is based on a spectral decomposition method to simulate such flows. Because of the high order of the method, we can solve the induction equation in terms of the magnetic vector potential and, therefore, ensure trivially that the magnetic fields in the numerical solution are divergence free. The spectral method also suffers minimally from numerical dissipation and allows for an easy implementation of models for subgrid physics. Both properties make our method ideal for studying MHD turbulent flows such as those found in accretion disks around compact objects. We verify our algorithm with a series of standard tests and use it to show the development of MHD turbulence in a simulation of an accretion disk. Finally, we study the evolution and saturation of the power spectrum of MHD turbulence driven by the magnetorotational instability.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Situational awareness-enhancing community-level load mapping with opportunistic machine learning

Motivated by present and forthcoming challenges in the adoption and integration of distributed renewable energy, we develop a machine learning (ML) approach that builds short-fuse mappings connecting the occasionally-unobservable true load in one target community with information-rich signals collected from relatively more instrumented reference communities. Our setting is inspired by and tailored to target communities with significant unobservable behind-the-meter solar generation, where true load (a relatively well-behaved quantity of interest to grid operators) is hard to discern during daytime due to insufficient instrumentation and/or privacy reasons, but that can be related to reference communities with low unobservable distributed variable generation or with sufficient instrumentation. The developed mapping, herein realized with Support Vector Machine regression, is built using nighttime data from all communities, when their distributed generation is low or zero. Our ML algorithm opportunistically learns to correlate signals of interest and then is operationally used the next day to shed light into target community load evolution. The mapping is subsequently rebuilt, rolling its short-fuse scope perpetually forward in time. Here, we demonstrate the efficacy of our approach on nine synthetically generated topologies and associated timeseries stemming from real-world data, on which we observe cumulative error performance that yields lower than 10% and 15% daily-averaged mean absolute percentage errors in target community load estimation on more than about 75% and 90% of days, respectively, in multiple yearly evaluations that shed light on long-term performance also under seasonal and one-off effects. The proposed ML-powered methodology can offer grid operators much-improved visibility into a previously obscure space and can also serve as an additional source of information in broader, multi-modal solar disaggregation solutions.

14 SOLAR ENERGY↗