Search NASA⌕ Search

SEARCH · Search NASA

Results for “data parallel”

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 1,549 records · Page 86
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Full spectrum optical constant interface to the Materials Project

Optical constants characterize the interaction of materials with light and are important properties in material design. Here we present a Python-based Corvus workflow for simulations of full spectrum optical constants from the visible and ultraviolet to hard x-ray wavelengths based on the real-space Green’s function code FEFF10 and structural data from the Materials Project (MP). The Corvus workflow manager and its associated tools provide an interface to FEFF10 and the MP database. The workflow parallelizes the FEFF computations of optical constants over all absorption edges for each material in the MP database specified by a unique MP-ID. The workflow tools determine the distribution of computational resources needed for that case. Similarly, the optical constants for selected sets of materials can be computed in a single-shot. Additionally, to illustrate the approach, we present results for several elemental solids in the periodic table, as well as a sample compound, and compare our predictions with experimental results. In addition, we provide a database of calculated results for all elements for which there is a stable elemental solid at standard conditions available in the Materials Project database. As in x-ray absorption spectra, these results are interpreted in terms of an atomic-like background and fine-structure contributions.

36 MATERIALS SCIENCE↗
DOE OSTI2021

A k-mer based approach for classifying viruses without taxonomy identifies viral associations in human autism and plant microbiomes

Viruses are an underrepresented taxa in the study and identification of microbiome constituents; however, they play an essential role in health, microbiome regulation, and transfer of genetic material. Only a few thousand viruses have been isolated, sequenced, and assigned a taxonomy, which limits the ability to identify and quantify viruses in the microbiome. Additionally, the vast diversity of viruses represents a challenge for classification, not only in constructing a viral taxonomy, but also in identifying similarities between a virus’ genotype and its phenotype. However, the diversity of viral sequences can be leveraged to classify their sequences in metagenomic and metatranscriptomic samples, even if they do not have a taxonomy. To identify and quantify viruses in transcriptomic and genomic samples, we developed a dynamic programming algorithm for creating a classification tree out of 715,672 metagenome viruses. To create the classification tree, we clustered proportional similarity scores generated from the k-mer profiles of each of the metagenome viruses to create a database of metagenomic viruses. The resulting Kraken2 database of the metagenomic viruses can be found here: https://www.osti.gov/biblio/1615774 and is compatible with Kraken2. We then integrated the viral classification database with databases created with genomes from NCBI for use with ParaKraken (a parallelized version of Kraken provided in Supplemental Zip 1), a metagenomic/transcriptomic classifier. To illustrate the breadth of our utility for classifying metagenome viruses, we analyzed data from a plant metagenome study identifying genotypic and compartment specific differences between two Populus genotypes in three different compartments. We also identified a significant increase in abundance of eight viral sequences in post mortem brains in a human metatranscriptome study comparing Autism Spectrum Disorder patients and controls. We also show the potential accuracy for classifying viruses by utilizing both the JGI and NCBI viral databases to identify the uniqueness of viral sequences. Finally, we validate the accuracy of viral classification with NCBI databases containing viruses with taxonomy to identify pathogenic viruses in known COVID-19 and cassava brown streak virus infection samples. Our method represents the compulsory first step in better understanding the role of viruses in the microbiome by allowing for a more complete identification of sequences without taxonomy. Better classification of viruses will improve identifying associations between viruses and their hosts as well as viruses and other microbiome members. Despite the lack of taxonomy, this database of metagenomic viruses can be used with any tool that utilizes a taxonomy, such as Kraken, for accurate classification of viruses.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Scalable Implicit Solvers with Dynamic Mesh Adaptation for a Relativistic Drift-Kinetic Fokker–Planck–Boltzmann Model

In this work we consider a relativistic drift-kinetic model for runaway electrons along with a Fokker–Planck operator for small-angle Coulomb collisions, a radiation damping operator, and a secondary knock-on (Boltzmann) collision source. Here, we develop a new scalable fully implicit solver utilizing finite volume and conservative finite difference schemes and dynamic mesh adaptivity. A new data management framework in the PETSc library based on the p4est library is developed to enable simulations with dynamic adaptive mesh refinement (AMR), distributed memory parallelization, and dynamic load balancing of computational work. This framework and the runaway electron solver building on the framework are able to dynamically capture both bulk Maxwellian at the low-energy region and a runaway tail at the high-energy region. To effectively capture features via the AMR algorithm, a new AMR indicator prediction strategy is proposed that is performed alongside the implicit time evolution of the solution. This strategy is complemented by the introduction of computationally cheap feature-based AMR indicators that are analyzed theoretically. Numerical results quantify the advantages of the prediction strategy in better capturing features compared with nonpredictive strategies; and we demonstrate trade-offs regarding computational costs. The robustness with respect to model parameters, algorithmic scalability, and parallel scalability are demonstrated through several benchmark problems including manufactured solutions and solutions of different physics models. We focus on demonstrating the advantages of using implicit time stepping and AMR for runaway electron simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Evolution of the Horizontal Winds in Jupiter's Great Red Spot From One Jovian Year of HST/WFC3 Maps

We measured the horizontal winds in Jupiter's Great Red Spot (GRS) using data from the WFC3/UVIS instrument on board the Hubble Space Telescope (HST). The data cover 11 epochs from 2009 to 2020. Long-term monotonic trends in size and shape previously noted from the visible cloud appearance are paralleled by changes in the high-speed ring around the vortex. The circularization of the GRS cannot be explained by changes in the horizontal wind shear of the surrounding environment. The velocity fields suggest no long-term trend in the static stability inside or outside the vortex. Instead, the changes are accompanied by a 4%–8% increase in the mean wind speeds of the high-speed ring from 2009 to 2020. Changes in the wind field coincided with the South Equatorial Belt Outbreak storms of 2016–2017, but not with 2019 "flaking" events involving detachment of red material from the main oval.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Learning local equivariant representations for large-scale atomistic dynamics

Abstract A simultaneously accurate and computationally efficient parametrization of the potential energy surface of molecules and materials is a long-standing goal in the natural sciences. While atom-centered message passing neural networks (MPNNs) have shown remarkable accuracy, their information propagation has limited the accessible length-scales. Local methods, conversely, scale to large simulations but have suffered from inferior accuracy. This work introduces Allegro, a strictly local equivariant deep neural network interatomic potential architecture that simultaneously exhibits excellent accuracy and scalability. Allegro represents a many-body potential using iterated tensor products of learned equivariant representations without atom-centered message passing. Allegro obtains improvements over state-of-the-art methods on QM9 and revMD17. A single tensor product layer outperforms existing deep MPNNs and transformers on QM9. Furthermore, Allegro displays remarkable generalization to out-of-distribution data. Molecular simulations using Allegro recover structural and kinetic properties of an amorphous electrolyte in excellent agreement with ab-initio simulations. Finally, we demonstrate parallelization with a simulation of 100 million atoms.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2017

A numerical analysis of a magnetocaloric refrigerator with a 16-layer regenerator

A numerical analysis was conducted to study a room temperature magnetocaloric refrigerator with a 16-layer parallel plates active magnetic regenerator (AMR). Sixteen layers of LaFeMnSiH having different Curie temperatures were employed as magnetocaloric material (MCM) in the regenerator. Measured properties data was used. A transient one dimensional (1D) model was employed, in which a unique numerical method was developed to significantly accelerate the simulation speed of the multi-layer AMR system. As a result, the computation speed of a multi-layer AMR case was very close to the single-layer configuration. The performance of the 16-layer AMR system in different frequencies and utilizations has been investigated using this model. To optimize the layer length distribution of the 16-layer MCMs in the regenerator, a set of 137 simulations with different MCM distributions based on the Design of Experiments (DoE) method was conducted and the results were analyzed. The results show that the 16-layer AMR system can operate up to 84% of Carnot cycle COP at a temperature span of 41 K, which cannot be obtained using an AMR with fewer layers. Here, the DoE results indicate that for a 16-layer AMR system, the uniform distribution is very close to the optimized design.

36 MATERIALS SCIENCE↗
DOE OSTI2014

Damping of lower hybrid waves in large spectral gap configurations

Extensive experimental data support reliable power deposition and current drive by lower-hybrid (LH) waves in conditions where a large spectral gap exists between the nominal parallel index of refraction prescribed by the antenna characteristics and phasing, and that required for significant Landau damping to take place. We argue that only a significant modification of the initial spectrum at the plasma edge could explain experimental observations. Based on this assumption, a new prescription for reliable simulations of LH current drive using ray-tracing and Fokker-Planck modelling is proposed. A remarkable agreement between experimental observations in the Tore Supra tokamak and simulations is obtained for relevant parametric scans, including electron density and LH waveguide phasing. In an effort to investigate the possible role of fluctuations, it is shown that the spectral gap can be bridged dynamically in the presence of a fluctuating LH spectrum.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Including the parallel mass flow in calculating the steady-state solutions and stability of the momentum balance equations for a quasisymmetric stellarator

The Helically Symmetric Experiment (HSX) is a quasisymmetric stellarator with minimal parallel viscous damping in a helical direction. The parallel flow (Vǁ) along the magnetic field is similarly weakly damped by viscosity. In this paper, the self-consistent steady-state parallel and poloidal momentum balance equations are used to show that a large Vǁ on the order of the ion thermal velocity can increase the ion resonant radial electric field (Er) beyond the value calculated using the typical approximation that Vǁ is zero. By altering the damping of Vǁ, either by degrading the quasisymmetry or varying the neutral density, the ion resonant Er can shift in a controllable fashion. It is shown explicitly that there exist stable and unstable steady-state solutions in the two-dimensional space of Vǁ and Er. A stability analysis of each solution is performed by calculating the eigenvalues and eigenvectors of the Jacobian. The unstable solution corresponds to a saddle point in which the eigenvalues have opposite signs. The analysis leads to the conclusion that unstable solutions occur when the derivative of the total poloidal damping with respect to Er is positive. A hysteresis in Er and Vǁ is observed when the radial current density is linearly increased to a maximum and then decreased back to zero. Jumps in the radial electric field and the parallel flow are observed as the radial current density drives the evolution from one stable point to the next. This result is similar to experimental data observed on several devices.

Physics↗
DOE OSTI2016

Scintillation Light Detection System in LArIAT

The LArIAT experiment is currently taking data at Fermilab using a Liquid Argon TPC, with the aim of studying particle interactions and characterizing detector response for neutrino detectors using argon. In parallel, it serves as a test-bench to develop and evaluate the performance of the simulation, reconstruction, and analysis software used in LAr neutrino experiments. LArIAT also takes advantage of the scintillating capabilities of liquid argon and will evaluate the feasibility of using the light signal to determine calorimetric information and particle identification. To test this possibility, a scintillation light detection system consisting of high Quantum Efficiency (QE) PMT and Silicon Photomultiplier (SiPM) devices is installed in the cryostat, viewing the interior of the TPC. Light collection efficiency is maximized by means of lining the walls with reflector foils covered by a wavelength shifter layer. Collecting the light reflected at the boundaries of the active volume greatly improves also the uniformity of the light yield. Presented here are initial results of the LArIAT light detection system calibration together with the preliminary results of the dedicated simulation and its application in future LAr TPC experiments

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2015

TU-CD-304-06: Using FFF Beams Improves Tumor Control in Radiotherapy of Lung Cancers

Purpose: Electron disequilibrium at the lung-tumor interface results in an under-dosage of tumor regions close to its surface. This under-dosage is known to be significant and can compromise tumor control. Previous studies have shown that in FFF beams, disequilibrium effects are less pronounced, which is manifested in an increased skin dose. In this study we investigate the improvement in tumor dose coverage that can be achieved with FFF beams. The significance of this improvement is evaluated by comparing tumor control probabilities of FFF beams and conventional flattened beams. Methods: The dosimetric coverage was investigated in a virtual phantom representing the chest wall, lung tissue and the tumor. A range of tumor sizes was investigated, and two tumor locations – central and adjacent to the chest wall. Calculations were performed with BEAMnrc Monte Carlo code. Parallel-opposed and multiple coplanar 6-MV beams were simulated. The tumor control probabilities were calculated using the logistic model with parameters derived from clinical data for non-small lung cancer patients. Results: FFF beams were not entirely immune to disequilibrium effects. They nevertheless consistently delivered more uniform dose distribution throughout the volume of the tumor, and eliminated up to ∼15% of under-dosage in the most affected by disequilibrium 1-mm thick surface region of the tumor. A voxel-by-voxel comparison of tumor control probabilities between FFF and conventional flattened beams showed an advantage of FFF beams that, depending on the set up, was from a few to ∼9 percent. Conclusion: A modest improvement in tumor control probability on the order of a few percent can be achieved by replacing conventional flattened beams with FFF beams. However, given the large number of lung cancer patients undergoing radiotherapy, these few percent can potentially prevent local tumor recurrence for a significant number of patients.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Oineus v1.0

A library for multi-threaded computation of persistence diagrams. The algorithm for computing persistence diagrams in a lock-free manner was published in the 'Towards Lock-free Persistent Homology' (D. Morozov, A. Nigmetov, Brief Announcement: SPAA 2020); it scales better than the only other shared-memory parallel implementation of persistent homology computation PHAT. Library includes python bindings to compute persistence diagrams and their vectorizations for lower-star filtrations on grid data. It is intended to be used by scientists working on Topological Data Analysis and its applications in different areas.

Nigmetov, Arnur↗
DOE OSTI2026

PRISMA: PARALLEL REFINEMENT AND INTEGRATION SYSTEM FOR MULTI-AZIMUTHAL ANALYSIS

The Parallel Refinement and Integration System for Multi-azimuthal Analysis (PRISMA, version 1.1.0) is a Python application for processing X-ray diffraction (XRD) image data. PRISMA wraps GSAS-II to perform azimuthally-binned peak refinement, computes per-frame strain and d-spacing from those fits, and provides three PyQt5 graphical interfaces: (1) a Recipe Builder for selecting GSAS-II control (.imctrl) files, optional mask (.immask) files or threshold-ased masking, reference and experiment image sets, peaks, zimuthal range and bin size, and an optional ceria-based auto-calibration; (2) a Batch Processor that uses Dask on local workstations and pure MPI (mpi4py.futures.MPICommExecutor) on HPC to distribute GSAS-II refinement across cores or compute nodes and write results to a 4-dimensional (peaks x frames x azimuths x measurements) Zarr dataset; and (3) a Data Analyzer that renders heatmaps of fit parameters, strain, frame-to-frame deltas, and percent-change-vs-reference, and exports user-defined subsections to CSV or Excel. The peak-refinement algorithm is deterministic. Benchmark on ALCF Crux: a 20,000-image set, single-peak fit in frame mode with 44 azimuthal bins on 128 nodes x 128 workers, 48 seconds total wall time.

Lorenzo Martin, Maria De La Cinta [Argonne Nationa↗
DOE OSTI2018

PIPER: Performance Insights for Programmers and Exascale Runtimes

During the lifetime of the project, the PIPER at the University of Utah worked in collaboration with the team from the partner institutions to establish a set of software tools for analyzing and improving the performance parallel computing tools. These activities complement and complete the work performed by the other X-Stack 2 projects with the definition of a common data models and computing infrastructures, which have been a central element in the targeted performance analysis pipeline and new programming models. The University of Utah team have focused mainly on developing data analysis and visualization systems to facilitate exploration, comparison and evaluation of the behavior and performance of complex algorithms in modern HPC infrastructures. This is involved several demonstrations of the performance achieved and presentation of the results in a way that facilitates the users understand bottlenecks and ways to overcome them. One major focus of the University of Utah activities has been the analysis of the performance characteristics of Fat-Tree and Dragonfly topology networks. The work involved the development of practical visualization systems especially in collaboration with the team at LLNL, and published several papers and gave invited talks at prestigious venues such as the Salishan Conference on High-Speed Computing or the International Conference on High Performance Computing, Data, and Analytics. In addition, the university of Utah team has advanced the core activities on analyzing the performance characteristics of I/O and other data movement systems and their practical use for scaling Uintah and other simulation codes poised for use in the exascale computing environments of the future.

42 ENGINEERING↗
DOE OSTI2019

2018 Benefits Study of Emergency IEA Oil Stocks: Final CRADA Report

This CRADA work was performed with the International Energy Agency (IEA) by Oak Ridge National Laboratory (ORNL) to support ongoing IEA, and U.S. DOE, discussions on future oil market challenges by IEA member countries. ORNL completed an update of a 2012 study for the IEA that accounts for changes in oil market and global economic conditions since 2013. The ORNL study evaluates the collective benefits of IEA emergency oil stocks, counting benefits to all countries, not just IEA, that are net oil importers. The IEA provided oil market data and projections, provided recommendations on parameter values and key case assumptions, in coordination with IEA member countries and coordinated the ORNL study with a parallel study on stockholding costs by an IEA subcontractor. IEA also combined the results of the ORNL benefits study and the IEA-funded cost study in a summary report by IEA, Insights Series 2018 - Costs and Benefits of Emergency Stockholding.

02 PETROLEUM↗
DOE OSTI2023

Computing the Properties of Matter with Leadership Computing Resources (Closeout Report for DE-SC0018121)

In order to add more capabilities to Halide, we have designed a new framework called Tiramisu and integrated this framework into Halide. Since Tiramisu enables Halide to target heterogeneous architectures, our development efforts have been refocused on Tiramisu. Most high-performance computer systems today are complex and increasingly heterogeneous; they may have CPUs, GPUs and FPGAs. Achieving best performance requires taking full advantage of all these different architectures. To address this issue, we have designed Tiramisu, an optimization framework that enables Halide (and other DSLs) to target heterogeneous architectures. Tiramisu is an optimization framework that takes as input a high level, architecture-independent representation of code and a set of scheduling and data mapping commands that guide code transformation. The input can either be generated by a domain-specific language (DSL) compiler such as Halide or directly written by a programmer. Tiramisu then applies the user-specified code and data-layout transformations and generates an architecture-specific, low-level intermediate representation (IR) that takes advantage of modern architectural features such as multicore parallelism, non-uniform memory (NUMA) hierarchies, clusters, and accelerators like GPUs and FPGAs. We integrated Tiramisu within Halide and implemented a representative set of benchmarks to evaluate this integration. Tiramisu is now open source and is available for public use (http://tiramisu-compiler.org/). A paper about Tiramisu was published, it shows that Tiramisu extends Halide with many new capabilities and that Tiramisu can generate efficient code for multicores, GPUs, FPGAs and distributed heterogeneous systems. The performance of code generated by the Tiramisu backends matches or exceeds hand optimized reference implementations. For example, the multicore backend matches the highly optimized Intel MKL library on many kernels and shows speedups reaching 4x over the original Halide. In addition to making Tiramisu more robust, we have used Tiramisu to implement a set of representative tensor operation for constructing baryon building blocks required for multi baryon contractions in LQCD. In order to implement this code, we needed to generalize Tiramisu in two ways: first we needed to support indirect array accesses, and second, we needed to add support for complex numbers to Tiramisu. The code generated by Tiramisu is 6x faster than the reference code. Our efforts towards an MPI based multi-node version of tiramisu have matured and the resulting code scales well on multiple nodes (tests up to 512 KNL nodes have been undertaken).

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2016

THE QUEST FOR DUSTY STAR-FORMING GALAXIES AT HIGH REDSHIFT z ≳ 4

We exploit the continuity equation approach and “main-sequence” star formation timescales to show that the observed high abundance of galaxies with stellar masses ≳ a few 10{sup 10} M {sub ⊙} at redshift z ≳ 4 implies the existence of a galaxy population featuring large star formation rates (SFRs) ψ ≳ 10{sup 2} M {sub ⊙} yr{sup −1} in heavily dust-obscured conditions. These galaxies constitute the high-redshift counterparts of the dusty star-forming population already surveyed for z ≲ 3 in the far-IR band by the Herschel Space Observatory . We work out specific predictions for the evolution of the corresponding stellar mass and SFR functions out to z ∼ 10, determining that the number density at z ≲ 8 for SFRs ψ ≳ 30 M {sub ⊙} yr{sup −1} cannot be estimated relying on the UV luminosity function alone, even when standard corrections for dust extinction based on the UV slope are applied. We compute the number counts and redshift distributions (including galaxy-scale gravitational lensing) of this galaxy population, and show that current data from the AzTEC - LABOCA , SCUBA-2 , and ALMA - SPT surveys are already addressing it. We demonstrate how an observational strategy based on color preselection in the far-IR or (sub-)millimeter band with Herschel and SCUBA-2 , supplemented by photometric data from on-source observations with ALMA , can allow us to reconstruct the bright end of the SFR functions out to z ≲ 8. In parallel, such a challenging task can be managed by exploiting current UV surveys in combination with (sub-)millimeter observations by ALMA and NIKA2 and/or radio observations by SKA and its precursors.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Characterization of flow recirculation zones at the Perdigão site using multi-lidar measurements

Because flow recirculation can generate significant amounts of turbulence, it can impact the success of wind energy projects. This study uses unique Doppler lidar observations to quantify occurrences of flow recirculation on lee sides of ridges. An extensive dataset of observations of flow over complex terrain is available from the Perdigão 2017 field campaign over a period of 3 months. The campaign site was selected because of the unique terrain feature of two nearly parallel ridges with a valley-to-ridge-top height difference of about 200 m and a ridge-to-ridge distance of 1.4 km. Six scanning Doppler lidars probed the flow field in several vertical planes orthogonal to the ridges using range–height indicator scans. With this lidar setup, we achieved vertical scans of the recirculation zone at three positions along two parallel ridges. We construct a method to identify flow recirculation zones in the scans, as well as define characteristics of these zones. According to our data analysis, flow recirculation, with reverse flow wind speeds greater than 0.5 m s -1 , occurs over 50 % of the time when the wind direction is perpendicular to the direction of the ridges. Atmospheric conditions, such as atmospheric stability and wind speed, affect the occurrence of flow recirculation. Flow recirculation occurs more frequently during periods with wind speeds above 8 m s -1 . Recirculation within the valley affects the mean wind and turbulence fields at turbine heights on the downwind ridge in magnitudes significant for wind resource assessment.

17 WIND ENERGY↗
DOE OSTI2018

HOMMEXX 1.0: A Performance Portable Atmospheric Dynamical Core for the Energy Exascale Earth System Model

Abstract. We present an architecture-portable and performant implementation of the atmospheric dynamical core (HOMME) of the Energy Exascale Earth System Model (E3SM). The original Fortran implementation is highly performant and scalable on conventional architectures using MPI and OpenMP. We rewrite the model in C++ and use the Kokkos library to express on-node parallelism in a largely architecture-independent implementation. Kokkos provides an abstraction of a compute node or device, layout-polymorphic multidimensional arrays, and parallel execution constructs. Here, the new implementation achieves the same or better performance on conventional multicore computers and is portable to GPUs. We present performance data for the original and new implementations on multiple platforms, on up to 5400 compute nodes, and study several aspects of the single- and multi-node performance characteristics of the new implementation on conventional CPU, Intel Xeon Phi Knights Landing, and Nvidia V100 GPU.

54 ENVIRONMENTAL SCIENCES↗