Search NASA⌕ Search

SEARCH · Search NASA

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 1,117 records · Page 62
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

General field evaluation in high-order meshes on GPUs

Robust and scalable function evaluation at any arbitrary point in the finite/spectral element mesh is required for querying the partial differential equation solution at points of interest, comparison of solution between different meshes, and Lagrangian particle tracking. This is a challenging problem, particularly for high-order unstructured meshes partitioned in parallel with MPI, as it requires identifying the element that overlaps a given point and computing the corresponding reference space coordinates. Here, we present a robust and efficient technique for general field evaluation in large-scale high-order meshes with quadrilaterals and hexahedra. In the proposed method, a combination of globally partitioned and processor-local maps are used to first determine a list of candidate MPI ranks, and then locally candidate elements that could contain a given point. Next, element-wise bounding boxes further reduce the list of candidate elements. Finally, Newton’s method with trust region is used to determine the overlapping element and corresponding reference space coordinates. Since GPU-based architectures have become popular for accelerating computational analyses using meshes with tensor-product elements, specialized kernels have been developed to utilize the proposed methodology on GPUs. The method is also extended to enable general field evaluation on surface meshes. The paper concludes by demonstrating the use of the proposed method in various applications ranging from mesh-to-mesh transfer during r-adaptivity to Lagrangian particle tracking.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A novel approach to increase accuracy in remotely sensed evapotranspiration through basin water balance and flux tower constraints

Remote sensing-derived evapotranspiration (RSET) products capture the spatiotemporal variations of evapotranspiration (ET) from field to basin scales with unprecedented details. However, their accuracy varies across RSET estimation methods and diverse hydroclimate regions. While ET modeling efforts to account for biophysical processes and controlling parameters have made good progress in recent years, a parallel approach of integrating in-situ ET with RSET could reduce biases in RSET products. Basin water balance ET (WBET) and flux tower ET are widely applied to evaluate RSET accuracy, yet such ET measurements are rarely used for RSET bias corrections, especially for large area applications. To address this issue, we propose a novel approach: the water balance equivalence (WABE) method, which generates spatially continuous WBET for correcting biases in RSET products. The WABE method computes synthetic WBET by integrating observed WBET and flux tower-derived FLUXCOM ET, which fills the spatial gaps of observed WBET and generates a spatially continuous WBET dataset. Synthetic WBET (2002–2015 annual average) of eight-digit hydrologic unit code (HUC8) basins across the conterminous United States (CONUS), constituting 44 % (887 out of 2035 basins) of CONUS basins, was determined within 2.0 % (RMSE = 12 %) of observed WBET at CONUS and between 1–12 % (RMSE = 3–33 %) across 18 regions in CONUS. With WABE-based bias corrections, the overall annual bias of RSET decreased from 10 % (RMSE = 34 %) to 6 % (RMSE = 26 %) across 37 flux tower sites. The WABE method offers a new approach for RSET accuracy improvement and shows great promise for large area implementations with a potential to yield substantial benefits for building accurate basin water budgets and water management decisions.

Khand, Kul↗
DOE OSTI2019

Targeting GPUs with OpenMP directives on Summit: A simple and effective Fortran experience

We use OpenMP to target hardware accelerators (GPUs) on Summit, a newly deployed supercomputer at the Oak Ridge Leadership Computing Facility (OLCF), demonstrating simplified access to GPU devices for users of our astrophysics code GenASiS and useful speedup on a sample fluid dynamics problem. We modify our workhorse class for data storage to include members and methods that significantly streamline the persistent allocation of and association to GPU memory. Users offload computational kernels with OpenMP target directives that are rather similar to constructs already familiar from multi-core parallelization. In this initial example we ask, “With a given number of Summit nodes, how fast can we compute with and without GPUs?”, and find total wall time speedups of ~ 12X. We also find reasonable weak scaling up to 8000 GPUs (1334 Summit nodes). We make available the source code from this work at https://github.com/GenASiS/GenASiS_Basics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Spherical Region Queries on Multicore Architectures

In this short paper, we report the performance of multiple thread-parallel algorithms for spherical region queries on multicore architectures motivated by a challenging data analytics application in materials science. Performances of two tree-based algorithms and a naive algorithm are compared to identify the length scales at which these approaches perform optimally. The optimal algorithm is then used to scale the driving materials science application, which is shown to deliver over 17X speedup using 32 OpenMP threads on data sets containing many millions of atoms.

Lu, Hao↗
DOE OSTI2021

SDSS-IV MaNGA: 3D spin alignment of spiral and S0 galaxies

ABSTRACT We investigate the 3D spin alignment of galaxies with respect to the large-scale filaments using the MaNGA survey. The cosmic web is reconstructed from the Sloan Digital Sky Survey using disperse and the 3D spins of MaNGA galaxies are estimated using the thin disc approximation with integral field spectroscopy kinematics. Late-type spiral galaxies are found to have their spins parallel to the closest filament’s axis. The alignment signal is found to be dominated by low-mass spirals. Spins of S0-type galaxies tend to be oriented preferentially in perpendicular direction with respect to the filament’s axis. This orthogonal orientation is found to be dominated by S0s that show a notable misalignment between their kinematic components of stellar and ionized gas velocity fields and/or by low-mass S0s with lower rotation support compared to their high-mass counterparts. Qualitatively similar results are obtained when splitting galaxies based on the degree of ordered stellar rotation, such that galaxies with high spin magnitude have their spin aligned, and those with low spin magnitude in perpendicular direction to the filaments. In the context of conditional tidal torque theory, these findings suggest that galaxies’ spins retain memory of their larger scale environment. In agreement with measurements from hydrodynamical cosmological simulations, the measured signal at low redshift is weak, yet statistically significant. The dependence of the spin-filament orientation of galaxies on their stellar mass, morphology, and kinematics highlights the importance of sample selection to detect the signal.

Kraljic, Katarina↗
DOE OSTI2018

Iterative Importance Sampling Algorithms for Parameter Estimation

In parameter estimation problems one computes a posterior distribution over uncertain parameters defined jointly by a prior distribution, a model, and noisy data. Markov chain Monte Carlo (MCMC) is often used for the numerical solution of such problems. An alternative to MCMC is importance sampling, which can exhibit near perfect scaling with the number of cores on high performance computing systems because samples are drawn independently. However, finding a suitable proposal distribution is a challenging task. Several sampling algorithms have been proposed over the past years that take an iterative approach to constructing a proposal distribution. We investigate the applicability of such algorithms by applying them to two realistic and challenging test problems, one in subsurface flow, and one in combustion modeling. More specifically, we implement importance sampling algorithms that iterate over the mean and covariance matrix of Gaussian or multivariate t-proposal distributions. Our implementation leverages massively parallel computers, and we present strategies to initialize the iterations using “coarse” MCMC runs or Gaussian mixture models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

High Performance Computing Based Parallel HIearchical Modal Association Clustering (HPAR HMAC)

For many applications, clustering is a crucial step in order to gain insight into the makeup of a dataset. The best approach to a given problem often depends on a variety of factors, such as the size of the dataset, time restrictions, and soft clustering requirements. The HMAC algorithm seeks to combine the strengths of 2 particular clustering approaches: model-based and linkage-based clustering. One particular weakness of HMAC is its computational complexity. HMAC is not practical for mega-scale data clustering. For high-definition imagery, a user would have to wait months or years for a result; for a 16-megapixel image, the estimated runtime skyrockets to over a decade! To improve the execution time of HMAC, it is reasonable to consider an multi-core implementation that utilizes available system resources. An existing imple-mentation (Ray and Cheng 2014) divides the dataset into N partitions - one for each thread prior to executing the HMAC algorithm. This implementation benefits from 2 types of optimization: parallelization and divide-and-conquer. By running each partition in parallel, the program is able to accelerate computation by utilizing more system resources. Although the parallel implementation provides considerable improvement over the serial HMAC, it still suffers from poor computational complexity, O(N2). Once the maximum number of cores on a system is exhausted, the program exhibits slower behavior. We now consider a modification to HMAC that involves a recursive partitioning scheme. Our modification aims to exploit divide-and-conquer benefits seen by the parallel HMAC implementation. At each level in the recursion tree, partitions are divided into 2 sub-partitions until a threshold size is reached. When the partition can no longer be divided without falling below threshold size, the base HMAC algorithm is applied. This results in a significant speedup over the parallel HMAC.

Patlolla, Dilip R↗
DOE OSTI2017

On the Scalability of Data Reduction Techniques in Current and Upcoming HPC Systems from an Application Perspective

We implement and benchmark parallel I/O methods for the fully-manycore driven particle-in-cell code PIConGPU. Identifying throughput and overall I/O size as a major challenge for applications on today’s and future HPC systems, we present a scaling law characterizing performance bottlenecks in state-of-the-art approaches for data reduction. Consequently, we propose, implement and verify multi-threaded data-transformations for the I/O library ADIOS as a feasible way to trade underutilized host-side compute potential on heterogeneous systems for reduced I/O latency.

Huebl, Axel↗
DOE OSTI2022

Investigation of Cycle-to-Cycle Variations in Internal Combustion Engine Using Proper Orthogonal Decomposition

The understanding, modeling and control of the cycle-to-cycle variation (CCV) in the modern internal combustion engine (ICE) is a key scientific challenge to achieve stable engine operation. High CCV in the engine combustion chamber may contribute to partial burn, misfire and knock, which adversely affects the engine performance and may potentially damage the engine. The objective of the current study is to leverage high-fidelity numerical simulations to improve the understanding of the causes of CCV. Using the massively parallel code, Nek5000, multi-cycle, wall-resolved large-eddy simulations (LES) were performed for the General Motors (GM), Transparent Combustion Chamber (TCC-III) optical engine under motored operating conditions. Further, the large-scale structures of the in-cylinder flow were investigated using a triple proper orthogonal decomposition (POD) technique to explore the characteristics of different parts of the flow and their contributions to CCV. The kinetic energy of the subset of flow structures were determined and correlated between the intake and compression strokes. The insights from the analysis of the large-scale flow structures will be used to assist the development of improved engine designs with reduced CCV and enhance the engine performance.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2018

Effect of Orientation of Weld Line on Formability of Electron Beam-Welded Dissimilar Thickness Titanium Sheets

Recently, manufacturing industries are looking forward to get insight into the influence of weld orientation on formability of tailor-welded blanks (TWBs) of titanium sheets for design and fabrication of lightweight components. Hence, commercially pure titanium (CP Ti) sheets of 1.0 and 1.2 mm thickness were joined together by electron beam welding process using accelerating voltage of 55 kV, beam current of 14.9 mA and welding speed of 865 mm/min. Two different types of TWBs with weld line perpendicular to the rolling direction (WL ⊥ RD) and weld line parallel to the rolling direction (WL || RD) were fabricated, and subsequently, the tensile test, microstructure and microhardness characterizations were conducted to ensure quality of weld. The limiting dome height (LDH) tests were carried out using laboratory-scale setup to evaluate forming behavior of both the above TWBs in terms of FLD, strain distribution, weld line movement and failure location. It was found that the tensile stress–strain response and formability performance of TWBs were significantly influenced by weld line orientation with lower ductility, ultimate tensile strength and LDH in TWB of WL || RD. Moreover, significant weld line movement and non-uniform strain distribution with necking and subsequently fracture were observed away from the weld line in thinner 1.0 mm CP Ti sheets depending on both sample geometry and weld line orientation.

36 MATERIALS SCIENCE↗
DOE OSTI2017

GPU-accelerated red blood cells simulations with transport dissipative particle dynamics

Mesoscopic numerical simulations provide a unique approach for the quantification of the chemical influences on red blood cell functionalities. The transport Dissipative Particle Dynamics (tDPD) method can lead to such effective multiscale simulations due to its ability to simultaneously capture mesoscopic advection, diffusion, and reaction. In this paper, we present a GPU-accelerated red blood cell simulation package based on a tDPD adaptation of our red blood cell model, which can correctly recover the cell membrane viscosity, elasticity, bending stiffness, and cross-membrane chemical transport. The package essentially processes all computational workloads in parallel by GPU, and it incorporates multi-stream scheduling and non-blocking MPI communications to improve inter-node scalability. Our code is validated for accuracy and compared against the CPU counterpart for speed. Strong scaling and weak scaling are also presented to characterize scalability. We observe a speedup of on one GPU over all cores within a single node, and a weak scaling efficiency of across nodes. The program enables quick-turnaround and high-throughput numerical simulations for investigating chemical-driven red blood cell phenomena and disorders.

Computer Science↗
DOE OSTI2023

Neoclassical transport in strong gradient regions of large aspect ratio tokamaks

We present a new neoclassical transport model for large aspect ratio tokamaks where the gradient scale lengths are of the size of the ion poloidal gyroradius. Previous work on neoclassical transport across transport barriers assumed large density and potential gradients but a small temperature gradient, or neglected the gradient of the mean parallel flow. Using large aspect ratio and low collisionality expansions, we relax these restrictive assumptions. We define a new set of variables based on conserved quantities, which simplifies the drift kinetic equation whilst keeping strong gradients, and derive equations describing the transport of particles, parallel momentum and energy by ions in the banana regime. The poloidally varying parts of density and electric potential are included. Studying contributions from both passing and trapped particles, we show that the resulting transport is dominated by trapped particles. We find that a non-zero neoclassical particle flux requires parallel momentum input which could be provided through interaction with turbulence or impurities. We derive upper and lower bounds for the energy flux across a transport barrier in both temperature and density and present example profiles and fluxes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Operando Bragg Coherent Diffraction Imaging of LiNi 0.8 Mn 0.1 Co 0.1 O 2 Primary Particles within Commercially Printed NMC811 Electrode Sheets

Due to complex degradation mechanisms, disparities between the theoretical and practical capacities of lithium-ion battery cathode materials persist. Specifically, Ni-rich chemistries such as LiNi 0.8 Mn 0.1 Co 0.1 O 2 (or NMC811) are one of the most promising choices for automotive applications; however, they continue to suffer severe degradation during operation that is poorly understood, thus challenging to mitigate. Here in this paper we use operando Bragg coherent diffraction imaging for 4D analysis of these mechanisms by inspecting the individual crystals within primary particles at various states of charge (SoC). Although some crystals were relatively homogeneous, we consistently observed non-uniform distributions of inter- and intracrystal strain at all measured SoC. Pristine structures may already possess heterogeneities capable of triggering crystal splitting and subsequently particle cracking. During low-voltage charging (2.7–3.5 V), crystal splitting may still occur even during minimal bulk deintercalation activity; and during discharging, rotational effects within parallel domains appear to be the precursor for the nucleation of screw dislocations at the crystal core. Ultimately, this discovery of the central role of crystal grain splitting in the charge/discharge dynamics may have ramifications across length scales that affect macroscopic performance loss during real-world battery operation.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

Statistical Properties of Magnetic Structures and Energy Dissipation during Turbulent Reconnection in the Earth's Magnetotail

Here, we present the first statistical study of magnetic structures and associated energy dissipation observed during a single period of turbulent magnetic reconnection, by using the in situ measurements of the Magnetospheric Multiscale mission in the Earth's magnetotail on 26 July 2017. The structures are selected by identifying a bipolar signature in the magnetic field and categorized as plasmoids or current sheets via an automated algorithm which examines current density and plasma flow. The size of the plasmoids forms a decaying exponential distribution ranging from subelectron up to ion scales. The presence of substantial number of current sheets is consistent with a physical picture of dynamic production and merging of plasmoids during turbulent reconnection. The magnetic structures are locations of significant energy dissipation via electric field parallel to the local magnetic field, while dissipation via perpendicular electric field dominates outside of the structures. Significant energy also returns from particles to fields.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Scaling Ultrahigh-Resolution E3SM Land Model for Leadership-Class Supercomputers

This paper presents advancements in scaling the ultrahigh-resolution E3SM Land Model (uELM) for deployment on leadership-class supercomputers, addressing the increased demand for km-scale Earth system modeling. By focusing on km-scale ELM simulations, we enhance predictive capabilities for climate interactions, facilitating improved responses to climate change impacts on energy systems, agriculture, and water resources. Our approach leverages innovative software architecture optimizations, sophisticated data handling techniques, and advanced parallel processing, achieving strong scalability on two leadership supercomputers (2400 nodes (105,600 cores) on Summit, and 1200 nodes (76,800 cores) on Frontier). Results from extensive scalability assessments on the Summit and Frontier also demonstrate outstanding I/O performance (close to 400 GB/s write throughput) and the model's ability to efficiently handle increasing computational demands. This study not only establishes uELM's capability for high-resolution simulations over vast geographical domains, but also sets a foundation for future Earth system modeling breakthroughs.

Wang, Dali [ORNL] (ORCID:0000000168065108)↗
DOE OSTI2018

Scalable molecular dynamics with NAMD on the Summit system

According to the article, NAnoscale Molecular Dynamics (NAMD) is a parallel molecular dynamics application that has been used to make breakthroughs in understanding the structure and dynamics of large biomolecular complexes, such as viruses like HIV and various types of influenza. State-of-the-art biomolecular simulations often require integration of billions of timesteps, computing all interatomic forces for each femtosecond timestep. Molecular dynamics simulation of large biomolecular systems and long-timescale biological phenomena requires tremendous computing power. NAMD harnesses the power of thousands of heterogeneous processors to meet this demand. In this paper, we present algorithmic improvements and performance optimizations that enable NAMD to achieve high performance on the IBM Newell platform (with IBM POWER9 processors and NVIDIA Volta V100 GPUs), which underpins the Oak Ridge National Laboratory's Summit and Lawrence Livermore National Laboratory's Sierra supercomputers. The Top-500 supercomputers November 2018 list shows Summit at the number one spot, with 200 petaflop/s peak performance, and Sierra second with 125 petaflop/s. Optimizations for NAMD on Summit include: data layout changes for GPU acceleration and CPU vectorization, improving GPU offload efficiency, increasing performance with Parallel Active Messaging Interface support in Charm++, improving efficiency of fast Fourier transform calculations, improving load balancing, enabling better CPU vectorization and cache performance, and providing an alternative thermostat through stochastic velocity rescaling. We also present performance scaling results on early Newell systems.

Computer Science↗
DOE OSTI2020

Statistical properties of magnetic structures and energy dissipation during turbulent reconnection in the Earth's magnetotail

We present the first statistical study of magnetic structures and associated energy dissipation observed during a single period of turbulent magnetic reconnection, by using the in situ measurements of the Magnetospheric Multiscale mission in the Earth's magnetotail on 26 July 2017. The structures are selected by identifying a bipolar signature in the magnetic field and categorized as plasmoids or current sheets via an automated algorithm which examines current density and plasma flow. The size of the plasmoids forms a decaying exponential distribution ranging from subelectron up to ion scales. The presence of substantial number of current sheets is consistent with a physical picture of dynamic production and merging of plasmoids during turbulent reconnection. The magnetic structures are locations of significant energy dissipation via electric field parallel to the local magnetic field, while dissipation via perpendicular electric field dominates outside of the structures. Significant energy also returns from particles to fields.

Magnetotail↗