Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed Computing”

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 937 records · Page 52
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Lattice QCD calculation of the pion generalized parton distribution

We present the results of a Lattice QCD computation of pion generalized parton distribution (GPD), employing perturbative matching up to next-to-next-to-leading order (NNLO). The computations are based on an ensemble of Nf=2+1 highly improved staggered quarks (HISQ) with a pion mass of 300 MeV and a lattice spacing of 0.04 fm. Centered on the zero-skewness limit, we utilize a recently proposed Lorentz-invariant definition of GPD, which is derived from Lorentz-invariant amplitudes. We analyze and compare these amplitudes in both Breit and non-Breit kinematic frames at comparable momentum transfers, validating their frame-independent nature. To obtain light-cone GPD, we integrate hybrid scheme renormalization with the large momentum effective theory (LaMET). Moreover, we determine the first three iso-vector generalized form factors (GFFs) of the pion using the ratio scheme renormalization and leading-twist factorization, achieving NNLO accuracy.

Ding, Heng-Tong↗
NASA NTRS1978

Velocity, temperature, and electrical conductivity profiles in hydrogen-oxygen MHD duct flows

This paper presents results of two-dimensional duct flow computations for radial distributions of velocity, temperature, and electrical conductivity. Calculations were carried out for the flow conditions representative of NASA Lewis hydrogen-oxygen combustion driven MHD duct. Results are presented for two sets of computations: (1) profiles of developing flow in a smooth duct, and (2) profiles of fully developed pipe flow with a specified streamwise shear stress distribution. The predicted temperature and electrical conductivity profiles for the developing flows compared well with available experimental data.

Greywall, M. S.↗
NASA NTRS1981

Numerical optimization techniques for bound circulation distribution for minimum induced drag of Nonplanar wings: Computer program documentation

A two dimensional advanced panel far-field potential flow model of the undistorted, interacting wakes of multiple lifting surfaces was developed which allows the determination of the spanwise bound circulation distribution required for minimum induced drag. This model was implemented in a FORTRAN computer program, the use of which is documented in this report. The nonplanar wakes are broken up into variable sized, flat panels, as chosen by the user. The wake vortex sheet strength is assumed to vary linearly over each of these panels, resulting in a quadratic variation of bound circulation. Panels are infinite in the streamwise direction. The theory is briefly summarized herein; sample results are given for multiple, nonplanar, lifting surfaces, and the use of the computer program is detailed in the appendixes.

Kuhlman, J. M.↗
NASA NTRS1978

Measurements of noise produced by flow past lifting surfaces

Wind tunnel studies have been conducted to determine the specific locations of aerodynamic noise production within the flow field about various lifting-surface configurations. The models tested included low aspect ratio shapes intended to represent aircraft flaps, a finite aspect ratio NACA 0012 wing, and a multi-element wing section consisting of a main section, a leading edge flap, and dual trailing edge flaps. Turbulence was induced on the models by surface roughness. Lift and drag were measured for the flap models. Hot-wire anemometry was used for study of the flap-model vortex roll-up. Apparent noise source distributions were measured by use of a directional microphone system, located outside the tunnel, which was scanned about the flow region to be analyzed under computer control. These distributions exhibited a diversity of pattern, suggesting that several flow processes are important to lifting-surface noise production. Speculation concerning these processes is offered.

Kendall, J. M.↗
DOE OSTI2024

Posterior Covariance Matrix Approximations

Here, the Davis equation of state (EOS) is commonly used to model thermodynamic relationships for high explosive (HE) reactants. Typically, the parameters in the EOS are calibrated, with uncertainty, using a Bayesian framework and Markov Chain Monte Carlo (MCMC) methods. However, MCMC methods are computationally expensive, especially for complex models with many parameters. This paper provides a comparison between MCMC and less computationally expensive Variational methods (Variational Bayesian and Hessian Variational Bayesian) for computing the posterior distribution and approximating the posterior covariance matrix based on heterogeneous experimental data. All three methods recover similar posterior distributions and posterior covariance matrices. This study demonstrates that for this EOS parameter calibration application, the assumptions made in the two Variational methods significantly reduce the computational cost but do not substantially change the results compared to MCMC.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1983

Stellar number densities for magnitudes 0.0-9.0 from SKYMAP

Statistical information regarding the stellar number density distribution brighter than 9.0 mag in B and V of the Johnson magnitude system is presented. Data are extracted from SKYMAP Master Catalog Version 3.1 using computer techniques. The distribution as a function of (B - V) color, galactic latitude, and nearest-neighbor separation is examined. Comparisons of the SKYMAP data are made to four other sources of similar types of data.

Mclaughlin, S. F.↗
NASA NTRS1976

Measurements of the stochastic nature of atmospheric spectral amplitudes

The stochastic nature of the power spectral amplitudes of the neutral atmospheric boundary layer is examined. Probability density distributions and probability distributions of longitudinal and lateral power spectra amplitudes are computed from neutral atmospheric boundary layers. The statistical distributions are computed for frequencies of 0.006, 0.01, 0.03, 0.06, 0.1, and 0.5 Hz at each of the elevations of 18, 30, 60, 90, 120, and 150 m. When the probability density distributions are properly nondimensionalized, the data tend to collapse to a universal curve. An empirical curve fit to the universal nondimensionalized probability density distribution is also given. Probability distributions of individual frequency power spectral amplitudes are also presented for all elevations and frequencies. An interesting observation from the data is that greater than 10 percent of the time the power spectral amplitude at a given frequency will genrally be more than three times the temporal mean value computed by standard Fourier techniques. The standard power spectral density curves are also included in the report.

Cliff, W. C.↗
NASA NTRS1997

Probabilistic Micromechanics and Macromechanics for Ceramic Matrix Composites

The properties of ceramic matrix composites (CMC's) are known to display a considerable amount of scatter due to variations in fiber/matrix properties, interphase properties, interphase bonding, amount of matrix voids, and many geometry- or fabrication-related parameters, such as ply thickness and ply orientation. This paper summarizes preliminary studies in which formal probabilistic descriptions of the material-behavior- and fabrication-related parameters were incorporated into micromechanics and macromechanics for CMC'S. In this process two existing methodologies, namely CMC micromechanics and macromechanics analysis and a fast probability integration (FPI) technique are synergistically coupled to obtain the probabilistic composite behavior or response. Preliminary results in the form of cumulative probability distributions and information on the probability sensitivities of the response to primitive variables for a unidirectional silicon carbide/reaction-bonded silicon nitride (SiC/RBSN) CMC are presented. The cumulative distribution functions are computed for composite moduli, thermal expansion coefficients, thermal conductivities, and longitudinal tensile strength at room temperature. The variations in the constituent properties that directly affect these composite properties are accounted for via assumed probabilistic distributions. Collectively, the results show that the present technique provides valuable information about the composite properties and sensitivity factors, which is useful to design or test engineers. Furthermore, the present methodology is computationally more efficient than a standard Monte-Carlo simulation technique; and the agreement between the two solutions is excellent, as shown via select examples.

Murthy, Pappu L. N.↗
DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (distributed parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

graph algorithms, high performance comptuing↗
DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗
NASA NTRS1947

The Turbulent Flow in Diffusers of Small Divergence Angle

The turbulent flow in a conical diffuser represents the type of turbulent boundary layer with positive longitudinal pressure gradient. In contrast to the boundary layer problem, however, it is not necessary that the pressure distribution along the limits of the boundary layer(along the axis of the diffuser) be given, since this distribution can be obtained from the computation. This circumstance, together with the greater simplicity of the problem as a whole, provides a useful basis for the study of the extension of the results of semiempirical theories to the case of motion with a positive pressure gradient. In the first part of the paper,formulas are derived for the computation of the velocity and.pressure distributions in the turbulent flow along, and at right angles to, the axis of a diffuser of small cone angle. The problem is solved.

Gourzhienko, G. A.↗
NASA NTRS2013

An Offload NIC for NASA, NLR, and Grid Computing

This work addresses distributed data management and access dynamically configurable high-speed access to data distributed and shared over wide-area high-speed network environments. An offload engine NIC (network interface card) is proposed that scales at nX10-Gbps increments through 100-Gbps full duplex. The Globus de facto standard was used in projects requiring secure, robust, high-speed bulk data transport. Novel extension mechanisms were derived that will combine these technologies for use by GridFTP, bandwidth management resources, and host CPU (central processing unit) acceleration. The result will be wire-rate encrypted Globus grid data transactions through offload for splintering, encryption, and compression. As the need for greater network bandwidth increases, there is an inherent need for faster CPUs. The best way to accelerate CPUs is through a network acceleration engine. Grid computing data transfers for the Globus tool set did not have wire-rate encryption or compression. Existing technology cannot keep pace with the greater bandwidths of backplane and network connections. Present offload engines with ports to Ethernet are 32 to 40 Gbps f-d at best. The best of ultra-high-speed offload engines use expensive ASICs (application specific integrated circuits) or NPUs (network processing units). The present state of the art also includes bonding and the use of multiple NICs that are also in the planning stages for future portability to ASICs and software to accommodate data rates at 100 Gbps. The remaining industry solutions are for carrier-grade equipment manufacturers, with costly line cards having multiples of 10-Gbps ports, or 100-Gbps ports such as CFP modules that interface to costly ASICs and related circuitry. All of the existing solutions vary in configuration based on requirements of the host, motherboard, or carriergrade equipment. The purpose of the innovation is to eliminate data bottlenecks within cluster, grid, and cloud computing systems, and to add several more capabilities while reducing space consumption and cost. Provisions were designed for interoperability with systems used in the NASA HEC (High-End Computing) program. The new acceleration engine consists of state-ofthe- art FPGA (field-programmable gate array) core IP, C, and Verilog code; novel communication protocol; and extensions to the Globus structure. The engine provides the functions of network acceleration, encryption, compression, packet-ordering, and security added to Globus grid or for cloud data transfer. This system is scalable in nX10-Gbps increments through 100-Gbps f-d. It can be interfaced to industry-standard system-side or network-side devices or core IP in increments of 10 GigE, scaling to provide IEEE 40/100 GigE compliance.

Awrach, James↗
NASA NTRS2002

Turbulent Navier-Stokes Flow Analysis of an Advanced Semispan Diamond-Wing Model in Tunnel and Free Air at High-Lift Conditions

Turbulent Navier-Stokes computational results are presented for an advanced diamond wing semispan model at low-speed, high-lift conditions. The numerical results are obtained in support of a wind-tunnel test that was conducted in the National Transonic Facility at the NASA Langley Research Center. The model incorporated a generic fuselage and was mounted on the tunnel sidewall using a constant-width non-metric standoff. The computations were performed at to a nominal approach and landing flow conditions.The computed high-lift flow characteristics for the model in both the tunnel and in free-air environment are presented. The computed wing pressure distributions agreed well with the measured data and they both indicated a small effect due to the tunnel wall interference effects. However, the wall interference effects were found to be relatively more pronounced in the measured and the computed lift, drag and pitching moment. Although the magnitudes of the computed forces and moment were slightly off compared to the measured data, the increments due the wall interference effects were predicted reasonably well. The numerical results are also presented on the combined effects of the tunnel sidewall boundary layer and the standoff geometry on the fuselage forebody pressure distributions and the resulting impact on the configuration longitudinal aerodynamic characteristics.

Ghaffari, Farhad↗
DOE OSTI2025

Communication Lower Bounds and Optimal Algorithms for Symmetric Matrix Computations

In this article, we focus on the communication costs of three symmetric matrix computations: (i) multiplying a matrix with its transpose, known as a symmetric rank-k update (SYRK) (ii) adding the result of the multiplication of a matrix with the transpose of another matrix and the transpose of that result, known as a symmetric rank-2k update (SYR2K) (iii) performing matrix multiplication with a symmetric input matrix (SYMM). All three computations appear in the Level 3 Basic Linear Algebra Subroutines (BLAS) and have wide use in applications involving symmetric matrices. We establish communication lower bounds for these kernels using sequential and distributed-memory parallel computational models, and we show that our bounds are tight by presenting communication-optimal algorithms for each setting. Our lower bound proofs rely on applying a geometric inequality for symmetric computations and analytically solving constrained nonlinear optimization problems. As a result, the symmetric matrix and its corresponding computations are accessed and performed according to a triangular block partitioning scheme in the optimal algorithms.

Al Daas, Hussam [Rutherford Appleton Laboratory, D↗
DOE OSTI2026

Tensor network simulations of quasi-GPDs in the massive Schwinger model

Generalized parton distribution functions (GPDs) are off-diagonal light-cone matrix elements that encode the internal structure of hadrons in terms of quark and gluon degrees of freedom. In this work, we present the first nonperturbative study of quasi-GPDs in the massive Schwinger model, quantum electrodynamics in 1+1 dimensions (QED 2 ), within the Hamiltonian formulation of lattice field theory. Quasidistributions are spatial correlation functions of boosted states, which approach the relevant light-cone distributions in the luminal limit. Using tensor networks, we prepare the first excited state in the strongly coupled regime and boost it to close to the light-cone on lattices of up to 400 lattice sites. We compute both quasiparton distribution functions and, for the first time, quasi-GPDs, and study their convergence for increasingly boosted states. In addition, we perform analytic calculations of GPDs in the two-particle Fock-space approximation and in the Reggeized limit, providing qualitative benchmarks for the tensor network results. Our analysis establishes computational benchmarks for accessing partonic observables in low-dimensional gauge theories, offering a starting point for future extensions to higher dimensions, non-Abelian theories, and quantum simulations.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS1996

Research in Parallel Algorithms and Software for Computational Aerosciences

Phase I is complete for the development of a Computational Fluid Dynamics parallel code with automatic grid generation and adaptation for the Euler analysis of flow over complex geometries. SPLITFLOW, an unstructured Cartesian grid code developed at Lockheed Martin Tactical Aircraft Systems, has been modified for a distributed memory/massively parallel computing environment. The parallel code is operational on an SGI network, Cray J90 and C90 vector machines, SGI Power Challenge, and Cray T3D and IBM SP2 massively parallel machines. Parallel Virtual Machine (PVM) is the message passing protocol for portability to various architectures. A domain decomposition technique was developed which enforces dynamic load balancing to improve solution speed and memory requirements. A host/node algorithm distributes the tasks. The solver parallelizes very well, and scales with the number of processors. Partially parallelized and non-parallelized tasks consume most of the wall clock time in a very fine grain environment. Timing comparisons on a Cray C90 demonstrate that Parallel SPLITFLOW runs 2.4 times faster on 8 processors than its non-parallel counterpart autotasked over 8 processors.

Domel, Neal D.↗
NASA NTRS1996

Research in Parallel Algorithms and Software for Computational Aerosciences

Phase 1 is complete for the development of a computational fluid dynamics CFD) parallel code with automatic grid generation and adaptation for the Euler analysis of flow over complex geometries. SPLITFLOW, an unstructured Cartesian grid code developed at Lockheed Martin Tactical Aircraft Systems, has been modified for a distributed memory/massively parallel computing environment. The parallel code is operational on an SGI network, Cray J90 and C90 vector machines, SGI Power Challenge, and Cray T3D and IBM SP2 massively parallel machines. Parallel Virtual Machine (PVM) is the message passing protocol for portability to various architectures. A domain decomposition technique was developed which enforces dynamic load balancing to improve solution speed and memory requirements. A host/node algorithm distributes the tasks. The solver parallelizes very well, and scales with the number of processors. Partially parallelized and non-parallelized tasks consume most of the wall clock time in a very fine grain environment. Timing comparisons on a Cray C90 demonstrate that Parallel SPLITFLOW runs 2.4 times faster on 8 processors than its non-parallel counterpart autotasked over 8 processors.

Domel, Neal D.↗