SEARCH · Search NASA

Results for “parallel cluster”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 487 records · Page 27

All sources NASA NTRS DOE OSTI

NASA NTRS1984

Oxygen diffusion in alpha-Al2O3

Oxygen self diffusion coefficients were determined in single crystal alpha-Al2O3 using the gas exchange technique. The samples were semi-infinite slabs cut from five different boules with varying background impurities. The diffusion direction was parallel to the c-axis. The tracer profiles were determined by two techniques, single spectrum proton activation and secondary ion mass spectrometry. The SIMS proved to be a more useful tool. The determined diffusion coefficients, which were insensitive to impurity levels and oxygen partial pressure, could be described by D = .00151 exp (-572kJ/RT) sq m/s. The insensitivities are discussed in terms of point defect clustering. Two independent models are consistent with the findings, the first considers the clusters as immobile point defect traps which buffer changes in the defect chemistry. The second considers clusters to be mobile and oxygen diffusion to be intrinsic behavior, the mechanism for oxygen transport involving neutral clusters of Schottky quintuplets.

Cawley, J. D.↗

DOE OSTI2023

Porting fragmentation methods to GPUs using an OpenMP API: Offloading the resolution-of-the-identity second-order Møller–Plesset perturbation method

Here, using an OpenMP Application Programming Interface, the resolution-of-the-identity second-order Møller–Plesset perturbation (RI-MP2) method has been off-loaded onto graphical processing units (GPUs), both as a standalone method in the GAMESS electronic structure program and as an electron correlation energy component in the effective fragment molecular orbital (EFMO) framework. First, a new scheme has been proposed to maximize data digestion on GPUs that subsequently linearizes data transfer from central processing units (CPUs) to GPUs. Second, the GAMESS Fortran code has been interfaced with GPU numerical libraries (e.g., NVIDIA cuBLAS and cuSOLVER) for efficient matrix operations (e.g., matrix multiplication, matrix decomposition, and matrix inversion). The standalone GPU RI-MP2 code shows an increasing speedup of up to 7.5× using one NVIDIA V100 GPU with one IBM 42-core P9 CPU for calculations on fullerenes of increasing size from 40 to 260 carbon atoms using the 6-31G(d)/cc-pVDZ-RI basis sets. A single Summit node with six V100s can compute the RI-MP2 correlation energy of a cluster of 175 water molecules using the correlation consistent basis sets cc-pVDZ/cc-pVDZ-RI containing 4375 atomic orbitals and 14 700 auxiliary basis functions in ~0.85 h. In the EFMO framework, the GPU RI-MP2 component shows near linear scaling for a large number of V100s when computing the energy of an 1800-atom mesoporous silica nanoparticle in a bath of 4000 water molecules. The parallel efficiencies of the GPU RI-MP2 component with 2304 and 4608 V100s are 98.0% and 96.1%, respectively.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Asynchronous domain decomposition methods for nonlinear PDEs

One- and two-level parallel asynchronous methods for the numerical solution of nonlinear systems of equations, especially those arising from (nonlinear) partial differential equations, are studied. The proposed methods are based on domain decomposition techniques. Local convergence theorems are presented in several cases, with appropriate hypotheses. Computational results on a shared memory multiprocessor machine for various problems exhibiting nonlinearities are reported, illustrating the potential of these asynchronous methods, especially for heterogeneous clusters.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2003

Transverse Dimensions of Chorus in the Source Region

We report measurement of whistler-mode chorus by the four Cluster spacecraft at close separations. We focus our analysis on the generation region close to the magnetic equatorial plane at a radial distance of 4.4 Earth's radii. We use both linear and rank correlation analysis to define perpendicular dimensions of the sources of chorus elements below one half of the electron cyclotron frequency. Correlation is significant throughout the range of separation distances of 60-260 km parallel to the field line and 7-100 km in the perpendicular plane. At these scales, the correlation coefficient is independent for parallel separations, and decreases with perpendicular separation. The observations are consistent with a statistical model of the source region assuming individual sources as gaussian peaks of radiated power with a common half-width of 35 km perpendicular to the magnetic field. This characteristic scale is comparable to the wavelength of observed waves.

Santolik, O.↗

DOE OSTI2020

Modular performance prediction for scientific workflows using Machine Learning

Scientific workflows provide an opportunity for declarative computational experiment design in an intuitive and efficient way. A distributed workflow is typically executed on a variety of resources, and it uses a variety of computational algorithms or tools to achieve the desired outcomes. Such a variety imposes additional complexity in scheduling these workflows on large scale computers. As computation becomes more distributed, insights into expected workload that a workflow presents become critical for effective resource allocation. In this paper, we present a modular framework that leverages Machine Learning for creating precise performance predictions of a workflow. The central idea is to partition a workflow in such a way that makes the task of forecasting each atomic unit manageable and gives us a way to combine the individual predictions efficiently. We recognize a combination of an executable and a specific physical resource as a single module. This gives us a handle to characterize workload and machine power as a single unit of prediction. Overall, our modular technique of creating atomic modules and deployment of longest-path approach to estimate workflow performance, allows the framework to adapt to highly complex nested directed acyclic workflows and scale to new scenarios, since it does not make assumptions of underlying workflow structure. We present performance estimation results of independent workflow modules executed on the XSEDE SDSC Comet cluster using various Machine Learning algorithms. The results provide insights into the behavior and effectiveness of different algorithms in the context of scientific workflow performance prediction.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2003

Density Irregularities Inside the Plasmasphere: Cluster Observations

The electron density profiles derived from the EFW and WHISPER instruments onboard the four Cluster spacecraft reveal small-scale density irregularities inside the plasmasphere and at its outer boundary, the plasmapause. We review statistics of the plasmapause position and thickness, as well as statistics of these density structures. We focus on a particular plasmasphere crossing on 11 April 2002, with several density irregularities, as well as two plasma tails, observed by Cluster on the legs of the inbound and outbound passes. We derive the density gradient vectors from simultaneous density measurements by the four spacecraft. We determine also the normal velocity of the surface of these irregularities, assuming they are planar boundaries, from the time delays between density structures in the four individual density profiles. These new observations yield novel insights about (1) the dimensions of plasma irregularities across and parallel to magnetic field lines, (2) the dynamics of these small-scale structures, (3) their bulk velocities, and (4) their position and distribution as a function of the magnetic local time (MLT) and the geomagnetic conditions (as determined by Kp).

Darrouzet, F.↗

NASA NTRS1998

The P-Mesh: A Commodity-based Scalable Network Architecture for Clusters

We designed a new network architecture, the P-Mesh which combines the scalability and fault resilience of a torus with the performance of a switch. We compare the scalability, performance, and cost of the hub, switch, torus, tree, and P-Mesh architectures. The latter three are capable of scaling to thousands of nodes, however, the torus has severe performance limitations with that many processors. The tree and P-Mesh have similar latency, bandwidth, and bisection bandwidth, but the P-Mesh outperforms the switch architecture (a lower bound for tree performance) on 16-node NAB Parallel Benchmark tests by up to 23%, and costs 40% less. Further, the P-Mesh has better fault resilience characteristics. The P-Mesh architecture trades increased management overhead for lower cost, and is a good bridging technology while the price of tree uplinks is expensive.

Nitzberg, Bill↗

DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗

NASA NTRS1996

The Structure and Stability of B(n)H(+) Clusters

The geometries of the B(n)H(+) clusters for n=1-13 have been optimized at the B3LYP level of theory. Excluding B2H(+) all clusters are low-spin coupled. The structures appear to be related to the bare B(+)(n) clusters in two ways: 1) an H atom is added to the B(+)(n) cluster or 2) a BH is added to the B(+)(n-1) cluster. The B(+)(n)-H binding energies are computed at the B3LYP level of theory, and calibrated n using the CCSD(T) level of theory. The computed results tend to fall between the experimental best estimates and the experimental lower bounds. The B(+)(n)-H binding energies show an inverse correspondence with the B+(n-1)-B values) while the B(+)(n-1)-B and B(+)(n-1)-BH results tend to parallel each other.

Ricca, Alessandra↗

DOE OSTI2022

Theoretical study of the CO 2 –O 2 van der Waals complex: potential energy surface and applications

A four-dimensional-potential energy surface (4D-PES) of the atmospherically relevant carbon dioxide–oxygen molecule (CO 2 –O 2 ) van der Waals complex is mapped using the ab initio explicitly correlated coupled cluster method with single, double, and perturbative triple excitations (UCCSD(T)-F12b), and extrapolation to the complete basis set (CBS) limit using the cc-pVTZ-F12/cc-pVQZ-F12 bases and the l –3 formula. An analytic representation of the 4D-PES was fitted using the method of interpolating moving least squares (IMLS). These calculations predict that the most stable configuration of CO 2 –O 2 complex corresponds to a planar slipped-parallel structure with a binding energy of V ~ –243 cm –1 . Another isomer is found on the PES, corresponding to a non-planar cross-shaped structure, with V ~ –218 cm –1 . The transition structure connecting the two minima is found at V ~ –211 cm –1 . We also performed comparisons with some CO 2 –X van der Waals complexes. Moreover, we provide a SAPT analysis of this molecular system. Then, we discuss the complexation induced shifts of CO 2 and O 2 . Afterwards, this new 4D-PES is employed to compute the second virial coefficient including temperature dependence. A comparison between quantities obtained in our calculations and those from experiments found close agreement attesting to the high quality of the PES and to the importance of considering a full description of the anisotropic potential for the derivation of thermophysical properties of CO 2 –O 2 mixtures.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Comparing the Performance of Julia on CPUs versus GPUs and Julia-MPI versus Fortran-MPI: a case study with MPAS-Ocean (Version 7.1)

Abstract. Some programming languages are easy to develop at the cost of slow execution, while others are fast at runtime but much more difficult to write. Julia is a programming language that aims to be the best of both worlds – a development and production language at the same time. To test Julia's utility in scientific high-performance computing (HPC), we built an unstructured-mesh shallow water model in Julia and compared it against an established Fortran-MPI ocean model, the Model for Prediction Across Scales–Ocean (MPAS-Ocean), as well as a Python shallow water code. Three versions of the Julia shallow water code were created: for single-core CPU, graphics processing unit (GPU), and Message Passing Interface (MPI) CPU clusters. Comparing identical simulations revealed that our first version of the Julia model was 13 times faster than Python using NumPy, where both used an unthreaded single-core CPU. Further Julia optimizations, including static typing and removing implicit memory allocations, provided an additional 10–20× speed-up of the single-core CPU Julia model. The GPU-accelerated Julia code was almost identical in terms of performance to the MPI parallelized code on 64 processes, an unexpected result for such different architectures. Parallelized Julia-MPI performance was identical to Fortran-MPI MPAS-Ocean for low processor counts and ranges from 2× faster to 2× slower for higher processor counts. Our experience is that Julia development is fast and convenient for prototyping but that Julia requires further investment and expertise to be competitive with compiled codes. We provide advice on Julia code optimization for HPC systems.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Streamlined spatial and environmental expression signatures characterize the minimalist duckweed Wolffia australiana

Single-cell genomics permits a new resolution in the examination of molecular and cellular dynamics, allowing global, parallel assessments of cell types and cellular behaviors through development and in response to environmental circumstances, such as interaction with water and the light–dark cycle of the Earth. Here, we leverage the smallest, and possibly most structurally reduced, plant, the semiaquaticWolffia australiana, to understand dynamics of cell expression in these contexts at the whole-plant level. We examined single-cell-resolution RNA-sequencing data and foundWolffiacells divide into four principal clusters representing the above- and below-water-situated parenchyma and epidermis. Although these tissues share transcriptomic similarity with model plants, they display distinct adaptations thatWolffiahas made for the aquatic environment. Within this broad classification, discrete subspecializations are evident, with select cells showing unique transcriptomic signatures associated with developmental maturation and specialized physiologies. Assessing this simplified biological system temporally at two key time-of-day (TOD) transitions, we identify additional TOD-responsive genes previously overlooked in whole-plant transcriptomic approaches and demonstrate that the core circadian clock machinery and its downstream responses can vary in cell-specific manners, even in this simplified system. Distinctions between cell types and their responses to submergence and/or TOD are driven by expression changes of unexpectedly few genes, characterizingWolffiaas a highly streamlined organism with the majority of genes dedicated to fundamental cellular processes.Wolffiaprovides a unique opportunity to apply reductionist biology to elucidate signaling functions at the organismal level, for which this work provides a powerful resource.

Biochemistry & Molecular Biology↗

DOE OSTI2019

Parallelization of a Proxy Transport App Using ComputeCPP and SYCL

This document details the attempts to parallelize a multi-group Monte Carlo proxy app using SYCL and the ComputeCPP Community Edition compiler. SYCL is a standard set by the Khronos Group and is described as a, “cross-platform abstraction layer that builds on the underlying concepts, portability and efficiency of OpenCL that enables code for heterogeneous processors to be written in a “single-source” style using completely standard C++.” ComputeCpp Community Edition (CE) is a heterogeneous parallel programming platform that provides a conformant implementation of the SYCL™ 1.2.1 Khronos specification. ComputeCPP provides a compiler and an SDK containing a build system to improve the usability of the compiler. The supported OpenCL 1.2 platforms for ComputeCpp are AMD® and Intel®, with experimental support for PTX which is used on Nvidia graphics cards as well as experimental support for ARM chips. All testing reported in this document was done on the Darwin computer cluster using an Nvidia GTX Titan X graphics card. Since ComputeCPP does not support using this card with OpenCL, ComputeCPP’s experimental PTX64 bit-code generation was used to generate device code.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

NASA NTRS1982

Influence of layer thickness on the strength of angle-ply laminates

Experimental results are presented showing that the strength and toughness of finite width angle-ply laminates can be increased significantly by using an alternating layer stacking sequence as opposed to a clustered configuration. The ultimate tensile stress of an alternating plus/minus theta laminate of the form (+ or - theta) sub 2 sub s can be much as 1.5 times that of a clustered configuration of the form theta sub 2/-theta sub 2 sub s. Further, the toughness of the alternating layer configuration can be as much as 2.7 times that of the clustered configuration. These differences are explained analytically through consideration of the influence of layer thickness on the magnitude of the interlaminar shear stress and by examination of failed specimens. It is shown that the two laminate configurations exhibit distinctly different failure modes for some fiber angles. Both laminate configurations exhibit catastrophic failure with the damage limited essentially to a small region defined by the length of a single crack across the width of the specimen, parallel to the fiber direction. Results are presented for T300/5208 graphite-epoxy for fiber orientations of 10, 30, and 45 deg.

Herakovich, C. T.↗

NASA NTRS1992

Hubble illuminates the universe

Latest observations by the Hubble Space Telescope (HST) are described, including the first 'parallel' observations (on January 6, 1992) by the two of the Hubble's instruments of two different targets at the same time. On this date, the faint-object camera made images of the quasar 3C 273 in Virgo, while the wide-field and planetary camera recorded an adjacent field. The new HST images include those of the nucleus and the jet of M85, the giant elliptical galaxy at the heart of the Virgo cluster, and what appears to be a black hole of mass 2.6 billion solar masses in M87, and an image of N66, a planetary nebula in the LMC. Other images yield evidence of 'blue stragglers' in the core of 47 Tucanae, a globular cluster about 16,000 light-years from earth. The Goddard spectrograph recorded the spectrum of the star Capella at very high wavelength resolution, which made it possible to measure deuterium from the Big Bang.

Maran, Stephen P.↗

DOE OSTI2025

Using Apptainer in a Pilot-based Distributed Workload

GlideinWMS is a pilot and pressure-based workload manager for distributed scientific computing. Many experiments like CMS and Fermilab’s Neutrino experiments use it to provision elastic clusters for their analysis and simulations, split into close to a million concurrent jobs. Most user jobs require containers, and the pilots use Apptainer to set up the desired platform. For the pilots that run as regular batch jobs, Apptainer is safer, lighter, and easier to use than other containerization solutions. Many images used by the pilots are expanded SIF images distributed via the CernVM-FS: this combination is very efficient. At Fermilab, for example, we store on GitHub Dockerfiles that mimic the platform in the worker nodes of local clusters. GitHub workflows build and push the images to Docker Hub, and a service periodically pulls and converts them to the expanded SIF images in the CernVM-FS, so the scientists can find a familiar environment everywhere. Apptainer has also been used to run services inside the pilot jobs, like benchmarks that characterize the worker node being used, or a Triton Inference Server that allows sharing a GPU with all the jobs that run in parallel on a node.

Mambelli, Marco [Fermilab] (ORCID:0000000294892681↗

DOE OSTI2019

Stochastic density functional theory

Linear-scaling implementations of density functional theory (DFT) reach their intended efficiency regime only when applied to systems having a physical size larger than the range of their Kohn–Sham density matrix (DM). This causes a problem since many types of large systems of interest have a rather broad DM range and are therefore not amenable to analysis using DFT methods. For this reason, the recently proposed stochastic DFT (sDFT), avoiding exhaustive DM evaluations, is emerging as an attractive alternative linear-scaling approach. This review develops a general formulation of sDFT in terms of a (non)orthogonal basis representation and offers an analysis of the statistical errors (SEs) involved in the calculation. Using a new Gaussian-type basis-set implementation of sDFT, applied to water clusters and silicon nanocrystals, it demonstrates and explains how the standard deviation and the bias depend on the sampling rate and the system size in various types of calculations. We also develop a basis-set embedded-fragments theory, demonstrating its utility for reducing the SEs for energy, density of states and nuclear force calculations. Finally, we discuss the algorithmic complexity of sDFT, showing it has CPU wall-time linear-scaling. Lastly, the method parallelizes well over distributed processors with good scalability and therefore may find use in the upcoming exascale computing architectures.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2019

Making many-body interactions nearly pairwise additive: The polarized many-body expansion approach

The Many-Body Expansion (MBE) is a useful tool to simulate condensed phase chemical systems, often avoiding the steep computational cost of usual electronic structure methods. However, it often requires higher than 2-body terms to achieve quantitative accuracy. In this work, we propose the Polarized MBE (PolBE) method where each MBE energy contribution is treated as an embedding problem. In each energy term, a smaller fragment is embedded into a larger, polarized environment and only a small region is treated at the high-level of theory using embedded mean-field theory. The role of polarized environment was found to be crucial in providing quantitative accuracy at the 2-body level. PolBE accurately predicts noncovalent interaction energies for a number of systems, including CO 2 , water, and hydrated ion clusters, with a variety of interaction mechanisms, from weak dispersion to strong electrostatics considered in this work. We further demonstrate that the PolBE interaction energy is predominantly pairwise unlike the usual vacuum MBE that requires higher-order terms to achieve similar accuracy. We numerically show that PolBE often performs better than other widely used embedded MBE methods such as the electrostatically embedded MBE. Finally,owing to the lack of expensive diagonalization of Fock matrices and its embarrassingly parallel nature, PolBE is a promising way to access condensed phase systems with hybrid density functionals that are difficult to treat with currently available methods.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗