Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed parallelization”

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 1,297 records · Page 72

Decentralized Interleaving of Parallel-Connected Buck Converters

We present a decentralized control strategy that yields switch interleaving for parallel-connected dc-dc buck converters. Compared to state-of-the-art methods that are distributed at best, the proposed architecture requires no communication, and hence, presents a variety of advantages with regard to reliability, modularity, and cost. The method is based on the digital implementation of the dynamics of a Lienard-type oscillator circuit as the controller for the converters. Each controller only requires the locally measured output current to synthesize the pulsewidth modulation (PWM) carrier waveform. The intrinsic electrical coupling between converters drives the nonlinear-oscillator-based controllers to converge to an interleaved state with uniform phase spacing across PWM carriers, independent of the number of converters, the load, and initial conditions. We provide analytical guarantees for existence and stability of the interleaved state as well as extensive hardware results for a system of five 120 W 48 V-to-12 V dc-dc buck converters that demonstrate convergence to the interleaved state in the face of a variety of large-signal disturbances.

24 POWER TRANSMISSION AND DISTRIBUTION↗

The features of X-ray topographic contrast formation in silicon with dislocation clusters

The features of formation of diffraction images of edge dislocation sets forming clusters (of two, three and more dislocations) as well as small-angle dislocation boundaries (walls) have been studied. A variety of diffraction effects of wave fields created in strongly distorted crystals regions along dislocation lines have been observed. Various intensity interference effects of rescattering and internal reflection of the newly formed and already existing wave fields on thickness distributions of intensity for the case of presence in the same glide plane of edge dislocations with parallel and anti-parallel Burgers vectors were discovered.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

symPACK v2.0

SymPACK is a parallel direct solver for sparse symmetric systems of linear equations. SymPACK is implemented for large- scale distributed-memory platforms. It employs several innovative ideas, including the use of an asynchronous task paradigm, one-sided communication, and dynamic scheduling.

Ng, EsmondG↗

DASSA v0.0.1

DASSA (Parallel DAS Data Storage and Analysis) provides a data storage engine and analysis engine for data from distributed acoustic sensing and other methods. It supports various data analysis operations, from FFT , signal filter, cross-correlation, compression, stacking etc.

Dong, Bin↗

Qthreads Support for MPICH

SAND2024-00944O Qthread Support for MPICH is software that provides additions needed to enable the use of the Qthreads library. The high-performance message passing interface (MPICH) is an open-source implementation of MPI mainly developed and distributed by Argonne National Laboratory. Qthreads is a lightweight, user-level threading library developed and distributed by Sandia National Laboratories. MPICH currently supports Posix threads, Windows threads, and Argobots. This software enables parallel programs built with the MPICH implementation of MPI to use Qthreads user-level threads rather than Posix system-level threads. The software uses existing infrastructure in MPICH to interface to the Qthreads library. The existing interfaces in MPICH allow for creating, destroying, and managing the execution of multiple threads within a process and this software translates these calls to the equivalent Qthreads library functions. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Ciesko, Jan↗

Use of Neutron Flux Calculated by Shift in a Grizzly Reactor Pressure Vessel Fracture Simulation

The reactor pressure vessel (RPV) plays the critical role of containing the reactor and coolant in a light water reactor nuclear power plant, and must be able to safely perform this function under a variety of normal and off-normal transient loading conditions. The RPV is subjected to harsh environmental conditions (elevated temperature and high neutron flux) whenever the plant is operating, which leads to embrittlement of the steel over time. RPVs contain populations of flaws introduced during the manufacturing process, and the primary safety concern is that during a transient event, a fracture could initiate at the site of one of these flaws and lead to rupture of the RPV. RPVs are very rugged structures, and the probability of this occurring is very low, but as the RPV's steel becomes embrittled over time, its resistance to fracture decreases and this becomes more likely. Assessing the likelihood of RPV fracture during a transient event involves performing a probabilistic fracture mechanics analysis, in which random sampling procedures are used to assess the probability of fracture of a population of flaws. Grizzly offers unique capabilities for modeling the RPV using 1D, 2D, or 3D representations, taking advantage of parallel computing for this type of analysis. One of the important inputs to Grizzly is the spatial distribution of the neutron fluence, which has a large impact on the material embrittlement, and should thus be characterized as accurately as possible. The VERA core simulator developed by the CASL program takes advantage of high performance computing resources to perform high-fidelity multiphysics simulations of reactor physics, including the effects of neutron transport, fuel performance, and thermal hydraulics. Recently a capability was developed to also evaluate neutron fluxes away from the reactor core through the Shift code. This allows for a detailed 3D map of the spatial variation of the fluence in components such as the RPV to be computed, which is ideal for use with Grizzly. This report documents a procedure developed to use the fluences computed in Shift in a Grizzly simulation, which allows for improved realisim in the prediction of the effects of environmental exposure on propensity for reactor pressure vessel fracture. This capability demonstrated on RPVs with multiple types of configurations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

THE INFRARED SPECTRAL PROPERTIES OF MAGELLANIC CARBON STARS

The Infrared Spectrograph on the Spitzer Space Telescope observed 184 carbon stars in the Magellanic Clouds. This sample reveals that the dust-production rate (DPR) from carbon stars generally increases with the pulsation period of the star. The composition of the dust grains follows two condensation sequences, with more SiC condensing before amorphous carbon in metal-rich stars, and the order reversed in metal-poor stars. MgS dust condenses in optically thicker dust shells, and its condensation is delayed in more metal-poor stars. Metal-poor carbon stars also tend to have stronger absorption from C{sub 2}H{sub 2} at 7.5 μ m. The relation between DPR and pulsation period shows significant apparent scatter, which results from the initial mass of the star, with more massive stars occupying a sequence parallel to lower-mass stars, but shifted to longer periods. Accounting for differences in the mass distribution between the carbon stars observed in the Small and Large Magellanic Clouds reveals a hint of a subtle decrease in the DPR at lower metallicities, but it is not statistically significant. The most deeply embedded carbon stars have lower variability amplitudes and show SiC in absorption. In some cases they have bluer colors at shorter wavelengths, suggesting that the central star is becoming visible. These deeply embedded stars may be evolving off of the asymptotic giant branch and/or they may have non-spherical dust geometries.

79 ASTRONOMY AND ASTROPHYSICS↗

Toward local core outlet temperature monitoring in gas-cooled nuclear reactors using distributed fiber-optic temperature sensors

Gas-cooled nuclear reactors operate at temperatures up to 950 °C with significant spatial variations in power generation and coolant flow through hundreds of parallel flow channels, resulting in complex mixing at the core outlet. The high temperatures and complex mixing can damage downstream components, challenge reactor calorimetry for power determination, and result in significant conservatism in calculated peak fuel temperatures, which ultimately limits the total power output. Directly measuring each gas stream individually is unrealistic using single point thermocouples, requiring more robust sensing techniques. Fiber-optic sensors are resilient to high temperatures (up to 1,000 °C) and radiation damage. Moreover, distributed measurements can be made along the length of one fiber, making them potential candidates for monitoring local core outlet temperatures to improve core calorimetry and identify hot channels. Here, to the authors’ knowledge, this manuscript is the first to report spatially distributed fiber optic temperature measurements to quantify mixing at the outlet of a relevant orifice plate under prototypic temperature and flow regimes to assess the feasibility of using fiber-optic sensors for distributed measurements of coolant temperature in gas-cooled reactors. A single optical fiber captured dynamic changes in local temperatures, whereas the mixed outlet temperature exhibited a muted response and could not identify which channels were responsible for the change in the mixed outlet temperature. The discussion focuses on potential challenges for deploying distributed optical fibers in gas-cooled reactors, including the effects of vibrations, radiation-induced signal attenuation and drift, and routing of the fiber while minimizing flow obstructions.

42 ENGINEERING↗

Improving Data Availability for Better Access Performance: A Study on Caching Scientific Data on Distributed Workstations

Client-side data caching serves as an excellent mechanism to store and analyze the rapidly growing amount of scientific data. In our previous work, we built a distributed local cache on unreliable desktop storage contributions. This offers several desirable properties, such as performance impedance matching, improved space utilization, and high parallel I/O bandwidth. Such a low-cost, best-effort cache, however, is faced with the vagaries of storage node availability: these donated machines may be significantly less reliable than dedicated systems and cannot be controlled centrally. In this paper, we address %the tradeoffs between techniques that favor %availability or performance when it comes to cache management. the performance impact of data availability in the distributed scientific data cache setting. We then present a novel approach to storage cache management, {\em remote partial data recovery (RPDR)}. We compare our approach to two standard techniques, namely replication and erasure coding, both extended to the target caching environment. Our evaluation uses a trace-driven simulation parameterized with benchmarking results from our distributed cache prototype. The results with multiple real-world traces indicate that RPDR significantly outperforms both replication and erasure coding in many cases and overall the combination of RPDR and erasure coding yields the best performance.

99 GENERAL AND MISCELLANEOUS↗

Distributed control of reactive power flow in a radial distribution circuit with high photovoltaic penetration

We show how distributed control of reactive power can serve to regulate voltage and minimize resistive losses in a distribution circuit that includes a significant level of photovoltaic (PV) generation. To demonstrate the technique, we consider a radial distribution circuit with a single branch consisting of sequentially-arranged residential-scale loads that consume both real and reactive power. In parallel, some loads also have PV generation capability. We postulate that the inverters associated with each PV system are also capable of limited reactive power generation or consumption, and we seek to find the optimal dispatch of each inverter's reactive power to both maintain the voltage within an acceptable range and minimize the resistive losses over the entire circuit. We assume the complex impedance of the distribution circuit links and the instantaneous load and PV generation at each load are known. We compare the results of the optimal dispatch with a suboptimal local scheme that does not require any communication. On our model distribution circuit, we illustrate the feasibility of high levels of PV penetration and a significant (20% or higher) reduction in losses.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Real-time and post-hoc compression for data from Distributed Acoustic Sensing

Distributed Acoustic Sensing (DAS) is an emerging sensing technology that records the strain-rate along fiber optic cables at high spatial and temporal resolution. This technique is becoming a popular tool in seismology, hydrology, and other subsurface monitoring applications. However, due to the large coverage (10’s of km) and high density of measurements (1m spacing at 100’s of Hz), a DAS installation could produce terabytes of data records per day. Because many DAS instruments are deployed in remote locations, this large data size poses significant challenges to its transfer and storage. In this paper, we explore lossless compression methods to reduce the storage requirement in both real-time and post-hoc scenarios. Here we propose a two-stage compression method to improve the compression ratio and compression speed. This two-stage compression method could reduce the storage requirement by 40%, which is 20% more than other lossless methods, such as ZSTD. We demonstrate that the compression method could complete its operation well before the DAS instrument needs to output the next file, making it suitable for real-time DAS acquisition. We also implement a parallel compression method for a post-hoc scenario and demonstrate that our method could effectively utilize a parallel computer. With 256 CPU cores, our parallel compression method achieves the speed of 26GB/second.

58 GEOSCIENCES↗

FuseIM: Fusing Probabilistic Traversals for Influence Maximization on Exascale Systems

Probabilistic breadth-first traversals (BPTs) are used in many network science and graph machine learning applications. In this paper, we are motivated by the application of BPTs in stochastic diffusion-based graph problems such as influence maximization. These applications heavily rely on BPTs to implement a Monte-Carlo sampling step for their approximations. Given the large sampling complexity, stochasticity of the diffusion process, and the inherent irregularity in real-world graph topologies, efficiently parallelizing these BPTs remains significantly challenging. In this paper, we present a new algorithm to fuse massive number of concurrently executing BPTs with random starts on the input graph. Our algorithm is designed to fuse BPTs by combining separate traversals into a unified frontier on distributed multi-GPU systems. To show the general applicability of the fused BPT technique, we have incorporated it into two state-of-the-art influence maximization parallel implementations (gIM and Ripples). Our experiments on up to 4K nodes of the OLCF Frontier supercomputer (32,768 GPUs and 196K CPU cores) show strong scaling behavior, and that fused BPTs can improve the performance of these implementations up to 34x (for gIM) and ~360x (for Ripples).

Neff, Reece W.↗

Microscopic Gold Particle-Based Fiducial Markers for Proton Therapy of Prostate Cancer

Purpose: We examined the feasibility of using fiducial markers composed of microscopic gold particles and human-compatible polymers as a means to overcome current problems with conventional macroscopic gold fiducial markers, such as dose reduction and artifact generation, in proton therapy for prostate cancer. Methods and Materials: We examined two types of gold particle fiducial marker interactions: that with diagnostic X-rays and with a therapeutic proton beam. That is, we qualitatively and quantitatively compared the radiographic visibility of conventional gold and gold particle fiducial markers and the CT artifacts and dose reduction associated with their use. Results: The gold particle fiducials could be easily distinguished from high-density structures, such as the pelvic bone, in diagnostic X-rays but were nearly transparent to a proton beam. The proton dose distribution was distorted <5% by the gold particle fiducials with a 4.9% normalized gold density; this was the case even in the worst configuration (i.e., parallel alignment with a single-direction proton beam). In addition, CT artifacts were dramatically reduced for the gold particle mixture. Conclusion: Mixtures of microscopic gold particles and human-compatible polymers have excellent potential as fiducial markers for proton therapy for prostate cancer. These include good radiographic visibility, low distortion of the depth-dose distribution, and few CT artifacts.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Image quality of microcalcifications in digital breast tomosynthesis: Effects of projection-view distributions

Purpose: To analyze the effects of projection-view (PV) distribution on the contrast and spatial blurring of microcalcifications on the tomosynthesized slices (X-Y plane) and along the depth (Z) direction for the same radiation dose in digital breast tomosynthesis (DBT). Methods: A GE GEN2 prototype DBT system was used for acquisition of DBT scans. The system acquires PV images from 21 angles in 3 deg. increments over a {+-}30 deg. range. From these acquired PV images, the authors selected six subsets of PV images to simulate DBT of different angular ranges and angular increments. The number of PV images in each subset was fixed at 11 to simulate a constant total dose. These different PV distributions were subjectively divided into three categories: uniform group, nonuniform central group, and nonuniform extreme group with different angular ranges and angular increments. The simultaneous algebraic reconstruction technique (SART) was applied to each subset to reconstruct the DBT slices. A selective diffusion regularization method was employed to suppress noise. The image quality of microcalcifications in the reconstructed DBTs with different PV distributions was compared using the DBT scans of an American College of Radiology phantom and three human subjects. The contrast-to-noise ratio (CNR) and the full width at half maximum (FWHM) of the line profiles of microcalcifications within their in-focus DBT slices (parallel to detector plane) and the FWHMs of the interplane artifact spread function (ASF) in the Z-direction (perpendicular to detector plane) were used as image quality measures. Results: The results indicate that DBT acquired with a large angular range or, for an equal angular range,with a large fraction of PVs at large angles yielded superior ASF with smaller FWHM in the Z-direction. PV distributions with a narrow angular range or a large fraction of PVs at small angles had stronger interplane artifacts. In the X-Y focal planes, the effect of PV distributions on spatial blurring depended on the directions. In the X-direction (perpendicular to the chestwall), the normalized line profiles of the calcifications reconstructed with the different PV distributions were similar in terms of FWHM; the differences in the FWHMs between the different PV distributions were less than half a pixel. In the Y-direction (x-ray source motion), the normalized line profiles of the calcifications reconstructed with PVs acquired with a narrow angular range or a large fraction of PVs at small angles had smaller FWHMs and thus less blurring of the line profiles. In addition, PV distributions with a narrow angular range or a large fraction of PVs at small angles yielded slightly higher CNR than those with a wide angular range for small, subtle microcalcifications; however, PV distributions had no obvious effect on CNR for relatively large microcalcifications. Conclusions: PV distributions affect the image quality of DBT. The relative importance of the impact depends on the characteristics of the signal and the direction (perpendicular or parallel) relative to the direction of x-ray source motion. For a given number of PVs, the angular range and the distribution of the PVs affect the degree of in-plane and interplane blurring in opposite ways. The design of the scan parameters of tomosynthesis systems would require proper consideration of the characteristics of the signals of interest and the potential trade-off of the image quality of different types of signals.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Hierarchical fractional-step approximations and parallel kinetic Monte Carlo algorithms

We present a mathematical framework for constructing and analyzing parallel algorithms for lattice kinetic Monte Carlo (KMC) simulations. The resulting algorithms have the capacity to simulate a wide range of spatio-temporal scales in spatially distributed, non-equilibrium physiochemical processes with complex chemistry and transport micro-mechanisms. Rather than focusing on constructing exactly the stochastic trajectories, our approach relies on approximating the evolution of observables, such as density, coverage, correlations and so on. More specifically, we develop a spatial domain decomposition of the Markov operator (generator) that describes the evolution of all observables according to the kinetic Monte Carlo algorithm. This domain decomposition corresponds to a decomposition of the Markov generator into a hierarchy of operators and can be tailored to specific hierarchical parallel architectures such as multi-core processors or clusters of Graphical Processing Units (GPUs). Based on this operator decomposition, we formulate parallel Fractional step kinetic Monte Carlo algorithms by employing the Trotter Theorem and its randomized variants; these schemes, (a) are partially asynchronous on each fractional step time-window, and (b) are characterized by their communication schedule between processors. The proposed mathematical framework allows us to rigorously justify the numerical and statistical consistency of the proposed algorithms, showing the convergence of our approximating schemes to the original serial KMC. The approach also provides a systematic evaluation of different processor communicating schedules. We carry out a detailed benchmarking of the parallel KMC schemes using available exact solutions, for example, in Ising-type systems and we demonstrate the capabilities of the method to simulate complex spatially distributed reactions at very large scales on GPUs. Finally, we discuss work load balancing between processors and propose a re-balancing scheme based on probabilistic mass transport methods.

97 MATHEMATICS AND COMPUTING↗

Evaluation of normalized metal artifact reduction (NMAR) in kVCT using MVCT prior images for radiotherapy treatment planning

Purpose: To evaluate the metal artifacts in kilovoltage computed tomography (kVCT) images that are corrected using a normalized metal artifact reduction (NMAR) method with megavoltage CT (MVCT) prior images.Methods: Tissue characterization phantoms containing bilateral steel inserts are used in all experiments. Two MVCT images, one without any metal artifact corrections and the other corrected using a modified iterative maximum likelihood polychromatic algorithm for CT (IMPACT) are translated to pseudo-kVCT images. These are then used as prior images without tissue classification in an NMAR technique for correcting the experimental kVCT image. The IMPACT method in MVCT included an additional model for the pair/triplet production process and the energy dependent response of the MVCT detectors. An experimental kVCT image, without the metal inserts and reconstructed using the filtered back projection (FBP) method, is artificially patched with the known steel inserts to get a reference image. The regular NMAR image containing the steel inserts that uses tissue classified kVCT prior and the NMAR images reconstructed using MVCT priors are compared with the reference image for metal artifact reduction. The Eclipse treatment planning system is used to calculate radiotherapy dose distributions on the corrected images and on the reference image using the Anisotropic Analytical Algorithm with 6 MV parallel opposed 5 × 10 cm{sup 2} fields passing through the bilateral steel inserts, and the results are compared. Gafchromic film is used to measure the actual dose delivered in a plane perpendicular to the beams at the isocenter.Results: The streaking and shading in the NMAR image using tissue classifications are significantly reduced. However, the structures, including metal, are deformed. Some uniform regions appear to have eroded from one side. There is a large variation of attenuation values inside the metal inserts. Similar results are seen in commercially corrected image. Use of MVCT prior images without tissue classification in NMAR significantly reduces these problems. The radiation dose calculated on the reference image is close to the dose measured using the film. Compared to the reference image, the calculated dose difference in the conventional NMAR image, the corrected images using uncorrected MVCT image, and IMPACT corrected MVCT image as priors is ∼15.5%, ∼5%, and ∼2.7%, respectively, at the isocenter.Conclusions: The deformation and erosion of the structures present in regular NMAR corrected images can be largely reduced by using MVCT priors without tissue segmentation. The attenuation value of metal being incorrect, large dose differences relative to the true value can result when using the conventional NMAR image. This difference can be significantly reduced if MVCT images are used as priors. Reduced tissue deformation, better tissue visualization, and correct information about the electron density of the tissues and metals in the artifact corrected images could help delineate the structures better, as well as calculate radiation dose more correctly, thus enhancing the quality of the radiotherapy treatment planning.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Toward designing effective exascale scientific computing workflows: experiences and best practices

Many fields within scientific computing have embraced advances in big-data analysis and machine learning, which often requires the deployment of large, distributed and complicated workflows that may combine training neural networks, performing simulations, running inference, and performing database queries and data analysis in asynchronous, parallel and pipelined execution frameworks. Such a shift has brought into focus the need for scalable, efficient workflow management solutions with reproducibility, error and provenance handling, traceability, and checkpoint-restart capabilities, among other needs. Here, we discuss challenges and best-practices for deploying exascale-generation computational science workflows on resources at the Oak Ridge Leadership Computing Facility (OLCF). We present our experiences with large-scale deployment of distributed workflows on the Summit supercomputer, including for bioinformatics and computational biophysics, materials science, and deep learning model optimization. We also present problems and solutions created by working within a Python-centric software base on traditional HPC systems, and discuss steps that will be required before the convergence of HPC, AI, and data science can be fully realized. Our results point to a wealth of exciting new possibilities for harnessing this convergence to tackle new scientific challenges.

Coletti, Mark↗

Cross-scale Efficient Tensor Contractions for Coupled Cluster Computations Through Multiple Programming Model Backends

Coupled-cluster methods provide highly accurate models of molecular structure by explicit numerical calculation of tensors representing the correlation between electrons. These calculations are dominated by a sequence of tensor contractions, motivating the development of numerical libraries for such operations. While based on matrix-matrix multiplication, these libraries are specialized to exploit symmetries in the molecular structure and in electronic interactions, and thus reduce the size of the tensor representation and the complexity of contractions. The resulting algorithms are irregular and their parallelization has been previously achieved via the use of dynamic scheduling or specialized data decompositions. We introduce our efforts to extend the Libtensor framework to work in the distributed memory environment in a scalable and energy efficient manner. We achieve up to 240 speedup compared with the best optimized shared memory implementation. We attain scalability to hundreds of thousands of compute cores on three distributed-memory architectures, (Cray XC30&XC40, BlueGene/Q), and on a heterogeneous GPU-CPU system (Cray XK7). As the bottlenecks shift from being compute-bound DGEMM's to communication-bound collectives as the size of the molecular system scales, we adopt two radically different parallelization approaches for handling load-imbalance. Nevertheless, we preserve a uni ed interface to both programming models to maintain the productivity of computational quantum chemists.

74 ATOMIC AND MOLECULAR PHYSICS↗