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 109 records · Page 6

Frequency Recovery in Power Grids Using High-Performance Computing

Maintaining electric power system stability is paramount, especially in extreme contingencies involving unexpected outages of multiple generators or transmission lines that are typical during severe weather events. Such outages often lead to large supply-demand mismatches followed by subsequent system frequency deviations from their nominal value. The extent of frequency deviations is an important metric of system resilience, and its timely mitigation is a central goal of power system operation and control. This paper develops a novel nonlinear model predictive control (NMPC) method to minimize frequency deviations when the grid is affected by an unforeseen loss of multiple components. Our method is based on a novel multi-period alternating current optimal power flow (ACOPF) formulation that accurately models both nonlinear electric power flow physics and the primary and secondary frequency response of generator control mechanisms. We develop a distributed parallel Julia package for solving the large-scale nonlinear optimization problems that result from our NMPC method and thereby address realistic test instances on existing high-performance computing architectures. Our method demonstrates superior performance in terms of frequency recovery over existing industry practices, where generator levels are set based on the solution of single-period classical ACOPF models.

nonlinear model predictive control↗

Integrated Network Decompositions and Dynamic Programming for Graph Optimization (INDDGO)

The INDDGO software package offers a set of tools for finding exact solutions to graph optimization problems via tree decompositions and dynamic programming algorithms. Currently the framework offers serial and parallel (distributed memory) algorithms for finding tree decompositions and solving the maximum weighted independent set problem. The parallel dynamic programming algorithm is implemented on top of the MADNESS task-based runtime.

Source record↗

Integrated Network Decompositions and Dynamic Programming for Graph Optimization (INDDGO)

The INDDGO software package offers a set of tools for finding exact solutions to graph optimization problems via tree decompositions and dynamic programming algorithms. Currently the framework offers serial and parallel (distributed memory) algorithms for finding tree decompositions and solving the maximum weighted independent set problem. The parallel dynamic programming algorithm is implemented on top of the MADNESS task-based runtime.

Source record↗

plexos-coad (Plexos Class-Object-Attribute Data manipulation tool)

Clean energy systems including the future power grid are enabled via the development, analysis and application of advanced simulation of complex systems based on large datasets. The ability to handle and enable the simulation of complex systems allows researchers and analysts to address significant problems with greater confidence and greater levels of integrity. Parallel execution of complex systems is paramount to addressing increasing complexity. Programmatic interfaces for software configuration and parallel execution enable handling greater complexity and improving simulation integrity. The Class Object Attribute Data (COAD) software is written as a programmatic interface to the PLEXOS dataset that enables the decomposition of the dataset in time and execution in parallel without loss of integrity. COAD also enable the recomposition of solution datasets that are the output of distributed parallel execution of the core simulator.

Jones, Wes↗

Direct measurement of electron sloshing of an inertial Alfvén wave

Here, we report laboratory measurements of the parallel current carried by suprathermal electrons associated with inertial Alfvén wave excitation in the laboratory. The experiments presented here use a novel wave absorption diagnostic that measures the suprathermal tails of the electron distribution parallel to the mean magnetic field. The diagnostic is used to probe the electron distribution as an inertial Alfvén wave propagates along the mean magnetic field. These results identify, for the first time, the periodic motion of suprathermal electrons participating in the inertial Alfvén wave itself, in agreement with predictions from linear kinetic theory.

74 ATOMIC AND MOLECULAR PHYSICS↗

SU-E-T-301: Dosimetric Comparison Between Adaptive and Rectilinear Template-Based Prostate Seed Implants

Purpose: To compare the dosimetry of a standard rectilinear and an adaptive technique used in I125 prostate seed implants. Methods: To achieve favorable dosimetry in prostate implants we used adaptive needle updates to match actual positions in real-time. The seed locations were optimized based on actual needle locations. The seeds were delivered automatically with a robotic device seedSelectron™ (Elekta Brachytherapy). In this study, we evaluated the former approach against the standard rectilinear technique in which the needles have a parallel distribution. The treatment plans for 10 patients were analyzed. For comparison, the actual treatment plans were revised so each needle was repositioned to its original parallel location through the template. The analysis was performed by comparing the target coverage and dose to the organs at risk. The comparison was done using the following planning goals: the target D90> 90%, V100% > 90%, V50% <70% and V200% <30%; the urethra V125% < 1cm3 and V150%= 0cm3; and the Rectum V100%<1cm3 and V69% < 8cm3. The prescription dose to the target was 145Gy. Results: The average target volume and number of seeds were 44.39cm3(SD=11.14) and 74(SD=12), respectively. The D90 for adaptive and rectilinear plans was 159.9Gy(SD=2.99) and 155.53Gy(SD=4.04) resulting in a 2.74% difference for the average target coverage. A similar difference (1.75%) was noticed in the target V100[%]. No significant difference was noticed in the dose to the urethra and rectum. All planning goals were met with both the adaptive and rectilinear approach for each plan. Conclusion: The study reveals enhanced coverage of the target when using the adaptive needle adjustments as compared to the rectilinear approach for the analyzed cases. However, the differences in dosimetry did not translate to meaningful clinical outcomes.

60 APPLIED LIFE SCIENCES↗

A Distributed Python HPC Framework: ODIN, PyTrilinos, & Seamless

Under this grant, three significant software packages were developed or improved, all with the goal of improving the ease-of-use of HPC libraries. The first component is a Python package, named DistArray (originally named Odin), that provides a high-level interface to distributed array computing. This interface is based on the popular and widely used NumPy package and is integrated with the IPython project for enhanced interactive parallel distributed computing. The second Python package is the Distributed Array Protocol (DAP) that enables separate distributed array libraries to share arrays efficiently without copying or sending messages. If a distributed array library supports the DAP, it is then automatically able to communicate with any other library that also supports the protocol. This protocol allows DistArray to communicate with the Trilinos library via PyTrilinos, which was also enhanced during this project. A third package, PyTrilinos, was extended to support distributed structured arrays (in addition to the unstructured arrays of its original design), allow more flexible distributed arrays (i.e., the restriction to double precision data was lifted), and implement the DAP. DAP support includes both exporting the protocol so that external packages can use distributed Trilinos data structures, and importing the protocol so that PyTrilinos can work with distributed data from external packages.

97 MATHEMATICS AND COMPUTING↗

Axom

Axom is an open-source library of "building block" software components that provide core infrastructure capabilities for HPC applications. Such capabilities include: input file parsing and verification for various file formats, format specification for material shape input to multi-material simulations and tools for placing those shapes on meshes, parallel distributed coordination of diagnostic messages, geometric primitives, spatial queries and spatial search acceleration data structures, in memory key-value data store for managing simulation data and parallel file I/O. Axom components are used widely across LLNL Advanced Simulation and Computing program applications. It is also part of the LLNL institutionally-supported RADIUSS project, which promotes and funds its adoption by projects across LLNL.

Zagaris, George↗

A first look at scalable I/O in Linux commands

Data created from and used by terascale and petascale applications continues to increase, but our ability to handle and manage these files is still limited by the capabilities of the standard serialized Linux command set. This paper introduces the Center for Computational Sciences (NCCS) at Oak Ridge National Laboratory (ORNL) efforts towards providing parallelized and more efficient versions of the commonly used Linux commands. The design and implementation details as well as performance analysis of an in-house developed distributed parallelized version of the cp tool, spdcp is presented. Tests show that our spdcp utility can achieve 73 times more performance than its serialized counterpart. In addition, we introduce current work to extend this approach to other tools.

97 MATHEMATICS AND COMPUTING↗

An Asynchronous Task-based Fan-Both Sparse Cholesky Solver

Systems of linear equations arise at the heart of many scientific and engineering applications. Many of these linear systems are sparse; i.e., most of the elements in the coefficient matrix are zero. Direct methods based on matrix factorizations are sometimes needed to ensure accurate solutions. For example, accurate solution of sparse linear systems is needed in shift-invert Lanczos to compute interior eigenvalues. The performance and resource usage of sparse matrix factorizations are critical to time-to-solution and maximum problem size solvable on a given platform. In many applications, the coefficient matrices are symmetric, and exploiting symmetry will reduce both the amount of work and storage cost required for factorization. When the factorization is performed on large-scale distributed memory platforms, communication cost is critical to the performance of the algorithm. At the same time, network topologies have become increasingly complex, so that modern platforms exhibit a high level of performance variability. This makes scheduling of computations an intricate and performance-critical task. In this paper, we investigate the use of an asynchronous task paradigm, one-sided communication and dynamic scheduling in implementing sparse Cholesky factorization (symPACK) on large-scale distributed memory platforms. Our solver symPACK relies on efficient and flexible communication primitives provided by the UPC++ library. Performance evaluation shows good scalability and that symPACK outperforms state-of-the-art parallel distributed memory factorization packages, validating our approach on practical cases.

Jacquelin, Mathias↗

An analytic formula for the relativistic incoherent Thomson backscattering spectrum for a drifting bi-Maxwellian plasma

An analytic formula has been derived for the relativistic incoherent Thomson backscattering spectrum for a drifting anisotropic plasma when the scattering vector is parallel to the drifting direction. The shape of the scattering spectrum is insensitive to the electron temperature perpendicular to the scattering vector, but its amplitude may be modulated. As a result, while the measured temperature correctly represents the electron distribution parallel to the scattering vector, the electron density may be underestimated when the perpendicular temperature is higher than the parallel temperature. Since the scattering spectrum in shorter wavelengths is greatly enhanced by the existence of drift, the diagnostics might be used to measure local electron current density in fusion plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Rexsss Performance Analysis: Domain Decomposition Algorithm Implementations for Resilient Numerical Partial Differential Equation Solvers

The future of extreme-scale computing is expected to magnify the influence of soft faults as a source of inaccuracy or failure in solutions obtained from distributed parallel computations. The development of resilient computational tools represents an essential recourse for understanding the best methods for absorbing the impacts of soft faults without sacrificing solution accuracy. The Rexsss (Resilient Extreme Scale Scientific Simulations) project pursues the development of fault resilient algorithms for solving partial differential equations (PDEs) on distributed systems. Performance analyses of current algorithm implementations assist in the identification of runtime inefficiencies.

97 MATHEMATICS AND COMPUTING↗

A Fast Parallel Algorithm for Selected Inversion of Structured Sparse Matrices with Application to 2D Electronic Structure Calculations

We present an efficient parallel algorithm and its implementation for computing the diagonal of $H^-1$ where $H$ is a 2D Kohn-Sham Hamiltonian discretized on a rectangular domain using a standard second order finite difference scheme. This type of calculation can be used to obtain an accurate approximation to the diagonal of a Fermi-Dirac function of $H$ through a recently developed pole-expansion technique \cite{LinLuYingE2009}. The diagonal elements are needed in electronic structure calculations for quantum mechanical systems \citeHohenbergKohn1964, KohnSham 1965,DreizlerGross1990. We show how elimination tree is used to organize the parallel computation and how synchronization overhead is reduced by passing data level by level along this tree using the technique of local buffers and relative indices. We analyze the performance of our implementation by examining its load balance and communication overhead. We show that our implementation exhibits an excellent weak scaling on a large-scale high performance distributed parallel machine. When compared with standard approach for evaluating the diagonal a Fermi-Dirac function of a Kohn-Sham Hamiltonian associated a 2D electron quantum dot, the new pole-expansion technique that uses our algorithm to compute the diagonal of $(H-z_i I)^-1$ for a small number of poles $z_i$ is much faster, especially when the quantum dot contains many electrons.

74 ATOMIC AND MOLECULAR PHYSICS↗

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↗

MixSim : An R Package for Simulating Data to Study Performance of Clustering Algorithms

The R package MixSim is a new tool that allows simulating mixtures of Gaussian distributions with different levels of overlap between mixture components. Pairwise overlap, defined as a sum of two misclassification probabilities, measures the degree of interaction between components and can be readily employed to control the clustering complexity of datasets simulated from mixtures. These datasets can then be used for systematic performance investigation of clustering and finite mixture modeling algorithms. Among other capabilities of MixSim, there are computing the exact overlap for Gaussian mixtures, simulating Gaussian and non-Gaussian data, simulating outliers and noise variables, calculating various measures of agreement between two partitionings, and constructing parallel distribution plots for the graphical display of finite mixture models. All features of the package are illustrated in great detail. The utility of the package is highlighted through a small comparison study of several popular clustering algorithms.

97 MATHEMATICS AND COMPUTING↗

Microwave-assisted hydrothermal synthesis of V{sub 2}O{sub 5} nanorods assemblies with an improved Li-ion batteries performance

Highlights: • V{sub 2}O{sub 5} nanorods and their assemblies were synthesized by microwave way. • Electrochemical performance in Li-ion batteries was studied. • CV has revealed reversible redox behavior with charge–discharge cycling. • V{sub 2}O{sub 5} nanorods assemblies show superior initial discharge capacity. • Low polarization of charge transfer reaction determines the enhanced capacity. - Abstract: Vanadium pentoxide nanorods assemblies were synthesized by a microwave-assisted hydrothermal synthesis, combined with subsequently annealing treatment. The structure and morphology of the nanorods were characterized by XRD, FESEM and HRTEM, and the electrochemical properties of the electrodes made from the V{sub 2}O{sub 5} nanorods were investigated. The V{sub 2}O{sub 5} nanorods with an average diameter of 100 nm and lengths up to several micrometers are almost parallel distributed in the assemblies. The V{sub 2}O{sub 5} nanorods assemblies exhibit an initial discharge capacity of 330 mAh g{sup −1} at a current density of 50 mA g{sup −1}, which is very higher than that of the separated V{sub 2}O{sub 5} nanorods. The V{sub 2}O{sub 5} nanorods assemblies also show a lower capacity fading rate in comparison with the separated V{sub 2}O{sub 5} nanorods. A low polarization of the charge transfer reaction and a high diffusion rate of lithium ion inside the electrode composed of the paralleled nanorods are considered responsible for the enhanced capacity.

36 MATERIALS SCIENCE↗

GPU acceleration of all-electron electronic structure theory using localized numeric atom-centered basis functions

We present an implementation of all-electron density-functional theory for massively parallel GPU-based platforms, using localized atom-centered basis functions and real-space integration grids. Special attention is paid to domain decomposition of the problem on non-uniform grids, which enables compute- and memory-parallel execution across thousands of nodes for real-space operations, e.g. the update of the electron density, the integration of the real-space Hamiltonian matrix, and calculation of Pulay forces. To assess the performance of our GPU implementation, we performed benchmarks on three different architectures using a 103-material test set. We find that operations which rely on dense serial linear algebra show dramatic speedups from GPU acceleration: in particular, SCF iterations including force and stress calculations exhibit speedups ranging from 4.5 to 6.6. For the architectures and problem types investigated here, this translates to an expected overall speedup between 3–4 for the entire calculation (including non-GPU accelerated parts), for problems featuring several tens to hundreds of atoms. Additional calculations for a 375-atom Bi2Se3 bilayer show that the present GPU strategy scales for large-scale distributed-parallel simulations.

42 ENGINEERING↗

Singular value decomposition utilizing parallel algorithms on graphical processors

One of the current challenges in underwater acoustic array signal processing is the detection of quiet targets in the presence of noise. In order to enable robust detection, one of the key processing steps requires data and replica whitening. This, in turn, involves the eigen-decomposition of the sample spectral matrix, Cx = 1/K xKX(k)XH(k) where X(k) denotes a single frequency snapshot with an element for each element of the array. By employing the singular value decomposition (SVD) method, the eigenvectors and eigenvalues can be determined directly from the data without computing the sample covariance matrix, reducing the computational requirements for a given level of accuracy (van Trees, Optimum Array Processing). (Recall that the SVD of a complex matrix A involves determining V, , and U such that A = U VH where U and V are orthonormal and is a positive, real, diagonal matrix containing the singular values of A. U and V are the eigenvectors of AAH and AHA, respectively, while the singular values are the square roots of the eigenvalues of AAH.) Because it is desirable to be able to compute these quantities in real time, an efficient technique for computing the SVD is vital. In addition, emerging multicore processors like graphical processing units (GPUs) are bringing parallel processing capabilities to an ever increasing number of users. Since the computational tasks involved in array signal processing are well suited for parallelization, it is expected that these computations will be implemented using GPUs as soon as users have the necessary computational tools available to them. Thus, it is important to have an SVD algorithm that is suitable for these processors. This work explores the effectiveness of two different parallel SVD implementations on an NVIDIA Tesla C2050 GPU (14 multiprocessors, 32 cores per multiprocessor, 1.15 GHz clock - peed). The first algorithm is based on a two-step algorithm which bidiagonalizes the matrix using Householder transformations, and then diagonalizes the intermediate bidiagonal matrix through implicit QR shifts. This is similar to that implemented for real matrices by Lahabar and Narayanan ("Singular Value Decomposition on GPU using CUDA", IEEE International Parallel Distributed Processing Symposium 2009). The implementation is done in a hybrid manner, with the bidiagonalization stage done using the GPU while the diagonalization stage is done using the CPU, with the GPU used to update the U and V matrices. The second algorithm is based on a one-sided Jacobi scheme utilizing a sequence of pair-wise column orthogonalizations such that A is replaced by AV until the resulting matrix is sufficiently orthogonal (that is, equal to U ). V is obtained from the sequence of orthogonalizations, while can be found from the square root of the diagonal elements of AH A and, once is known, U can be found from column scaling the resulting matrix. These implementations utilize CUDA Fortran and NVIDIA's CUB LAS library. The primary goal of this study is to quantify the comparative performance of these two techniques against themselves and other standard implementations (for example, MATLAB). Considering that there is significant overhead associated with transferring data to the GPU and with synchronization between the GPU and the host CPU, it is also important to understand when it is worthwhile to use the GPU in terms of the matrix size and number of concurrent SVDs to be calculated.

99 GENERAL AND MISCELLANEOUS↗