Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “algorithms scalability”

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 253 records · Page 14

Contact Graph Routing

Contact Graph Routing (CGR) is a dynamic routing system that computes routes through a time-varying topology of scheduled communication contacts in a network based on the DTN (Delay-Tolerant Networking) architecture. It is designed to enable dynamic selection of data transmission routes in a space network based on DTN. This dynamic responsiveness in route computation should be significantly more effective and less expensive than static routing, increasing total data return while at the same time reducing mission operations cost and risk. The basic strategy of CGR is to take advantage of the fact that, since flight mission communication operations are planned in detail, the communication routes between any pair of bundle agents in a population of nodes that have all been informed of one another's plans can be inferred from those plans rather than discovered via dialogue (which is impractical over long one-way-light-time space links). Messages that convey this planning information are used to construct contact graphs (time-varying models of network connectivity) from which CGR automatically computes efficient routes for bundles. Automatic route selection increases the flexibility and resilience of the space network, simplifying cross-support and reducing mission management costs. Note that there are no routing tables in Contact Graph Routing. The best route for a bundle destined for a given node may routinely be different from the best route for a different bundle destined for the same node, depending on bundle priority, bundle expiration time, and changes in the current lengths of transmission queues for neighboring nodes; routes must be computed individually for each bundle, from the Bundle Protocol agent's current network connectivity model for the bundle s destination node (the contact graph). Clearly this places a premium on optimizing the implementation of the route computation algorithm. The scalability of CGR to very large networks remains a research topic. The information carried by CGR contact plan messages is useful not only for dynamic route computation, but also for the implementation of rate control, congestion forecasting, transmission episode initiation and termination, timeout interval computation, and retransmission timer suspension and resumption.

Burleigh, Scott C.↗

High-Performance Computing Optimization for Aladyn – Adaptive Neural Network Molecular Dynamics Mini-Application

This report provides a description and performance evaluation of the optimization techniques for high performance computing (HPC) implementation of the open source Computational Materials mini-application Aladyn (https://github.com/nasa/aladyn). Aladyn is a basic molecular dynamics code written in FORTRAN 2003, which is designed to demonstrate the use of adaptive neural networks (ANNs) in atomistic simulations. The role of ANNs is to efficiently reproduce the very complex energy landscape resulting from the atomic interactions in materials with the accuracy of the more expensive quantum mechanics-based calculations. The ANN is trained on a large set of atomic structures calculated using the density functional theory (DFT) method. While achieving orders of magnitude faster computational performance than DFT, the ANN-based approach was still very computationally demanding compared to the conventional approach of using empirically fitted energy functions. After its initial development, Aladyn was evaluated and optimized by experts at the NASA Advanced Supercomputing (NAS) division to exploit modern supercomputer architectures. The code has been optimized for execution on multicore central processing units (CPUs), including Intel® Skylake microarchitecture, and on graphic accelerators, such as Nvidia® V100 graphic processing units (GPUs), using Open Multi-Processing (OpenMP) and Open Accelerators (OpenACC) programming interfaces. The optimization achieved a speedup of 4.7 times the baseline version on CPU performance and an additional 2.4 times on CPU+GPU performance. Atomistic computer simulations are a fundamental tool in materials research to model material properties form physics-based first principles. Atomic interaction, governed by Quantum Mechanics (QM) require sophisticated and highly computationally demanding mathematical models to calculate [1]. Classical methods use approximate functional forms, empirically fitted through a set of variable parameters to emulate atomic energies as direct functions of atomic coordinates [2]. While empirical potentials are computationally much simpler, allowing simulations of large-scale systems of up to a trillion (1012) atoms [3], they are substantially less accurate compared to quantum calculations and applicable only to very specific atomic configurations or predefined crystallographic phases. A recently suggested approach is to use heuristic machine learning methods [4], such as those based on Adaptive Neural Networks (ANNs) to predict atomic energies, after being trained on a sufficiently large database of QM-calculated structures [5,6]. This approach reduces significantly the computational complexity, allowing for simulations of orders of magnitude larger systems compared to QM-based methods without compromising accuracy. Still, compared to classical methods using empirical energy functions, ANN methods remain two- to three orders of magnitude more computationally demanding. Hence, the computational cost of simulations, together with the need for extensive training of ANNs, still makes the practical implementation of ANN-based methods quite challenging. The purpose of the Aladyn mini-application software [7], available as open source at https://github.com/nasa/aladyn, is to be a testbed for exploring possible optimization strategies to develop highly scalable parallel algorithms for ANN-based atomistic simulations. Aladyn is aimed at utilizing the architecture of the high-end modern highperformance computing (HPC) hardware based on multicore central processing units (CPUs) equipped with graphic processing unit (GPU) accelerators. Specifically, the goal is to optimize the performance on a single HPC compute node, before implementing scaling to multi-node parallelization using message passing interface (MPI). At the same time, the open source code of Aladyn can serve as a training model for students and professors in academia.

Yamakov, Vesselin I.↗

Overlapping clusters for distributed computation.

Scalable, distributed algorithms must address communication problems. We investigate overlapping clusters, or vertex partitions that intersect, for graph computations. This setup stores more of the graph than required but then affords the ease of implementation of vertex partitioned algorithms. Our hope is that this technique allows us to reduce communication in a computation on a distributed graph. The motivation above draws on recent work in communication avoiding algorithms. Mohiyuddin et al. (SC09) design a matrix-powers kernel that gives rise to an overlapping partition. Fritzsche et al. (CSC2009) develop an overlapping clustering for a Schwarz method. Both techniques extend an initial partitioning with overlap. Our procedure generates overlap directly. Indeed, Schwarz methods are commonly used to capitalize on overlap. Elsewhere, overlapping communities (Ahn et al, Nature 2009; Mishra et al. WAW2007) are now a popular model of structure in social networks. These have long been studied in statistics (Cole and Wishart, CompJ 1970). We present two types of results: (i) an estimated swapping probability {rho}{infinity}; and (ii) the communication volume of a parallel PageRank solution (link-following {alpha} = 0.85) using an additive Schwarz method. The volume ratio is the amount of extra storage for the overlap (2 means we store the graph twice). Below, as the ratio increases, the swapping probability and PageRank communication volume decreases.

99 GENERAL AND MISCELLANEOUS↗

TESS

Computing a Voronoi or Delaunay tessellation from a set of points is a core part of the analysis of many simulated and measured datasets. As the scale of simulations and observations surpasses billions of particles, a distributed-memory scalable parallel algorithm is the only feasible approach. The primary contribution of this software is a distributed-memory parallel Delaunay and Voronoi tessellation algorithm based on existing serial computational geometry libraries that automatically determines which neighbor points need to be exchanged among the subdomains of a spatial decomposition. Other contributions include the addition of periodic and wall boundary conditions.

Dmitriy Morozov, Tom Peterka↗

A Principled Kernel Testbed for Hardware/Software Co-Design Research

Recently, advances in processor architecture have become the driving force for new programming models in the computing industry, as ever newer multicore processor designs with increasing number of cores are introduced on schedules regimented by marketing demands. As a result, collaborative parallel (rather than simply concurrent) implementations of important applications, programming languages, models, and even algorithms have been forced to adapt to these architectures to exploit the available raw performance. We believe that this optimization regime is flawed. In this paper, we present an alternate approach that, rather than starting with an existing hardware/software solution laced with hidden assumptions, defines the computational problems of interest and invites architects, researchers and programmers to implement novel hardware/software co-designed solutions. Our work builds on the previous ideas of computational dwarfs, motifs, and parallel patterns by selecting a representative set of essential problems for which we provide: An algorithmic description; scalable problem definition; illustrative reference implementations; verification schemes. This testbed will enable comparative research in areas such as parallel programming models, languages, auto-tuning, and hardware/software codesign. For simplicity, we focus initially on the computational problems of interest to the scientific computing community but proclaim the methodology (and perhaps a subset of the problems) as applicable to other communities. We intend to broaden the coverage of this problem space through stronger community involvement.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Holistic Approaches to HPC Power & Workflow Management: Preprint

Constraints on power consumption are having pervasive effects on high-performance computing (HPC) systems, the facilities in which they are housed, and the application codes themselves. Whether these constraints are driven by physical limits on available power within a facility, are due to utility demand response, result from opportunities to reduce utility costs, or are imposed by sponsoring agencies, power management must now be added to the traditional goals of application and algorithm correctness, scalability, and performance. The specifics of these power constraints are likely to vary from site to site, and optimal strategies for managing power will vary. In this paper, we present the results of implementing several strategies for managing HPC system power and quantify the impact of these power reductions on application performance. These can be added to the suite of extant options that can be used to manage power and workflow on HPC systems.

97 MATHEMATICS AND COMPUTING↗

A scalable mixed-integer decomposition approach for optimal power system restoration

The optimal restoration problem lies at the foundation of the evaluation and improvement of resilience in power systems. In this paper we present a scalable decomposition algorithm, based on the integer L-shaped method, for solving this problem for realistic power systems. The algorithm works by partitioning the problem into a master problem and a slave problem. The master problem optimizes over energization sequences of generators, buses and branches, for the entire restoration horizon, while respecting stylized energization requirements. The slave problem verifies that there exist power flow solutions supporting the energization sequences proposed by the master problem, adding cuts to the master if an infeasible sequence is detected. The power flow verification is carried out using a piece-wise linear approximation of the power flow equations, capable of capturing overvoltage situations common in restoration procedures. We develop specialized binary cuts and hybrid Benders-binary cuts for separating infeasible islands, which are stronger than regular no-good cuts, as well as heuristics for obtaining feasible solutions. We present numerical results for the IEEE 39- and 118-bus systems, and for the Chilean 1500-bus grid, where our algorithm finds near-optimal restoration sequences orders of magnitude faster than the state-of-the-art, demonstrating the effectiveness of the proposed approach.

24 POWER TRANSMISSION AND DISTRIBUTION↗

The Future of Renewable Energy Transmission: An Autonomous Energy Grid

The drastic price reduction in variable renewable energy, such as wind and solar, coupled with the ease of use of smart technologies at the consumer level, is driving dramatic changes to the power system that will significantly transform how power is made, delivered, and used. Distributed energy resources (DERs)—which can include solar photovoltaic (PV), fuel cells, microturbines, gensets, distributed energy storage (e.g., batteries, ice storage), and new loads (e.g., electric vehicles (EVs), light-emitting diode (LED) lighting, smart appliances, and electric heat pumps)—are being added to electric grids and causing bidirectional power flows and voltage fluctuations that can impact optimal control and system operation. Residential solar installations, customer battery systems, and EVs are all seeing rapid increases in deployments. With DER seeing such increased use, it is not unreasonable to imagine a residential electricity customer having at least five controllable DERs. In future electric grids, as more DERs are integrated, the number of active control points will be too much for current control approaches to effectively manage.

30 DIRECT ENERGY CONVERSION↗

Renewable energy integration and system operation challenge: control and optimization of millions of devices

The electric power infrastructure, originally designed and built on large-scale power plants, is evolving into a more resilient power generation and delivery system in which millions of smaller units of distributed energy generation resources units will be installed in sub-transmission and distribution networks. In order to control, manage and optimize the future grid, a hierarchical design is presented in this chapter which enables the distributed control on grid edge while inheriting the existing centralized control structure. This layered design of large-scale power system operation and control uses the following principle: reactive power control is treated as a primary control for voltage stability, and the real power control is primarily a grid-level control but can also be a supplementary control for voltage support in the case of insufficient reactive power control capacity. For the purpose of active control and operation at the distribution level, a recursive power network model is derived from nodal injection and branch power flow models. Based on the model, the proposed algorithms of hierarchical control, grid-edge inference and dynamic hosting allowance are developed and presented for multi-level controlled operation. And, a co-simulation architecture of integrated T&D system is presented to validate and demonstrate the feasibility and scalability of proposed algorithms.

Xu, Ying↗

Entity Resolution at Large Scale: Benchmarking and Algorithmics

We seek scalable benchmarks for entity resolution problems. Solutions to these problems range from trivial approaches such as string sorting to sophisticated methods such as statistical relational learning. The theoretical and practical complexity of these approaches varies widely, so one of the primary purposes of a benchmark will be to quantify the trade-off between solution quality and runtime. We are motivated by the ubiquitous nature of entity resolution as a fundamental problem faced by any organization that ingests large amounts of noisy text data. A benchmark is typically a rigid specification that provides an objective measure usable for ranking implementations of an algorithm. For example the Top500 and HPCG500 bench- marks rank supercomputers based on their performance of dense and sparse linear algebra problems (respectively). These two benchmarks require participants to report FLOPS counts attainable on various machines. Our purpose is slightly different. Whereas the supercomputing benchmarks mentioned above hold algorithms constant and aim to rank machines, we are primarily interested in ranking algorithms. As mentioned above, entity resolution problems can be approached in completely different ways. We believe that users of our benchmarks must decide what sort of procedure to run before comparing implementations and architectures. Eventually, we also wish to provide a mechanism for ranking machines while holding algorithmic approach constant . Our primary contributions are parallel algorithms for computing solution quality mea- sures per entity. We find in some real datasets that many entities are quite easy to resolve while others are difficult, with a heavy skew toward the former case. Therefore, measures such as global confusion matrices, F measures, etc. do not meet our benchmarking needs. We design methods for computing solution quality at the granularity of a single entity in order to know when proposed solutions do well in difficult situations (perhaps justifying extra computational), or struggling in easy situations. We report on progress toward a viable benchmark for comparing entity resolution algo- rithms. Our work is incomplete, but we have designed and prototyped several algorithms to help evalute the solution quality of competing approaches to these problems. We envision a benchmark in which the objective measure is a ratio of solution quality to runtime.

97 MATHEMATICS AND COMPUTING↗

Highly scalable distributed-memory sparse triangular solution algorithms.

This paper presents a highly efficient distributed-memory parallel sparse triangular solver. The triangular solution phase is often performed following factorization phase in the sparse linear solvers and has become increasingly computa­tionally expensive for direct solvers with many right hand sides (RHSs) or preconditioned iterative solvers. However, the low arithmetic intensity and sequential nature of the triangular solve algorithm pose performance challenges for its large-scale distributed-memory parallelization. In this work, we propose several strategies to enhance scalability of an algorithm with 2D block cyclic process layout. First, an asynchronous binary-tree-based communication scheme implemented via non-blocking MPI functions is leveraged to broadcast partial solutions and reduce partial updates among a subset of processes for each block column and row of the triangular matrix, respectively. This scheme reduces message latency, improves communication load balance and significantly accelerates asynchronous execution of the triangular solve. In addition, efficient BLAS operations and threading implementations are exploited to accelerate local computations and further reduce process idle time. The proposed strategies are implemented in SuperLU_DIST and numerical experiments show up to 4.4x improvement with one right-hand side and up to 6.1x improvement with 50 right- hand sides on 4096 processes, compared to the current release. This is the first time that sparse triangular solution is demonstrated strong scaling on more than 4000 cores.

Liu, Yang↗

Multilevel graph embedding

The goal of the present paper is the design of embeddings of a general sparse graph into a set of points in $\mathbb{R}^d$ for appropriate d ≥ 2. The embeddings that we are looking at here aim to keep vertices that are grouped in communities together and keep the rest apart. To achieve this property, we utilize coarsening that respects possible community structures of the given graph. We employ a hierarchical multilevel coarsening approach that identifies communities (strongly connected groups of vertices) at every level. The multilevel strategy allows any given (presumably expensive) graph embedding algorithm to be made into a more scalable (and faster) algorithm. We demonstrate the presented approach on a number of given embedding algorithms and large-scale graphs and achieve speed-up over the methods in a recent paper.

97 MATHEMATICS AND COMPUTING↗

FINAL REPORT: Scalable Methods for Electronic Excitations and Optical Responses of Nanostructures: Mathematics to Algorithms to Observables

Work in nanoscience has increased substantially in recent years owing to its potential technological applications and to fundamental scientific interest. A driving force for this activity is to capitalize on new phenomena that occurs at the nanoscale. For example, the physical confinement of electronic states, i.e., quantum confinement, can dramatically alter the electronic and optical properties of matter. A prime example of this occurs for the optical properties of nanoscale crystals such as those composed of elemental silicon. Silicon in the bulk state is optically inactive due to the small size of the optical gap, which can only be accessed by indirect transitions. However, at the nanoscale, this material becomes optically active. The size of the optical gap is increased by confinement and the conservation of crystal momentum ceases to hold, resulting in the viability of indirect transitions. Our work associated with this grant has focused on developing new scalable algorithms for describing the electronic and optical properties of matter at the nanoscale such as nano structures of silicon and related semiconductor properties.

36 MATERIALS SCIENCE↗

Scalable Plug-and-Play ADMM with Convergence Guarantees

Plug-and-play priors (PnP) is a broadly applicable methodology for solving inverse problems by exploiting statistical priors specified as denoisers. Recent work has reported the state-of-the-art performance of PnP algorithms using pre-trained deep neural nets as denoisers in a number of imaging applications. However, current PnP algorithms are impractical in large-scale settings due to their heavy computational and memory requirements. This work addresses this issue by proposing an incremental variant of the widely used PnP-ADMM algorithm, making it scalable to problems involving a large number measurements. Here, we theoretically analyze the convergence of the algorithm under a set of explicit assumptions, extending recent theoretical results in the area. Additionally, we show the effectiveness of our algorithm with nonsmooth data-fidelity terms and deep neural net priors, its fast convergence compared to existing PnP algorithms, and its scalability in terms of speed and memory.

97 MATHEMATICS AND COMPUTING↗

Online Event Detection in Synchrophasor Data with Graph Signal Processing

Online detection of anomalies is crucial to enhancing the reliability and resiliency of power systems. We propose a novel data-driven online event detection algorithm with synchrophasor data using graph signal processing. In addition to being extremely scalable, our proposed algorithm can accurately capture and leverage the spatio-temporal correlations of the streaming PMU data. This paper also develops a general technique to decouple spatial and temporal correlations in multiple time series. Finally, we develop a unique framework to construct a weighted adjacency matrix and graph Laplacian for product graph. Case studies with real-world, large-scale synchrophasor data demonstrate the scalability and accuracy of our proposed event detection algorithm. Compared to the state-of-the-art benchmark, the proposed method not only achieves higher detection accuracy but also yields higher computational efficiency.

Event detection↗

Online Event Detection in Synchrophasor Data with Graph Signal Processing

Online detection of anomalies is crucial to enhancing the reliability and resiliency of power systems. We propose a novel data-driven online event detection algorithm with synchrophasor data using graph signal processing. In addition to being extremely scalable, our proposed algorithm can accurately capture and leverage the spatio-temporal correlations of the streaming PMU data. This paper also develops a general technique to decouple spatial and temporal correlations in multiple time series. Finally, we develop a unique framework to construct a weighted adjacency matrix and graph Laplacian for product graph. Case studies with real-world, large-scale synchrophasor data demonstrate the scalability and accuracy of our proposed event detection algorithm. Compared to the state-of-the-art benchmark, the proposed method not only achieves higher detection accuracy but also yields higher computational efficiency.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Scalable Domain Decomposed Monte Carlo Particle Transport

In this dissertation, we present the parallel algorithms necessary to run domain decomposed Monte Carlo particle transport on large numbers of processors (millions of processors). Previous algorithms were not scalable, and the parallel overhead became more computationally costly than the numerical simulation.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗