SEARCH · Engineering Papers
Results for “Scalable”
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.
Best Practices for Scalable Power Measurement and Control
Abstract not provided
Scalable Collectives for Distributed Asynchronous Many-Task Runtimes.
Abstract not provided.
A scalable graph generation algorithm to sample over a given shell distribution.
Abstract not provided.
Shared-Memory Scalable k-Core Maintenance on Dynamic Graphs and Hypergraphs.
Abstract not provided.
A Scalable Pipeline for Gigapixel Whole Slide Imaging Analysis on Leadership Class HPC Systems
Whole Slide Imaging (WSI) captures microscopic details of a patient's histopathological features at multiple res-olutions organized across different levels. Images produced by WSI are gigapixel-sized, and saving a single image in memory requires a few gigabytes which is scarce since a complicated model occupies tens of gigabytes. Performing a simple met-ric operation on these large images is also expensive. High-performance computing (HPC) can help us quickly analyze such large images using distributed training of complex deep learning models. One popular approach in analyzing these images is to divide a WSI image into smaller tiles (patches) and then train a simpler model with these reduced-sized but large numbers of patches. However, we need to solve three pre-processing challenges efficiently for pursuing this patch-based approach. 1) Creating small patches from a high-resolution image can result in a high number (hundreds of thousands per image) of patches. Storing and processing these images can be challenging due to a large number of I/O and arithmetic operations. To reduce I/Oand memory accesses, an optimal balance between the size and number of patches must exist to reduce I/O and memory accesses. 2) WSI images may have tiny annotated regions for cancer tissue and a significant portion with normal and fatty tissues; correct patch sampling should avoid dataset imbalance. 3) storing and retrieving many patches to and from disk storage might incur I/O latency while training a deep learning model. An efficient distributed data loader should reduce I/O latency during the training and inference steps. This paper explores these three challenges and provides empirical and algorithmic solutions deployed on the Summit supercomputer hosted at the Oak Ridge Leadership Computing Facility.
Scalability Challenges in Current MPI One-Sided Implementations
Explore the source record for details and available documents.
VoroClust: Scalable Clustering for Remote Sensing
Although supervised machine learning provides a powerful framework for image classification and segmentation, it requires comprehensive consistent datasets, which are not available for many remote-sensing applications. Remote-sensing datasets are expensive to collect, and each is acquired under different environmental conditions or with significant variations in system operating parameters. Unsupervised clustering algorithms analyze the structure of each dataset independently, rather than drawing on similarities with existing “training” examples, and are thus well suited for practical remote-sensing applications. We introduce VoroClust, a fast density-based unsupervised clustering algorithm applicable to high-resolution and high-dimensional data. VoroClust runs as fast as distance-based clustering methods, while capturing complex regional geometries at least as well as current-density-based methods. It uses a data-centered sphere cover to reduce computational demands, while still capturing data topology. It then propagates clusters outward from local peaks in density. We show that VoroClust provides fast state-of-the-art clustering for both high-resolution polarimetric synthetic aperture radar and high-dimensional hyperspectral imaging datasets.
Scalable Microring-Based Silicon Clos Switch Fabric With Switch-and-Select Stages
Not Available
A Perspective on Scalable AI on High-Performance Computing and Leadership Class Supercomputing Facilities [Industrial and Governmental Activities]
Many scientific applications that support the mission of the US Department of Energy (US-DoE) require modeling complex engineering and/or physical systems. Here, examples of such complex systems arise from: (a) materials science to develop new compounds with exceptional mechanical and thermodynamical properties (e.g., resistance to mechanical stresses and high temperatures), (b) structural and nuclear engineering to model the temporal evolution of the structural damage of concrete shields exposed to continuous neutron and gamma radiations emitted by the nuclear reactor core, (c) urban sciences (e.g., transportation and smart buildings), and (d) power grid systems.
Scalable Reactive Molecular Dynamics Simulations for Computational Synthesis
Reactive molecular dynamics (MD) simulation is a powerful research tool for describing chemical reactions. We eliminate the speed-limiting charge iteration in MD with a novel extended-Lagrangian scheme. The extended-Lagrangian reactive MD (XRMD) code drastically improves energy conservation while substantially reducing time-to-solution. Furthermore, we introduce a new polarizable charge equilibration (PQEq) model to accurately predict atomic charges and polarization. The XRMD code based on hybrid message passing+multithreading achieves a weak-scaling parallel efficiency of 0.977 on 786 432 IBM Blue Gene/Q cores for a 67.6 billion-atom system. The performance is portable to the second-generation Intel Xeon Phi, Knights Landing. Blue Gene/Q simulations for the computational synthesis of materials via novel exfoliation mechanisms for synthesizing atomically thin transition metal dichalcogenide layers will dominate nanomaterials science in this century.
Scalable Analysis of Authentic Viral Envelopes on FRONTERA
Not Available
A Compact, Highly Scalable, Low-Power, and Multi-Channel Charge Digitizer for Beam Profile Monitoring
Explore the source record for details and available documents.
Stability Assessment of a System Comprising a Single Machine and Inverter with Scalable Ratings
Synchronous machines have traditionally acted as the foundation of large-scale electrical infrastructures and their physical properties have formed the cornerstone of system operations. However, with the increased integration of distributed renewable resources and energy-storage technologies, there is a need to systematically acknowledge the dynamics of power-electronics inverters - the primary energy-conversion interface in such systems - in all aspects of modeling, analysis, and control of the bulk power network. In this paper, we assess the properties of coupled machine-inverter systems by studying an elementary system comprised of a synchronous generator, three-phase inverter, and a load. The inverter model is formulated such that its power rating can be scaled continuously across power levels while preserving its closed-loop response. Accordingly, the properties of the machine-inverter system can be assessed for varying ratios of machine-to-inverter power ratings. After linearizing the model and assessing its eigenvalues, we show that system stability is highly dependent on the inverter current controller and machine exciter, thus uncovering a key concern with mixed machine-inverter systems and motivating the need for next-generation grid-stabilizing inverter controls.
VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing
Explore the source record for details and available documents.
A Scalable Decomposition Algorithm for PMU Placement Under Multiple-Failure Contingencies.
Abstract not provided.
PV Hosting Capacity Estimation: Experiences with Scalable Framework
Hosting capacity is an indication of the amount of solar photovoltaics (PV) that can be hosted in a distribution system without additional changes to infrastructure or oper-ations. This paper presents a framework for estimating the PV hosting capacity at scale. First, we analyze computational, modeling and other key challenges of performing relevant, large-scale simulations, provided along with the experiences and lessons learned. Then, we develop two open-source Python-based software tools to conduct repeatable distribution analyses: the Distribution Integration Solution Cost Options (DISCO) for configuring and analyzing simulations and the Job Automation and Deployment Engine (JADE) for parallelizing jobs on high-performance computing clusters. A case study of hosting capacity estimation for the SMART-DS San Francisco (SFO) 2000+ synthetic feeders, is used to demonstrate the capability of the developed DISCO+JADE framework and tools. The framework and tools can help utilities assess the overall hosting capacity of their service territory, which can help them better plan for the overall upgrade costs to integrate more PV in the future. The experiences are shared to aid the tool users and researchers to conduct relevant studies and research.
Scalable Triadic Analysis of Large-Scale Graphs: Multi-Core vs. Multi-Processor vs. Multi-Threaded Shared Memory Architectures
Triadic analysis encompasses a useful set of graph mining methods that is centered on the concept of a triad, which is a subgraph of three nodes and the configuration of directed edges across the nodes. Such methods are often applied in the social sciences as well as many other diverse fields. Triadic methods commonly operate on a triad census that counts the number of triads of every possible edge configuration in a graph. Like other graph algorithms, triadic census algorithms do not scale well when graphs reach tens of millions to billions of nodes. To enable the triadic analysis of large-scale graphs, we developed and optimized a triad census algorithm to efficiently execute on shared memory architectures. We will retrace the development and evolution of a parallel triad census algorithm. Over the course of several versions, we continually adapted the code’s data structures and program logic to expose more opportunities to exploit parallelism on shared memory that would translate into improved computational performance. We will recall the critical steps and modifications that occurred during code development and optimization. Furthermore, we will compare the performances of triad census algorithm versions on three specific systems: Cray XMT, HP Superdome, and AMD multi-core NUMA machine. These three systems have shared memory architectures but with markedly different hardware capabilities to manage parallelism.