Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Computer Systems”

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 1,405 records · Page 78
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

Control and Information Systems for the National Ignition Facility

Orchestration of every National Ignition Facility (NIF) shot cycle is managed by the Integrated Computer Control System (ICCS), which uses a scalable software architecture running code on more than 1950 front-end processors, embedded controllers, and supervisory servers. The ICCS operates laser and industrial control hardware containing 66 000 control and monitor points to ensure that all of NIF’s laser beams arrive at the target within 30 ps of each other and are aligned to a pointing accuracy of less than 50 μm root-mean-square, while ensuring that a host of diagnostic instruments record data in a few billionths of a second. NIF’s automated control subsystems are built from a common object-oriented software framework that distributes the software across the computer network and achieves interoperation between different software languages and target architectures. A large suite of business and scientific software tools supports experimental planning, experimental setup, facility configuration, and post-shot analysis. Standard business services using open-source software, commercial workflow tools, and database and messaging technologies have been developed. An information technology infrastructure consisting of servers, network devices, and storage provides the foundation for these systems. Thus, this work is an overview of the control and information systems used to support a wide variety of experiments during the National Ignition Campaign.

42 ENGINEERING↗
DOE OSTI2015

High Performance Data Analytics on a Commodity Private Cloud

Sandia is researching novel methods of analysis for large datasets. The term “Big Data” has been used frequently in recent years to describe a discipline of computer science that attempts to distil an increasing quantity of data into a result or meaningful subset that can be easily visualized and acted upon by human consumers. These data are frequently characterized by one or more of the following: high volume, velocity, variety, and veracity. Sandia scientists and researchers are no strangers to large datasets, which often typify the result of high-performance computing workloads. The challenge for Sandia data scientists, however, comes at the arrival of exascale computing, which has become mandated by executive order for national computing centers. Because of power and networking limitations, exascale computing precludes the movement of datasets at exascale from data production to data analysis. Such analysis must be done in-situ, to mitigate the time and power costs of network transport. Currently, many of Sandia’s data analytics environments exist as independent entities, often specialized for individual use cases, interconnected to other data analytics, high-performance computing, and storage systems. Sandia is procuring, installing, and researching future platforms for such data analytics. A memory footprint of 256 GB per node, fourteen data rate (FDR) InfiniBand networking, PCIe connected non-volatile memory (NVMe) data storage, and an object data store will characterize the coming institutional data analytics platforms. The combined systems will contain 300 compute nodes. A cloud-inspired software stack resulting from collaboration between the Sandia centers will allow the systems to support a flexible mix of user and system-facing workloads and use cases including code development and testing in R and Python, Apache Hadoop and Spark, distributed in-memory databases, graph analytics, emulytics, system log and predictive analytics, and data visualization for institutional and mission customers. These systems will arrive at the end of FY 2015 and production is planned by the spring of FY 2016.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

The CCONE Code System and its Application to Nuclear Data Evaluation for Fission and Other Reactions

A computer code system, CCONE, was developed for nuclear data evaluation within the JENDL project. The CCONE code system integrates various nuclear reaction models needed to describe nucleon, light charged nuclei up to alpha-particle and photon induced reactions. The code is written in the C++ programming language using an object-oriented technology. At first, it was applied to neutron-induced reaction data on actinides, which were compiled into JENDL Actinide File 2008 and JENDL-4.0. It has been extensively used in various nuclear data evaluations for both actinide and non-actinide nuclei. The CCONE code has been upgraded to nuclear data evaluation at higher incident energies for neutron-, proton-, and photon-induced reactions. It was also used for estimating β-delayed neutron emission. This paper describes the CCONE code system indicating the concept and design of coding and inputs. Details of the formulation for modelings of the direct, pre-equilibrium and compound reactions are presented. Applications to the nuclear data evaluations such as neutron-induced reactions on actinides and medium-heavy nuclei, high-energy nucleon-induced reactions, photonuclear reaction and β-delayed neutron emission are mentioned.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

The Applicability of Unit Systems to High-Performance Computing Applications

Dimensional analysis is a key technique used to verify the soundness of scientific models. Most experts agree that engineering and scientific software would be made more reliable by integrating dimensional analysis in their type system. We explored how High Performance Computing (HPC) applications could integrate compile-time dimensional analysis. We started by investigating various implementation of unit systems for C++. Eventually, selecting the latest (and most advanced) one to apply to our test codes. We worked with code of increasing complexity, from a projectile trajectory calculation to the proxy-application Lulesh. This included our code, Springs-3D, which focuses on demonstrating language features while performing simple physic computations. Finally, our main contribution is a source-code analysis which extracts constraints on the dimension of all variables, functions, and constants in an application. This resulting system of equations is solved using the dimensions of a few of these objects. This analysis has the potential to greatly reduce the time spent performing dimensional analysis when refactoring application to use a representation of units.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Rigorous justification for the space–split sensitivity algorithm to compute linear response in Anosov systems

Ruelle gave a formula for linear response of transitive Anosov diffeomorphisms. Recently, practically computable realizations of Ruelle's formula have emerged that potentially enable sensitivity analysis of certain high-dimensional chaotic numerical simulations encountered in the applied sciences. In this paper, we provide full mathematical justification for the convergence of one such efficient computation, the space–split sensitivity, or S3, algorithm. In S3, Ruelle's formula is computed as a sum of two terms obtained by decomposing the perturbation vector field into a coboundary and a remainder that is parallel to the unstable direction. Such a decomposition results in a splitting of Ruelle's formula that is amenable to efficient computation. Here, we prove the existence of the S3 decomposition and the convergence of the computations of both resulting components of Ruelle's formula.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Energy–Performance Trade-offs in Privacy-Preserving Federated Learning on SmartNIC-Enabled HPC Systems

Federated learning (FL) is increasingly deployed on accelerator-rich high-performance computing (HPC) systems, yet the system-level energy cost of privacy-aware FL remains poorly understood, particularly across heterogeneous networking and server-placement options. We present a measurement-driven study of energy–performance trade-offs for FL on GH200-class nodes across three deployment configurations: CPU-Ethernet, CPU-InfiniBand (RDMA-capable), and a DPU-hosted FL server over InfiniBand using a BlueField-3 SmartNIC/DPU. Using NVIDIA FLARE (NVFLARE), we align node-level power telemetry with per-round timing extracted from NVFLARE logs to quantify time-to-solution (TTS), energy-to-solution (ETS), energy-delay product (EDP), and synchronization behavior for three transformer models (ALBERT, DistilBERT, BERT), trained with and without differential privacy (DP). We find that interconnect choice is the dominant driver of runtime and energy: host-managed InfiniBand consistently reduces communication overhead versus Ethernet, yielding lower TTS/ETS/EDP. In contrast, in our NVFLARE deployment, placing the FL server on the DPU does not consistently match CPU-InfiniBand performance and can be slower—especially for larger models—highlighting that server placement alone is not sufficient to guarantee end-to-end gains. Finally, under our fixed-round protocol, DP increases per-round cost and runtime variance; ETS increases largely in proportion to TTS because average node power remains relatively stable across configurations.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2018

Shrink or Substitute: Handling Process Failures in HPC Systems Using In-Situ Recovery

Efficient utilization of today's high-performance computing (HPC) systems with complex software and hardware components requires that the HPC applications are designed to tolerate process failures at runtime. With low mean-time-to-failure (MTTF) of current and future HPC systems, long running simulations on these systems requires capabilities for gracefully handling process failures by the applications themselves. In this paper, we explore the use of fault tolerance extensions to Message Passing Interface (MPI) called user-level failure mitigation (ULFM) for handling process failures without the need to discard the progress made by the application. We explore two alternative recovery strategies, which use ULFM along with application-driven in-memory checkpointing. In the first case, the application is recovered with only the surviving processes, and in the second case, spares are used to replace the failed processes, such that the original configuration of the application is restored. Our experimental results demonstrate that graceful degradation is a viable alternative for recovery in environments where spares may not be available.

Ashraf, Rizwan↗
DOE OSTI2020

On Transfer Learning Of Neural Networks Using Bi-Fidelity Data For Uncertainty Propagation

Due to their high degree of expressiveness, neural networks have recently been used as surrogate models for mapping inputs of an engineering system to outputs of interest. Once trained, neural networks are computationally inexpensive to evaluate and remove the need for repeated evaluations of computationally expensive models in uncertainty quantification applications. However, given the highly parameterized construction of neural networks, especially deep neural networks, accurate training often requires large amounts of simulation data that may not be available in the case of computationally expensive systems. In this paper, to alleviate this issue for uncertainty propagation, we explore the application of transfer learning techniques using training data generated from both high- and low-fidelity models. We explore two strategies for coupling these two datasets during the training procedure, namely, the standard transfer learning and the bi-fidelity-weighted learning. In the former approach, a neural network model mapping the inputs to the outputs of interest is trained based on the low-fidelity data. The high-fidelity data are then used to adapt the parameters of the upper layer(s) of the low-fidelity network, or train a simpler neural network to map the output of the low-fidelity network to that of the high-fidelity model. In the latter approach, the entire low-fidelity network parameters are updated using data generated via a Gaussian process model trained with a small high-fidelity dataset. The parameter updates are performed via a variant of stochastic gradient descent with learning rates given by the Gaussian process model. Using three numerical examples, we illustrate the utility of these bi-fidelity transfer learning methods where we focus on accuracy improvement achieved by transfer learning over standard training approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Compact folded metasurface spectrometer

Abstract An optical design space that can highly benefit from the recent developments in metasurfaces is the folded optics architecture where light is confined between reflective surfaces, and the wavefront is controlled at the reflective interfaces. In this manuscript, we introduce the concept of folded metasurface optics by demonstrating a compact spectrometer made from a 1-mm-thick glass slab with a volume of 7 cubic millimeters. The spectrometer has a resolution of ~1.2 nm, resolving more than 80 spectral points from 760 to 860 nm. The device is composed of three reflective dielectric metasurfaces, all fabricated in a single lithographic step on one side of a substrate, which simultaneously acts as the propagation space for light. The folded metasystem design can be applied to many optical systems, such as optical signal processors, interferometers, hyperspectral imagers, and computational optical systems, significantly reducing their sizes and increasing their mechanical robustness and potential for integration.

47 OTHER INSTRUMENTATION↗
DOE OSTI2019

Spack-Based Packaging and Development for HEP

The art event-based analysis framework is used by multiple Intensity Frontier and other experiments and projects in High Energy Physics (HEP). A system of tools and scripts based around a Fermilab-originated package management system called UNIX Product Support (UPS) has evolved to provide development, packaging, release management, and distribution of the art suite, related experimental software and external dependencies in relocatable binary form. The existing system has limitations in environments such as macOS with System Integrity Protection (SIP) enabled and the various High Performance Computing (HPC) systems that the field of HEP is increasingly looking to leverage. This has led to a search for other ways of providing experiments with a packaging and build system that meets their needs. We describe our efforts to develop a packaging and release management system based on the Spack HPC package management tool to replace the existing UPS-based system. We additionally describe a companion system: SpackDev and cetmodules, allowing simultaneous development of multiple HEP software packages in a consistent environment. A successful implementation of the intended system would have applicability across HEP rather than merely to the users of the art framework.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2015

Numerical prediction of fiber orientation in injection-molded short-fiber/thermoplastic composite parts with experimental validation

Numerical prediction of the fiber orientation in the short-glass fiber (GF) reinforced polyamide 6 (PA6) composites with the fiber weight concentration of 30%, 50%, and 70% manufactured by the injection molding process is presented. And the fiber orientation was also directly observed and measured through X-ray computed tomography. During the injection molding process of the short-fiber/thermoplastic composite, the fiber orientation is produced by the flow states and the fiber-fiber interaction. Folgar and Tucker equation is the well known for modeling the fiber orientation in a concentrated suspension. They included into Jeffrey’s equation a diffusive type of term by introducing a phenomenological coefficient to account for the fiber-fiber interaction. Our developed model for the fiber-fiber interaction was proposed by modifying the rotary diffusion term of the Folgar-Tucker equation. This model was presented in a conference paper of the 29{sup th} International Conference of the Polymer Processing Society published by AIP conference proceeding. For modeling fiber interaction, the fiber dynamic simulation was introduced in order to obtain a global fiber interaction coefficient, which is sum function of the fiber concentration, aspect ratio, and angular velocity. The fiber orientation is predicted by using the proposed fiber interaction model incorporated into a computer aided engineering simulation package C-Mold. An experimental program has been carried out in which the fiber orientation distribution has been measured in 100 x 100 x 2 mm injection-molded plate and 100 x 80 x 2 mm injection-molded weld by analyzed with a high resolution 3D X-ray computed tomography system XVA-160α, and calculated by X-ray computed tomography imaging. The numerical prediction shows a good agreement with experimental validation. And the complex fiber orientation in the injection-molded weld was investigated.

42 ENGINEERING↗
DOE OSTI2023

Proxy Applications for Converged Workloads: DMC LDRD Initiative

Modern scientific applications are complicated and require coordination of several components. Proxy application driven software-hardware co-design plays a vital role in driving innovation among the developments of applications, software infrastructure and hardware architecture. Proxy applications are self-contained and simplified codes that are intended to model the performance-critical computations within applications. Applications executing on modern High Performance Computing (HPC) systems are susceptible to network congestion, insufficient memory bandwidth within and across compute nodes, and inadvertent loss of performance due to bugs and unoptimized programming models. Modern numerical simulations and machine learning models play a critical role in studying physical phenomenon under myriad uncertainties. Such applications often exhibit irregular computation and memory accesses at specific regions of the application code, which can contribute to various performance bottlenecks at scale. To mitigate such issues and prepare the next generation hardware for a variety of computation and data movement contingencies, a well-known practice is to consider "proxy" applications as representative motifs for various classes of scientific applications. While there is disagreement in the HPC community on the mechanisms of construction of the proxy applications, there is a strong consensus on their positive impact in co-design. Proxy Applications for Converged Workloads (PACER) is about facilitating software-hardware co-design through proxy applications with the goal of improving the performance of converged science workflows on heterogeneous systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Systems and methods for distributed power system model calibration

A computing device for distributed power system model calibration is provided. The computing device is programmed to receive event data and model response data associated with a model to simulate, wherein the model includes a plurality of parameters, divide the event data into a plurality of sets, wherein each set includes associated parameters, and transmit the plurality of sets of event data to a plurality of client nodes. Each client node of the plurality of client nodes is programmed to analyze a corresponding set of event data to determine updated parameters for the model. The computing device is further programmed to receive a plurality of updated parameters for the model from the plurality of client nodes and analyze the received plurality of updated parameters to determine at least one adjusted parameter.

Wang, Honggang↗
DOE OSTI2025

Generative Vulnerability Assessment for Cyber-Physical Systems

Cyber-physical systems (CPS) are highly susceptible to malicious attacks due to their complex dynamics and interconnectivity. A comprehensive understanding of their vulnerabilities is essential for designing effective resilience measures. This paper presents a data-driven attack generative system for evaluating the vulnerability of CPS. The proposed approach formulates the vulnerability assessment problem as determining the feasibility of a specific attack set based on two boundary functions that represent the effectiveness and stealthiness of attacks. The attack generative model is trained using a custom loss function, with two universal approximators designed to learn the effectiveness and stealthiness functions simultaneously. Theoretical results for successful generation and asymptotic convergence of the resulting training algorithm are given. As a result, the proposed approach is evaluated via numerical simulation of an IEEE 14-bus system and gas pipeline systems, demonstrating its viability in learning how to attack nonlinear CPS and identify potential vulnerabilities.

Computer systems organization↗
DOE OSTI2020

Supercritical Reforming of Wet Ethanol for High Efficiency Direct-injection Heavy-duty Compression-ignition Engines

The purpose of the research was to investigate the potential of using a mature bio-fuel in heavy-duty compression ignition engines. By co-optimizing both the fuel characteristics and engine system the potential for a superior outcome was demonstrated. The use of wet bio-ethanol eliminates the majority of the energy intensive distilling and dehydrating fuel production processes, which moves the fuel towards carbon neutral and also lowers the fuel costs. The relatively high water content of the resulting fuel is leveraged in the proposed novel combustion system by incorporating an integrated high efficiency exhaust waste heat recovery system. This results in significantly higher thermal efficiency. In addition the combustion system features low criteria pollutant emissions and the potential to reduce the initial cost of the engine system hardware. Substantial societal benefits are demonstrated through the co-optimization of the fuel and engine system. A computational proof-of-concept study has been performed to demonstrate the potential benefits of a novel wet ethanol heavy-duty compression ignition combustion system featuring integrated exhaust waste heat recovery. A combined in-cylinder closed cycle 3D computational fluid dynamics (CFD) - 1D engine system simulation approach was used. The models were validated to baseline engine data using diesel fuel and then applied to the wet ethanol study. The original concept was to maximize exhaust waste heat recovery through supercritical reforming of the wet ethanol fuel. Phase I simulation results indicated that the optimal solution for maximum engine efficiency gains were realized through maximizing thermo-mechanical recuperation with negligible fuel reformation. The results show the potential to achieve impressive gains in brake thermal efficiency (BTE) over the base diesel engine. The potential to increase BTE up to 20.9% over the base diesel engine was demonstrated, with even larger gains possible through reduced in-cylinder heat transfer losses. The majority of the efficiency gains were realized through integrated high efficiency exhaust waste heat recovery. The concept also has the potential to achieve future ultra-low NO x emissions standards and negligible engine-out soot emissions. The mixing controlled combustion of high temperature wet ethanol features relatively low engine-out NO x emissions without the need for exhaust gas recirculation (EGR). The soot free combustion enabled by the relatively high oxygen content of ethanol also allows for the use of stoichiometric mixing controlled combustion, which is not practical with diesel fuel. When stoichiometric combustion is used a simple passive 3-way catalyst can be used for exhaust emissions after-treatment and near zero tailpipe emissions. The Phase I simulations results have defined the system layout and requirements in preparation for the Phase II experimental proof-of-concept study. The potential applications of the research include most current applications of diesel engines. The Phase I study focused on heavy-duty on-highway class 8 trucks. However, virtually any application that requires highly efficient clean power generation would benefit from the novel engine system proposed. The results indicate substantial fuel cost savings and reduced greenhouse gas emissions with similar or reduced initial system hardware costs compared to modern diesel engine systems.

09 BIOMASS FUELS↗
DOE OSTI2016

Data Movement in Data-Intensive High Performance Computing.

The cost of executing a floating point operation has been decreasing for decades at a much higher rate than that of moving data. Bandwidth and latency, two key metrics that determine the cost of moving data, have degraded significantly relative to processor cycle time and execution rate. Despite the limitation of sub-micron processor technology and the end of Dennard scaling, this trend will continue in the short-term making data movement a performance-limiting factor and an energy/power efficiency concern. Even more so in the context of large-scale and data-intensive systems and workloads. This chapter gives an overview of the aspects of moving data across a system, from the storage system to the computing system down to the node and processor level, with case study and contributions from researchers at the San Diego Supercomputer Center, the Oak Ridge National Laboratory, the Pacific Northwest National Laboratory, and the University of Delaware.

Data Movement↗