SEARCH · Engineering Papers
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.
This software package orchestrates execution of a workflow of jobs on distributed computing resources. It is optimized for use on HPCs with Slurm, but also can be used in the cloud and on local computers. Please refer to the documentation at https://nrel.github.io/torc
SF-25-127AdaParse (Adaptive Parallel PDF Parsing and Resource Scaling Engine) enables scalable, high-accuracy PDF parsing. AdaParse is a data-driven strategy that assigns an appropriate parser to each document, offering high accuracy for any computational budget. Moreover, it offers a workflow of various PDF parsing software that includes extraction tools: PyMuPDF, pypdf traditional OCR: Tesseract, modern OCR (e.g., Vision Transformers): Nougat and Marker
LBNL_DIATOMICS is a software package developed by P. Zarzycki (Lawrence Berkeley National Laboratory) for computing isotopic effects in diatomic molecules using mass-dependent spectroscopic parameters obtained experimentally or from first principles. The package provides a streamlined pipeline from the potential energy surface to the equilibrium constant of an isotopic exchange reaction.
Ubiquitous web-based visualization is essential to delivering large-scale data visualization to various stakeholders, from the scientist to the board member. These stakeholders will not tolerate a stalled application or a pop-up window asking them to wait for the processing to complete. They require a responsive and interactive visualization environment with high-quality imagery suitable for detailed analysis and boardroom presentations. At Kitware, Inc., we have accomplished web visualization to this point, leveraging state-of-the-art tools like HTML5, CSS3, SVG, Canvas, and WebGL. Solutions that leverage a combination of these technologies are necessary to handle workloads that vary significantly in data size efficiently. However, it is not always practical to move large data to the web client for visualization. Kitware's ParaView as a Service combines client-side visualization using both distributed processing and remote rendering on big data impractical to move. Existing distributed processing and remote rendering solution's interactivity is below the expectations of web-based applications. Our project examined proposed solutions to the areas outlined above in ParaView as a Service. We have investigated concurrent pipelines, streaming images, progressive rendering, and optimization of algorithms and data movement to address these concerns. For the Phase I project, we completed the proposed work plan. As a result, the project produced three prototypes of essential importance for web visualization and the ParaView as a Service community. We created a simple desktop application for an interactive streamline placement prototype, a web-based interactive streamline placement prototype, and a web-based progressive rendering utilizing raytracing prototype. These prototypes relied on the hardening of emerging software toolkits funded by the Department of Energy (DOE) Advanced Scientific Computing Research (ASCR) program (such as ParaView, VTK-m, and Mochi). We blended these components into web-based visualization prototypes that meet the industry's expectations for interactivity and responsiveness. The Phase I project had four essential focus areas: 1. Develop prototype ParaView as a Service backend server using asynchronous, non-blocking design principles. 2. Develop a prototype web application that uses the ParaView as a Service backend server for remote data visualization. 3. Implement image streaming with encoding/compression and progressive rendering capabilities in the proposed platform. 4. Evaluate the prototype developed and summarize observations, including the challenges and pitfalls of our approach. After our successful completion of Phase I, we are strongly positioned to propose a successful Phase II project.
The National Renewable Energy Laboratory's Future Automotive Systems Technology Simulator (FASTSim) captures the most important factors influencing vehicle power demands and performs large-scale fuel efficiency calculations very quickly. These features make FASTSim well suited to evaluate a representative distribution of real-world fuel efficiency over a large quantity of in-use driving profiles, which have become increasingly available in recent years owing to incorporation of Global Positioning System data collection into various travel surveys and studies. In addition, by being open source, computationally lightweight, freely available, and free from expensive third-party software requirements, analyses conducted using FASTSim may be easily replicated and critiqued in an open forum. This is highly desirable for situations in which technical experts seek to reach consensus over questions about what vehicle development plans or public interest strategies could maximize fuel savings and minimize adverse environmental impacts with an evolving vehicle fleet. While FASTSim continues to be refined and improved on an ongoing basis, this report compiles available runs using versions of the tool from the past few years to provide illustrative comparisons of the model results against measured data.
The demand for user defined software stacks (UDSS) has been increasing in the high-performance computing (HPC) community. Container technology has become popular due to the flexibility and isolation it provides to HPC users. Container images must be available to all nodes involved for use in HPC and can be distributed to compute nodes in a variety of ways. A common method for container image distribution is to simply copy the container image to memory on each compute node, which can be time consuming at scale, and uses valuable memory on each node. The kernel mounted squash filesystem (squashfs) has proven fast and efficient for this task but requires root-level access. This paper will show a user space mounted squashfs is an efficient and secure solution for container image distribution.
Innovation in HPC hardware and adoption of heterogeneous systems has led to a variety of unique programming models. This has led to a challenge for scientific visualization software (and indeed all HPC software) to take full advantage of recent generations of supercomputing. Edge computing, where hardware is specialized for the needs of the particular application, exacerbates the problem. VTK-m has had many successes on this front by providing device-agnostic algorithms that compare favorably to implementations written to specific devices as shown in Table 1. However, VTK-m has focused mostly on GPU and traditional CPU multicore technology. There are numerous processor technologies, both existing and potential future, that are not being addressed by current R&D efforts.
Engineering design studies are being performed to determine the feasibility of converting the High Flux Isotope Reactor (HFIR) from highly enriched uranium (HEU) to low-enriched uranium (LEU) fuel at Oak Ridge National Laboratory. This activity is sponsored by the Office of Reactor Conversion and Uranium Supply (ORCUS) under the auspices of the US Department of Energy National Nuclear Security Administration’s Office of Material Management and Minimization. HFIR is a very high flux, pressurized, light water–cooled and moderated, flux trap–type research reactor with a core made of involute shaped U 3 O 8 /Al cermet fuel plates and coolant channels. HFIR currently operates at a thermal power of 85 MW and supports key national and international missions in neutron scattering, isotope production, materials/fuels irradiation, neutron activation analysis, gamma irradiation, and neutrino research. Advanced multiphysics computational fluid dynamics models have been developed in the COMSOL Multiphysics software to simulate the steady-state operating conditions for the proposed low-and high-density LEU U 3 Si 2 -Al (uranium silicide dispersion) fuel designs. The COMSOL models for HFIR inner and outer fuel element models incorporate various essential inputs and physics such as spatially dependent nuclear heat deposition, multilayer heat conduction, conjugate heat transfer, turbulent flows (using Reynolds-averaged Navier Stokes turbulence models), structural mechanics (thermal–structural interactions and fuel swelling), and oxide layer build-up. This report presents the best-estimate thermal hydraulics results for the low- and high-density optimized silicide LEU core designs at 95 MW steady-state nominal operation.
The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem, especially in the high interaction density conditions expected during the future high-luminosity phase of the LHC (HL-LHC). Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task by embedding tracker data as a graph—nodes represent hits, while edges represent possible track segments—and classifying the edges as true or fake track segments. However, their study in hardware- or software-based trigger applications has been limited due to their large computational cost. In this paper, we introduce an automated translation workflow, integrated into a broader tool called hls4ml , for converting GNNs into firmware for field-programmable gate arrays (FPGAs). We use this translation tool to implement GNNs for charged particle tracking, trained using the TrackML challenge dataset, on FPGAs with designs targeting different graph sizes, task complexites, and latency/throughput requirements. This work could enable the inclusion of charged particle tracking GNNs at the trigger level for HL-LHC experiments.
Commercialization of autonomous vehicle technology is a major goal of the automotive industry, thus research in this space is rapidly expanding across the world. However, despite this high level of research activity, literature detailing a straightforward and cost-effective approach to the development of an AV research platform is sparse. To address this need, we present the methodology and results regarding the AV instrumentation and controls of a 2019 Kia Niro which was developed for a local AV pilot program. This platform includes a drive-by-wire actuation kit, Aptiv electronically scanning radar, stereo camera, MobilEye computer vision system, LiDAR, inertial measurement unit, two global positioning system receivers to provide heading information, and an in-vehicle computer for driving environment perception and path planning. Robotic Operating System software is used as the system middleware between the instruments and the autonomous application algorithms. After selection, installation, and integration of these components, our results show successful utilization of all sensors, drive-by-wire functionality, a total additional power* consumption of 242.8 Watts (*Typical), and an overall cost of $118,189 USD, which is a significant saving compared to other commercially available systems with similar functionality. This vehicle continues to serve as our primary AV research and development platform.
The ATLAS experiment's software production and distribution on the grid benefits from a semi-automated infrastructure that provides up-to-date information about software usability and availability through the CVMFS dis-tribution service for all relevant systems. The software development process uses a Continuous Integration pipeline involving testing, validation, packag-ing and installation steps. For opportunistic sites that can not access CVMFS, containerized releases are needed. These standalone containers are currently created manually to support Monte-Carlo data production at such sites. In this paper we will describe an automated procedure for the containerization of AT-LAS software releases in the existing software development infrastructure, its motivation, integration and testing in the distributed computing system.
In response to the COVID-19 pandemic, the Exascale Computing Project’s (ECP) Interoperable Design of Extreme-scale Application Software (IDEAS) productivity team launched the panel series Strategies for Working Remotely to facilitate informal, cross-organizational dialog in the absence of face-to-face meetings. In a time of pandemic, organizations increasingly need to reach across perceived boundaries to learn from each other, so that we can move beyond stand-alone silos to more connected multidisciplinary and multiorganizational configurations. The present paper argues that the unplanned transition to remote work, overuse of electronic communication, and need to unlearn habits associated with an overreliance on face-to-face, created unique opportunities to learn from the situation and accelerate cross-institutional cooperation and collaboration through online community dialog facilitated by informal panel discussions. Recommendations for facilitating online panel discussions to foster cross-organizational dialog are provided by applying the Simulation Experience Design Method.
Hosting capacity is an indication of the amount of photovoltaics (PV) can be hosted in a distribution system. This paper presents a framework for estimating distributed PV hosting capacity at scale. We first analyze the key challenges of performing relevant large scale simulation including computational and modeling challenges. Then, we develop two python-based software tools in order to conduct repeatable distribution analyses: Distribution Integration Solution Cost Options (DISCO) for configuring and analyzing simulations, and JADE for parallelizing jobs on HPC clusters. A case study of hosting capacity estimation for SMART-DS SFO 2000+ synthetic feeders is used to demonstrate the capability of the developed framework and tools. The framework and tools can help utilities assess the overall hosting capacity of their service territory, through which the overall upgrade cost can be better planned in order to integrate more PV in the future.
A traditional HPC computing facility provides a large amount of computing power but has a fixed environment designed to satisfy local needs. This makes it very challenging for users to deploy complex applications that span multiple sites and require specific application software, scheduling middleware, or sharing policies. This project addressed many of these challenges by making it possible for researchers to easily aggregate and share resources, install custom software environments, and deploy clustering frameworks across multiple HPC facilities through the concept of “virtual clusters”. We designed and implemented a prototype virtual cluster facility that enabled unprivileged users to create dynamic aggregations of computing power across multiple sites, deployed with custom middleware and complex software dependencies. This service is hosted at the University of Chicago and available through the site virtualclusters.org.
SAND2024-02099O The software is designed to allow researchers to perform kinetic Monte Carlo (KMC) simulations of catalytic reactions on a 2D lattice. The code is written efficiently to run on a variety of shared memory computing architectures (e.g. GPU, multi-core) and to natively express the full complexity of lateral interactions on reaction rates. The software allows researchers to perform KMC simulations of catalytic reactions on a 2D lattice. It uses parallel shared-memory computing architectures to reduce run-times and allows for simultaneous simulation of multiple independent runs. 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.
In high performance computing (HPC), often a wide range of knowledge about the particular domains, software applications, and hardware architectures are necessary for applying the right optimizations in the appropriate contexts. In today’s practice, however, such knowledge has been expressed and managed in an ad-hoc manner by each individual. Systematic accumulation, sharing and reuse of the knowledge across a broad community has been difficult. This paper introduces OpenK, an ontology-based open infrastructure for solving the problem. By centering around ontology – a generic knowledge representation – and extensible designs, it offers a promising support for lowering the barriers.
The advent of Exascale computing invites an assessment of existing best practices for developing application readiness on the world's largest supercomputers. This work details observations from the last four years in preparing scientific applications to run on the Oak Ridge Leadership Computing Facility's (OLCF) Frontier system. This paper addresses a range of topics in software including programmability, tuning, and portability considerations that are key to moving applications from existing systems to future installations. A set of representative workloads provides case studies for general system and software testing. We evaluate the use of early access systems for development across several generations of hardware. Finally, we discuss how best practices were identified and disseminated to the community through a wide range of activities including user-guides and trainings. We conclude with recommendations for ensuring application readiness on future leadership computing systems.
The advent of Exascale computing invites an assessment of existing best practices for developing application readiness on the world's largest supercomputers. This work details observations from the last four years in preparing scientific applications to run on the Oak Ridge Leadership Computing Facility's (OLCF) Frontier system. This paper addresses a range of topics in software including programmability, tuning, and portability considerations that are key to moving applications from existing systems to future installations. A set of representative workloads provides case studies for general system and software testing. We evaluate the use of early access systems for development across several generations of hardware. Finally, we discuss how best practices were identified and disseminated to the community through a wide range of activities including user-guides and trainings. We conclude with recommendations for ensuring application readiness on future leadership computing systems.