SEARCH · Search NASA

Results for “Implementation Variants”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Stochastic average model methods

We consider the solution of finite-sum minimization problems, such as those appearing in nonlinear least-squares or general empirical risk minimization problems. We are motivated by problems in which the summand functions are computationally expensive and evaluating all summands on every iteration of an optimization method may be undesirable. Here we present the idea of stochastic average model (SAM) methods, inspired by stochastic average gradient methods. SAM methods sample component functions on each iteration of a trust-region method according to a discrete probability distribution on component functions; the distribution is designed to minimize an upper bound on the variance of the resulting stochastic model. We present promising numerical results concerning an implemented variant extending the derivative-free model-based trust-region solver POUNDERS, which we name SAM-POUNDERS.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

DTLMod: A simulation framework for in situ workflow optimization

In situ processing workflows have become essential for coping with the explosion in data volume and velocity in large-scale scientific computing, providing domain scientists with early insights at runtime. Multiple frameworks implement this paradigm through a data transport layer (DTL), offering different data access modes and deployment schemes, but researchers currently lack the appropriate tools to assess design and deployment options before committing to costly real experiments. We introduce DTLMod, an open-source simulated DTL that enables performance evaluation of in situ workflow configurations at scale. Built on SimGrid, it links into any SimGrid-based simulator and is available in C++ and Python. We evaluate DTLMod along four axes: scalability (tens of thousands of simulated processes across interconnected clusters in seconds, with linear memory scaling), versatility (three implementation variants trading fidelity for speed), accuracy (simulated times faithfully reflecting real behavior), and practical utility (two use cases demonstrating evidence-based workflow design decisions).

Suter, Fred [ORNL] (ORCID:0000000319021955)↗

NASA NTRS2003

Modified Polar-Format Software for Processing SAR Data

HMPF is a computer program that implements a modified polar-format algorithm for processing data from spaceborne synthetic-aperture radar (SAR) systems. Unlike prior polar-format processing algorithms, this algorithm is based on the assumption that the radar signal wavefronts are spherical rather than planar. The algorithm provides for resampling of SAR pulse data from slant range to radial distance from the center of a reference sphere that is nominally the local Earth surface. Then, invoking the projection-slice theorem, the resampled pulse data are Fourier-transformed over radial distance, arranged in the wavenumber domain according to the acquisition geometry, resampled to a Cartesian grid, and inverse-Fourier-transformed. The result of this process is the focused SAR image. HMPF, and perhaps other programs that implement variants of the algorithm, may give better accuracy than do prior algorithms for processing strip-map SAR data from high altitudes and may give better phase preservation relative to prior polar-format algorithms for processing spotlight-mode SAR data.

Chen, Curtis↗

NASA NTRS2018

Evaluation of Opportunistic Contact Graph Routing in Random Mobility Environments

Routing in networks where nodes move randomly is particularly challenging due their potentially unpredictable, and rapidly changing topology. Several routing algorithms have been presented in the literature to address the needs of such networks, most of them implementing variants of controlled network ﬂooding in the hope of successful data delivery. In this note, we compare the results of previous routing algorithms with Opportunistic Contact Graph Routing (OCGR), an enhanced version of Contact Graph Routing (CGR) that is suitable for networks where contacts cannot always be scheduled ahead of time. To perform the benchmark, we simulate a network of nodes moving in a certain space according to the Random Waypoint Mobility Model, and then take measurements of bundle delivery probabilty and overhead ratio as metrics of performance and cost respectively. Through this exercise, we demonstrate that the performance of OCGR is highly dependent on the type of network under consideration (e.g. very sparse vs. densely connected) and the assumed mobility model.

Burleigh, Scott↗

NASA NTRSDate not supplied

DC Modeling of 4H-SiC JFET Gate Length Reduction at 500°C

The development of robust, high-performance integrated circuits (ICs) will enable numerous potential NASA missions of current interest, including long-duration robotic missions exploring the 460 °C surface of Venus. Currently, NASA is looking towards SiC-based devices to provide such a solution. However, the current NASA silicon carbide (SiC) JFET device with a channel length of 6μm (for recently fabricated Gen. 11 ICs) limits on mission relevant circuit capabilities [1]. In this study, we combined experiments with simulations to explore two straightforward fabrication strategies to reduce the SiC JFET channel length while maintaining turn-off behavior (Fig. 1a) needed to realize 500 °C circuit operation. The first fabrication strategy uses a shallow self-align nitrogen implant (Figure 1b) along the device's top surface but not below the gate combined with a high-dose phosphorous implant directly below the source and drain contacts. For the second fabrication strategy (Figure 1c), the high-dose phosphorous implants extended from below the contacts all the way up to the gate edges. Simulations guided gate length reductions without significant degradation in the turn-off performance. In total 12 SiC JFET variants implementing using the different fabrication strategies, gate lengths, and n-channel epilayer thickness were implemented in our simulation framework implemented in COMSOL. Since the COMSOL database does not have the material properties for 4H-SiC, these parameters were taken from the literature and implemented in COMSOL. The empirical models [2] for incomplete ionization, Auger recombination, low field mobility, and Shockley-Read-Hall recombination were implemented to account for material-specific device behavior.

4H-SiC JFET↗

DOE OSTI2025

Direct structural retrieval from gas-phase ultrafast diffraction data using a genetic algorithm

Ultrafast scattering techniques such as ultrafast electron diffraction and ultrafast x-ray diffraction have been utilized to elucidate the structural dynamics, reaction intermediates, and final products in molecular reactions following photoexcitation. The time-dependent structures are typically not directly retrieved from the experimental data, but they rely on comparison with calculations. The genetic algorithm (GA), a global optimization strategy, can be used to retrieve the molecular structures directly from diffraction patterns without any theoretical input. However, the robustness of the GA with respect to real experimental conditions such as a limited momentum transfer range, noise, and artifacts has not been studied in detail. In this work, we characterize the performance of the GA with simulated data that mimic realistic experimental conditions. We have developed and implemented a variant of the GA specific to diffraction measurements which performs better in the presence of imperfect data compared to the standard implementation of the GA. We demonstrate this method with both synthetic data and experimental ultrafast electron diffraction data on the UV-induced photodissociation of trifluoroiodomethane (C⁢F 3⁡ I) molecules.

74 ATOMIC AND MOLECULAR PHYSICS↗

DOE OSTI2025

Insights from Optimizing HPL Performance on Exascale Systems: A Comparative Analysis of Panel Factorization

High performance LINPACK (HPL) remains the primary benchmark for evaluating supercomputing performance. It includes many parts with substantial internal complexity, and its performance is affected by a large number of parameters that interact in ways that are difficult to predict on large-scale heterogeneous supercomputer systems. We present a comprehensive performance analysis of HPL on Frontier, the world’s first exascale supercomputer, which achieved HPL performance of 1.35 exaflops. Through empirical parameter tuning, detailed modeling, and comparative evaluation, we uncover critical performance insights, share lessons learned, and outline best practices for effective parameter tuning on exascale systems. We introduce and evaluate two novel PDFACT strategies: a dedicated-thread (DT) variant and a GPU-based variant (GPUPDFACT) implementation using HIP cooperative groups, demonstrating that GPU-based factorization outperforms conventional CPU-based PDFACT on Frontier’s architecture. Our findings establish key performance factors for HPL on exascale systems and offer valuable guidance for future high-performance computing and benchmarking efforts.

Lu, Hao [ORNL] (ORCID:000000018941870X)↗

DOE OSTI2024

Accuracy optimized neural networks do not effectively model optic flow tuning in brain area MSTd

Accuracy-optimized convolutional neural networks (CNNs) have emerged as highly effective models at predicting neural responses in brain areas along the primate ventral stream, but it is largely unknown whether they effectively model neurons in the complementary primate dorsal stream. We explored how well CNNs model the optic flow tuning properties of neurons in dorsal area MSTd and we compared our results with the Non-Negative Matrix Factorization (NNMF) model, which successfully models many tuning properties of MSTd neurons. To better understand the role of computational properties in the NNMF model that give rise to optic flow tuning that resembles that of MSTd neurons, we created additional CNN model variants that implement key NNMF constraints – non-negative weights and sparse coding of optic flow. While the CNNs and NNMF models both accurately estimate the observer's self-motion from purely translational or rotational optic flow, NNMF and the CNNs with nonnegative weights yield substantially less accurate estimates than the other CNNs when tested on more complex optic flow that combines observer translation and rotation. Despite its poor accuracy, NNMF gives rise to tuning properties that align more closely with those observed in primate MSTd than any of the accuracy-optimized CNNs. This work offers a step toward a deeper understanding of the computational properties and constraints that describe the optic flow tuning of primate area MSTd.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Robust Tensor Hypercontraction of the Particle–Particle Ladder Term in Equation-of-Motion Coupled Cluster Theory

One method of representing a high-rank tensor as a (hyper-)product of lower-rank tensors is the tensor hypercontraction (THC) method of Hohenstein et al. This strategy has been found to be useful for reducing the polynomial scaling of coupled-cluster methods by representation of a four-dimensional tensor of electron-repulsion integrals in terms of five two-dimensional matrices. Pierce et al. have already shown that the application of a robust form of THC to the particle–particle ladder (PPL) term reduces the cost of this term in couple-cluster singles and doubles (CCSD) from O(N 6 ) to O(N 5 ) with negligible errors in energy with respect to the density-fitted variant. In this work, we have implemented the least-squares variant of THC (LS-THC) which does not require a nonlinear tensor factorization, including the robust form (R-LS-THC), for the calculation of the excitation and electron attachment energies using equation-of-motion coupled cluster methods EOMEE-CCSD and EOMEA-CCSD, respectively. We have benchmarked the effect of the R-LS-THC-PPL approximation on excitation energies using the comprehensive QUEST database and the accuracy of electron attachment energies using the NAB22 database. Here, we find that errors on the order of 1 meV are achievable with a reduction in total calculation time of approximately 5x.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Implementation of an ICS Ransomware Testbed: Scenarios, Variants, and Evaluation Methods

Ransomware attacks on Industrial Control Systems (ICS) have emerged as a formidable threat to the United States’ critical infrastructure, eliciting grave concerns regarding national security. In March 2023, the FBI Internet Crime Complaint Center (IC3) unveiled its 2022 Internet Crime Report, highlighting a concerning 870 complaints related to ransomware impacting U.S. critical infrastructure. Of the country's 16 critical infrastructure sectors, 14 encountered at least one ransomware attack. Notably, while the Healthcare and Public Health sector suffered the most, reporting 210 attacks, sectors pivotal to ICS networks and governmental organizations were also targeted: the Defense Industrial Base reported 1 attack, Water and Wastewater Systems 3, Chemical 19, Energy 15, Government Facilities 115, and Critical Manufacturing 157. For instance, a ransomware attack on a major chemical company could jeopardize not only its production but also pose environmental risks should systems controlling hazardous materials be compromised. In 2022, three ransomware variants predominantly targeted U.S. critical infrastructure: HIVE, with 87 attacks; ALPHV/BlackCat, with 114; and LOCKBIT, with 149. Several cyber-attacks, such as the MOVEit data breach in May 2023 and the Colonial Pipeline ransomware attack in May 2021, have been so impactful that they commanded national attention. The DarkSide hacking group's assault on the Colonial Pipeline, initiated on May 6th, 2021, stands as one of the most substantial and publicly acknowledged cyber-attacks against U.S. critical infrastructure. The group exploited an exposed Virtual Private Network (VPN) password, paving the way for initial intrusion and subsequent data theft. A mere day later, DarkSide unleashed a ransomware attack that compromised vital accounting and billing systems, prompting an immediate shutdown of the pipeline to mitigate further ransomware proliferation across its network. This crisis spurred a robust response from the U.S. president and regulators, culminating in a national emergency declaration related to the pipeline shutdown on May 9th, 2021. This incident mirrors the 2017 NotPetya ransomware attack that significantly impacted the shipping giant Maersk, highlighting an urgent need for fortified cybersecurity across various industries. Future incidents, akin to the Colonial Pipeline attack, could potentially be mitigated—or entirely averted—should government agencies and private entities scrutinize system vulnerabilities, exploring various ransomware types and entry points. Proactive measures, such as conducting experiments on VPN accounts or auditing passwords to pinpoint duplicate usage across diverse systems and software, might illuminate feasible entry points and vulnerability zones within an organization's systems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS1997

Discretization and Preconditioning Algorithms for the Euler and Navier-Stokes Equations on Unstructured Meshes

Several stabilized discretization procedures for conservation law equations on triangulated domains will be considered. Specifically, numerical schemes based on upwind finite volume, fluctuation splitting, Galerkin least-squares, and space discontinuous Galerkin discretization will be considered in detail. A standard energy analysis for several of these methods will be given via entropy symmetrization. Next, we will present some relatively new theoretical results concerning congruence relationships for left or right symmetrized equations. These results suggest new variants of existing FV, DG, GLS and FS methods which are computationally more efficient while retaining the pleasant theoretical properties achieved by entropy symmetrization. In addition, the task of Jacobian linearization of these schemes for use in Newton's method is greatly simplified owing to exploitation of exact symmetries which exist in the system. These variants have been implemented in the "ELF" library for which example calculations will be shown. The FV, FS and DG schemes also permit discrete maximum principle analysis and enforcement which greatly adds to the robustness of the methods. Some prevalent limiting strategies will be reviewed. Next, we consider embedding these nonlinear space discretizations into exact and inexact Newton solvers which are preconditioned using a nonoverlapping (Schur complement) domain decomposition technique. Elements of nonoverlapping domain decomposition for elliptic problems will be reviewed followed by the present extension to hyperbolic and elliptic-hyperbolic problems. Other issues of practical relevance such the meshing of geometries, code implementation, turbulence modeling, global convergence, etc. will be addressed as needed.

Barth, Timothy↗

DOE OSTI2025

DIF3D-VARIANT 12.0: Updates and New Features

The DIF3D code has been a workhorse of fast reactor analysis work at Argonne National Laboratory for over 40 years. In 1995, a transport option called VARIANT was added to DIF3D to improve the flux solutions for fast reactor problems which we term DIF3D-VARIANT today. DIF3D-VARIANT performs nodal neutron transport calculations using P N or SP N theory in Cartesian and hexagonal two- and three-dimensional geometries. The limited computing capabilities of the time restricted DIF3D-VARIANT to use at most a 6 th order spatial approximation combined with a P3 flux approximation and P1 scattering kernel for a 33 group structure on most studied reactor problems. Computer capabilities have increased steadily since 1995 and today much larger space-angle-energy approximations are possible. This manuscript serves as an update to the theory section of the original DIF3D-VARIANT manual and details more than twenty years of changes made to DIF3D to make version 12 which was released on November 1 st , 2024. The primary focus of the initial work was to extend the space-angle approximations available in DIF3D-VARIANT such that the error due to transport approximations could be better understood. This work was started and completed in 2002 and marked the official version 10. Unfortunately, those higher order approximations could not be used at that time due to the memory constraints of the BPOINTER part of DIF3D (limited to 2 GB). In version 11, completed in 2012, BPOINTER was circumvented in DIF3D-VARIANT for the largest arrays by introducing a Fortran 90 module called LMA (Large Memory Array). This seamlessly replaces all of the functionality of the BPOINTER concept, but it allows 64 bit addressing for every array such that they can be larger than 2 GB. It is now common for DIF3D-VARIANT jobs to consume 50 GB of memory on modern workstations when using high order space-angle approximations and a large number of groups. Many improvements were made to version 11 from 2012 to 2022 when work to create version 12 started. For version 12, several parts of DIF3D were updated to improve performance and thread parallelism was introduced to further reduce the runtime. Numerous minor bugs were discovered in DIF3D-VARIANT as part of the process of creating the perturbation and sensitivity code PERSENT. All of these algorithmic problems were identified in the transition from version 10 to version 11 which prevented DIF3D-VARIANT from running efficiently and reliably. Firstly, the coarse mesh rebalance scheme would routinely diverge and a study detailed in this report demonstrates how it was also typically not effective. This is not a failure of the coarse mesh rebalance methodology, but a failure of its implementation in DIF3D-VARIANT for hexagonal geometries. The fission source extrapolation algorithm was also found to be unreliable on larger group structure problems, leading to divergence in some cases and a negligible improvement in performance overall. Finally, the “Omega” acceleration applied to the partial current solver routine of DIF3D-VARIANT was found to cause DIF3D-VARIANT to converge to the wrong answer. To resolve these issues, both the coarse mesh rebalance and fission source extrapolation were permanently disabled in version 11. The Tchebychev acceleration was put in as a temporary reliable alternative but it is generally inferior to coarse mesh rebalance or coarse mesh finite difference. For the Omega acceleration, the factor was restricted to guarantee that it would not cause follow-on errors in PERSENT. Due to limited funding to support maintenance and development of DIF3D in the last 10 years, no effort was spent since to resolve the outer iteration acceleration. Except for the threading work, all of the changes discussed in this manuscript refer to changes made between version 10 and version 11. Performance comparisons are done to demonstrate the improvements from version 9 to version 12. As will be demonstrated, the updated versi

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS2018

SLS Navigation Model-Based Design Approach

The SLS Program chose to implement a Model-based Design and Model-based Requirements approach for managing component design information and system requirements. This approach differs from previous large-scale design efforts at Marshall Space Flight Center where design documentation alone conveyed information required for vehicle design and analysis and where extensive requirements sets were used to scope and constrain the design. The SLS Navigation Team has been responsible for the Program-controlled Design Math Models (DMMs) which describe and represent the performance of the Inertial Navigation System (INS) and the Rate Gyro Assemblies (RGAs) used by Guidance, Navigation, and Controls (GN&C). The SLS Navigation Team is also responsible for the navigation algorithms. The navigation algorithms are delivered for implementation on the flight hardware as a DMM. For the SLS Block 1-B design, the additional GPS Receiver hardware is managed as a DMM at the vehicle design level. This paper provides a discussion of the processes and methods used to engineer, design, and coordinate engineering trades and performance assessments using SLS practices as applied to the GN&C system, with a particular focus on the Navigation components. These include composing system requirements, requirements verification, model development, model verification and validation, and modeling and analysis approaches. The Model-based Design and Requirements approach does not reduce the effort associated with the design process versus previous processes used at Marshall Space Flight Center. Instead, the approach takes advantage of overlap between the requirements development and management process, and the design and analysis process by efficiently combining the control (i.e. the requirement) and the design mechanisms. The design mechanism is the representation of the component behavior and performance in design and analysis tools. The focus in the early design process shifts from the development and management of design requirements to the development of usable models, model requirements, and model verification and validation efforts. The models themselves are represented in C/C++ code and accompanying data files. Under the idealized process, potential ambiguity in specification is reduced because the model must be implementable versus a requirement which is not necessarily subject to this constraint. Further, the models are shown to emulate the hardware during validation. For models developed by the Navigation Team, a common interface/standalone environment was developed. The common environment allows for easy implementation in design and analysis tools. Mechanisms such as unit test cases ensure implementation as the developer intended. The model verification and validation process provides a very high level of component design insight. The origin and implementation of the SLS variant of Model-based Design is described from the perspective of the SLS Navigation Team. The format of the models and the requirements are described. The Model-based Design approach has many benefits but is not without potential complications. Key lessons learned associated with the implementation of the Model Based Design approach and process from infancy to verification and certification are discussed

Oliver, T. Emerson↗

NASA NTRSDate not supplied

USM3D-ME Revised SA-neg Implementation and Assessment for Seventh Drag Prediction Workshop Solutions

Simulations performed by an unstructured-grid, cell-centered, finite-volume, mixed-element flow solver USM3D-MEwere presented at the Seventh Drag Prediction Workshop (DPW-7). Reynolds-averaged Navier-Stokes (RANS) solutions for the NASA high-speed common research model wing-body configuration were computed using a new implementation of the negative variant of the Spalart-Allmaras turbulence model (SA-neg) with hierarchical adaptive nonlinear iteration method (HANIM).ThisUSM3D-ME enhancement improved efficiency and robustness of RANS solutions resulting in fast iterative convergence to machine zero residuals on mixed-element unstructured grids provided by the DPW-7 organizing committee. This paper presents theoretical foundations for the new implementation of the SA-neg model and analyzesUSM3D-ME solutions for flow conditions corresponding to the required DPW-7 cases.

Boris Diskin↗

DOE OSTI2023

Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation

We evaluate AI-assisted generative capabilities on fundamental numerical kernels in high-performance computing (HPC), including AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG. We test the generated kernel codes for a variety of language-supported programming models, including (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). We use the GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code as of April 2023 to generate a vast amount of implementations given simple + + prompt variants. To quantify and compare the results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. Results suggest that the OpenAI Codex outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general purpose Python can benefit from adding code keywords, while Julia prompts perform acceptably well for its mature programming models (e.g., Threads and CUDA.jl). We expect for these benchmarks to provide a point of reference for each programming model's community. Overall, understanding the convergence of large language models, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

Godoy, William↗

NASA NTRS2018

Advanced Symbolic Analysis Tools for Fault-Tolerant Integrated Distributed Systems

The project aims to develop advanced model-checking algorithms and tools to automate the verification of fault-tolerant distributed systems for avionics. We present a new method called Property-Directed K-Induction (PD-KIND) for synthesizing K-inductive invariants of state-transition systems. PD-KIND builds upon Satifiability Modulo Theories (SMT) to generalize Bradley's IC3 method and its variants. This method is implemented in a new tool called SALLY. Case studies show that PD-KIND can automatically verify fault-tolerant algorithms under a variety of fault models and that SALLY is competitive with other SMT-based model checkers.

Dutertre, Bruno↗

NASA NTRS1995

Verification and validation of a reliable multicast protocol

This paper describes the methods used to specify and implement a complex communications protocol that provides reliable delivery of data in multicast-capable, packet-switching telecommunication networks. The protocol, called the Reliable Multicasting Protocol (RMP), was developed incrementally by two complementary teams using a combination of formal and informal techniques in an attempt to ensure the correctness of the protocol implementation. The first team, called the Design team, initially specified protocol requirements using a variant of SCR requirements tables and implemented a prototype solution. The second team, called the V&V team, developed a state model based on the requirements tables and derived test cases from these tables to exercise the implementation. In a series of iterative steps, the Design team added new functionality to the implementation while the V&V team kept the state model in fidelity with the implementation through testing. Test cases derived from state transition paths in the formal model formed the dialogue between teams during development and served as the vehicles for keeping the model and implementation in fidelity with each other. This paper describes our experiences in developing our process model, details of our approach, and some example problems found during the development of RMP.

Callahan, John R.↗

NASA NTRS1994

Toward fidelity between specification and implementation

Callahan, John R.↗