SEARCH · Engineering Papers

Results for “coding productivity”

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 1,135 records · Page 63

All sources NASA NTRS DOE OSTI

NASA NTRS2011

Rapid Calculation of Spacecraft Trajectories Using Efficient Taylor Series Integration

A variable-order, variable-step Taylor series integration algorithm was implemented in NASA Glenn's SNAP (Spacecraft N-body Analysis Program) code. SNAP is a high-fidelity trajectory propagation program that can propagate the trajectory of a spacecraft about virtually any body in the solar system. The Taylor series algorithm's very high order accuracy and excellent stability properties lead to large reductions in computer time relative to the code's existing 8th order Runge-Kutta scheme. Head-to-head comparison on near-Earth, lunar, Mars, and Europa missions showed that Taylor series integration is 15.8 times faster than Runge- Kutta on average, and is more accurate. These speedups were obtained for calculations involving central body, other body, thrust, and drag forces. Similar speedups have been obtained for calculations that include J2 spherical harmonic for central body gravitation. The algorithm includes a step size selection method that directly calculates the step size and never requires a repeat step. High-order Taylor series integration algorithms have been shown to provide major reductions in computer time over conventional integration methods in numerous scientific applications. The objective here was to directly implement Taylor series integration in an existing trajectory analysis code and demonstrate that large reductions in computer time (order of magnitude) could be achieved while simultaneously maintaining high accuracy. This software greatly accelerates the calculation of spacecraft trajectories. At each time level, the spacecraft position, velocity, and mass are expanded in a high-order Taylor series whose coefficients are obtained through efficient differentiation arithmetic. This makes it possible to take very large time steps at minimal cost, resulting in large savings in computer time. The Taylor series algorithm is implemented primarily through three subroutines: (1) a driver routine that automatically introduces auxiliary variables and sets up initial conditions and integrates; (2) a routine that calculates system reduced derivatives using recurrence relations for quotients and products; and (3) a routine that determines the step size and sums the series. The order of accuracy used in a trajectory calculation is arbitrary and can be set by the user. The algorithm directly calculates the motion of other planetary bodies and does not require ephemeris files (except to start the calculation). The code also runs with Taylor series and Runge-Kutta used interchangeably for different phases of a mission.

Scott, James R.↗

DOE OSTI2024

Using containers to speed up development, to run integration tests and to teach about distributed systems

GlideinWMS is a workload manager provisioning resources for many experiments including CMS and DUNE. The software is distributed both as native packages and specialized production containers. Following an approach used in other communities like web development we built our workspaces, system-like containers to ease development and testing. Developers can change the source tree or check out a different branch and quickly reconfigure the services to see the effect of their changes. In this paper, we’ll talk about what differentiates workspaces from other containers. We’ll describe our base system composed of three containers. A one-node cluster including a compute element and a batch system. A GlideinWMS Factory controlling pilot jobs. And a scheduler and Frontend, to submit jobs and provision resources. Additional containers can be used for optional components. This system can easily run on a laptop and we’ll share our evaluation of different container runtimes, with an eye for ease of use and performance. Finally, we’ll talk about our experience as developers and with students. The GlideinWMS workspaces are easily integrated with IDEs like VS Code, simplifying debugging and allowing development and testing of the system also when offline. They simplified the training and onboarding of new team members and Summer interns. And they were useful in workshops where students could have first-hand experience with the mechanisms and components that, in production, run millions of jobs.

Mambelli, Marco↗

DOE OSTI2025

Using Containers to Speed Up Development, to Run Integration Tests and to Teach About Distributed Systems

GlideinWMS is a workload manager provisioning resources for many experiments, including CMS and DUNE. The software is distributed both as native packages and specialized production containers. Following an approach used in other communities like web development, we built our workspaces, system-like containers to ease development and testing. Developers can change the source tree or check out a different branch and quickly reconfigure the services to see the effect of their changes. In this paper, we will talk about what differentiates workspaces from other containers. We will describe our base system, composed of three containers: a one-node cluster including a compute element and a batch system, a GlideinWMS Factory controlling pilot jobs, and a scheduler and Frontend to submit jobs and provision resources. Additional containers can be used for optional components. This system can easily run on a laptop, and we will share our evaluation of different container runtimes, with an eye for ease of use and performance. Finally, we will talk about our experience as developers and with students. The GlideinWMS workspaces are easily integrated with IDEs like VS Code, simplifying debugging and allowing development and testing of the system even when offline. They simplified the training and onboarding of new team members and summer interns. And they were useful in workshops where students could have first-hand experience with the mechanisms and components that, in production, run millions of jobs.

Mambelli, Marco [Fermilab] (ORCID:0000000294892681↗

DOE OSTI2026

Fast solvers for tokamak fluid models with PETSc

Multigrid (MG) is widely recognized as a highly effective solver for the model problem, the Laplacian, but textbook MG fails on most problems of interest. MG methods have been applied to complex, real-world applications with careful consideration of the physical model and discretization. In this work we develop the first step in applying MG methods to science and engineering relevant magnetohydrodynamics (MHD) tokamak models in the M3D-C1 (https://m3dc1.pppl.gov) fusion energy science code. The semi-implicit time integrator in M3D-C1 is composed of many linear solves. The implicit advance of the momentum equation is the most challenging and is the focus of this work. The current production solver in M3D-C1 is a block Jacobi (BJ) preconditioner within a Krylov solver, where blocks group degrees of freedom on planes of constant toroidal coordinate. BJ convergence degrades as the number of planes increases due to the spectral properties of the matrix preconditioned with BJ. The partially magnetic field-aligned, regular toroidal grid structure in M3D-C1 is amenable to semi-coarsening geometric MG in the toroidal direction. This paper develops such a solver and demonstrates competitive performance on a runaway electron model of a SPARC (https://cfs.energy/technology/sparc) disruption, and superior robustness on a stellarator model on which the BJ solver fails to converge.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

CLimate Impact: Determining Etiology thRough pAthways (CLDERA)

Climate impacts have broad economic, health, political, and national security ramifications. Societally relevant impacts are typically farther downstream, are the product of multiple interacting processes, and can arise over small regions and timeframes because their sources are short-term and localized. Short-term forcings (as can be seen in volcanic eruptions, climatic tipping points (e.g., the collapse of rainforests or the disappearance of sea ice), or in increasingly plausible climate interventions) fundamentally possess low signal-to-noise and could benefit from accounting for the multiple conditional processes through which a downstream impact arises. Under the Grand Challenge LDRD CLDERA (CLimate impacts: Discovering Etiology thRough pAthways), we have developed tools to enable downstream impact attribution from geographically and temporally localized source forcings in the climate. CLDERA developed methods that can distinguish how a localized source drives the climate system to respond with particular impacts. The how is embodied in pathways – the spatio-temporally evolving chain of physical processes that connects a source to a series of increasingly distant impacts. Novel analytic methods in pursuit of downstream impact attribution were developed and demonstrated on simulations and observations of the 1991 eruption of Mt. Pinatubo in the Philippines. As described within this report we have • developed stratospheric expertise and aerosol modeling capabilities in E3SM, • created original methods to detect and model pathways from source-to-impact, and • advanced climate attribution through novel methods, cases, and approaches. Further, CLDERA developed a tiered verification process consisting of controlled datasets to prototype, verify, and refine the original method development. CLDERA increased Sandia’s footprint in the climate analytics community and developed new climate collaborations whilst also creating a cadre of climate analysts at Sandia. The products from CLDERA have been extensive with a total of 9 journal articles published, 12 articles submitted and under review, and an additional 8 articles in preparation. We have produced 1750 simulated years and developed 9 code-bases. This report details these accomplishments and serves as a summary of the work completed during the CLDERA Grand Challenge.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Extension of SCALE/Sampler’s sensitivity index for the assessment of cross section, fission yield, and decay data uncertainties

Accurate prediction of nuclide compositions and neutron and gamma sources and spectra for fresh and spent nuclear fuel through computational modeling and simulations is the basis for safeguards instruments design, optimization, and calibration, and for validation of the measured responses. The accuracy of these simulations can be significantly impacted by uncertainties in input parameters to the applied computer code. Input parameters are, for example, dimensions, material compositions, and temperatures of the model. Additionally, important but sometimes neglected input parameters for simulations of nuclear systems are the nuclear data that include nuclear reaction cross sections, fission product yields, and decay data. It has been shown that uncertainties of calculated results are dominated by uncertainties of these nuclear data.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

NASA NTRS1987

Pressure scaling effects in a scramjet combustion chamber

The test results obtained for a model scramjet over a range of pressure levels corresponding to different flight altitudes involve enthalpies that vary from the ignition limit, at the low temperature end, to temperatures where the dissociation of combustion products severely limits heat release. The minimum temperature is noted to be highly pressure-sensitive; above the ignition limit, the amount of heat release increased markedly with pressure and with combustion chamber length. A FEM computer code has been used to model the mixing and combustion processes.

Morgan, R. G.↗

NASA NTRS1996

Distribution of a Generic Mission Planning and Scheduling Toolkit for Astronomical Spacecraft

Work is progressing as outlined in the proposal for this contract. A working planning and scheduling system has been documented and packaged and made available to the WIRE Small Explorer group at JPL, the FUSE group at JHU, the NASA/GSFC Laboratory for Astronomy and Solar Physics and the Advanced Planning and Scheduling Branch at STScI. The package is running successfully on the WIRE computer system. It is expected that the WIRE will reuse significant portions of the SWAS code in its system. This scheduling system itself was tested successfully against the spacecraft hardware in December 1995. A fully automatic scheduling module has been developed and is being added to the toolkit. In order to maximize reuse, the code is being reorganized during the current build into object-oriented class libraries. A paper describing the toolkit has been written and is included in the software distribution. We have experienced interference between the export and production versions of the toolkit. We will be requesting permission to reprogram funds in order to purchase a standalone PC onto which to offload the export version.

Kleiner, Steven C.↗

NASA NTRS2006

Three Years of Global Positioning System Experience on International Space Station

The International Space Station global positioning system (GPS) receiver was activated in April 2002. Since that time, numerous software anomalies surfaced that had to be worked around. Some of the software problems required waivers, such as the time function, while others required extensive operator intervention, such as numerous power cycles. Eventually enough anomalies surfaced that the three pieces of code included in the GPS unit have been re-written and the GPS units upgraded. The technical aspects of the problems are discussed, as well as the underlying causes that led to the delivery of a product that has had so many problems. The technical aspects of the problems included physical phenomena that were not well understood, such as the affect that the ionosphere would have on the GPS measurements. The underlying causes were traced to inappropriate use of legacy software, changing requirements, inadequate software processes, unrealistic schedules, incorrect contract type, and unclear ownership responsibilities..

Gomez, Susan↗

DOE OSTI2023

Decarbonization of Liquid Heating Fuels

Annually, residential and commercial buildings use about 5 billion gallons (18.9 billion liters) of distillate fuel for space and water heating. There is considerable interest in decarbonizing these markets through a combination of heat pumps and a future, carbon-free grid. An alternate approach that offers rapid and cost effective decarbonization involves substitution of low-carbon biofuels for fossil fuels within this market. Heating fuel marketers in North America and Europe are aggressively moving to achieve market penetration of biofuels. Processes for this include fuel specification standards, development of manufacturer-approved burners and all system components, development of standards for equipment listing, installation code changes, and generation of performance data. There has been considerable progress in these areas and each of these are reviewed in this paper. Currently, the most important biofuel for this market is biodiesel with a U.S. production capacity of 2.4 billion gallons (9.1 billion liters) and approximately a 75% reduction in GHG emissions. The biodiesel industry has stated a vision for dramatic increases in biodiesel production over the next decades. Fuel and equipment standards are in place to enable use of biodiesel blends to 20% and this blend is now widely used. Standard changes to extend this to as high as 100% biodiesel are nearing completion. Several states have implemented requirements for minimum levels of biodiesel in heating oil with these levels increasing over time.

09 BIOMASS FUELS↗

DOE OSTI2022

A User Guide to PARET/ANL

PARET was originally created in 1969 at what is now Idaho National Laboratory (INL), to analyze reactivity insertion events in research and test reactor cores cooled by light or heavy water, with fuel composed of either plates or pins. The use of PARET is also appropriate for fuel assemblies with curved fuel plates when their radii of curvatures are large with respect to the fuel plate thickness. The PARET/ANL version of the code has been developed at Argonne National Laboratory (ANL) under the sponsorship of the U.S. Department of Energy/NNSA since the inception of the Reactor Conversion Program. Since Reduced Enrichment for Research and Test Reactors (RERTR) began in 1978, PARET/ANL has been benchmarked to experimental data including SPERT testing, and used to determine the expected transient behavior of a large number of reactors regardless of enrichment both inside and outside the Reactor Conversion Program. This document provides the pertinent information for the use of PARET/ANL Version 7.6. PARET/ANL models the various fueled regions of a reactor core as channels. Each of these channels consists of a single flat fuel plate/pin (including cladding and, optionally, a gap) with water coolant on each side. In slab geometry the coolant channels for a given fuel plate are of identical dimensions (mirror symmetry), but they can be of different thickness in each channel. There can be many channels, but each channel is independent and coupled only through reactivity feedback effects to the whole core. The time-dependent differential equations that represent the system are replaced by an equivalent set of finite-difference equations in space and time, which are integrated numerically. PARET/ANL uses fundamentally the same numerical scheme as RELAP5 for the time-integration of the point-kinetics equations. The one-dimensional thermal-hydraulic model includes temperature-dependent thermal properties of the solid materials, such as heat capacity and thermal conductivity, as well as the transient heat production and heat transfer from the fuel meat to the coolant. Temperature- and pressure-dependent thermal properties of the coolant such as enthalpy, density, thermal conductivity, and viscosity are also used in determining parameters such as friction factors and heat transfer coefficients. The code first determines the steady-state solution for the initial state. Then the solution of the transient is obtained by integration in time and space. Multiple heat transfer, DNB and flow instability correlations are available. The code was originally developed to model reactors cooled by an open loop, which was adequate for rapid transients in pool-type cores. An external loop model appropriate for Miniature Neutron Source Reactors (MNSR’s) was also added to PARET/ANL to model natural circulation within the vessel, heat transfer from the vessel to pool and heat loss by evaporation from the pool. PARET/ANL also contains models for decay heat after shutdown, control rod reactivity versus time or position, time-dependent pump flow, and loss-of-flow event with flow reversal as well as logic for trips on period, power, and flow. Feedback reactivity effects from coolant density changes and temperature changes are represented by tables. Feedback reactivity from fuel heat-up (Doppler Effect) is represented by a four-term polynomial in powers of fuel temperature. Photo-neutrons produced in beryllium or in heavy water may be included in the point-kinetics equations by using additional delayed neutron groups.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Uncertainties in the production of iron-group nuclides in core-collapse supernovae from Monte Carlo variations of reaction rates

Core-collapse supernovae, occurring at the end of massive star evolution, produce heavy elements, including those in the iron peak. Although the explosion mechanism is not yet fully understood, theoretical models can reproduce optical observations and observed elemental abundances. However, many nuclear reaction rates involved in explosive nucleosynthesis have large uncertainties, impacting the reliability of abundance predictions. To address this, we have previously developed a Monte Carlo-based nucleosynthesis code that accounts for reaction rate uncertainties and has been applied to nucleosynthesis processes beyond iron. Our framework is also well suited for studying explosive nucleosynthesis in supernovae. In this paper, we investigate 1D explosion models using the ‘PUSH method’ , focusing on progenitors with varying metallicities and initial masses around $M_{\rm ZAMS} = 16\, {\rm M}_{\odot }$. Detailed post-process nucleosynthesis calculations and Monte Carlo analyses are used to explore the effects of reaction rate uncertainties and to identify key reaction rates in explosive nucleosynthesis. We find that many reactions have little impact on the production of iron-group nuclei, as these elements are primarily synthesized in the nuclear statistical equilibrium. However, we identify a few ‘key reactions’ that significantly influence the production of radioactive nuclei, which may affect astrophysical observables. In particular, for the production of ${}^{44}{\rm Ti}$, we confirm that several traditionally studied nuclear reactions have a strong impact. However, determining a single reaction rate is insufficient to draw a definitive conclusion.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

Declaration of the Chemical Composition of Waste-products for the German Repository Konrad Using Substance Vectors - 20500

The waste acceptance criteria of the German repository Konrad require beside a radiological declaration a compositional declaration to be able to avoid negative impact on the groundwater by a presumed leakage into the groundwater after complete corrosion of the containers in the future. The declaration of the composition has to specify compounds and substances not element analyses, because the chemical behavior and toxicity especially of organic compounds varies strongly The relevant compounds have to be described and quantified using defined substance codes provided by the operator. For simple waste types like pure concrete or steel components, the definition of the composition is rather simple. The composition of more complex waste streams is generally declared using producer specific material vectors, which can be derived for defined waste types (e.g. grouted fluids, ash from combustion, super-compacted mixed waste etc.). Additional substance vectors exist for containers, drums and grout, which together with the waste composition yield the total composition of the waste packages. The substance vectors for homogeneous waste streams like cementitious demolition waste, solidified fluids and ash are mostly based on analyses provided by the waste owner. In some cases, analyses from non-radioactive analogues or data sheets can also be used to demonstrate the composition. For each qualified treatment of radioactive waste streams the material composition is described and balanced on the basis of specific material vectors, which are composed of material codes from the material and cask list provided by the Federal company for radioactive waste disposal. For mixed waste streams like super-compacted or grouted mixed waste or materials simply packed in containers an analyses cannot be used. In these cases, the compositional information from the bookkeeping can be used for the entire waste stream to calculate a mean composition including a compositional range (min / max composition). Only waste packages with an approved material description can be delivered to Konrad. Therefore, the material declaration of all waste streams and the resulting waste products is crucial for all waste owners in Germany to be able to have enough waste packages ready, when the repository is going to open in 2027. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2025

How initial conditions-, structural-, and parameter-based model uncertainty interact and influence predictions in permafrost ecosystems: Modeling Archive

This dataset contains model output and input data, as well as source code examples for the Terrestrial Ecosystem Model with the Dynamic Vegetation Model and Dynamic Organic Soil (DVM-DOS-TEM) for the field sites Imnavait creek and the Bonanza creek Long Term Ecological Research Network (LTER). The data covers simulations from the last glacial maximum (LGM) until 2100 for a selection of paleo scenarios, setting the mean temperature of the LGM up to 10°C lower than pre-industrial conditions. The model structure was modulated to represent various model versions, and this dataset contains the relevant changes in the source code. The raw output data, the processed statistical data, the setup and processing scripts as well as parameter value distribution files from a parameter sensitivity analysis are included as well. Model outputs include active layer depth, organic soil carbon, soil layer depths, gross primary productivity (GPP) with and without nitrogen limitation, net primary productivity (NPP), soil liquid water content, heterotrophic, maintenance, and growth respiration, soil temperature, and vegetation carbon (*.nc files). The Next-Generation Ecosystem Experiments in the Arctic (NGEE Arctic) project is a research effort to reduce uncertainty in the Department of Energy’s Energy Exascale Earth System Model (E3SM) by developing a predictive understanding of Arctic tundra ecosystems underlain by permafrost and to quantify feedbacks from the Arctic tundra to the Earth system. NGEE Arctic is supported by the Department of Energy's Office of Biological and Environmental Research.Over Phases 1–3, observations made by the NGEE Arctic team across a gradient of permafrost landscapes in Arctic Alaska improved the representation of tundra processes in the land surface component of E3SM (the E3SM Land Model, ELM). Model improvements emphasized unique aspects of permafrost environments and explored reductions in model complexity while retaining predictive power. The Arctic-informed ELM developed by NGEE Arctic has been used to make novel predictions on processes ranging from permafrost thaw to soil biogeochemical cycling to Earth system feedbacks associated with the unique characteristics of tundra plants. In Phase 4, the NGEE Arctic team is evaluating our new predictive understanding under novel conditions across the Arctic domain. In collaboration with partners at long-term pan-Arctic research sites we are examining whether an Arctic-informed ELM can faithfully simulate interactions among surface and subsurface processes at site, regional, and pan-Arctic scales. In turn, we are using variety of tools to dynamically extend and evaluate ELM inference, with an emphasis on data synthesis and pan-Arctic model evaluation, reintegration of code with an evolving E3SM, scaling across heterogeneous Arctic landscapes, and the appropriate representation of the impacts of increasingly frequent Arctic disturbances.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Neural chaos: A spectral stochastic neural operator

Building surrogate models for operators with uncertainty quantification capabilities is essential for many engineering applications where randomness–such as variability in material properties, boundary conditions, and initial conditions–is unavoidable. Polynomial Chaos Expansion (PCE) is widely recognized as a go-to method for constructing stochastic surrogates in both intrusive and non-intrusive ways, and it has recently been used in the context of operator learning. However, its application becomes challenging for complex or high-dimensional processes, as achieving accuracy requires higher-order polynomials, which can increase computational demand and/or the risk of overfitting. Furthermore, PCE requires specialized treatments to manage random variables that are not independent, and these treatments may be problem-dependent or may fail with increasing complexity. Here, in this work, we adopt the same formalism as the spectral expansion used in PCE; however, we replace the classical polynomial basis functions with neural network (NN) basis functions to leverage their expressivity. To achieve this, we propose an algorithm that identifies NN-parameterized basis functions in a purely data-driven manner, without any prior assumptions about the joint distribution of the random variables involved, whether independent or dependent, or about their marginal distributions. The proposed algorithm identifies each NN-parameterized basis function sequentially, ensuring they are orthogonal with respect to the data distribution. The basis functions are constructed directly on the joint stochastic variables without requiring a tensor product structure or assuming independence of the random variables. This approach may offer greater flexibility for complex stochastic models, while simplifying implementation compared to the tensor product structures typically used in PCE to handle random vectors. This is particularly advantageous given the current state of open-source packages, where building and training neural networks can be done with just a few lines of code and extensive community support. We demonstrate the effectiveness of the proposed scheme through several numerical examples of varying complexity and provide comparisons with classical PCE.

Polynomial chaos expansion↗

DOE OSTI2020

Automated Construction of Potential Energy Surfaces Suitable to Describe van der Waals Complexes with Highly Excited Nascent Molecules: The Rotational Spectra of Ar–CS( v ) and Ar–SiS( v )

Some reactions produce extremely hot nascent products which nevertheless can form sufficiently long-lived van der Waals (vdW) complexes—with atoms or molecules from a bath gas—as to be observed via microwave spectroscopy. Theoretical calculations of such unbound resonance states can be much more challenging than ordinary bound-state calculations depending on the approach employed. One encounters not just the floppy, and perhaps multiwelled potential energy surface (PES) characteristic of vdWs complexes, but in addition, one must contend with excitation of the intramolecular modes and its corresponding influence on the PES. Straightforward computation of the (resonance) rovibrational levels of interest, involves the added complication of the unbound nature of the wave function, often treated with techniques such as introducing a complex absorbing potential. Here, we have demonstrated that a simplified approach of making a series of vibrationally effective PESs for the intermolecular coordinates—one for each reaction product vibrational quantum number of interest—can produce vdW levels for the complex with spectroscopic accuracy. This requires constructing a series of appropriately weighted lower-dimensional PESs for which we use our freely available PES-fitting code AUTOSURF. The applications of this study are the Ar–CS and Ar–SiS complexes, which are isovalent to Ar–CO and Ar–SiO, the latter of which we considered in a previously reported study. Using a series of vibrationally effective PESs, rovibrational levels and predicted microwave transition frequencies for both complexes were computed variationally. A series of shifting rotational transition frequencies were also computed as a function of the diatom vibrational quantum number. The predicted transitions were used to guide and inform an experimental effort to make complementary observations. Comparisons are given for the transitions that are within the range of the spectrometer and were successfully recorded. Calculations of the rovibrational level pattern agree to within 0.2% with experimental measurements.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Characterizing the Impact of GPU Power Management on an Exascale System

As GPU-accelerated high-performance computing (HPC) systems approach exascale performance, controlling energy consumption without compromising throughput is essential. Architectures such as the AMD MI250X-based Frontier supercomputer provide runtime mechanisms like frequency and power capping, enabling energy tuning without modifying application code. Although both target energy reduction, they operate via distinct hardware control paths and influence workloads differently. We present a comprehensive evaluation of these strategies on a leadership-class system using diverse HPC proxy applications representative of production workloads. Our study analyzes performance–energy trade-offs across multiple capping levels, node counts (1 and 32), and application profiles. Results show that frequency capping generally achieves higher energy efficiency and scalability, with gains of up to 13.2% without performance loss, while power capping is more effective for single-node runs or bursty GPU utilization. We also provide practical guidelines to help system administrators and users balance energy efficiency and performance in large-scale scientific workloads.

Costa, Mariana [Universidade Federal do Rio Grande↗

DOE OSTI2022

Five years of ForTrilinos ECP

The ForTrilinos subproject of the Exascale Computing Project (ECP) was initiated to bring the capabilities and scalability of the Trilinos numerical solver collection to Fortran scientific application codes. A novel Fortran extension to the Simplified Wrapper and Interface Generator (SWIG) tool, which automatically generates Fortran bindings from existing C/C++ library code, has been applied to key Trilinos solver libraries to generate the new ForTrilinos libraries. SWIG-Fortran has additionally been used to generate new Fortran compatibility layers for additional scientific libraries and applications. This report summarizes the products and impact of the ForTrilinos subproject.

97 MATHEMATICS AND COMPUTING↗