Search NASA⌕ Search

SEARCH · Search NASA

Results for “performance benchmarking”

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 685 records · Page 38
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Improving ProtoDUNE pion cross-section measurements with NuGraph Michel-electron tagging

Understanding hadron-argon interactions is essential for precise neutrino energy reconstruction and final-state interaction modeling in liquid-argon time projection chamber (LArTPC) experiments such as DUNE. In particular, pion absorption and charge-exchange processes constitute significant sources of systematic uncertainty in neutrino oscillation measurements. ProtoDUNE-SP, a large-scale LArTPC prototype operated at the CERN Neutrino Platform and exposed to charged-particle test beams in the few-GeV range, enables direct measurements of these processes. This work focuses on the measurement of differential cross sections for pion absorption and charge exchange using the 2 GeV/c pion beam data from the ProtoDUNE-SP run. A key component of this analysis is the identification of Michel electrons from $\pi \rightarrow \mu \rightarrow e$ decay chains, which helps separate different interaction topologies and improves background rejection. Michel electron identification will also assist in reliably calibrating the electromagnetic response in ProtoDUNE-SP data and for the future DUNE detectors. In this analysis, we apply NuGraph to identify Michel electrons. NuGraph is a graph neural network that models detector hits as nodes connected by spatial and temporal edges for particle and topology classification in LArTPC detectors. We first benchmark NuGraph’s Michel electron classification performance using ICEBERG data, a small-scale LArTPC prototype used for DUNE electronics and reconstruction development, and then transfer the approach to ProtoDUNE-SP. This poster presents the analysis strategy, NuGraph-based classification studies, and discusses how these developments are expected to improve the pion cross-section measurement.

Razafinime, Soamasina Herilala [Cincinnati U.] (OR↗
DOE OSTI2024

Global 1 km land surface parameters for kilometer-scale Earth system modeling

Earth system models (ESMs) are progressively advancing towards the kilometer scale (“k-scale”). However, the surface parameters for land surface models (LSMs) within ESMs running at the k-scale are typically derived from coarse-resolution and outdated datasets. This study aims to develop a new set of global land surface parameters with a resolution of 1 km for multiple years from 2001 to 2020, utilizing the latest and most accurate available datasets. Specifically, the datasets consist of parameters related to land use and land cover, vegetation, soil, and topography. Differences between the newly developed 1 km land surface parameters and conventional parameters emphasize their potential for higher accuracy due to the incorporation of the most advanced and latest data sources. To demonstrate the capability of these new parameters, we conducted 1 km resolution simulations using the E3SM Land Model version 2 (ELM2) over the contiguous United States. Our results demonstrate that land surface parameters contribute to significant spatial heterogeneity in ELM2 simulations of soil moisture, latent heat, emitted longwave radiation, and absorbed shortwave radiation. On average, about 31 % to 54 % of spatial information is lost by upscaling the 1 km ELM2 simulations to a 12 km resolution. Using eXplainable Machine Learning (XML) methods, the influential factors driving the spatial variability and spatial information loss of ELM2 simulations were identified, highlighting the substantial impact of the spatial variability and information loss of various land surface parameters, as well as the mean climate conditions. The comparison against four benchmark datasets indicates that ELM generally performs well in simulating soil moisture and surface energy fluxes. The new land surface parameters are tailored to meet the emerging needs of k-scale LSM and ESM modeling with significant implications for advancing our understanding of water, carbon, and energy cycles under global change. The 1 km land surface parameters are publicly available at https://doi.org/10.5281/zenodo.10815170 (Li et al., 2024).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

CLM5 CAMELS Basins Ensemble

Land surface models such as Community Land Model Version 5 (CLM5) are essential tools for simulating the behaviors of the terrestrial system. Despite the extensive application of CLM5, limited attention has been paid to the underlying uncertainties associated with its hydrologic parameters and the implications that these uncertainties have on water resources applications. To address this long-standing issue, we conduct a comprehensive hydrologic parameter uncertainty characterization (UC) of CLM5 over the hydroclimatic gradients of the Conterminous United States using five meteorological datasets. Key datasets produced from the UC experiment include a benchmark dataset of CLM5 default hydrological performance, parameter sensitivity identified for 28 hydrological metrics, and large ensemble outputs for hydrological predictions. The presented datasets can assist CLM5 calibration and to support broad applications such as evaluating vulnerabilities to droughts and floods. The dataset can be used to identify under what hydroclimate conditions parametric uncertainties demonstrate substantial effects on hydrological predictions and clarify where further investigations are needed to understand how land runoff uncertainties interact with other Earth system processes. Please refer to the included README.pdf for a description of the included files. Note that raw CLM5 model outputs for each forcing dataset are hosted on a Globus endpoint: https://app.globus.org/file-manager?destination_id=d22ef858-27b0-11ed-a910-fd3165076336.

Yan, Hongxiang↗
DOE OSTI2023

CLM5 CAMELS Basins Ensemble

Land surface models such as Community Land Model Version 5 (CLM5) are essential tools for simulating the behaviors of the terrestrial system. Despite the extensive application of CLM5, limited attention has been paid to the underlying uncertainties associated with its hydrologic parameters and the implications that these uncertainties have on water resources applications. To address this long-standing issue, we conduct a comprehensive hydrologic parameter uncertainty characterization (UC) of CLM5 over the hydroclimatic gradients of the Conterminous United States using five meteorological datasets. Key datasets produced from the UC experiment include a benchmark dataset of CLM5 default hydrological performance, parameter sensitivity identified for 28 hydrological metrics, and large ensemble outputs for hydrological predictions. The presented datasets can assist CLM5 calibration and to support broad applications such as evaluating vulnerabilities to droughts and floods. The dataset can be used to identify under what hydroclimate conditions parametric uncertainties demonstrate substantial effects on hydrological predictions and clarify where further investigations are needed to understand how land runoff uncertainties interact with other Earth system processes. Please refer to the README.pdf for a description of the included files. Note that raw CLM5 model outputs for each forcing dataset are hosted on a Globus endpoint: https://app.globus.org/file-manager?destination_id=d22ef858-27b0-11ed-a910-fd3165076336.

Yan, Hongxiang↗
DOE OSTI2021

Evaluating Cell Temperature Models and the Effect of Wind Speed in PV System Capacity Testing: Preprint

Capacity testing is a routine procedure for assessing a photovoltaic system's performance relative to expectations. The most common test method involves fitting a regression model that predicts system output power using operating weather conditions including wind speed. Structural modifications to the regression model to incorporate wind in different ways improved the model's ability to fit measured system performance, but the observed improvements were small and unlikely to change the result of a capacity test. However, the results showed that the choice of reporting wind speed and inclusion or exclusion of wind speed in the performance model used as the test benchmark can significantly change the test result.

41 EE - Solar Energy Technologies Office (EE-4S)↗
DOE OSTI2021

Closing the Loop on Automotive Carbon Fiber Prepreg Manufacturing Scrap

The project demonstrated how to “close the loop” on carbon fiber by integrating industrial carbon fiber scrap into new functional components in an automotive lightweighting application. The project serves as a validation of discontinuous recycled carbon fiber in a commercial context, while generating comprehensive material data throughout the production chain. To this end, the project exhibited increasing complexity as material evaluation progressed from benchtop to commercial scale through full-scale part production, with key material properties thoroughly characterized throughout the process. Of particular focus was the form of the fiber that was fed into compounding, as recycled fiber has historically been problematic to feed at commercial-scale. Carbon fiber is energy-intensive to manufacture, so reuse of existing fiber material can reduce costs and increase sustainability. Additionally, by integrating recovered short fiber into a thermoplastic, regrind processes can be used to provide feedstock for later generations of product. While regrind plastics are not “infinitely recyclable”, reusing the manufacturing scrap over several generations of products can greatly increase material sustainability and lower the fractional embodied energy of each successive product. As such, this project supports the IACMI technical goals of (1) 25% lower carbon fiber-reinforced polymer (CFRP) cost, (2) 50% reduction in CFRP embodied energy, and (3) 80% composite recyclability into useful products. The initial stage of the project involved down selecting surface treatment (sizing) chemistries. Sizing evaluations were performed on Vartega’s chemically recycled intermediate modulus fiber along with standard modulus dry scrap which was oversized with sizing provided by Michelman. More dramatic improvements from sizing were found on the standard rather than the intermediate modulus fibers. The strength of the chemically recycled individual fibers were evaluated by Michelman and ORNL through single fiber testing and found to be comparable to similarly evaluated virgin fibers. UDRI’s mechanical testing on injection molded test specimens identified similar mechanical properties and fiber distribution relative to benchmark specimens. Additional surface chemistry tests and visualizations were performed by the Colorado School of Mines to confirm close conformance between the benchmark and recycled-fiber specimens. As the mechanical test results exceeded the 80% threshold established as the go/no-go(GNG), the project scale was increased to use commercial-scale equipment that would both better characterize the manufacturing utility of the target product format and allow qualitative assessment of a complex commercial part. An upscaled compounding evaluation was performed with a 27 mm twin-screw compounding extruding using oversized standard modulus fibers that were formatted to improve bulk solids transfer. The project team anticipated that milestone mechanical benchmarks could be achieved given the favorable performance of the sized standard modulus material identified in the initial micro-compounding trials. While the mechanical performance did meet the milestone target for that phase of the project, mechanical properties for this standard modulus-based compound were still less than those of the Ford specification. To compare the performance, the project team oversized intermediate modulus dry fibers and compounded them with the project resin at BASF using a 40 mm compounder. Test specimen mechanical performance exceeded the targets laid out in both the project milestone and the Ford specification. A series of prototype parts were successfully molded, albeit with instances of short shot components due to the high thermal conductivity of the carbon fiber compared to glass fiber for which the prototype tool was designed for. The project demonstrated that recycled carbon fiber is a viable option in fiber reinforced compound, providing greatly increased strength and modulus for applications that require them. The “agglomerated” format that facilitated effective bulk solids transfer of recovered fiber showed promise for industrial application.

36 MATERIALS SCIENCE↗
DOE OSTI2023

The Structural Evaluation Test Unit (SETU) Benchmark Test Results

A series of extensively instrumented tests was performed on the Structural Evaluation Test Unit in the early 1990s. The purpose of these tests was to determine the response of a minimally designed cask to impacts that were more severe than the design basis impact. This test series provides an excellent opportunity for benchmarking explicit dynamic finite element analysis programs for behaviors that may be experienced by casks during regulatory and extra-regulatory impact events. This report provides the results of the four tests that were conducted. It is meant to go along with a companion report that defines the benchmark problem and gives the locations for the instrumentation and inspection points.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

The Structural Evaluation Test Unit (SETU) Benchmark Problem Statement

A series of extensively instrumented tests was performed on the Structural Evaluation Test Unit in the early 1990s. The purpose of these tests was to determine the response of a minimally designed cask to impacts that were more severe than the design basis impact. This test series provides an excellent opportunity for benchmarking explicit dynamic finite element analysis programs for behaviors that may be experienced by casks during regulatory and extra-regulatory impact events. This report provides the parameters of the test unit, the locations of instrumentation, the locations of inspection points, and the parameters of the four tests that were conducted. A companion report provides the results of the tests.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

GHG policy impacts for Seattle’s buildings: targets, timing, and scope

Many US cities are addressing climate change by setting goals to reduce their greenhouse gas (GHG) emissions by a specified amount within a specified time period. In order to achieve these goals, reducing emissions from existing buildings is crucial. Many cities are passing legislation to target existing buildings through benchmarking, auditing, retuning, or energy or emissions performance standards. As cities design legislation, they must consider the timing of the policies, how to prioritize building types and sizes, and how these design decisions will impact the city’s emissions. This paper addresses these questions for one particular US city: Seattle, Washington. A model of Seattle’s building stock was created with benchmarking and tax assessor data. It was then used to predict GHG emissions reductions due to different policy implementations for existing commercial and multifamily buildings. Key findings are: (1) the proposed emissions policy is expected to reduce cumulative emissions from buildings by 19% between 2020 and 2050; (2) delaying the implementation of the policy by five years could limit savings to 12%; and (3) including smaller buildings in the policy could increase savings to 34%. The lessons learned and how this can be used by other cities are discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

The Surface-Topography Challenge: A Multi-Laboratory Benchmark Study to Advance the Characterization of Topography

Surface performance is critically influenced by topography in virtually all real-world applications. The current standard practice is to describe topography using one of a few industry-standard parameters. The most commonly reported number is Ra, the average absolute deviation of the height from the mean line (at some, not necessarily known or specified, lateral length scale). However, other parameters, particularly those that are scale-dependent, influence surface and interfacial properties; for example the local surface slope is critical for visual appearance, friction, and wear. The present Surface-Topography Challenge was launched to raise awareness for the need of a multi-scale description, but also to assess the reliability of different metrology techniques. In the resulting international collaborative effort, 153 scientists and engineers from 64 research groups and companies across 20 countries characterized statistically equivalent samples from two different surfaces: a “rough” and a “smooth” surface. The results of the 2088 measurements constitute the most comprehensive surface description ever compiled. We find wide disagreement across measurements and techniques when the lateral scale of the measurement is ignored. Consensus is established through scale-dependent parameters while removing data that violates an established resolution criterion and deviates from the majority measurements at each length scale. Our findings suggest best practices for characterizing and specifying topography. The public release of the accumulated data and presented analyses enables global reuse for further scientific investigation and benchmarking.

42 ENGINEERING↗
DOE OSTI2023

An automated and portable method for selecting an optimal GPU frequency

Power consumption poses a significant challenge in current and emerging graphics processing unit (GPU) enabled high-performance computing systems. In modern GPUs, dynamic voltage frequency scaling (DVFS) appears to be a reliable control to regulate power consumption and performance. However, the DVFS design space is large - hence, brute-force approaches are infeasible to select the optimal frequency. Furthermore, no single frequency can be universally optimal for applications with varying computational intensities. Thus, the application's complexity and the availability of a wide range of frequency settings are a challenge in selecting the optimal frequency configuration for a given GPU workload. To that end, this paper proposes a systematic approach that consists of three steps. The feature characterization study identifies the fine-grain GPU utilization metrics that influence the power consumption and execution time of a given workload. To understand the performance, power, and energy consumption behaviors of a workload across GPU's DVFS design space, we derived analytical power and performance models using the identified fine-grain features. Here, it is shown that the same set of GPU utilization metrics can estimate both the power consumption and execution time while being agnostic of changes to frequency and input sizes. Applying a power control with the single objective of reducing power may cause performance degradation, leading to more energy consumption. A multi-objective approach is proposed to select the optimal GPU DVFS configuration for a workload that reduces power consumption with negligible degradation in performance. The evaluation was conducted using SPEC ACCEL benchmarks and three real applications - NAMD LAMMPS, and LSTM on NVIDIA GV100, GA100, and AMD MI210 GPUs. On average, real applications showed 29.6% energy savings with a performance loss of 5.2% on GA100 and 22.6% energy savings with a performance loss of 4.7% on GV100. Moreover, the proposed models are portable to real applications, GPU architectures, and vendors, and require metric collection at only the default frequency rather than all supported DVFS configurations. Additionally, we conducted a comparison between our models and the GPU assembly instructions (PTX)-based static models. The results revealed a significant reduction in the average error rates, with a decrease from 19.7% to 3.1% for power models and from 29.4% to 5.2% for performance models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

A discrete integral transform for rapid spectral synthesis

Accurate synthetic spectra that rely on large Line-By-Line (LBL)-databases are used in a wide range of applications such as high temperature combustion, atmospheric re-entry, planetary surveillance and laboratory plasmas. Conventionally synthetic spectra are calculated by computing a lineshape for every spectral line in the database and adding those together, which may take multiple hours for large databases. In this paper we propose a new approach for spectral synthesis based on an integral transform: the synthetic spectrum is calculated as the integral over the product of a Voigt profile and a newly proposed three-dimensional “lineshape distribution function”, which is a function of spectral position and Gaussian- & Lorentzian width coordinates. A fast discrete version of this transform based on the Fast Fourier Transform (FFT) is proposed, which improves performance compared to the conventional approach by several orders of magnitude while maintaining accuracy. Strategies that minimize the discretization error are discussed. A Python implementation of the method is compared against state-of-the-art spectral code RADIS, and is since adopted as RADIS's default synthesis method. The synthesis of a benchmark CO2 spectrum consisting of 1.8 M spectral lines and 200k spectral points took only 3.1 s using the proposed method (1011 lines × spectral points/s), a factor ~300 improvement over the state-of-the-art, with the relative improvement generally increasing for higher number of lines and/or number of spectral points. Finally, an experimental GPU-implementation of the method was also benchmarked, which demonstrated another 2~3 orders performance increase, achieving up to 5 ∙ 10 14 lines × spectral points/s.

42 ENGINEERING↗
DOE OSTI2022

3-regular three-XORSAT planted solutions benchmark of classical and quantum heuristic optimizers

With current semiconductor technology reaching its physical limits, special-purpose hardware has emerged as an option to tackle specific computing-intensive challenges. Optimization in the form of solving quadratic unconstrained binary optimization problems, or equivalently Ising spin glasses, has been the focus of several new dedicated hardware platforms. These platforms come in many different flavors, from highly-efficient hardware implementations on digital-logic of established algorithms to proposals of analog hardware implementing new algorithms. In this work, we use a mapping of a specific class of linear equations whose solutions can be found efficiently, to a hard constraint satisfaction problem (three-regular three-XORSAT, or an Ising spin glass) with a 'golf-course' shaped energy landscape, to benchmark several of these different approaches. We perform a scaling and prefactor analysis of the performance of Fujitsu's digital annealer unit (DAU), the D-Wave advantage quantum annealer, a virtual MemComputing machine, Toshiba's simulated bifurcation machine (SBM), the SATonGPU algorithm from Bernaschi et al, and our implementation of parallel tempering. We identify the SATonGPU and DAU as currently having the smallest scaling exponent for this benchmark, with SATonGPU having a small scaling advantage and in addition having by far the smallest prefactor thanks to its use of massive parallelism. Furthermore, our work provides an objective assessment and a snapshot of the promise and limitations of dedicated optimization hardware relative to a particular class of optimization problems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Flow boiling in geometrically modified microchannels

Microchannels are a promising solution for high-heat-flux thermal management scenarios, including high-performance microelectronics cooling and power electronics cooling. However, thermohydraulic instabilities result from the rapid vapor bubble formation. The prior literature has examined several methods, including constricted inlet microchannels, expanding microchannels, and auxiliary jetting microchannels, to mitigate the effect of these instabilities. Computational fluid dynamics and heat transfer (CFD/HT) modeling of the flow boiling phenomena in these microchannel configurations has seen limited examination, and one-to-one numerical comparisons of the different mitigation strategies have not been performed. In the present investigation, CFD/HT analyses using a three-dimensional (3D) volume of fluid model coupled with a phase-change model for the interfacial heat and mass transfer were performed for multiple microchannel configurations (constricted inlet, expanding, and auxiliary jetting microchannels). A benchmark case of a rectangular microchannel was examined to quantify baseline thermohydraulic performance. Results demonstrated slight to significant thermal performance improvements for all cases, and significant pressure benefits for the expanding and jetting cases, consistent with experimental results in the literature. Bubble dynamics and visualization for the baseline and alternative configurations are provided to give insight into their underlying physics, and the differences in performance were investigated and compared with available literature.

Broughton, Justin (ORCID:000000026848457X)↗
DOE OSTI2021

Correspondence of NNGP Kernel and the Matérn Kernel

Kernels representing limiting cases of neural network architectures have recently gained popularity. However, the application and performance of these new kernels compared to existing options, such as the Matérn kernel, is not well studied. We take a practical approach to explore the neural network Gaussian process (NNGP) kernel and its application to data in Gaussian process regression. We first demonstrate the necessity of normalization to produce valid NNGP kernels and explore related numerical challenges. We further demonstrate that the predictions from this model are quite inflexible, and therefore do not vary much over the valid hyperparameter sets. We then demonstrate a surprising result that the predictions given from the NNGP kernel correspond closely to those given by the Matérn kernel under specific circumstances, which suggests a deep similarity between overparameterized deep neural networks and the Matérn kernel. Finally, we demonstrate the performance of the NNGP kernel as compared to the Matérn kernel on three benchmark data cases, and we conclude that for its flexibility and practical performance, the Matérn kernel is preferred to the novel NNGP in practical applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Evidence of Zintl Intermediate Phase and Its Impacts on Li and Na Storage Performance of Pb-Based Alloying Anodes

Anode materials based on conversion and alloying reactions are promising to achieve high energy density of advanced sodium-ion batteries (SIBs). While the chemical similarities between sodium and lithium as alkali elements make the benchmarking strategy practical in developing new high-performance anodes, simply borrowing the anode material from one system to the other does not always guarantee success unless it is based on sound understanding of both Li- and Na-reaction mechanisms. In this work, we report the Na storage performance of a Pb-based anode and its fundamental reaction dynamics. In contrast to its excellent electrochemical performances in Li cells (reversible ~600 mAh/g), the newly developed Pb@PbO–C nanocomposite anode has limited electrochemical Na reaction properties showing moderate capacity and rate performances (~300 mAh/g at 20 mA/g). Synchrotron-based X-ray diffraction and absorption spectroscopy studies reveal the fundamental differences in the Na and Li reaction mechanism of the Pb-based anode. Further, unlike Li reaction, the unique Na reaction mechanism involves the formation of a highly ionic NaPb Zintl phase, which comprises tetrahedral Pb 4 clusters, as an intermediate phase. The strong covalent character of the Pb 4 Zintl clusters adversely affects the electronic conductivity and thus limits the electrochemical performance of the Pb-based anode in Na cells. These findings provide new insights applicable to developing high-performance alloying anode materials.

25 ENERGY STORAGE↗
DOE OSTI2021

Validation of SAS4A/SASSYS-1 for predicting steady-state single-phase natural circulation

The validation of system analysis codes for nuclear reactor systems is required for the development and application of these computational tools. Designed as a comprehensive system analysis code for advanced nuclear reactors, SAS4A/SASSYS-1 requires validation of its physics model for capturing single-phase natural circulation behavior. To support the validation of SAS4A/SASSYS-1, high-precision experiments are performed capturing steady-state single-phase natural circulation on a scaled facility with comprehensive instrumentation. In this work, dedicated tests are performed quantifying the critical modeling parameters, and a single-phase natural circulation benchmark dataset is obtained with well-documented uncertainty and comprehensive facility description. The validation is then performed against the dataset examining the capability of SAS4A/SASSYS-1 in simulating steady-state single-phase natural circulation. The experimental facility is modeled in the candidate code. Solution verification is performed using Richardson-extrapolation-based estimators which quantify and restrict numerical errors from discretization. Input uncertainty provided by the benchmark dataset is forward propagated through the candidate code, quantifying the output uncertainty in a Monte Carlo approach. The composition of the output uncertainty is also quantified through a variance-based sensitivity analysis. With the uncertainty quantified for each individual condition, a detailed comparison between the simulation results and experimental data is performed covering the whole dataset. The results show consistent agreement for all primary parameters. The current validation activity provides a valuable benchmark dataset for the validation of system analysis codes in capturing single-phase natural circulation and demonstrates satisfactory prediction capability of SAS4A/SASSYS1 for steady-state single-phase natural circulation.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

How efficiently can AI recognize Wireless Devices?

This poster presents a hardware benchmarking methodology for a 3-layer CNN waveform classifier deployed using ONNX Runtime on an NVIDIA Jetson AGX Orin. The dataset consist of 9 signal types, -30 to +30 dB SNR with 5dB increments. Benchmarking on the Jetson AGX Orin gave an accuracy of 91.9% and GPU throughput of 107,120 predictions/sec (23× faster than CPU). The Jetson GPU reached approximately 27M samples/sec with stable performance but fell below the 40 MHz rate needed for real-time radio feeds. Sustained testing of 5 minutes confirmed stable performance with no memory leaks, establishing a reproducible benchmarking baseline for future edge-deployment optimization.

99 - GENERAL AND MISCELLANEOUS↗