Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Task Analysis”

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 829 records · Page 46
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Using a Large Language Model as a Building Block to Generate Usable Validation and Verification Suite for OpenMP

In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using – whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of providing input to a production quality validation and verification suite, we manually implement the corrections required to make the tests valid according to the current OpenMP specification. We quantify this effort as small, medium, or large, and record the lines of code changed to correct the invalid tests. With the corrected tests we validate recent implementations from HPE, AMD, and GNU on the Frontier supercomputer. Our experiment and subsequent analysis show that although LLMs are capable of producing HPC specific codes, they are limited by their understanding of the deeper semantics and restrictions of programming models such as OpenMP. Unsurprisingly more commonly used features have better support, while some OpenMP 3.0 directives such as sections and tasking are not universally supported on accelerators. We demonstrate that successful compilation and execution to completion are inadequate metrics for evaluating generated code and that, at this time, commodity LLMs require expert intervention for code verification. This points to gaps in the training data that is currently available for HPC. We demonstrate that with "small" effort 37% of generated invalid C tests and 63% of generated invalid Fortran tests could be corrected. This improves productivity of test generation as we circumvent writing from scratch and the common programming errors associated with it.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗
DOE OSTI2024

ℤ2 × ℤ2 Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks

This paper presents a comparative analysis of the performance of Equivariant Quantum Neural Networks (EQNNs) and Quantum Neural Networks (QNNs), juxtaposed against their classical counterparts: Equivariant Neural Networks (ENNs) and Deep Neural Networks (DNNs). We evaluate the performance of each network with three two-dimensional toy examples for a binary classification task, focusing on model complexity (measured by the number of parameters) and the size of the training dataset. Our results show that the Z2×Z2 EQNN and the QNN provide superior performance for smaller parameter sets and modest training data samples.

Dong, Zhongtian (ORCID:0000000210003454)↗
DOE OSTI2022

Progress on Near-Term Tasks for the Development of Advanced Reactor Mechanistic Source Term Modeling and Simulation Tools

To assist both the advanced reactor industry and U.S. Nuclear Regulatory Commission (NRC) in the pursuit of reactor design and licensing, the U.S. Department of Energy (DOE) Nuclear Energy Advanced Modeling and Simulation (NEAMS) program has established a mechanistic source term (MST) research project under the auspices of the Multiphysics Applications technical area. MST analysis is central to the reactor licensing process and a focus of the NRC regarding their mission to provide reasonable assurance of adequate protection of public health and safety and environment. The MST research project is a collaboration between Argonne National Laboratory (Argonne) and Sandia National Laboratories (SNL) with a high-level objective to coordinate the development of comprehensive advanced reactor MST mod/sim capabilities to support risk-informed design and licensing decisions.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Proposed guidance for preparing and reviewing a molten salt non-power production or utilization facility application

Development of non-power molten salt reactors (MSRs) are under consideration to further establish an MSR experience base, support the requirements of Title 10 of the Code of Federal Regulations (10 CFR) Section 50.43(e), and provide any additional analyses needed for development of a full-scale MSR. Guidance provided in this report is based on MSRs operating with liquid fuel (i.e., fuel dissolved within a molten salt). These reactors, unless owned by the DOE or DOD, will require licensing by the US Nuclear Regulatory Commission (NRC) staff. Standard review plan (SRP) guidance for large light water reactors (LWRs) is available in NUREG-0800, Standard Review Plan for the Review of Safety Analysis Reports for Nuclear Power Plants; Light Water Reactor (LWR) Edition. However, NRC staff observed that NUREG-0800 is very cumbersome to apply to non-power reactors “because of the great differences in complexity and hazards between non-power reactors and nuclear power plants.” Therefore, a program to develop performance-based guidance applicable to non-power reactors was initiated. In 1996, NUREG-1537, Parts 1 and 2, Guidelines for Preparing and Reviewing Applications for the Licensing of Non-Power Reactors, was published. Part 1, the format and content guide, suggests a uniform format for presenting information in non-power reactor applications that is acceptable to the NRC staff, but conformance with the format and content is not required. Part 2, the SRP, ensures the quality and uniformity of the staff review of an application. Unfortunately, the application guidelines and SRP do not provide adequate guidance for all advanced non-LWR technologies and applications. This discrepancy eventually led to the 2012 development of interim staff guidance (ISG) for NUREG-1537, which includes criteria for describing and reviewing aqueous homogeneous reactors (AHRs). Specifically, NUREG-1537 ISG, 2012 expanded the original document to address three areas: 1. updated criteria for heterogeneous non-power reactors, 2. criteria for licensing AHRs, and 3. criteria for licensing a Part 50-licensed isotope production facility. In 2015, the US Department of Energy (DOE) opted to build on the AHR NUREG-1537 ISG experience by performing a gap analysis of the guidance that would be used to license a non-power MSR. MSRs represent one of the advanced non-LWR technologies selected by DOE for development through a multiyear cost share award with Southern Company Services. Under this Advanced Reactor Concepts 2015 (DOE Advanced Reactor Concepts [ARC] 15) award program, the DOE tasked Oak Ridge National Laboratory (ORNL) to evaluate the guidance changes that the NRC may need to consider when licensing an MSR non-power reactor. ORNL staff, with support from Boston Government Services, LLC, focused on five system-related chapters in NUREG-1537 that were considered most relevant to inform the effort that would be required for a non-power MSR applicant. ORNL documented this review in a technical report, ORNL/TM-2018/834, Proposed Guidance for Preparing and Reviewing Molten Salt Non-Power Reactor License Applications (NUREG-1537). The report was subsequently shared with industry and the NRC. The 2018 review was limited in scope, focusing on key system chapters based on the expected significance of each chapter relative to expected differences in addressing advanced non-LWR technologies, specifically non-power MSRs, compared with heterogeneously fueled non-power reactors. In the ORNL report, proposed generic adaptations were suggested for the following NUREG-1537 chapters: Chapter 4, “Reactor Description”; Chapter 5, “Reactor Coolant Systems”; Chapter 6, “Engineered Safety Features”; Chapter 9, “Auxiliary Systems”; Chapter 11, “Radiation Protection Program and Waste Management” The inclusion of Chapter 11 in the previous review effort was intended to provide guidance for categorizing the waste-handling process for an MSR operating with homogenous fuel. The introductions from Parts 1 and 2 of the 2012 NUREG-1537 ISG provide guidance for the application and review of production facilities. After a period of operation, non-power MSRs with homogenous fuel will include gaseous and soluble fission products. The gaseous fission products will be collected and held for decay in an off-gas system. There might also be an initiative to polish or filter the soluble fission products in the fuel salt by some mechanical or chemical means. The treatment and handling of fission products in the non-power MSR fuel salt and the description of this process in the safety analysis report (SAR) must be very precise to avoid the waste treatment facility being construed as a co-located special nuclear material (SNM) fuel cycle facility (see Section 2.3 of this report). Subsequent to the release of ORNL/TM-2018/834, NRC staff expressed a desire to continue the regulatory gap analysis that was begun in that report. This would provide additional clarity and information addressed in certain sections of the original report, while also providing new guidance on certain topics not addressed in the original report. This revision would benefit the NRC staff reviewing applications involving non-power MSR designs and would help developers understand how the NRC staff might approach the review of such applications. The focus of this report is to provide infrastructure support to the NRC staff for the regulatory review of non-power MSRs.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Investigation of process history and underlying phenomena associated with the synthesis of plutonium oxides using Vector Quantizing Variational Autoencoder

Accurate, high throughput, and unbiased analysis of plutonium oxide particles is needed for analysis of the phenomenology associated with process parameters in their synthesis. Compared to qualitative and taxonomic descriptors, quantitative descriptors of particle morphology through scanning electron microscopy (SEM) have shown success in analyzing process parameters of uranium oxides. Among other candidates, a neural network called a Vector Quantizing Variational Autoencoder (VQ-VAE) has shown the ability to quantitatively describe particle morphology to attain >85% accuracy in identifying uranium oxide processing routes. We utilize a VQ-VAE to quantitatively describe plutonium dioxide (PuO 2 ) particles created in a designed experiment and investigate their phenomenology and prediction of their process parameters. PuO 2 was calcined from Pu(III) oxalates that were precipitated under varying synthetic conditions that related to concentrations, temperature, addition and digestion times, precipitant feed, and strike order; the surface morphology of the resulting PuO 2 powders were analyzed by SEM. A pipeline was developed to extract and quantify useful image representations for individual particles with the VQ-VAE, then further reduce the dimensionality of the feature space using a bottlenecking neural network fit to perform multiple classification tasks simultaneously. The reduced feature space could predict process parameters with greater than 80% accuracies for some parameters with a single particle. They also showed utility for grouping particles with similar surface morphology characteristics together. Both the clustering and classification results reveal valuable information regarding which chemical process parameters chiefly influence the PuO 2 particle morphologies: strike order and oxalic acid feedstock. Doing the same analysis with multiple particles was shown to improve the classification accuracy on each process parameter over the use of a single particle, with statistically significant results generally seen with as few as four particles in a sample.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Development of a Pre-Combustion CO 2 Capture Process Using High-Temperature PBI Hollow-Fiber Membranes

The overall objective of this project was to evaluate the advantages of transformational polybenzimidazole (PBI) polymer hollow-fiber membrane (HFM)-based, carbon dioxide (CO 2 ) capture and purification technology at bench-scale using an actual coal-derived syngas stream from a coal gasification facility. The project was carried out over two budget periods. The technical objectives in Budget Period 1 (BP1) included preparing HFs and modules and upgrading the available skid for field testing. The technical objectives for BP2 were to field-test the skid unit with actual coal-derived syngas from an oxygen-blown gasifier to obtain performance data, update the Techno-Economic Analysis (TEA) that would assist with future process scale-up, and provide information on the design of a small pilot-scale test unit. The goal was to advance the PBI-HFM CO 2 capture and gas separation system for pre-combustion applications beyond second-generation economic performance predictions and make progress toward meeting overall fossil energy performance goals of CO 2 capture with 95% CO 2 purity at a cost of electricity (COE) 30% less than baseline capture approaches. The research program was designed with progressive technical tasks leading to both dynamic and steady-state testing of the PBI-HFM skid with actual coal-derived syngas. The work plan was to: (1) fabricate sufficient Generation-2 (GEN-2) fibers for module fabrication; (2) upgrade the fiber skid to accommodate large fiber modules for bench-scale field testing; (3) conduct dynamic and steady-state testing with coal-derived syngas from an oxygen-blown gasifier and obtain system performance data; (4) perform a TEA and environmental, health, and safety (EH&S) assessment; (5) update the State-Point Data Table, Technology Gap Analysis (TGA), and Technology Maturation Plan (TMP); (6) uninstall and return the test skid to the Recipient’s facilities; and (7) submit a Final Report that describes the results and analysis of the project research effort.

03 NATURAL GAS↗
DOE OSTI2026

Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales

As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.

Houben, Nikolaus↗
DOE OSTI2020

Characterizing, Modeling, and Accurately Simulating Power and Energy Consumption of I/O-intensive Scientific Workflows

While distributed computing infrastructures can provide infrastructure-level techniques for managing energy consumption, application-level energy consumption models have also been developed to support energy-efficient scheduling and resource provisioning algorithms. In this work, we analyze the accuracy of a widely-used application-level model that has been developed and used in the context of scientific workflow executions. To this end, we profile two production scientific workflows on a distributed platform instrumented with power meters. We then conduct an analysis of power and energy consumption measurements. This analysis shows that power consumption is not linearly related to CPU utilization and that I/O operations significantly impact power, and thus energy, consumption. We then propose a power consumption model that accounts for I/O operations, including the impact of waiting for these operations to complete, and for concurrent task executions on multi-socket, multi-core compute nodes. We implement our proposed model as part of a simulator that allows us to draw direct comparisons between real-world and modeled power and energy consumption. Here, we find that our model has high accuracy when compared to real-world executions. Furthermore, our model improves accuracy by about two orders of magnitude when compared to the traditional models used in the energy-efficient workflow scheduling literature.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

A case study on parallel HDF5 dataset concatenation for high energy physics data analysis

In High Energy Physics (HEP), experimentalists generate large volumes of data that, when analyzed, helps us better understand the fundamental particles and their interactions. This data is often captured in many files of small size, creating a data management challenge for scientists. In order to better facilitate data management, transfer, and analysis on large scale platforms, it is advantageous to aggregate data further into a smaller number of larger files. However, this translation process can consume significant time and resources, and if performed incorrectly the resulting aggregated files can be inefficient for highly parallel access during analysis on large scale platforms. In this paper, we present our case study on parallel I/O strategies and HDF5 features for reducing data aggregation time, making effective use of compression, and ensuring efficient access to the resulting data during analysis at scale. We focus on NOvA detector data in this case study, a large-scale HEP experiment generating many terabytes of data. Here, the lessons learned from our case study inform the handling of similar datasets, thus expanding community knowledge related to this common data management task.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Aeroelastic code comparison using the IEA 22MW reference turbine

Reference wind turbine designs and the associated aeroelastic models are widely used in both research and industry. Reference models representing future concepts are of particular interest. Current state of the art aeroelastic tools are relied upon to design the next generation of large wind turbines. However, modelling assumptions may be invalidated by upcoming very large turbines, and different aeroelastic tools may give inconsistent results. A 22MW turbine model has been defined as part of International Energy Agency (IEA) Wind Task 55 on Reference Wind Turbines and Farms to represent future turbines to be deployed in the 2030s. In this study, an aeroelastic model of this turbine has been created in four tools; Bladed, HAWC2, OpenFAST, and QBlade. Code comparisons are presented for steady state operation, linear stability analysis, and time domain power production simulations in steady and turbulent wind. Generally, the codes show a good agreement, but with some differences present in the linear stability analysis, periodic azimuthal variation, and time domain simulations. The models are a good basis for further study with the IEA 22MW turbine, and further code comparison exercises.

17 WIND ENERGY↗
DOE OSTI2020

E-PiPEline: Quick to Market Face Coverings and Face Shields Using Commonly Available Materials

The Center for Disease Control has recommended that the public should wear cloth face coverings in public settings. Face coverings and face shields can be made by using Commonly Available Materials (CAMs). As part of the Sandia COVID-19 LDRD effort (funded under the Materials Science Investment Area), the Sandia E-PiPEline task evaluated design options for face coverings and face shields considering their effectiveness, durability, build difficulty, build cost, and comfort. Observations from this investigation are presented here to provide guidelines for home construction of face coverings and face shields. This executive summary includes a brief roadmap of the analysis methodology, two one-page handouts geared to be distributed to the public at large (one for face coverings and one for face shields), and additional observations regarding potential solutions for face coverings and face shields included to further support the one-page handouts.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Rooftop Photovoltaics and Electric Vehicle Co-Adoption: Attitudes, Norms, Diffusion, and Economics

The overall objectives of the project were to (1) Identify personal and social norms, peer effects, demographics and contextual factors (such as household energy expenditures, experience with outages, charging infrastructure availability) that may facilitate or hinder Solar-EV co-adoption; (2) outline strategies for the design of programs and practices that will enable reasoned RPV and EV adoption and their co-adoption; and (3) assemble a dataset comprised of survey responses of RPV-EV co-adopters, RPV-only adopters, EV-only adopters, and non-adopters. These objectives were only partially fulfilled given the decision to terminate the project. The research team was able to complete the semi-structured interviews, the core BY1 task and summarize the results below. As well, once the team learned of the research project’s fate, it sought and obtained the DOE SETO Technical Manager’s approval to repurpose funds for BY2 tasks to the extent feasible. Rather than invest further resources in expanding the pool of potential survey respondents and having no budget to survey, the research team repurposed funds subject and undertook a more limited (geographically) survey, but also expanded to it to include contingent valuation questions. The analysis of the survey data will necessarily be delayed given the lack of budget support, although some information on the respondent sample is in the results. Given a lack of attention to co-adoption previously, the insights generated in this project should assist decision-makers and industry actors in the development of programs and practices that enable reasoned RPV adoption and EV adoption and their co-adoption.

14 SOLAR ENERGY↗
DOE OSTI2025

Monitored Natural Attenuation (MNA) Assessment for the Chemicals, Metals, and Pesticides (CMP) Pits Operable Unit (OU) and the Pen Branch Wetland

In October 2024, Savannah River National Laboratory (SRNL) was tasked to conduct an independent review of groundwater data and assess the monitored natural attenuation (MNA) performance related to the Chemicals, Metals, and Pesticides (CMP) Pits Operable Unit (OU) located in the central portion of the Savannah River Site (SRS). The SRNL assessment of MNA entailed an independent analysis of groundwater concentration data, groundwater elevation data, available surface water concentration data, soil concentration data, and relevant historical geological characterization logs for the CMP Pits OU. Historical data tables and records were obtained from both the Savannah River Nuclear Solutions - Area Completion Projects (SRNSACP) team and South Carolina State University (SCSU) and condensed into new data sets by the SRNL project team for more targeted analysis of MNA performance characteristics. All data pertaining to groundwater concentration, surface water concentration, and groundwater elevation were restricted to collection dates after any known active remediation for the CMP OU.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Map Applications to Target Exascale Architecture with Machine-Specific Performance Analysis, Including Challenges and Projections

This Exascale Computing Project (ECP) milestone report summarizes the status of all 30 ECP Applications Development (AD) subprojects at the end of FY20. In October and November of 2020, a comprehensive assessment of AD projects was conducted by the ECP leadership. Reviews occurred virtually between October 27, 2020 and November 12, 2020. The review committee—consisting of the AD lead, deputy, and L3—was tasked with evaluating each subproject’s progress in porting their codes to early exascale architectures considered precursors to the planned exascale machines. This includes characterizing which modules have been ported to multi-accelerator nodes, initial performance analyses, the status of software integration, and a current vision of successes, obstacles, and next steps. As such, this report contains not only an accurate snapshot of each subproject’s current status but also represents an unprecedentedly broad account of experiences in porting large scientific applications to next-generation high-performance computing architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Exploring Classification of Topological Priors With Machine Learning for Feature Extraction

In many scientific endeavors, increasingly abstract representations of data allow for new interpretive methodologies and conceptualization of phenomena. For example, moving from raw imaged pixels to segmented and reconstructed objects allows researchers new insights and means to direct their studies toward relevant areas. Thus, the development of new and improved methods for segmentation remains an active area of research. With advances in machine learning and neural networks, scientists have been focused on employing deep neural networks such as U-Net to obtain pixel-level segmentations, namely, defining associations between pixels and corresponding/referent objects and gathering those objects afterward. Topological analysis, such as the use of the Morse-Smale complex to encode regions of uniform gradient flow behavior, offers an alternative approach: first, create geometric priors, and then apply machine learning to classify. This approach is empirically motivated since phenomena of interest often appear as subsets of topological priors in many applications. Using topological elements not only reduces the learning space but also introduces the ability to use learnable geometries and connectivity to aid the classification of the segmentation target. Here, in this article, we describe an approach to creating learnable topological elements, explore the application of ML techniques to classification tasks in a number of areas, and demonstrate this approach as a viable alternative to pixel-level classification, with similar accuracy, improved execution time, and requiring marginal training data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Cluster-Graph Fingerprinting: A Framework for Quantitative Analysis of Machine-Learned Interatomic Model Training and Simulation Data

Machine-learned interatomic models represent a significant advancement in simulation methods, extending the predictive ability of first-principles methods to previously inaccessible length and time scales. However, the data-driven nature of these models can lead to difficult-to-detect errors that can compromise prediction accuracy. To address this challenge, we introduce a novel fingerprinting approach based on the Chebyshev Interaction Model for Efficient Simulation (ChIMES) ML-IAM graph-based descriptor. Our strategy enables efficient and statistically rigorous analysis of system configurations used in ML-IAM training and those generated by their application, e.g., in molecular dynamics simulations. We demonstrate that these fingerprints can effectively assess novelty of a configuration relative to an existing data set and determine dissimilarity among individual configurations, which are two key tasks in workflows for active learning-based ML-IAM training, data set curation, and on-the-fly uncertainty quantification.

36 MATERIALS SCIENCE↗
DOE OSTI2023

A deep neural network regressor for phase constitution estimation in the high entropy alloy system Al-Co-Cr-Fe-Mn-Nb-Ni

High Entropy Alloys (HEAs) are composed of more than one principal element and constitute a major paradigm in metals research. The HEA space is vast and an exhaustive exploration is improbable. Therefore, a thorough estimation of the phases present in the HEA is of paramount importance for alloy design. Machine Learning presents a feasible and non-expensive method for predicting possible new HEAs on-the-fly. A deep neural network (DNN) model for the elemental system of: Mn, Ni, Fe, Al, Cr, Nb, and Co is developed using a dataset generated by high-throughput computational thermodynamic calculations using Thermo-Calc. The features list used for the neural network is developed based on literature and freely available databases. A feature significance analysis matches the reported HEAs phase constitution trends on elemental properties and further expands it by providing so far-overlooked features. The final regressor has a coefficient of determination ( r 2 ) greater than 0.96 for identifying the most recurrent phases and the functionality is tested by running optimization tasks that simulate those required in alloy design. The DNN developed constitutes an example of an emulator that can be used in fast, real-time materials discovery/design tasks.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Investigating Resilience of Loops in HPC Programs: A Semantic Approach with LLMs

Soft errors have become one of the major concerns for the error resilience of the HPC applications as those errors may cause HPC applications to generate serious outcomes such as silent data corruptions (SDCs). Protecting the applications from soft errors is an essential while challenging task. Among different approaches, obtaining a profound understanding of the resilience proneness of an application is very important to devise efficient error detection and recovery strategies. Given the scale of the HPC applications both in the code size and execution time, there are often cases that the error propagation analysis on such applications would produce a massive volume of unstructured data, which requires a significant amount of efforts, to process and to obtain indicating actions towards error protection. In this paper, we present a control-flow based visual analysis framework to help the users conduct error propagation analysis and identify the critical sections of a program that may have a higher likelihood of leading to erroneous outcomes when affected by the control flow related errors. We also design and implement the scalable visualization framework - ResilienceVis that efficiently and effectively visualizes the affected program states under errors and the propagation traces for an application in a user-friendly manner, and eventually, we combine the analysis and visualization to exhibit the error-proneness of the different sections of applications.

Jiang, Hailong↗