Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computational Human Performance Modeling”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2012

The Use Of Computational Human Performance Modeling As Task Analysis Tool

During a review of the Advanced Test Reactor safety basis at the Idaho National Laboratory, human factors engineers identified ergonomic and human reliability risks involving the inadvertent exposure of a fuel element to the air during manual fuel movement and inspection in the canal. There were clear indications that these risks increased the probability of human error and possible severe physical outcomes to the operator. In response to this concern, a detailed study was conducted to determine the probability of the inadvertent exposure of a fuel element. Due to practical and safety constraints, the task network analysis technique was employed to study the work procedures at the canal. Discrete-event simulation software was used to model the entire procedure as well as the salient physical attributes of the task environment, such as distances walked, the effect of dropped tools, the effect of hazardous body postures, and physical exertion due to strenuous tool handling. The model also allowed analysis of the effect of cognitive processes such as visual perception demands, auditory information and verbal communication. The model made it possible to obtain reliable predictions of operator performance and workload estimates. It was also found that operator workload as well as the probability of human error in the fuel inspection and transfer task were influenced by the concurrent nature of certain phases of the task and the associated demand on cognitive and physical resources. More importantly, it was possible to determine with reasonable accuracy the stages as well as physical locations in the fuel handling task where operators would be most at risk of losing their balance and falling into the canal. The model also provided sufficient information for a human reliability analysis that indicated that the postulated fuel exposure accident was less than credible.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2012

Computational Human Performance Modeling For Alarm System Design

The introduction of new technologies like adaptive automation systems and advanced alarms processing and presentation techniques in nuclear power plants is already having an impact on the safety and effectiveness of plant operations and also the role of the control room operator. This impact is expected to escalate dramatically as more and more nuclear power utilities embark on upgrade projects in order to extend the lifetime of their plants. One of the most visible impacts in control rooms will be the need to replace aging alarm systems. Because most of these alarm systems use obsolete technologies, the methods, techniques and tools that were used to design the previous generation of alarm system designs are no longer effective and need to be updated. The same applies to the need to analyze and redefine operators’ alarm handling tasks. In the past, methods for analyzing human tasks and workload have relied on crude, paper-based methods that often lacked traceability. New approaches are needed to allow analysts to model and represent the new concepts of alarm operation and human-system interaction. State-of-the-art task simulation tools are now available that offer a cost-effective and efficient method for examining the effect of operator performance in different conditions and operational scenarios. A discrete event simulation system was used by human factors researchers at the Idaho National Laboratory to develop a generic alarm handling model to examine the effect of operator performance with simulated modern alarm system. It allowed analysts to evaluate alarm generation patterns as well as critical task times and human workload predicted by the system.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2015

Proof-of-Concept Demonstrations for Computation-Based Human Reliability Analysis. Modeling Operator Performance During Flooding Scenarios

The United States (U.S.) Department of Energy (DOE) Light Water Reactor Sustainability (LWRS) program has the overall objective to help sustain the existing commercial nuclear power plants (NPPs). To accomplish this program objective, there are multiple LWRS “pathways,” or research and development (R&D) focus areas. One LWRS focus area is called the Risk-Informed Safety Margin and Characterization (RISMC) pathway. Initial efforts under this pathway to combine probabilistic and plant multi-physics models to quantify safety margins and support business decisions also included HRA, but in a somewhat simplified manner. HRA experts at Idaho National Laboratory (INL) have been collaborating with other experts to develop a computational HRA approach, called the Human Unimodel for Nuclear Technology to Enhance Reliability (HUNTER), for inclusion into the RISMC framework. The basic premise of this research is to leverage applicable computational techniques, namely simulation and modeling, to develop and then, using RAVEN as a controller, seamlessly integrate virtual operator models (HUNTER) with 1) the dynamic computational MOOSE runtime environment that includes a full-scope plant model, and 2) the RISMC framework PRA models already in use. The HUNTER computational HRA approach is a hybrid approach that leverages past work from cognitive psychology, human performance modeling, and HRA, but it is also a significant departure from existing static and even dynamic HRA methods. This report is divided into five chapters that cover the development of an external flooding event test case and associated statistical modeling considerations.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2021

Localizing Clinical Patterns of Blast Traumatic Brain Injury Through Computational Modeling and Simulation

Blast traumatic brain injury is ubiquitous in modern military conflict with significant morbidity and mortality. Yet the mechanism by which blast overpressure waves cause specific intracranial injury in humans remains unclear. Reviewing of both the clinical experience of neurointensivists and neurosurgeons who treated service members exposed to blast have revealed a pattern of injury to cerebral blood vessels, manifested as subarachnoid hemorrhage, pseudoaneurysm, and early diffuse cerebral edema. Additionally, a seminal neuropathologic case series of victims of blast traumatic brain injury (TBI) showed unique astroglial scarring patterns at the following tissue interfaces: subpial glial plate, perivascular, periventricular, and cerebral gray-white interface. The uniting feature of both the clinical and neuropathologic findings in blast TBI is the co-location of injury to material interfaces, be it solid-fluid or solid-solid interface. This motivates the hypothesis that blast TBI is an injury at the intracranial mechanical interfaces. In order to investigate the intracranial interface dynamics, we performed a novel set of computational simulations using a model human head simplified but containing models of gyri, sulci, cerebrospinal fluid (CSF), ventricles, and vasculature with high spatial resolution of the mechanical interfaces. Simulations were performed within a hybrid Eulerian—Lagrangian simulation suite (CTH coupled via Zapotec to Sierra Mechanics). Because of the large computational meshes, simulations required high performance computing resources. Twenty simulations were performed across multiple exposure scenarios—overpressures of 150, 250, and 500 kPa with 1 ms overpressure durations—for multiple blast exposures (front blast, side blast, and wall blast) across large variations in material model parameters (brain shear properties, skull elastic moduli). All simulations predict fluid cavitation within CSF (where intracerebral vasculature reside) with cavitation occurring deep and diffusely into cerebral sulci. These cavitation events are adjacent to high interface strain rates at the subpial glial plate. Larger overpressure simulations (250 and 500kPa) demonstrated intraventricular cavitation—also associated with adjacent high periventricular strain rates. Additionally, models of embedded intraparenchymal vascular structures—with diameters as small as 0.6 mm—predicted intravascular cavitation with adjacent high perivascular strain rates. The co-location of local maxima of strain rates near several of the regions that appear to be preferentially damaged in blast TBI (vascular structures, subpial glial plate, perivascular regions, and periventricular regions) suggest that intracranial interface dynamics may be important in understanding how blast overpressures leads to intracranial injury.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Biomimetic, Soft-Material Synapse for Neuromorphic Computing: from Device to Network

Neuromorphic computing refers to a variety of brain-inspired computers, devices, and models inspired by the interconnectivity, performance, and energy efficiency of the human brain. Unlike the ubiquitous von Neumann computer architectures with complex processor cores and sequential computation, biological neurons and synapses operate by storing and processing information simultaneously with the capacity of flexible adaptation resulting in massive computational capability with much less power consumption. The search for a synaptic material which can closely imitate bio-synapse has led to an alamethicin-doped, synthetic biomembrane which can emulate key synaptic functions due to generic memristive property enabling learning and computation. This two-terminal, biomolecular memristor, in contrast to its solid-state counterparts, features similar structure, switching mechanism, and ionic transport modality as biological synapses while consuming considerably lower power. In this paper, we outline a methodology for using this biomolecular synapse to build neural networks capable of solving real-world problems. The physical mechanism underlying its volatile memristance is explored followed by the development of a model of this device for circuit simulation. We outline a circuit design technique to integrate this synapse with solid-state neuron circuit for hardware implementation. Based on these results, we develop a high level simulation framework and use a training scheme called Evolutionary Optimization for Neuromorphic System (EONS) to generate networks for solving two problems, namely iris dataset classification and EEG classification task. The small network size and comparable to state-of-the-art accuracy of these preliminary networks show its potential to enhance synaptic functionality in next generation neuromorphic hardware.

Sakib hasan, Md↗
DOE OSTI2015

Toward a clinical application of ex situ boron neutron capture therapy for lung tumors at the RA-3 reactor in Argentina

Purpose: Many types of lung tumors have a very poor prognosis due to their spread in the whole organ volume. The fact that boron neutron capture therapy (BNCT) would allow for selective targeting of all the nodules regardless of their position, prompted a preclinical feasibility study of ex situ BNCT at the thermal neutron facility of RA-3 reactor in the province of Buenos Aires, Argentina. (L)-4p-dihydroxy-borylphenylalanine fructose complex (BPA-F) biodistribution studies in an adult sheep model and computational dosimetry for a human explanted lung were performed to evaluate the feasibility and the therapeutic potential of ex situ BNCT. Methods: Two kinds of boron biodistribution studies were carried out in the healthy sheep: a set of pharmacokinetic studies without lung excision, and a set that consisted of evaluation of boron concentration in the explanted and perfused lung. In order to assess the feasibility of the clinical application of ex situ BNCT at RA-3, a case of multiple lung metastases was analyzed. A detailed computational representation of the geometry of the lung was built based on a real collapsed human lung. Dosimetric calculations and dose limiting considerations were based on the experimental results from the adult sheep, and on the most suitable information published in the literature. In addition, a workable treatment plan was considered to assess the clinical application in a realistic scenario. Results: Concentration-time profiles for the normal sheep showed that the boron kinetics in blood, lung, and skin would adequately represent the boron behavior and absolute uptake expected in human tissues. Results strongly suggest that the distribution of the boron compound is spatially homogeneous in the lung. A constant lung-to-blood ratio of 1.3 ± 0.1 was observed from 80 min after the end of BPA-F infusion. The fact that this ratio remains constant during time would allow the blood boron concentration to be used as a surrogate and indirect quantification of the estimated value in the explanted healthy lung. The proposed preclinical animal model allowed for the study of the explanted lung. As expected, the boron concentration values fell as a result of the application of the preservation protocol required to preserve the lung function. The distribution of the boron concentration retention factor was obtained for healthy lung, with a mean value of 0.46 ± 0.14 consistent with that reported for metastatic colon carcinoma model in rat perfused lung. Considering the human lung model and suitable tumor control probability for lung cancer, a promising average fraction of controlled lesions higher than 85% was obtained even for a low tumor-to-normal boron concentration ratio of 2. Conclusions: This work reports for the first time data supporting the validity of the ovine model as an adequate human surrogate in terms of boron kinetics and uptake in clinically relevant tissues. Collectively, the results and analysis presented would strongly suggest that ex situ whole lung BNCT irradiation is a feasible and highly promising technique that could greatly contribute to the treatment of metastatic lung disease in those patients without extrapulmonary spread, increasing not only the expected overall survival but also the resulting quality of life.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

A Research Roadmap for Computation-Based Human Reliability Analysis

The United States (U.S.) Department of Energy (DOE) is sponsoring research through the Light Water Reactor Sustainability (LWRS) program to extend the life of the currently operating fleet of commercial nuclear power plants. The Risk Informed Safety Margin Characterization (RISMC) research pathway within LWRS looks at ways to maintain and improve the safety margins of these plants. The RISMC pathway includes significant developments in the area of thermalhydraulics code modeling and the development of tools to facilitate dynamic probabilistic risk assessment (PRA). PRA is primarily concerned with the risk of hardware systems at the plant; yet, hardware reliability is often secondary in overall risk significance to human errors that can trigger or compound undesirable events at the plant. This report highlights ongoing efforts to develop a computation-based approach to human reliability analysis (HRA). This computation-based approach differs from existing static and dynamic HRA approaches in that it: (i) interfaces with a dynamic computation engine that includes a full scope plant model, and (ii) interfaces with a PRA software toolset. The computation-based HRA approach presented in this report is called the Human Unimodels for Nuclear Technology to Enhance Reliability (HUNTER) and incorporates in a hybrid fashion elements of existing HRA methods to interface with new computational tools developed under the RISMC pathway. The goal of this research effort is to model human performance more accurately than existing approaches, thereby minimizing modeling uncertainty found in current plant risk models.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2020

¬¬Integration of Quantification of Margins and Uncertainties Methodology into Parallel Discrete Event Simulator Framework

Parallel Discrete Events Simulation (PDES) is becoming increasingly important to lab efforts in security and intelligence. It is used to model complex asynchronous systems such as computer networks, satellite systems, vehicular traffic, and human performance. Uncertainty Quantification (UQ) techniques have become a mainstay of Verification and Validation (V&V) efforts on physics simulations. However, PDES models are very different from traditional physics simulations, and research into UQ techniques for PDES is in its infancy. It is not clear which traditional UQ techniques can be applied to PDES, or what new techniques will need to be developed. The goal of this project was to identify existing UQ techniques that can be applied to PDES, and to develop new techniques as necessary. The project implemented or developed techniques to handle issues that do not appear in traditional physics simulations, but are common among PDES, including sampling techniques for high-dimensional homogenous inputs, response surfaces for high-variance heteroskedastic output, and characterization of skewed output distributions. These are foundational UQ techniques that must be used in any complete UQ analysis (Tong 2018).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Toward A High-Performance Emulation Platform for Brain-Inspired Intelligent Systems Exploring Dataflow-Based Execution Model and Beyond

Brain-inspired computing is a novel computing technology based on neural morphological engineering, which draws lessons from methods of human brain information processing and storage. Combining with the high-performance computing (HPC) platform, they constitute the foundation of general artificial intelligence. However, current brain HPC platforms generally suffer from slow speed, poor scalability, and high energy consumption, which severely restrain its potential and circumscribe the development of general artificial intelligence. The dataflow model was first proposed in the 1970s, providing a novel idea for the development of HPC. In addition, the dataflow model shares similar information processing mechanisms with human's neural system, which makes dataflow models naturally suit the emulation of brain-inspired computing. Based on the contemporary progress of the dataflow model, the Codelet model was proposed. Through a fine-grained asynchronous program execution and resource allocation, the Codelet model successfully realized the distributed computing on the heterogeneous system, effectively improved the computing power and speed, and open up a new path to overcome the shortcomings of the existing high-performance computing technology. We propose a dataflow-based emulation platform, aiming at providing high-performance computing technology support for general brain-inspired intelligent system, as well as using characteristics of dataflow models to fully explore the potential of brain-inspired intelligence. As an example, we will select a convolutional neural network (LeNet5) that already has a spectacular user base to initially verify the superiority and feasibility of our proposal.

brain-inspired intelligent system↗
DOE OSTI2017

MIRAGE: A Framework for Data-Driven Collaborative High-Resolution Simulation

Information about how human populations shift in response to various stimuli is limited because no single model is capable of addressing these stimuli simultaneously, and integration of the best existing models has been challenging because of the vast disparity among constituent model purposes, architectures, scales, and execution environments. To demonstrate a potential model coupling for approaching this problem, three major model components are integrated into a fully coupled system that executes a worldwide infection-infected routine where a human population requires a food source for sustenance and an infected population can spread an infection when it is in contact with the remaining healthy population. To enable high-resolution data-driven model federation and an ability to capture dynamics and behaviors of billions of humans, a high-performance computing agent-based framework has been created and is demonstrated in this chapter.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2019

Optimal Operator Training Reference Models for Human-in-the-loop Systems

The human operator is an integral part of a stable and safe power system. While there is increasing attention paid to automation improvements, the importance of understanding and training human operators may be understated. This paper discusses a project to enhance operator training programs by evaluating human performance relative to a reference operator model identified using optimal control theory. Along with establishing a simple computer-based operator workstation for future training purpose, this paper describes the optimal control response design methodology for a human-in-the-loop power system experiment. The overall system model is presented. An optimal controller synthesis methodology is applied to the model system and the optimal controller is designed. The performance of the optimal controller is then compared to human subject performance.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Data analysis and modeling pipelines for controlled networked social science experiments

There is large interest in networked social science experiments for understanding human behavior at-scale. Significant effort is required to perform data analytics on experimental outputs and for computational modeling of custom experiments. Moreover, experiments and modeling are often performed in a cycle, enabling iterative experimental refinement and data modeling to uncover interesting insights and to generate/refute hypotheses about social behaviors. The current practice for social analysts is to develop tailor-made computer programs and analytical scripts for experiments and modeling. This often leads to inefficiencies and duplication of effort. In this work, we propose a pipeline framework to take a significant step towards overcoming these challenges. Our contribution is to describe the design and implementation of a software system to automate many of the steps involved in analyzing social science experimental data, building models to capture the behavior of human subjects, and providing data to test hypotheses. The proposed pipeline framework consists of formal models, formal algorithms, and theoretical models as the basis for the design and implementation. We propose a formal data model, such that if an experiment can be described in terms of this model, then our pipeline software can be used to analyze data efficiently. The merits of the proposed pipeline framework is elaborated by several case studies of networked social science experiments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A level-of-details framework for representing occupant behavior in agent-based models

We report agent-based modeling is an advanced computational technique capable of representing complex and dynamic processes of human behavior in building performance simulation. Though the agent-based approach supports diverse applications concerning human behavior modeling within the built environment, there is no consensus on the optimal amount of information or level of granularity needed for occupant information representation. This paper attempts to formalize the level of details (LoD) needed for occupant behavior representation in agent-based environments. A novel framework, grounded on the concept of LoD, is proposed to select the required details in representing occupants in agent-based models. Ten attributes related to occupants' presence, movement, behavioral processes, and repertoire are considered to define the LoD. The framework identifies use case parameters as the guiding principle and allows a hybrid approach for selecting varying degrees of occupant attributes to serve the purpose of simulation. A discussion on the pertinence of different occupant behavior LoDs in relation to the desired objective and simulation context is also presented. The study intends to support the occupant behavior research by advancing agent-based occupant modeling in building performance simulation.

42 ENGINEERING↗
DOE OSTI2025

Multi-Objective Optimization of Uranium Target Assembly–3: A Comparison of Genetic and Traditional Methods

Commonly produced as a byproduct of uranium fission, 99 Mo is a key medical isotope that is in high demand in the United States. An international goal is to switch from medical isotope production technologies that require highly enriched uranium to medical isotope production technologies that require only low-enriched uranium. Niowave Inc. is contributing to this goal by developing an accelerator-driven subcritical assembly called the Uranium Target Assembly (UTA). This work compares the performance of Dakota’s Multi-Objective Genetic Algorithm (MOGA) against traditional sensitivity analysis in the neutronic optimization of the UTA-3 system. The design objectives are k-eigenvalue (k eff ) and natural uranium fission power, which are directly correlated with the amount of 99 Mo produced. Dakota:MOGA did not perform as well as human engineering ingenuity in optimization studies with high numbers of input parameters, such as fuel rod type selection and fuel rod placement. However, Dakota:MOGA did outperform traditional sensitivity analysis in optimization studies with fewer than 20 parameters and revealed the degree to which each parameter influences the optimal design space for k eff and natural uranium fission power (to a lesser extent). As the design model became more complex in the final stage of design, the computational resources required to calculate the design objective values in the Monte Carlo N-Particle transport code from selected input parameter combinations limited Dakota:MOGA’s performance, and, unfortunately, human intervention was required to discern the optimal design space. In conclusion, future work will attempt to reduce computational resource constraints by incorporating areduced-order neutronics model into the optimization cycle.

Accelerator-driven systems↗
DOE OSTI2013

4π Non-Coplanar Liver SBRT: A Novel Delivery Technique

Purpose: To improve the quality of liver stereotactic body radiation therapy (SBRT) treatments, a novel 4π framework was developed with accompanying algorithms to optimize non-coplanar beam orientations and fluences. The dose optimization is performed on a patient-specific deliverable beam geometry solution space, parameterized with patient and linear accelerator gantry orientations. Methods and Materials: Beams causing collision between the gantry and the couch or patient were eliminated by simulating all beam orientations using a precise computer assisted design model of the linear accelerator and a human subject. Integrated beam orientation and fluence map optimizations were performed on remaining beams using a greedy column generation method. Testing of the new method was performed on 10 liver SBRT cases previously treated with 50 to 60 Gy in 5 fractions using volumetric modulated arc therapy (VMAT). For each patient, both 14 and 22 non-coplanar fields were selected and optimized to meet the objective of ≥95% of the planning target volume (PTV) covered by 100% of the prescription dose. Doses to organs at risk, normal liver volumes receiving <15 Gy, integral dose, and 50% dose spillage volumes were compared against the delivered clinical VMAT plans. Results: Compared with the VMAT plans, the 4π plans yielded reduced 50% dose spillage volume and integral dose by 22% (range 10%-40%) and 19% (range 13%-26%), respectively. The mean normal liver volume receiving <15 Gy was increased by 51 cc (range 21-107 cc) with a 31% reduction of the mean normal liver dose. Mean doses to the left kidney and right kidney and maximum doses to the stomach and spinal cord were on average reduced by 70%, 51%, 67%, and 64% (P≤.05). Conclusions: This novel 4π non-coplanar radiation delivery technique significantly improved dose gradient, reduced high dose spillage, and improved organ at risk sparing compared with state of the art VMAT plans.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2021

Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition

Humans quickly and accurately learn new visual concepts from sparse data, sometimes just a single example. The impressive performance of artificial neural networks which hierarchically pool afferents across scales and positions suggests that the hierarchical organization of the human visual system is critical to its accuracy. These approaches, however, require magnitudes of order more examples than human learners. We used a benchmark deep learning model to show that the hierarchy can also be leveraged to vastly improve the speed of learning. We specifically show how previously learned but broadly tuned conceptual representations can be used to learn visual concepts from as few as two positive examples; reusing visual representations from earlier in the visual hierarchy, as in prior approaches, requires significantly more examples to perform comparably. These results suggest techniques for learning even more efficiently and provide a biologically plausible way to learn new visual concepts from few examples.

Rule, Joshua S.↗
DOE OSTI2026

Ecosystems for Scientific Computing in the Age of AI

Scientific computing is at an inflection point. Artificial intelligence (AI) is reshaping how scientific software is developed, how teams collaborate, how projects are governed, and how the next generation is trained. Drawing on insights from a 2025 workshop report, this article argues that the future of discovery will depend on agile, robust ecosystems built through socio-technical co-design—the intentional integration of technical and human systems. This perspective is essential for ensuring that future scientific computing remains trustworthy, sustainable, and scalable. It combines advances in AI, high-performance computing, and software with new models for cross-disciplinary collaboration, education, and workforce development. Key recommendations include building modular, trustworthy AI-enabled software ecosystems; enabling teams to integrate AI into scientific workflows while preserving human creativity, integrity, and rigor; and developing adaptive training pathways that keep pace with rapid technological change. By sharing these perspectives, we hope to stimulate broader community dialogue and encourage coordinated action.

AI↗
DOE OSTI2024

Large language model evaluation for high–performance computing software development

We apply AI-assisted large language model (LLM) capabilities of GPT-3 targeting high-performance computing (HPC) kernels for (i) code generation, and (ii) auto-parallelization of serial code in C ++, Fortran, Python and Julia. Our scope includes the following fundamental numerical kernels: AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG, and language/programming models: (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). Kernel implementations are generated using GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code given simple + + prompt variants. To quantify and compare the generated results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. For auto-parallelization, we use ChatGPT interactively giving simple prompts as in a dialogue with another human including simple “prompt engineering” follow ups. Results suggest that correct outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general-purpose Python can benefit from adding language keywords, while Julia prompts perform acceptably well for its Threads and CUDA.jl programming models. Finally, we expect to provide an initial quantifiable point of reference for code generation in each programming model using a state-of-the-art LLM. Overall, understanding the convergence of LLMs, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

97 MATHEMATICS AND COMPUTING↗