Results for “Association Learning” — Page 5

NASA NTRS2014

Cost Analysis In A Multi-Mission Operations Environment

Spacecraft control centers have evolved from dedicated, single-mission or single missiontype support to multi-mission, service-oriented support for operating a variety of mission types. At the same time, available money for projects is shrinking and competition for new missions is increasing. These factors drive the need for an accurate and flexible model to support estimating service costs for new or extended missions; the cost model in turn drives the need for an accurate and efficient approach to service cost analysis. The National Aeronautics and Space Administration (NASA) Huntsville Operations Support Center (HOSC) at Marshall Space Flight Center (MSFC) provides operations services to a variety of customers around the world. HOSC customers range from launch vehicle test flights; to International Space Station (ISS) payloads; to small, short duration missions; and has included long duration flagship missions. The HOSC recently completed a detailed analysis of service costs as part of the development of a complete service cost model. The cost analysis process required the team to address a number of issues. One of the primary issues involves the difficulty of reverse engineering individual mission costs in a highly efficient multimission environment, along with a related issue of the value of detailed metrics or data to the cost model versus the cost of obtaining accurate data. Another concern is the difficulty of balancing costs between missions of different types and size and extrapolating costs to different mission types. The cost analysis also had to address issues relating to providing shared, cloud-like services in a government environment, and then assigning an uncertainty or risk factor to cost estimates that are based on current technology, but will be executed using future technology. Finally the cost analysis needed to consider how to validate the resulting cost models taking into account the non-homogeneous nature of the available cost data and the decreasing flight rate. This paper presents the issues encountered during the HOSC cost analysis process, and the associated lessons learned. These lessons can be used when planning for a new multi-mission operations center or in the transformation from a dedicated control center to multi-center operations, as an aid in defining processes that support future cost analysis and estimation. The lessons can also be used by mature serviceoriented, multi-mission control centers to streamline or refine their cost analysis process.

Newhouse, M.↗

NASA NTRS2016

Design, Development and Hotfire Testing of Monolithic Copper and Bimetallic Additively Manufactured Combustion Chambers

NASA and industry partners are working towards fabrication process development to reduce costs and schedules associated with manufacturing liquid rocket engine components with the goal of reducing overall mission costs. One such technique being evaluated is powder-bed fusion or selective laser melting (SLM) otherwise commonly referred to as additive manufacturing. The NASA Low Cost Upper Stage Propulsion (LCUSP) program was designed to develop processes and material characterization for the GRCop-84 copper-alloy commensurate with powder bed additive manufacturing, evaluate bimetallic deposition and complete testing of a full scale combustion chamber. As part of this development, the process has been transferred to industry partners to enable a long-term supply chain of monolithic copper combustion chambers. As a direct spin off of this program, NASA is working with industry partners to further develop the printing process for the GRCop-84 material in addition to the C-18150 (CuCrZr) material. To advance the process further and allow for optimization with multiple materials, NASA is also investigating the feasibility of bimetallic additively manufactured chambers. A 1.2k sized thrust-chamber was designed and developed to compare the printing process of the GRCop-84 and C-18150 SLM materials. A series of similar MCC liners also completed development with an Inconel 625 jacket bonded to the GRcop-84 liner evaluating direct metal deposition (DMD) laser and arc-based techniques. This paper describes the design, development, manufacturing and testing of these combustion chambers and associated lessons learned throughout the design and development process.

Gradl, Paul↗

NASA NTRS2017

Development and Hot-fire Testing of Additively Manufactured Copper Combustion Chambers for Liquid Rocket Engine Applications

NASA and industry partners are working towards fabrication process development to reduce costs and schedules associated with manufacturing liquid rocket engine components with the goal of reducing overall mission costs. One such technique being evaluated is powder-bed fusion or selective laser melting (SLM), commonly referred to as additive manufacturing (AM). The NASA Low Cost Upper Stage Propulsion (LCUSP) program was designed to develop processes and material characterization for GRCop-84 (a NASA Glenn Research Center-developed copper, chrome, niobium alloy) commensurate with powder-bed AM, evaluate bimetallic deposition, and complete testing of a full scale combustion chamber. As part of this development, the process has been transferred to industry partners to enable a long-term supply chain of monolithic copper combustion chambers. To advance the processes further and allow for optimization with multiple materials, NASA is also investigating the feasibility of bimetallic AM chambers. In addition to the LCUSP program, NASA has completed a series of development programs and hot-fire tests to demonstrate SLM GRCop-84 and other AM techniques. NASA's efforts include a 4K lbf thrust liquid oxygen/methane (LOX/CH4) combustion chamber and subscale thrust chambers for 1.2K lbf LOX/hydrogen (H2) applications that have been designed and fabricated with SLM GRCop-84. The same technologies for these lower thrust applications are being applied to 25-35K lbf main combustion chamber (MCC) designs. This paper describes the design, development, manufacturing and testing of these numerous combustion chambers, and the associated lessons learned throughout their design and development processes.

Gradl, Paul R.↗

NASA NTRS2017

Development and Hotfire Testing of Additively Manufactured Copper Combustion Chambers for Liquid Rocket Engine Applications

NASA and industry partners are working towards fabrication process development to reduce costs and schedules associated with manufacturing liquid rocket engine components with the goal of reducing overall mission costs. One such technique being evaluated is powder-bed fusion or selective laser melting (SLM), commonly referred to as additive manufacturing (AM). The NASA Low Cost Upper Stage Propulsion (LCUSP) program was designed to develop processes and material characterization for GRCop-84 (a NASA Glenn Research Center-developed copper, chrome, niobium alloy) commensurate with powder bed AM, evaluate bimetallic deposition, and complete testing of a full scale combustion chamber. As part of this development, the process has been transferred to industry partners to enable a long-term supply chain of monolithic copper combustion chambers. To advance the processes further and allow for optimization with multiple materials, NASA is also investigating the feasibility of bimetallic AM chambers. In addition to the LCUSP program, NASA’s Marshall Space Flight Center (MSFC) has completed a series of development programs and hot-fire tests to demonstrate SLM GRCop-84 and other AM techniques. MSFC’s efforts include a 4,000 pounds-force thrust liquid oxygen/methane (LOX/CH4) combustion chamber. Small thrust chambers for 1,200 pounds-force LOX/hydrogen (H2) applications have also been designed and fabricated with SLM GRCop-84. Similar chambers have also completed development with an Inconel 625 jacket bonded to the GRCop-84 material, evaluating direct metal deposition (DMD) laser- and arc-based techniques. The same technologies for these lower thrust applications are being applied to 25,000-35,000 pounds-force main combustion chamber (MCC) designs. This paper describes the design, development, manufacturing and testing of these numerous combustion chambers, and the associated lessons learned throughout their design and development processes.

Gradl, Paul R.↗

NASA NTRS2018

Using Board Games as Subject Matter for Developing Expertise in Model-Based Systems Engineering

As more organizations transition from traditional document-centric systems engineering to a model-based approach, many are challenged to train their staff in new languages, tools, and methodologies, while managing the expectations of stakeholders and their expected model outcomes. In particular, challenges associated with learning a new modeling language and developing skills in the 'art' of modeling present organizations with formidable obstacles to realizing this transition. This paper hypothesizes that systems engineers may more readily learn how to correctly model with SysML, and develop intuition about the art of modeling and using patterns, if their learning references a commonly and thoroughly-understood subject, such as a board game. This paper presents a case for the use of board games as subject matter for new modelers. It demonstrates the concept with a sample model of Hasbro's popular board game, Monopoly, and discusses the limitations of this approach and potential adaptations that may broaden the applicability of the learned skills to projects. Finally, results from a small feasibility assessment and concepts for more formal study to evaluate the hypothesis are presented.

Model-Based Systems Engineering↗

NASA NTRS2018

Using Board Games as Subject Matter for Developing Expertise in Model-Based Systems Engineering

As more organizations transition from traditional document-centric systems engineering to a model-based approach, many are challenged to train their staff in new languages, tools, and methodologies, and manage the expectations of stakeholders and their expected model outcomes. In particular, challenges associated with learning a new modeling language and developing skills in the 'art' of modeling present organizations with formidable obstacles to realizing this transition. This paper hypothesizes that systems engineers may more readily learn how to correctly model with SysML, and develop intuition about the art of modeling and using patterns, if their learning references a commonly and thoroughly-understood subject matter, such as a board game. This paper presents a case for the use of board games as subject matter for new modelers, demonstrates the concept with a sample model of Hasbro's popular board game, Monopoly, and discusses the limitations of this approach and potential adaptations that may broaden the applicability of the learned skills to projects.

Systems Engineering↗

NASA NTRSDate not supplied

Search Enhancements using Natural Language Processing Techniques

NASA Goddard Earth Sciences Data and Information Services Center (GESDISC) is one of the 12 NASA Science Mission Directorate Data Centers. The main goal of GESDISC is to provide earth science data, information, and services to the earth science data community. Consequently, data discovery is at the center of our mission and our search engine is the primary tool for our users to interact, find, and access our data. Existing search approaches are largely focused on hard-matching of keywords in the search query with dataset metadata. Here we propose to expand the search by introducing a complementary natural language processing (NLP) search. At the heart of our proposed NLP search, we trained a joint embedding using scientific text corpus and a curated set of dataset metadata. The embedding learns the association between words in our dataset metadata and those of the scientific text corpus. This enables us to go beyond simple hard-matching of a query and data set metadata and have a notion of “similarity” between the search query and the datasets. We further integrated our NLP search into the Elastic Search (ES) framework leveraging similarity search capabilities offered through the “dense_vector” field type. Our preliminary evaluations show that our proposed NLP search has the potential to be utilized to complement the existing search engine and serve as a base for a dataset recommendation system.

Armin Mehrabian↗

NASA NTRSDate not supplied

Early Information Parameter-Set Analysis for Satellite Close Approaches using Machine Learning

Understanding orbital mechanics is essential in space flight and navigation applications, and leveraging modern force models for flight path projection remains an important aspect in space mission design and operation. However, force models do not capture all the dynamics or perturbations in the space environment and thus are subject to errors in predicting the state vectors. The further out the predicted miss distance between spacecraft is from the time of closest approach (TCA), the larger the propagated errors in the predicted miss distance at TCA is. The dependency on these force models for spacecraft flight state prediction calls for a more reliable method that can quantify, or even reduce, these propagated errors. With recent advances in the field artificial intelligence, specifically in machine and deep learning algorithms, a model that implements these approaches can improve on the modern force model approach. The goal for this work is to provide an early-information decision-making threshold, in order to prioritize risk assessment implementation, given the ongoing increase of space objects. In analyzing the relationship of several parameters from conjunction data messages(CDMs) and solar information, early information becomes viable in miss distance prediction with unsupervised learning techniques, which learn the parameters that are linked together with miss distance and probability of collision (Pc) variables. Another approach implemented for identifying relationships within CDMs is supervised learning, in which a shallow neural network binary classifier learns to distinguish events with Pc values¡108. These parameters detected in the unsupervised process are then applied to a regression neural network, which predicts the miss distance at TCA for a specific event within a given uncertainty bound. For the regression neural network, a Long Short Term Memory (LSTM) neural network is implemented, which yields memory about each time step in an event. Using an LSTM network, the model learns to predict miss distance within 0.2km of the value measured at TCA. Although there is a limited amount of "close miss" data to train a network, the network learns to associate parameters, like large energy dissipation rates with the secondary object, with an elevated Pc

Brianna I. Robertson↗

NASA NTRSDate not supplied

Uncertainty in Servicing and Assembly Tasks for Space Robotic Manipulators

This presentation will discuss a subset of the sources of uncertainty that impact autonomous in-space servicing, assembly, and manufacturing missions. These include robotic manipulator modeling uncertainties in both kinematics and dynamics, perception error associated machine learning models for pose estimation, and sensor noise. Mitigation strategies will be discussed including the incorporation of capture envelopes in the design of robotic tools and selection of robot goal poses to minimize end-effector sensitivity in manipulators with redundant degrees of freedom.

robotics↗

NASA NTRSDate not supplied

Big Data Challenges at CCMC

Like other research centers, the Community Coordinated Modeling Center (CCMC, https://ccmc.gsfc.nasa.gov) at NASA Goddard Space Flight Center (GSFC) is also experiencing the big data challenges. CCMC hosts over 80 space weather models for Runs On Request (ROR), Continuous Runs and Instant Runs simulation services for the research community. In addition, CCMC has started to support simulation output onboarding in response to the Open Science initiative. Overall, we have accumulated over petabytes of simulation output data and are rapidly growing. In this presentation, we will discuss our data and storage challenges. We will present our attempts to address our challenges and any associated lessons learned. CCMC uses Apache Airflow to ensure data transfer is consistent. We will give a brief overview on how we leverage Apache Airflow to enhance our environment.

space weather↗

NASA NTRSDate not supplied

Big Data Challenges at the Community Coordinated Modeling Center (CCMC)

Like other research centers, the Community Coordinated Modeling Center (CCMC, https://ccmc.gsfc.nasa.gov) at NASA Goddard Space Flight Center (GSFC) is also experiencing the big data challenges. CCMC hosts over 80 space weather models for Runs On Request (ROR), Continuous Runs and Instant Runs simulation services for the research community. In addition, CCMC has started to support simulation output onboarding in response to the Open Science initiative. Overall, we have accumulated over petabytes of simulation output data and are rapidly growing. In this presentation, we will discuss our data and storage challenges. We will present our attempts to address our challenges and any associated lessons learned. CCMC uses Apache Airflow to ensure data transfer is consistent. We will give a brief overview on how we leverage Apache Airflow to enhance our environment.

space weather↗

DOE OSTI2020

Complementary workflows for identifying one-hop network behavior and multi-hop network dependencies

A network analysis tool evaluates network flow information in complementary workflows to identify one-hop behavior of network assets and also identify multi-hop dependencies between network assets. In one workflow (e.g., using association rule learning), the network analysis tool can identify significant one-hop communication patterns to and/or from network assets, taken individually. Based on the identified one-hop behavior, the network analysis tool can discover patterns of similar communication among different network assets, which can inform decisions about deploying patch sets, mitigating damage, configuring a system, or detecting anomalous behavior. In a different workflow (e.g., using deep learning or cross-correlation analysis), the network analysis tool can identify significant multi-hop communication patterns that involve network assets in combination. Based on the identified multi-hop dependencies, the network analysis tool can discover functional relationships between network assets, which can inform decisions about configuring a system, managing critical network assets, or protecting critical network assets.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Data-Driven Model Predictive Control for Temperature Management of Heat Pipe Microreactor

To enable the self-regulating capability of heat pipe (HP) microreactors, an anticipatory control strategy through model predictive control (MPC) could proactively respond to potential disturbances and deviations in operating setpoints. However, a key factor prohibiting the widespread adoption of MPCs in nuclear applications is the effort and computational costs associated with learning and calibrating first-principles-based process models when the target system is complex and when there are gaps between modeled and target reactor systems. In this paper, we demonstrate data-driven MPC using three approaches for modeling the system dynamics, including a linear state-space model, feedforward neural network, and recurrent neural networks long short-term memory. We present the development and validation process of each model and compare the performance of data-driven MPCs in controlling the temperatures of selected HPs at the evaporator and condenser regions in a 37-HP-monolith system. Our results show that, qualitatively, all data-driven MPCs are producing similar control actions, while quantitatively, with artificial neural nets (especially feedforward neural nets), MPC can better follow drastic changes in setpoints with smallest errors.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Recruiting Military Talent through Solar Ready Vets Training Partnerships Webinar

SkillBridge training programs provide opportunities for service members to gain valuable civilian work experience through career training prior to separation. Employers are invited to join this webinar hosted by Solar Energy Industries Association to learn more about these programs, featuring success stories from across the industry.

Cohen Hall, E'Lon↗

NASA NTRS1990

The real-time learning mechanism of the Scientific Research Associates Advanced Robotic System (SRAARS)

Scientific research associates advanced robotic system (SRAARS) is an intelligent robotic system which has autonomous learning capability in geometric reasoning. The system is equipped with one global intelligence center (GIC) and eight local intelligence centers (LICs). It controls mainly sixteen links with fourteen active joints, which constitute two articulated arms, an extensible lower body, a vision system with two CCD cameras and a mobile base. The on-board knowledge-based system supports the learning controller with model representations of both the robot and the working environment. By consecutive verifying and planning procedures, hypothesis-and-test routines and learning-by-analogy paradigm, the system would autonomously build up its own understanding of the relationship between itself (i.e., the robot) and the focused environment for the purposes of collision avoidance, motion analysis and object manipulation. The intelligence of SRAARS presents a valuable technical advantage to implement robotic systems for space exploration and space station operations.

Chen, Alexander Y.↗

DOE OSTI2026

Data and scripts associated with a manuscript analyzing ELM-FATES parameter sensitivity under pre-fire and postfire scenarios using machine learning

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “Fire Severity-Dependent Shifts in Vegetation Parameter Sensitivity: A Pre- and Post-Fire Analysis Using ELM-FATES and Explainable AI” submitted to Journal of Advances in Modeling Earth Systems (Zahura et al. 2026). The study examines vegetation physiological parameters controlling pre-fire and post-fire vegetation dynamics. To support this analysis, 73 vegetation parameters in Functionally Assembled Terrestrial Ecosystem Simulator (FATES) (Fisher et al., 2018) , which is coupled with E3SM (Energy Exascale Earth System Model) land model (ELM, ELM-FATES), were perturbed using a Sobol sequence to generate 1,024 ensemble members for two plant functional types: needleleaf evergreen extratropical trees (NEET) and C3 grass. Simulations were conducted for the pre-fire period (2016) and post-fire period (2018–2023). Burn severity was represented by modifying the Nesterov index in FATES to 75,000, 150,000, and 300,000 for low, moderate, and high severity, respectively. A no-fire scenario was also included. Simulations were performed for 16 grid cells in the American River Watershed across different burn severities and plant functional types. XGBoost (eXtreme Gradient Boosting) models were trained using the parameter ensembles and ELM-FATES-simulated outputs, including leaf area index (LAI), gross primary productivity (GPP), aboveground biomass, vegetation evaporation, transpiration, and soil evaporation. Models were trained separately for each year and burn severity, followed by SHAP (SHapley Additive exPlanations) analysis to identify changes in dominant parameters after fire disturbance. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. The data package contains the ELM-FATES simulation data. The scripts and data related to the analysis will be added later. The inputs and outputs from ELM-FATES are inside the “FATES” folder. “FATES_domain_surface” contains the domain and surface netcdfs that were used to run ELM-FATES in the study area. “FATES_parameters” contains the 1024 ensembles that were generated using Sobol sequence. “FATES_outputs” folder contains ELM-FATES simulated variables. All files are .csv and .nc (NetCDF).

Aboveground biomass↗

DOE OSTI2025

Machine learning model inputs, outputs, and scripts associated with “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions”

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions” (Malhotra et al., in prep). This effort was designed following ICON (integrated, coordinated, open, and networked) principles to facilitate a model-experiment (ModEx) iteration approach, leveraging crowdsourced sampling across the contiguous United States (CONUS). New machine learning models were created every month to guide sampling locations. Data from the resulting samples were used to test and rebuild the machine learning models for the next round of sampling guidance. Associated sediment and water geochemistry and in situ sensor data can be found at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1923689, https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1729719, and https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1603775. This data package is associated with two GitHub repositories found at https://github.com/parallelworks/dynamic-learning-rivers and https://github.com/WHONDRS-Hub/ICON-ModEx_Open_Manuscript. In addition to this readme, this data package also includes two file-level metadata (FLMD) files that describes each file and two data dictionaries (DD) that describe all column/row headers and variable definitions. This data package consists of two main folders (1) dynamic-learning-rivers and (2) ICON-ModEx_Open_Manuscript which contain snapshots of the associated GitHub repositories. The input data, output data, and machine learning models used to guide sampling locations are within dynamic-learning-rivers. The folder is organized into five top-level directories: (1) “input_data” holds the training data for the ML models; (2) “ml_models” holds machine learning (ML) models trained on the data in “input_data”; (3) “examples” contains files for direct experimentation with the machine learning model, including scripts for setting up “hindcast” run; (4) “scripts” contains data preprocessing and postprocessing scripts and intermediate results specific to this data set that bookend the ML workflow; and (5) “output_data” holds the overall results of the ML model on that branch. Each trained ML model resides on its own branch in the repository; this means that inputs and outputs can be different branch-to-branch. There is also one hidden directory “.github/workflows”. This hidden directory contains information for how to run the ML workflow as an end-to-end automated GitHub Action but it is not needed for reusing the ML models archived here. Please see the top-level README.md in the GitHub repository for more details on the automation. The scripts and data used to create figures in the manuscript are within ICON-ModEx_Open_Manuscript. The folder is organized into four folders which contain the scripts, data, and pdf for each figure. Within the “fig-model-score-evolution” folder, there is a folder called “intermediate_branch_data” which contains some intermediate files pulled from dynamic-learning-rivers and reorganized to easily integrate into the workflows. NOTE: THIS FOLDER INCLUDES THE FILES AT THE POINT OF PAPER SUBMISSION. IT WILL BE UPDATED ONCE THE PAPER IS ACCEPTED WITH ANY REVISIONS AND WILL INCLUDE A DD/FLMD AT THAT POINT. We thank the United States Forest Service, Washington Department of Fish and Wildlife, Washington Department of Natural Resources, Cowiche Canyon Conservatory, Washington State Parks and Recreation Commission (Scientific Research Permit #210901), and the Confederated Tribes and Bands of the Yakama Nation for access to field locations where the samples labeled “SSS” were collected. We also thank the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate sample collection and optimization of data usage according to their values and worldview. WHONDRS consortium members were asked to provide any acknowledgments for the collection of samples labeled “CM” and the following is a list of acknowledgments that were submitted with their corresponding Site IDs: (MART) Research activities were conducted in part on the Wind River Experimental Forest within the Gifford Pinchot National Forest; (MP- 100379) Philadelphia is part of Lenapehoking, the ancestral homelands of the Lenape peoples; (MP-102398) Land surveyed is the ancestral homelands of the Nookhose'iinenno (Arapaho), Tsis tsis'tas (Cheyenne), and Nuuchu (Ute); (MP-100749 and MP- 100747) Georgia Coastal Ecosystem LTER, OCE-1832178; (SP-70 and SP-72) Eastern Shoshone, Shoshone-Bannock; (MP- 102944) Funded by Oregon Watershed Enhancement Board. On the traditional lands of the Confederated Tribes of the Siletz, Confederated Tribes of the Grand Rhonde, and the Clatsop-Nehalem Confederated Tribe; (MP- 100607) Holiday Creek is located on the traditional territory of the Monacan Indian Nation; (SP-45) Lafayette Blue Springs State Park; (MP-102420) NSF DEB-2016749; (MP-100019) New Hampshire Agriculture Experiment Station; (SP-35) Rayonier (land owner; https://www.rayonier.com/); (MP- 101276) US Department of Energy, Office of Science, Biological and Environmental Research, Subsurface Biogeochemical Research, Watershed Dynamics and Evolution SFA at ORNL; (MP- 103224) Watershed Dynamics and Evolution SFA at ORNL; (MP- 101584) Traditional lands of the Oceti Sakowin (Dakota, Lakota, Nakoda) and Anishinaabe Peoples.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications

Run to run variability in parallel programs caused by floating-point non-associativity has been known to significantly affect reproducibility in iterative algorithms, due to accumulating errors. Non-reproducibility can critically affect the efficiency and effectiveness of correctness testing for stochastic programs. Recently, the sensitivity of deep learning training and inference pipelines to floating-point non-associativity has been found to sometimes be extreme. It can prevent certification for commercial applications, accurate assessment of robustness and sensitivity, and bug detection. New approaches in scientific computing applications have coupled deep learning models with high-performance computing, leading to an aggravation of debugging and testing challenges. Here we perform an investigation of the statistical properties of floating-point non-associativity within modern parallel programming models, and analyze performance and productivity impacts of replacing atomic operations with deterministic alternatives on GPUs. We examine the recently-added deterministic options in PyTorch within the context of GPU deployment for deep learning, uncovering and quantifying the impacts of input parameters triggering run to run variability and reporting on the reliability and completeness of the documentation. Finally, we evaluate the strategy of exploiting automatic determinism that could be provided by deterministic hardware, using the Groq LPUTM accelerator for inference portions of the deep learning pipeline. We demonstrate the benefits that a hardware-based strategy can provide within reproducibility and correctness efforts.

Shanmugavelu, Sanjif↗