Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network acceleration”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A Robust Neural Network for Extracting Dynamics from Electrostatic Force Microscopy Data

Advances in scanning probe microscopy (SPM) methods such as time-resolved electrostatic force microscopy (trEFM) now permit the mapping of fast local dynamic processes with high resolution in both space and time, but such methods can be time-consuming to analyze and calibrate. Here, we design and train a regression neural network (NN) that accelerates and simplifies the extraction of local dynamics from SPM data directly in a cantilever-independent manner, allowing the network to process data taken with different cantilevers. We validate the NN’s ability to recover local dynamics with a fidelity equal to or surpassing conventional, more time-consuming, calibrations using both simulated and real microscopy data. We apply this method to extract accurate photoinduced carrier dynamics on n = 1 butylammonium lead iodide, a halide perovskite semiconductor film that is of interest for applications in both solar photovoltaics and quantum light sources. Lastly, we use SHapley Additive exPlanations to evaluate the robustness of the trained model, confirm its cantilever-independence, and explore which parts of the trEFM signal are important to the network.

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

A PEPS Plugin for TNQVM

This work introduces an extension to the Tensor Network Quantum Virtual Machine (TNQVM) tool, enhancing the existing stack of ExaScale Tensor Network (ExaTN), ExaScale Accelerator (XACC), and TNQVM. It features a new plugin that enables efficient simulation of a Projected Entangled Pair State (PEPS), a 2D tensor network. To improve simulation efficiency for PEPS, we have implemented the snake boundary contraction algorithm. By integrating this capability into the existing stack, we enhance the overall functionality and versatility of the framework. We tested this new PEPS topology for a simple GHZ bell-pair generation quantum circuit and saw that its runtime is very close to that of the MPS topology. We estimate that the real potential of the PEPS topology becomes discernible when quantum circuits with multidimensional entanglement are simulated using tensor networks. In such cases, 1D tensor networks fail to represent or contract them efficiently.

Chundury, Srikar↗
DOE OSTI2025

Evaluating Function-as-a-Service (FaaS) frameworks for the Accelerator Control System

As particle accelerator control systems evolve in complexity and scale, the need for responsive, scalable, and cost-effective computational infrastructure becomes increasingly critical. Function-as-a-Service (FaaS) offers an alternative to traditional monolithic architecture by enabling event-driven execution, automatic scaling, and fine-grained resource utilization. This paper explores the applicability and performance of FaaS frameworks in the context of a modern particle accelerator control system, with the objective of evaluating their suitability for short lived and triggered workloads. In this paper, we evaluate prominent open-source FaaS platforms in executing functional logic, triggers, and diagnostics routines. Evaluation metrics consist of cold-start latency, scalability, performance, integration with other open-source tools like Kafka. Experimental workloads were designed to simulate real-world control tasks when implemented as stateless FaaS functions. These workloads were benchmarked under various invocation loads and network conditions. Self-hosted FaaS platforms, when deployed within accelerator networks, offer greater control over execution environment, better integration with legacy systems, and support for real-time guarantees when paired with message queues. Based on lessons learned and evaluation metrics, this paper describes reliability of the FaaS framework for the Accelerator Control Systems (ACS).

Jaikar, A. [Fermilab] (ORCID:0000000332046217)↗
DOE OSTI2024

Real-Time Neuromorphic Processing of Spatiotemporal Data for Scientific Discovery

Spiking Neural Networks (SNNs) are brain-inspired computing models incorporating unique temporal dynamics and event-driven processing. Rich dynamics in both space and time offer great challenges and opportunities for efficient processing of sparse spatiotemporal data compared with conventional artificial neural networks (ANNs). Under this context, the goal of this project is to develop spiking neural network based neuromorphic computing to enable energy-efficient real-time learning and processing of spatiotemporal data. This report summarizes the key results on network architecture design, training methods, and SNN hardware acceleration achieved under this project, demonstrating the promise of spiking neural networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Human Factors Design for Particle Accelerator Control Room Interfaces

Fermilab, the birthplace of many scientific discoveries in physics and particle accelerator sciences, is in the midst of a widescale modernization effort. The Accelerator Control Operations Research Network (ACORN project’s goal is to modernize the accelerator control system by replacing end-of-life power supplies and enhance future operations of the Fermilab accelerator complex with megawatt particle beams. Within ACORN, opportunities for process improvement concerning software development, human-system interface design, and task performance are also being considered. Human factors researchers from Idaho National Laboratory in collaboration with usability experts from Fermilab, are currently investigating human-centered design improvements for the accelerator control system. For example, substantial tribal knowledge and memory recall are required to effectively operate the accelerator system. This contributes to high cognitive workload and potential burnout of accelerator operators. Developing guidance for consistent visual and functional design enables a more intuitive interaction and relieves operators of cognitive burden. Additionally, developing more intuitive and integrated interfaces can also lead to improved accelerator efficacy by empowering operators with greater understanding and control of the systems. The challenge in developing such interfaces is in designing for a wide variety of user goals, system specifications, and level of experience in users. The challenges need to be met while e also considering the maintainability of the control system. The purpose of this paper is to detail the human factors process and design within the ACORN project, describe results gathered thus far, and discuss the larger implications for this work.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

Accelerating cosmological inference with Gaussian processes and neural networks – an application to LSST Y1 weak lensing and galaxy clustering

ABSTRACT Studying the impact of systematic effects, optimizing survey strategies, assessing tensions between different probes and exploring synergies of different data sets require a large number of simulated likelihood analyses, each of which cost thousands of CPU hours. In this paper, we present a method to accelerate cosmological inference using emulators based on Gaussian process regression and neural networks. We iteratively acquire training samples in regions of high posterior probability which enables accurate emulation of data vectors even in high dimensional parameter spaces. We showcase the performance of our emulator with a simulated 3×2 point analysis of LSST-Y1 with realistic theoretical and systematics modelling. We show that our emulator leads to high-fidelity posterior contours, with an order of magnitude speed-up. Most importantly, the trained emulator can be re-used for extremely fast impact and optimization studies. We demonstrate this feature by studying baryonic physics effects in LSST-Y1 3×2 point analyses where each one of our MCMC runs takes approximately 5 min. This technique enables future cosmological analyses to map out the science return as a function of analysis choices and survey strategy.

Astronomy & Astrophysics↗
DOE OSTI2024

Accelerate microstructure evolution simulation using graph neural networks with adaptive spatiotemporal resolution

Abstract Surrogate models driven by sizeable datasets and scientific machine-learning methods have emerged as an attractive microstructure simulation tool with the potential to deliver predictive microstructure evolution dynamics with huge savings in computational costs. Taking 2D and 3D grain growth simulations as an example, we present a completely overhauled computational framework based on graph neural networks with not only excellent agreement to both the ground truth phase-field methods and theoretical predictions, but enhanced accuracy and efficiency compared to previous works based on convolutional neural networks. These improvements can be attributed to the graph representation, both improved predictive power and a more flexible data structure amenable to adaptive mesh refinement. As the simulated microstructures coarsen, our method can adaptively adopt remeshed grids and larger timesteps to achieve further speedup. The data-to-model pipeline with training procedures together with the source codes are provided.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Accelerating defect predictions in semiconductors using graph neural networks

First-principles computations reliably predict the energetics of point defects in semiconductors but are constrained by the expense of using large supercells and advanced levels of theory. Machine learning models trained on computational data, especially ones that sufficiently encode defect coordination environments, can be used to accelerate defect predictions. Here, we develop a framework for the prediction and screening of native defects and functional impurities in a chemical space of group IV, III–V, and II–VI zinc blende semiconductors, powered by crystal Graph-based Neural Networks (GNNs) trained on high-throughput density functional theory (DFT) data. Using an innovative approach of sampling partially optimized defect configurations from DFT calculations, we generate one of the largest computational defect datasets to date, containing many types of vacancies, self-interstitials, anti-site substitutions, impurity interstitials and substitutions, as well as some defect complexes. We applied three types of established GNN techniques, namely crystal graph convolutional neural network, materials graph network, and Atomistic Line Graph Neural Network (ALIGNN), to rigorously train models for predicting defect formation energy (DFE) in multiple charge states and chemical potential conditions. We find that ALIGNN yields the best DFE predictions with root mean square errors around 0.3 eV, which represents a prediction accuracy of 98% given the range of values within the dataset, improving significantly on the state-of-the-art. We further show that GNN-based defective structure optimization can take us close to DFT-optimized geometries at a fraction of the cost of full DFT. The current models are based on the semi-local generalized gradient approximation-Perdew–Burke–Ernzerhof (PBE) functional but are highly promising because of the correlation of computed energetics and defect levels with higher levels of theory and experimental data, the accuracy and necessity of discovering novel metastable and low energy defect structures at the PBE level of theory before advanced methods could be applied, and the ability to train multi-fidelity models in the future with new data from non-local functionals. The DFT-GNN models enable prediction and screening across thousands of hypothetical defects based on both unoptimized and partially optimized defective structures, helping identify electronically active defects in technologically important semiconductors.

Rahman, Md Habibur (ORCID:000000027705984X)↗
DOE OSTI2023

ESnet/JLab FPGA Accelerated Transport

To increase the science rate for high data rates/volumes, Thomas Jefferson National Accelerator Facility (JLab) has partnered with Energy Sciences Network (ESnet) to define an edge to data center traffic shaping / steering transport capability featuring data event aware network shaping and forwarding. The keystone of this ESnet+JLab FPGA Accelerated Transport (EJFAT) is the joint development of an AI/ML directed dynamic compute work Load Balancer (LB) of UDP streamed data. The LB is a suite consisting of a Field Programmable Gate Array (FPGA) executing the dynamically configurable, low fixed latency LB data plane featuring real-time packet redirection and high throughput, and a control plane running on the FPGA host computer that monitors network and compute farm telemetry in order to make dynamic AI/ML guided decisions for destination compute host redirection/load balancing and destination resource provisioning. The LB provides for three-tier horizontal scaling across LB suites, core compute hosts, and CPUs within a host. The LB effectively provides seamless integration of edge/core computing to support direct experimental data processing for immediate use by JLab science programs and others such as the EIC as well as data centers of the future requiring high throughput and low latency for both hot and cooled data for both running experiment data acquisition systems and data center use cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A generalizable machine learning-assisted fast Fourier transform algorithm to simulate the large strain phenomena in polycrystalline materials

Machine learning methods have shown initial promise in constitutive modeling for single crystals or homogenized polycrystals, delivering notable computational efficiency. However, existing machine learning-based constitutive models often lack generalizability, limiting their application across diverse boundary value problems. This study introduces a thermodynamics-informed artificial neural network model to accelerate rate-tangent crystal plasticity fast Fourier transform simulations for cross-scale deformation behaviors of polycrystals under complex loading. Our model integrates microstructural variability and local interactions effectively. To address local effects in each grain, we employ K-means clustering to group Gauss points within the microstructure into clusters assumed to be in similar mechanical states. This approach, based on self-clustering analysis, extends model scope from macroscopic stress response to the granular level, capturing mechanical responses and orientation evolution across grains. This reduces the number of nonlinear problems to solve, with cluster responses propagated throughout each group. The thermodynamics-based artificial neural network-extracted features are further processed using local material state clusters to account for history-dependent deformation and evolving microstructures. Additionally, representative volume element simulations with rate-tangent crystal plasticity fast Fourier transform provide reliable datasets for model training. The proposed model demonstrates high efficiency, accuracy, self-consistency, and enhanced generalizability in predicting strain–stress responses and orientation evolution at both individual grain and aggregate scales under complex loading conditions, such as biaxial tension and arbitrary loading scenarios.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗
DOE OSTI2026

PowerMappeR: Power-Optimized Mapping of SNNs onto ReRAM Crossbars coupled via Packet-Switched NoCs

Many recent efforts in developing hardware-accelerated spiking neural networks (SNNs) are characterized by deep co-design between algorithms, architectures, and devices. Architectural advances overcome device constraints by coupling together many small resistive-RAM (ReRAM) crossbars via a network-on-chip (NoC) for neuromorphic component operation. Concurrently, improved SNN training methods increase accuracy and structural sparsity in networks despite growing problem sizes. Finally, compilers leverage these attributes to minimize area and inter-crossbar communication while mapping large SNNs to sophisticated architectures. However, for compiler-driven co-design to realize increasingly complex and profitable optimizations, a compile-time view of power consumption is critical. We present PowerMappeR to express and optimize over mapping-, architecture-, and device-specific power consumption information. By modeling the dynamic power of well-established components, we develop an integer linear programming (ILP)-based, encoding-agnostic, parametric power estimation model. Using this model, we demonstrate practical improvements in area and inter-crossbar communication by 0%–9.5% and 1.4%–5.1%, respectively. We also limit hotspot formation during optimization, achieving comparable or better results in targeted metrics with up to 96.4%–97.1% restriction of hotspot magnitude. Finally, we introduce profile-guided formulations to reduce worst-case and expected-case hotspot magnitude by 40.7%–69.5% and 40.6%–56.3%, respectively. Optimizing worst-case hotspot magnitude incidentally improves expected-case magnitude by 10.85%–33.45%. Reciprocally, optimizing expected-case magnitude incidentally improves worst-case magnitude by 4.33%–39.87%. Validation against hardware simulators confirms that PowerMappeR can decrease dynamic power consumption by 12.6%–27.3%.

Pohl, Devin [ORNL] (ORCID:0009000040149027)↗
DOE OSTI2025

Closing the Loop between In Situ Stress Complexity and EGS Fracture Complexity

We present an agent-guided approach to CAD geometry decomposition that automates hex/hybrid meshing with graph neural networks (GNNs) to accelerate next-generation ModSim workflows. Our end-to-end pipeline (i) reduces 3D boundary-representation (B-Rep) models to a 2D chordal axis skeleton (CAT) and then to a 1D bipartite graph of surface and curve nodes, (ii) assigns per node labels as Cubit® WebCut actions, (iii) trains a multi-action GNN under supervised learning, and (iv) predicts five surface-node and three curve-node actions on out-of-distribution test geometries. Each graph node carries geometric, topological, and meshing attributes drawn from the B-Rep “skin” and CAT “skeleton,” with two-way mappings across 3D↔2D↔1D representations to maintain traceability back to 3D CAD. The supervised learning model exhibits stable convergence of the binary cross-entropy loss and achieves 98.7% accuracy on unseen lattice models. To operationalize decision-making, we rank predicted commands by geometric significance and prototyped the agent-guided workflow through the Cubit® Meshing PowerTool GUI. As a stretch goal, we explore reinforcement learning (RL) to reduce or remove label requirements and to learn policies for action sequences that maximize total reward (e.g., size of hex-meshable regions and resulting hex mesh quality). When all-hex meshing is not feasible, the agent assists in producing hybrid meshes—prioritizing hex in critical regions and transitioning to tetrahedral elements (tets) elsewhere—maintaining fidelity while ensuring robustness. The overarching objective is to replace manual, heuristics-based decomposition with data-driven, reproducible automation, cutting meshing turnaround time by orders of magnitude. We anticipate direct impact on simulation workflows through intelligent, scalable decomposition of complex CAD models into hex-meshable subdomains.

42 ENGINEERING↗
DOE OSTI2025

Software Tools Ecosystem Project (STEP) Midyear Report CY2025

This document provides a technical project report for the first six months of 2025 for the Software Tools Ecosystem Project (STEP). The mission of STEP is to enable critical software tools to proactively adapt to emerging platform technologies (such as new accelerators, storage devices, network technologies, and smart devices) and emerging application use cases (such as advanced machine learning and workflow frameworks) so that they continue to meet the needs of scientific computing and provide a strong foundation for future Advanced Scientific Computing Research activities. Our challenges include the wide breadth of our stakeholders and rapidly evolving platform technology dependencies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Software Tools Ecosystem Project (STEP): CY2025 Annual Report

This document provides a technical project report for the Software Tools Ecosystem Project (STEP) during calendar year 2025. The mission of STEP is to enable critical software tools to proactively adapt to emerging platform technologies (such as new accelerators, storage devices, network technologies, and smart devices) and emerging application use cases (such as advanced machine learning and workflow frameworks) so that they continue to meet the needs of scientific computing and provide a strong foundation for future Advanced Scientific Computing Research activities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Addressing GPU memory limitations for Graph Neural Networks in High-Energy Physics applications

Introduction Reconstructing low-level particle tracks in neutrino physics can address some of the most fundamental questions about the universe. However, processing petabytes of raw data using deep learning techniques poses a challenging problem in the field of High Energy Physics (HEP). In the Exa.TrkX Project, an illustrative HEP application, preprocessed simulation data is fed into a state-of-art Graph Neural Network (GNN) model, accelerated by GPUs. However, limited GPU memory often leads to Out-of-Memory (OOM) exceptions during training, due to the large size of models and datasets. This problem is exacerbated when deploying models on High-Performance Computing (HPC) systems designed for large-scale applications. Methods We observe a high workload imbalance issue during GNN model training caused by the irregular sizes of input graph samples in HEP datasets, contributing to OOM exceptions. We aim to scale GNNs on HPC systems, by prioritizing workload balance in graph inputs while maintaining model accuracy. Our paper introduces diverse balancing strategies aimed at decreasing the maximum GPU memory footprint and avoiding the OOM exception, across various datasets. Results Our experiments showcase memory reduction of up to 32.14% compared to the baseline. We also demonstrate the proposed strategies can avoid OOM in application. Additionally, we create a distributed multi-GPU implementation using these samplers to demonstrate the scalability of these techniques on the HEP dataset. Discussion By assessing the performance of these strategies as data loading samplers across multiple datasets, we can gauge their effectiveness in both single-GPU and distributed environments. Our experiments, conducted on datasets of varying sizes and across multiple GPUs, broaden the applicability of our work to various GNN applications that handle input datasets with irregular graph sizes.

Lee, Claire Songhyun↗
DOE OSTI2023

Accelerating discrete dislocation dynamics simulations with graph neural networks

Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials. However, the computational cost of DDD simulations remains a bottleneck that limits its range of applicability. Here, we introduce a new DDD-GNN framework in which the expensive time-integration of dislocation motion is entirely substituted by a graph neural network (GNN) model trained on DDD trajectories. As a first application, we demonstrate the feasibility and potential of our method on a simple yet relevant model of a dislocation line gliding through an array of obstacles. We show that the DDD-GNN model is stable and reproduces very well unseen ground-truth DDD simulation responses for a range of straining rates and obstacle densities, without the need to explicitly compute nodal forces or dislocation mobilities during time-integration. Our approach opens new promising avenues to accelerate DDD simulations and to incorporate more complex dislocation motion behaviors.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Upgrading Fermilab s Accelerator Control System with ACORN

The Fermilab Accelerator Complex is the largest national user facility in the Office of High Energy Physics (DOE/HEP) program and the only national user facility operating at Fermilab. Fermilab serves as the host to the Long Baseline Neutrino Facility/Deep Underground Neutrino Experiment (LBNF/DUNE), the laboratory’s flagship project for neutrino science that is under construction. LBNF/DUNE will be powered by megawatt beams from an upgraded accelerator, the Proton Improvement Plan II (PIP-II) that will replace the laboratory’s aging linear accelerator with a new one based on superconducting radio-frequency cavities. The Accelerator Controls Operations Research Network (ACORN) Project will support LBNF/DUNE and PIP-II by modernizing the accelerator control system. The project is at the conceptual design phase and looking to achieve Critical Decision 1 (CD-1) later this year. The scope and structure of the project will be presented, along with an overview of how that has changed in the past year. Current design and technology choices will be shared. Specific challenges facing the project will be addressed, along with current thinking on solutions.

Roehrig, Christian [Fermilab]↗