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 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗
DOE OSTI2021

AI-Enhanced Co-Design for Next-Generation Microelectronics: Innovating Innovation (Workshop Report)

On April 6-8, 2021, Sandia National Laboratories hosted a virtual workshop to explore the potential for developing AI-Enhanced Co-Design for Next-Generation Microelectronics (AICoM). The workshop brought together two themes. The first theme was articulated in the 2018 Department of Energy Office of Science (DOE SC) “Basic Research Needs for Microelectronics” (BRN) report, which called for a “fundamental rethinking” of the traditional design approach to microelectronics, in which subject matter experts (SMEs) in each microelectronics discipline (materials, devices, circuits, algorithms, etc.) work near-independently. Instead, the BRN called for a non-hierarchical, egalitarian vision of co-design, wherein “each scientific discipline informs and engages the others” in “parallel but intimately networked efforts to create radically new capabilities.” The second theme was the recognition of the continuing breakthroughs in artificial intelligence (AI) that are currently enhancing and accelerating the solution of traditional design problems in materials science, circuit design, and electronic design automation (EDA).

36 MATERIALS SCIENCE↗
DOE OSTI2025

LEBT Buncher / Feed Forward / Frequency Generation: System Design Document (SDD)

The LAMP Low Energy Beam Transport (LEBT) transfers a continuous beam at 100 keV from the ion source to RFQ in LEBT. A LEBT buncher imposes an energy tilt to initiate velocy bunching in the chopped beam pulse about 25 ns long to form a short MPEG bunch. One possible option for the LEBT buncher based on a two-gap LC-circuit driven structure was considered, which is similar to the existing LANSCE low-frequncy buncher (LFB). Another possible option is a non-resonant element driven by a pulse-forming-network that provides a single pulse at the repetition frequency of MPEG beam, with a period of 1.8 µs. The LEBT operation is synchronized with the accelerator timing system.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

DenKv: Addressing Design Trade-offs of Key-value Stores for Scientific Applications

High-performance computing (HPC) facilities have employed flash-based storage tier near to compute nodes to absorb high I/O demand by HPC applications during periodic system-level checkpoints. To accelerate these checkpoints, proxy-based distributed key-value stores (PD-KVS) gained particular attention for their flexibility to support multiple backends and different network configurations. PD-KVS rely internally on monolithic KVS, such as LevelDB or RocksDB, to exploit the KV interface and query support. However, PD-KVS are unaware of the high redundancy factor in checkpoint data, which can be up to GBs to TBs, and therefore, tend to generate high write and space amplification on these storage layers. In this paper, we propose DenKv which is deduplication-extended node-local LSM-tree-based KVS. DenKv employs asynchronous partially inline dedup (APID) and aims to maintain the performance characteristics of LSM-tree-based KVS while reducing the write and space amplification problems. We implemented DenKv atop BlobDB and showed that our proposed solution maintains performance while reducing write amplification up to 2× and space amplification by 4× on average.

Khan, Awais↗
DOE OSTI2020

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classication is found to be easily misled by increasingly complex image features due to the usage of pooling operations, hence unable to preserve accurate position and pose information of the objects. To address this challenge, a novel neural network structure called Capsule Network has been proposed, which introduces equivariance through capsules to signicantly enhance the learning ability for image segmentation and object detection. Due to its requirement of performing a high volume of matrix operations, CapsNets have been generally accelerated on modern GPU platforms that provide highly optimized software library for common deep learning tasks. However, based on our performance characterization on modern GPUs, CapsNets exhibit low effciency due to the special program and execution features of their routing procedure, including massive unshareable intermediate variables and intensive syn- chronizations, which are very dicult to optimize at software level. To address these challenges, we propose a hybrid computing architecture design named PIM-CapsNet. It preserves GPU's on-chip computing capability for accelerating CNN types of layers in CapsNet, while pipelining with an off-chip in-memory acceleration solution that effectively tackles routing procedure's ineffciency by leveraging the processing-in-memory capability of today's 3D stacked memory. Using routing procedure's inherent parallellization feature, our design enables hierarchical improvements on CapsNet inference effciency through minimizing data movement and maximizing parallel processing in memory. Evaluation results demonstrate that our proposed design can achieve substantial improvement on both performance and energy savings for CapsNet inference, with almost zero accuracy loss. The results also suggest good performance scalability in optimizing the routing procedure with increasing network size.

Zhang, Xingyao↗
DOE OSTI2024

Rapid Inverse Parameter Inference Using Physics-Informed Neural Network

As Li-ion batteries become more essential in today's economy, tools need to be developed to accurately and rapidly diagnose a battery's internal state-of-health. Using a Li-ion battery's (high-rate) voltage response, it is proposed to determine a battery's internal state through Bayesian calibration. However, Bayesian calibration is notoriously slow and requires thousands of model runs. To accelerate parameter inference using Bayesian calibration, a surrogate model is developed to replace the underlying physics-based Li-ion model. Developing a surrogate model for rapid Bayesian calibration analysis is discussed for both the single particle model (SPM) and the pseudo two-dimensional (P2D) model. Surrogate models are constructed using physics-informed neural networks (PINNs) that encode the influence of internal properties on observed voltage responses. In practice, a neural network can be trained by: 1) using simulation results of the physics-based model (i.e., a data-loss approach); 2) using the residuals of the governing equations themselves (i.e., a physics-loss approach); or 3) using a combination of simulation results and governing equation residuals. In the present work, PINNs are developed using a variety of training losses and neural network architectures. In this analysis, it is shown that a PINN surrogate model can be reliably trained with only physics-informed loss. However, using a coupled data-informed and physics-loss approach produced the most accurate PINNs.

Bayesian calibration↗
DOE OSTI2025

Global tuning of hadronic interaction models with accelerator-based and astroparticle data

In high-energy and astroparticle physics, event generators play an essential role, even in the simplest data analyses. As analysis techniques become more sophisticated, e.g. based on deep neural networks, their correct description of the observed event characteristics becomes even more important. Physical processes occurring in hadronic collisions are simulated within a Monte Carlo framework. A major challenge is the modeling of hadron dynamics at low momentum transfer, which includes the initial and final phases of every hadronic collision. QCD-inspired phenomenological models used for these phases cannot guarantee completeness or correctness over the full phase space. These models usually include parameters which must be tuned to suitable experimental data. Until now, event generators have been developed and tuned mainly on the basis of data from high-energy physics experiments at accelerators. The wealth of data available from the latest generation of astroparticle experiments has not yet been fully exploited, and in many cases is not satisfactorily described. Both kinds of data sets are complementary as astroparticle experiments provide sensitivity especially to hadrons produced nearly parallel to the collision axis and cover center-of-mass energies up to several hundred TeV, well beyond those reached at colliders so far. In this report, we provide an overview of state-of-the-art event generators and their tuning, including the most relevant inputs from high-energy accelerator and astroparticle experiments. We present a road map that shows, for the first time, how the unified tuning of event generators with accelerator-based and astroparticle data can be performed.

Albrecht, J. [Ruhr U., Bochum, RAPP Ctr.; Ruhr U.,↗
DOE OSTI2025

End-to-End Workflow for Machine-Learning-Based Qubit Readout With QICK and hls4ml

In this article, we present an end-to-end workflow for superconducting qubit readout that embeds codesigned neural networks into the quantum instrumentation control kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx radiofrequency system-on-chip field-programmable gate arrays (FPGAs), we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python application programming interfaces. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32.25 ns and less than 16% FPGA lookup table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications.

42 ENGINEERING↗
DOE OSTI2021

An adaptive approach to machine learning for compact particle accelerators

Abstract Machine learning (ML) tools are able to learn relationships between the inputs and outputs of large complex systems directly from data. However, for time-varying systems, the predictive capabilities of ML tools degrade if the systems are no longer accurately represented by the data with which the ML models were trained. For complex systems, re-training is only possible if the changes are slow relative to the rate at which large numbers of new input-output training data can be non-invasively recorded. In this work, we present an approach to deep learning for time-varying systems that does not require re-training, but uses instead an adaptive feedback in the architecture of deep convolutional neural networks (CNN). The feedback is based only on available system output measurements and is applied in the encoded low-dimensional dense layers of the encoder-decoder CNNs. First, we develop an inverse model of a complex accelerator system to map output beam measurements to input beam distributions, while both the accelerator components and the unknown input beam distribution vary rapidly with time. We then demonstrate our method on experimental measurements of the input and output beam distributions of the HiRES ultra-fast electron diffraction (UED) beam line at Lawrence Berkeley National Laboratory, and showcase its ability for automatic tracking of the time varying photocathode quantum efficiency map. Our method can be successfully used to aid both physics and ML-based surrogate online models to provide non-invasive beam diagnostics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization

Abstract Atmospheric radiation is the main driver of weather and climate, yet due to a complicated absorption spectrum, the precise treatment of radiative transfer in numerical weather and climate models is computationally unfeasible. Radiation parameterizations need to maximize computational efficiency as well as accuracy, and for predicting the future climate many greenhouse gases need to be included. In this work, neural networks (NNs) were developed to replace the gas optics computations in a modern radiation scheme (RTE+RRTMGP) by using carefully constructed models and training data. The NNs, implemented in Fortran and utilizing BLAS for batched inference, are faster by a factor of 1–6, depending on the software and hardware platforms. We combined the accelerated gas optics with a refactored radiative transfer solver, resulting in clear‐sky longwave (shortwave) fluxes being 3.5 (1.8) faster to compute on an Intel platform. The accuracy, evaluated with benchmark line‐by‐line computations across a large range of atmospheric conditions, is very similar to the original scheme with errors in heating rates and top‐of‐atmosphere radiative forcings typically below 0.1 K day −1 and 0.5 W m −2 , respectively. These results show that targeted machine learning, code restructuring techniques, and the use of numerical libraries can yield material gains in efficiency while retaining accuracy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Symplectic machine learning model for fast simulation of space-charge effects

Symplectic simulation of space-charge effects is crucial for the design and operation of high-intensity particle accelerators. Traditional methods for simulating these effects are often computationally expensive, resulting in significant overhead. In this work, we introduce a generative model based on a U-Net architecture within a generative adversarial network framework to efficiently simulate space-charge effects. The model is trained to predict the transverse multiparticle space-charge Hamiltonian, which can be physically computed using a gridless spectral method. The one-step symplectic transverse transfer map for the particles is then obtained by differentiating the predicted Hamiltonian. Benchmarking results demonstrate that this generative model achieves an order of magnitude higher computational efficiency compared to the spectral method, providing a highly efficient alternative for simulating space-charge effects with a large number of particles. By maintaining symplecticity, the model effectively preserves the phase-space structure and mitigates nonphysical errors in long-term simulations. This model has been integrated into jutrack, a novel autodifferentiable accelerator modeling code developed in the julia programming language.

Beam code development & simulation techniques↗
DOE OSTI2023

Permutationally Invariant Networks for Enhanced Sampling (PINES): Discovery of Multimolecular and Solvent-Inclusive Collective Variables

The typically rugged nature of molecular free energy landscapes can frustrate efficient sampling of the thermodynamically relevant phase space due to the presence of high free energy barriers. Enhanced sampling techniques can improve phase space exploration by accelerating sampling along particular collective variables (CVs). A number of techniques exist for data-driven discovery of CVs parameterizing the important large scale motions of the system. A challenge to CV discovery is learning CVs invariant to symmetries of the molecular system, frequently rigid translation, rigid rotation, and permutational relabeling of identical particles. Of these, permutational invariance has proved a persistent challenge in frustrating the data-driven discovery of multi-molecular CVs in systems of self-assembling particles and solvent-inclusive CVs for solvated systems. In this work, we integrate Permutation Invariant Vector (PIV) featurizations with autoencoding neural networks to learn nonlinear CVs invariant to translation, rotation, and permutation, and perform interleaved rounds of CV discovery and enhanced sampling to iteratively expand sampling of configurational phase space and obtain converged CVs and free energy landscapes. Here, we demonstrate the Permutationally Invariant Network for Enhanced Sampling (PINES) approach in applications to the self-assembly of a 13-atom Argon cluster, association/dissociation of a NaCl ion pair in water, and hydrophobic collapse of a C 45 H 92 n-pentatetracontane polymer chain. We make the approach freely available as a new module within the PLUMED2 enhanced sampling libraries.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Science Uses Deployment Operations-Advanced Wireless: Exploring Open Radio Access Network Technologies for Energy Science

Open Radio Access Network is emerging as a solution to the increasing demand for more flexible, cost-effective, and advanced mobile network infrastructures. This evolution is driven by advancements in wireless technologies and the growing complexity of deploying and managing these networks. O-RAN represents a significant shift in wireless technology, building upon the 3rd Generation Partnership Project framework to foster openness, flexibility, and interoperability. By decoupling hardware and software components, Open Radio Access Network enables a multi-vendor ecosystem that encourages innovation and diverse solutions. Open Radio Access Network's potential extends beyond traditional wireless applications, with growing interest in its role in advancing energy systems, particularly in the context of smart grids, microgrids, and the integration of renewable energy sources. While the role of open-wireless technologies in driving energy transformation is increasingly recognized, further exploration is needed. Vendors and utilities are investigating how Open Radio Access Network technologies can optimize energy use cases and improve the performance of 5G and beyond applications. This report outlines efforts under the Science Uses Deployment Operations Advance Wireless project, a collaboration between the National Laboratory of the Rockies' Cybersecurity Research Center, Argonne National Laboratory, Lawrence Berkeley National Laboratory, and the Department of Energy's Energy Science Network research and operations staff. The focus of this project is on due diligence, through testing and evaluation, preparing for the deployment of advanced wireless infrastructure for scientific use cases, with an emphasis on Open Radio Access Network technology, its components, integrations, and its ability to support vertical stack application across the energy sector. Additionally, the report highlights the value cases for utilities, underscoring how adopting open wireless standards can accelerate the evolution of energy systems, foster innovation, and improve the integration of critical energy technologies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Equivariant, safe and sensitive — graph networks for new physics

This study introduces a novel Graph Neural Network (GNN) architecture that leverages infrared and collinear (IRC) safety and equivariance to enhance the analysis of collider data for Beyond the Standard Model (BSM) discoveries. By integrating equivariance in the rapidity-azimuth plane with IRC-safe principles, our model significantly reduces computational overhead while ensuring theoretical consistency in identifying BSM scenarios amidst Quantum Chromodynamics backgrounds. The proposed GNN architecture demonstrates superior performance in tagging semi-visible jets, highlighting its potential as a robust tool for advancing BSM search strategies at high-energy colliders.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Discovering Innovations in Stress Tolerance through Comparative Gene Regulatory Network Analysis and Cell-Type Specific Expression Maps (Final Technical Report with Cover Page)

Through this grant, we developed a comparative framework to elucidate the mechanisms behind variations in environmental stress responses among a diverse group of species within the Brassicaceae family. Our focus was on the differences in physiological and transcriptomic responses to abscisic acid (ABA), a hormone associated with water stress. We examined the differential growth responses of four Brassicaceae species, finding that most exhibited reduced root growth correlated with smaller meristem size. In contrast, Schrenkiella parvula showed accelerated growth due to increased root cell elongation. We employed RNA sequencing to analyze the transcriptional responses to ABA across these species, and innovative bioinformatics techniques were used to pinpoint biological pathways with significant divergence. Additionally, we utilized DAP-seq to map the gene regulatory networks associated with ABAresponsive transcription factors, revealing that variations in the regulation of growth hormone biosynthesis play a critical role in the distinct ABA effects on root growth among the species. This research sets a new standard for comparative physiology by integrating comparative genomics and transcriptomics to uncover pathway divergences.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Lucina pectinata oxyhemoglobin (II-III) heterodimer pH susceptibility

Lucina pectinata live in high concentrations of hydrogen sulfide (H 2 S) and contains one hemoglobin, Hemoglobin I (HbI), transporting H 2 S and two hemoglobins, Hemoglobin II (HbII) and Hemoglobin (HbIII), transferring dioxygen to symbionts. HbII and HbIII contain B10 tyrosine (Tyr) and E7 glutamine (Gln) in the heme pocket generating an efficient hydrogen bonding network with the (HbII-HbIII)-O 2 species, leading to very low ligand dissociation rates. The results indicate that the oxy-hemeprotein is susceptible to pH from 4 to 9, at acidic conditions, and as a function of the potassium ferricyanide concentration, 100% of the met-aquo derivative is produced. Without a strong oxidant, pH 5 generates a small concentration of the met-aquo complex. The process is accelerated by the presence of salts, as indicated by the crystallization structures and UV–Vis spectra. The results suggest that acidic pH generates conformational changes associated with B10 and E7 heme pocket amino acids, weakening the (HbII-HbIII)-O 2 hydrogen bond network. The observation is supported by X-ray crystallography, since at pH 4 and 5, the heme-Fe tends to oxidize, while at pH 7, the oxy-heterodimer is present. Additionally, conformational changes are observed at higher pH by the presence of a 605 nm transition associated with the iron heme-Tyr interaction. Therefore, pH is one crucial factor regulating the (HbII-HbIII)-O 2 complex hydrogen-bonding network. Thus, it can be proposed that the hydrogen bonding adjustments between the heme bound O 2 and the Tyr and Gln amino acids contribute to oxygen dissociation from the (HbII-HbIII)-O 2 system.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Image-Based Fracture Surface Defect Characterization Methods for Additively Manufactured Ti-6Al-4V Tested in Fatigue

Abstract Fatigue initiation in additively manufactured samples/parts often occurs at processed-induced defects such as lack-of-fusion (LoF), keyhole, or other morphological/microstructural defects that have unique characteristics and measurable qualities. Attempts at identifying and minimizing such defects have utilized optimized processing conditions along with in situ and ex situ characterization that includes metallography and/or X-ray computed tomography (XCT). This paper highlights the benefits of using fracture surface analyses to detect and quantify defects that may not be detected by metallography/XCT due to sectioning and resolution limits. In addition to using manual quantification of fatigue initiating LoF and keyhole defects on fracture surfaces, image-based machine learning using convolutional neural networks such as U-Net were also used to automate the process. Statistical analyses were used to identify the extreme cases of defects that initiated and accelerated fatigue and to model the distribution of defect size and shape characteristics to distinguish the type of defect. Initial results show agreement between trained machine learning models and ground truth data in defect segmentation, and the distributions of defect characteristics are distinguishable to particular process-induced defect types.

Materials Science↗
DOE OSTI2020

Communication-Constrained Expansion Planning for Resilient Distribution Systems

Distributed generation and remotely controlled switches have emerged as important technologies to improve the resiliency of distribution grids against extreme weather-related disturbances. Therefore it becomes important to study how best to place them on the grid in order to meet a resiliency criteria, while minimizing costs and capturing their dependencies on the associated communication systems that sustain their distributed operations. This paper introduces the Optimal Resilient Design Problem for Distribution and Communication Systems (ORDPDC) to address this need. The ORDPDC is formulated as a two-stage stochastic mixed-integer program that captures the physical laws of distribution systems, the communication connectivity of the smart grid components, and a set of scenarios that specifies which components are affected by potential disasters. The paper proposes an exact branch-and-price algorithm for the ORDPDC that features a strong lower bound and a variety of acceleration schemes to address degeneracy. The ORDPDC model and branch-and-price algorithm were evaluated on a variety of test cases with varying disaster intensities and network topologies. The results demonstrate the significant impact of the network topologies on the expansion plans and costs, as well as the computational benefits of the proposed approach.

97 MATHEMATICS AND COMPUTING↗