SEARCH · Engineering Papers

Results for “Architecture patterns”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 325 records · Page 18

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Integrating LEO and GEO Observations: Toward Optimal Summertime Satellite Precipitation Retrieval

Abstract Reliable quantitative precipitation estimation with a rich spatiotemporal resolution is vital for understanding the Earth’s hydrological cycle. Precipitation estimation over land and coastal regions is necessary for addressing the high degree of spatial heterogeneity of water availability and demand, and for resolving the extremes that modulate and amplify hazards such as flooding and landslides. Advancements in computation power along with unique high spatiotemporal and spectral resolution data streams from passive meteorological sensors aboard geosynchronous Earth-orbiting (GEO) and low Earth-orbiting (LEO) satellites offer exciting opportunities to retrieve information about surface precipitation phenomena using data-driven machine learning techniques. In this study, the capabilities of U-Net–like architecture are investigated to map instantaneous, summertime surface precipitation intensity at the spatial resolution of 2 km. The calibrated brightness temperature products from the Global Precipitation Measurement (GPM) Microwave Imager (GMI) radiometer are combined with multispectral images (visible, near-infrared, and infrared bands) from the Advanced Baseline Imager (ABI) aboard the GOES-R satellites as main inputs to the U-Net–like precipitation algorithm. Total precipitable water and 2-m temperature from the Global Forecast System (GFS) model are also used as auxiliary inputs to the model. The results show that the U-Net–like algorithm can capture fine-scale patterns and intensity of surface precipitation at high spatial resolution over stratiform and convective precipitation regimes. The evaluations reveal the potential of extracting relevant, high spatial features over complex surface types such as mountainous regions and coastlines. The algorithm allows users to interpret the inputs’ importance and can serve as a starting point for further exploration of precipitation systems within the field of hydrometeorology.

Meteorology & Atmospheric Sciences↗

DOE OSTI2023

Enhancing photonic systems using topology and non-Hermiticity

The broad goal of this project was to develop new analytical and numerical insights for how important photonic processes can be improved using recently discovered principles in topological and non-Hermitian physics. In particular, there are two recent discoveries that we aimed to harness to achieve this goal. First, it was discovered in condensed matter physics that crystalline symmetries can protect low-dimensional topologically protected states in lattices without the need for breaking time-reversal symmetry. These so-called ‘higher-order’ topological systems represent an important development for photonic systems, where it is very difficult to break time-reversal symmetry, and which had been previously thought necessary to realize topological phenomena. Second, the last decade has seen a significant amount of interest in phenomena which are unique to non-Hermitian systems, i.e., systems which do not conserve energy. For example, spatially patterned gain and loss can be used to realize exceptional points, which are degeneracies in a system’s spectrum where the system becomes defective, while the existence of radiative losses also enables a new route to confinement through bound states in the continuum. For such non-Hermitian phenomena, photonics again represents a critical platform, as photonic systems naturally lose light to their radiative environments, making them generally non-Hermitian, and it is also possible to incorporate additional gain or loss. Based on these broad principles, we pursued a range of projects to harness bound states in the continuum in a variety of different systems and architectures, develop real-space methods for classifying topological systems to yield better photonic design principles, and a novel Brillouin-based fiber laser for sensing strain.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

DOE OSTI2021

Programmable Site‐Specific Functionalization of DNA Origami with Polynucleotide Brushes

Abstract Combining surface‐initiated, TdT (terminal deoxynucleotidyl transferase) catalyzed enzymatic polymerization (SI‐TcEP) with precisely engineered DNA origami nanostructures (DONs) presents an innovative pathway for the generation of stable, polynucleotide brush‐functionalized DNA nanostructures. We demonstrate that SI‐TcEP can site‐specifically pattern DONs with brushes containing both natural and non‐natural nucleotides. The brush functionalization can be precisely controlled in terms of the location of initiation sites on the origami core and the brush height and composition. Coarse‐grained simulations predict the conformation of the brush‐functionalized DONs that agree well with the experimentally observed morphologies. We find that polynucleotide brush‐functionalization increases the nuclease resistance of DONs significantly, and that this stability can be spatially programmed through the site‐specific growth of polynucleotide brushes. The ability to site‐specifically decorate DONs with brushes of natural and non‐natural nucleotides provides access to a large range of functionalized DON architectures that would allow for further supramolecular assembly, and for potential applications in smart nanoscale delivery systems.

Yang, Yunqi↗

DOE OSTI2023

Microscale spatiotemporal patterns of water, soil organic carbon, and enzymes in plant litter detritusphere

Understanding biophysical and biochemical processes in detritusphere is critical to quantifying and modeling plant residue decomposition dynamics and subsequent soil organic carbon (C) accrual. The objectives of the study were to explore (i) micro-environmental conditions within the detritusphere formed around decomposing corn and soybean leaves, and (ii) the relationships between moisture distribution, enzyme activity, and C dynamics during decomposition. We assessed spatial and temporal dynamics of moisture distribution using X-ray and neutron computed tomography, and activities of β-glucosidase and chitinase, two enzymes involved in soil C and N processing, using zymography. We used 13 C labeled residue to track residue contribution to atmospheric CO 2 and soil organic C. Moisture redistribution pattern varied depending on the residue type. While the water was immediately absorbed by the corn leaves and maintained afterward, switchgrass leaves absorbed water more slowly and created water-deficient zones within ~1mm from the residue. This initial moisture depletion led to lower chitinase activity and residue-derived CO 2 emissions in switchgrass. In contrast to chitinase, β-glucosidase activity was influenced by a combination of vegetation history and residue type, and it was higher when the origin of the residue matched the vegetation history of the soil. Pore size had an opposite impact on the studied enzymes, supporting the notion that contrasting soil pore architecture can stimulate activities of different enzymes through a selection of dominant enzyme producers. We concluded that the decomposition dynamics of plant residues is not only a simple function of residue chemistry, but rather a combined effect of the vegetation history, in part through its effect on microbial community composition, the plant residue chemical and likely physical characteristics, and the soil pore structure in the detritusphere. Together, they create temporally dynamic micro-environmental conditions influencing decomposition. Specifically, our study demonstrated that the initial micro-environment formulated in detritusphere can play an important role in enzyme activities and consequent C dynamics.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

CAHS: Context-Aware Homology Search

Protein homology search is foundational to bioinformatics: it supports annotation transfer, structure/function inference, and evolutionary analysis over rapidly expanding sequence repositories (e.g., UniProtKB). Profile hidden Markov models (pHMMs), as implemented in HMMER, remain the most widely trusted approach because they provide statistically calibrated E-values; however, their gap behavior is fixed once a profile is trained, despite biological evidence that insertion/deletion tolerance varies across flexible loops and intrinsically disordered regions. We present CAHS (Context-Aware Homology Search), a lightweight query-time adapter for pHMM search that incorporates learned and biologically motivated signals without changing HMMER's downstream search pipeline or its calibrated E-value reporting. Given a query sequence, CAHS computes per-residue representations from a protein language model and a disorder predictor, maps these to profile coordinates, and modulates only match-state transition rows (gap-open and gap-extension probabilities) while preserving Plan7 constraints. We comprehensively evaluate CAHS across six structurally diverse protein families and multi-domain architectures against a 570k-sequence target corpus. CAHS expands detection capability, retrieving thousands of additional remote homologs at relaxed thresholds by maintaining alignment quality through flexible regions. For multi-domain proteins, context-aware modulation resolves 94% of fragmented alignments. Crucially, CAHS preserves hit-set invariance at stringent operating points (E<10-10), demonstrating increased statistical confidence without inflating false positives. Furthermore, sharper statistical distinction between homologs and background noise during early filter stages yields up to a 3.87× acceleration in end-to-end wall-clock time on high-performance computing clusters. Overall, CAHS illustrates a practical AI-for-science design pattern: augmenting a trusted probabilistic model with query-specific learned signals to improve interpretable, reproducible inference in data-rich biology.

Bhattaram, Swethasree [Georgia Institute of Techno↗

DOE OSTI2020

Data-Driven Template Discovery Using Graph Convolutional Neural Networks

Modeling adversarial activities is a critical component of developing high-con?dence indicators of efforts to acquire, fabricate, proliferate, and/or deploy weapons of mass terror (WMTs). Current approaches to generating representative patterns of interest (a.k.a templates) from the real-world domains involve a Subject Matter Expert (SME)-guided manual process. The goal of Data-Driven Template Discovery (DDTD) is to use a (potentially small) set of SME generated templates to discover other previously unknown and interesting templates in an attributed graph. A template is an activity pattern describing a set of interactions among a group of nodes in the graph. The motivation behind DDTD is to expand the original set of templates, without having SMEs craft all the templates by hand. DDTD also provides seed templates to SMEs, to help them construct larger, high-?delity, and scenario-oriented templates. In these cases, obtaining a larger set of templates that are related (contain similar signals) to the original set is of great value. In this work, we propose to use Graph Convolutional Neural Networks (GCNs) to discover new templates that are heavily related to the original set. GCNs are a family of Neural Network (NN) architectures especially designed to work directly on graphs. In contrast to the traditional NNs, that require considerable amounts of labeled data, GCNs do not require a big labeled training set because they can directly leverage the graph structure instead. This property makes GCNs the perfect tool for creating activity templates.

Joaristi, Mikel↗

DOE OSTI2025

Electrically Reconfigurable Liquid Metal Nanophotonic Platform for Color Display and Imaging

Dynamically tunable optical materials and device architectures are essential for future photonic technologies, yet conventional solid metals lack the intrinsic tunability required for advanced functionalities. Gallium-based liquid metals (LMs) present an appealing alternative thanks to their distinctive mechanical and optical properties; however, their practical integration in tunable photonic elements remains largely unexplored. Here, in this study, an electrochemically controlled nanophotonic platform is demonstrated that integrates a dynamically reconfigurable LM ground plane with gold nanoantenna arrays within a microfluidic system, enabling precise and reversible modulation of optical resonances across the visible to mid-infrared spectral ranges. By employing moderate operational voltages (1.5–3.0 V), real-time tuning of high-resolution structural color patterns is achieved through nanoscale control of the interfacial gap between the LM and Au nanoantennas. This innovative platform facilitates electrically programmable, high-contrast color patterns suitable for dynamic optical displays, secure anti-counterfeiting labels, and imaging applications. Additionally, this platform enables tunable mid-infrared spectral responses, which may be utilized for chemical and biological sensing applications. This versatile integrated LM-based nanophotonic platform opens new paths toward multifunctional, actively tunable/reconfigurable photonic device and system technologies.

Imaging↗

DOE OSTI2024

Hierarchical Phased-Array Antennas Coupled to Al KIDs: A Scalable Architecture for Multi-band Millimeter/Submillimeter Focal Planes

We present the optical characterization of two-scale hierarchical phased-array antenna kinetic inductance detectors (KIDs) for millimeter/submillimeter wavelengths. Our KIDs have a lumped-element architecture with parallel plate capacitors and aluminum inductors. The incoming light is received with a hierarchical phased array of slot dipole antennas, split into 4 frequency bands (between 125 GHz and 365 GHz) with on-chip lumped-element band-pass filters, and routed to different KIDs using microstriplines. Individual pixels detect light for the 3 higher-frequency bands (190–365 GHz), and the signals from four individual pixels are coherently summed to create a larger pixel detecting light for the lowest frequency band (125–175 GHz). The spectral response of the band-pass filters was measured using Fourier transform spectroscopy (FTS), the far-field beam pattern of the phased-array antennas was obtained using an infrared source mounted on a 2-axis translating stage, and the optical efficiency of the KIDs was characterized by observing loads at 294 K and 77 K. We report on the results of these three measurements.

47 OTHER INSTRUMENTATION↗

DOE OSTI2020

Predicting the Activity and Selectivity of Bimetallic Metal Catalysts for Ethanol Reforming using Machine Learning

Machine learning is ideally suited for the pattern detection in large uniform datasets, but consistent experimental datasets on catalyst studies are often small. Here we demonstrate how a combination of machine learning and first-principles calculations can be used to extract knowledge from a relatively small set of experimental data. The approach is based on combining a complex machine-learning model trained on an extensive computational library of transition-state energies with simple linear regression models of experimental catalytic activities and selectivities from the literature. Using the combined model, we identify the key C–C bond scission reactions involved in ethanol reforming and perform a computational screening for ethanol reforming on monolayer bimetallic catalysts with architectures TM-Pt-Pt(111) and Pt-TM-Pt(111) (TM = 3d transition metals). The model also predicts four promising catalyst compositions for future experimental studies. In conclusion, the approach is not limited to ethanol reforming but is of general use for the interpretation of experimental observations as well as for the computational discovery of novel catalytic materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

PLANC: Parallel Low-rank Approximation with Nonnegativity Constraints

In this work, we consider the problem of low-rank approximation of massive dense nonnegative tensor data, for example, to discover latent patterns in video and imaging applications. As the size of data sets grows, single workstations are hitting bottlenecks in both computation time and available memory. We propose a distributed-memory parallel computing solution to handle massive data sets, loading the input data across the memories of multiple nodes, and performing efficient and scalable parallel algorithms to compute the low-rank approximation. We present a software package called Parallel Low-rank Approximation with Nonnegativity Constraints, which implements our solution and allows for extension in terms of data (dense or sparse, matrices or tensors of any order), algorithm (e.g., from multiplicative updating techniques to alternating direction method of multipliers), and architecture (we exploit GPUs to accelerate the computation in this work). We describe our parallel distributions and algorithms, which are careful to avoid unnecessary communication and computation, show how to extend the software to include new algorithms and/or constraints, and report efficiency and scalability results for both synthetic and real-world data sets.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Glancing Angle Deposition in Gas Sensing: Bridging Morphological Innovations and Sensor Performances

Glancing Angle Deposition (GLAD) has emerged as a versatile and powerful nanofabrication technique for developing next-generation gas sensors by enabling precise control over nanostructure geometry, porosity, and material composition. Through dynamic substrate tilting and rotation, GLAD facilitates the fabrication of highly porous, anisotropic nanostructures, such as aligned, tilted, zigzag, helical, and multilayered nanorods, with tunable surface area and diffusion pathways optimized for gas detection. This review provides a comprehensive synthesis of recent advances in GLAD-based gas sensor design, focusing on how structural engineering and material integration converge to enhance sensor performance. Key materials strategies include the construction of heterojunctions and core–shell architectures, controlled doping, and nanoparticle decoration using noble metals or metal oxides to amplify charge transfer, catalytic activity, and redox responsiveness. GLAD-fabricated nanostructures have been effectively deployed across multiple gas sensing modalities, including resistive, capacitive, piezoelectric, and optical platforms, where their high aspect ratios, tailored porosity, and defect-rich surfaces facilitate enhanced gas adsorption kinetics and efficient signal transduction. These devices exhibit high sensitivity and selectivity toward a range of analytes, including NO2, CO, H2S, and volatile organic compounds (VOCs), with detection limits often reaching the parts-per-billion level. Emerging innovations, such as photo-assisted sensing and integration with artificial intelligence for data analysis and pattern recognition, further extend the capabilities of GLAD-based systems for multifunctional, real-time, and adaptive sensing. Finally, current challenges and future research directions are discussed, emphasizing the promise of GLAD as a scalable platform for next-generation gas sensing technologies.

Chemistry↗

DOE OSTI2025

Lines of Bound States in the Continuum in Monodisperse Microsphere Structures

Incorporating epitaxially grown active semiconductor media into self-assembled microsphere crystals has remained a major challenge as the curved geometry of the spheres is incompatible with conventional planar growth and patterning techniques. As a result, active photonic devices based on such self-assembled structures, which have other desirable properties such as enabling the rapid assembly of large area systems, have been elusive. Here, we numerically demonstrate an alternative route to creating high-Q resonances in microsphere-based nanophotonic assemblies compatible with standard optical gain materials. We show that close-packed layers of monodisperse microspheres can exhibit symmetry bandgaps, regardless of their layer stacking order. Thus, this microsphere environment can be used to create lines of bound states in the continuum (BICs) of an embedded slab made of active material. Using a realistic ZnS@SiO 2 (core-shell) architecture and sphere diameters compatible with scalable colloidal assembly, we predict sharp spectral features in angle-resolved transmission that trace these lines of BICs and persist in the presence of some fabrication disorder. Altogether, in enabling the integration of unpatterned epitaxial gain slabs with large-area colloidal microsphere assemblies, this approach opens a practical path toward active, dynamically reconfigurable photonic devices that leverage BIC physics for narrow-linewidth lasing and enhanced light–matter interactions.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

Programmable Site-Specific Functionalization of DNA Origami with Polynucleotide Brushes

Combining surface-initiated, TdT (terminal deoxynucleotidyl transferase) catalyzed enzymatic polymerization (SI-TcEP) with precisely engineered DNA origami nanostructures (DONs) presents an innovative pathway for the generation of stable, polynucleotide brush-functionalized DNA nanostructures. Here we demonstrate that SI-TcEP can site-specifically pattern DONs with brushes containing both natural and non-natural nucleotides. The brush functionalization can be precisely controlled in terms of the location of initiation sites on the origami core and the brush height and composition. Coarse-grained simulations predict the conformation of the brush-functionalized DONs that agree well with the experimentally observed morphologies. We find that polynucleotide brush-functionalization increases the nuclease resistance of DONs significantly, and that this stability can be spatially programmed through the site-specific growth of polynucleotide brushes. The ability to site-specifically decorate DONs with brushes of natural and non-natural nucleotides provides access to a large range of functionalized DON architectures that would allow for further supramolecular assembly, and for potential applications in smart nanoscale delivery systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Semi-supervised permutation invariant particle-level anomaly detection

The development of analysis methods to distinguish potential beyond the Standard Model phenomena in a model-agnostic way can significantly enhance the discovery reach in collider experiments. However, the typical machine learning (ML) algorithms employed for this task require fixed length and ordered inputs that break the natural permutation invariance in collision events. To address this, a semi-supervised anomaly detection tool is presented that takes a variable number of particle-level inputs and leverages a signal model to encode this information into a permutation invariant, event-level representation via supervised training with a Particle Flow Network (PFN). Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. Performance of the ANTELOPE architecture is evaluated on simulated samples of hadronic processes in a high energy collider experiment, showing good capability to distinguish disparate models of new physics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment

X-ray crystallography reconstruction, which transforms discrete X-ray diffraction patterns into three-dimensional molecular structures, relies critically on accurate Bragg peak finding for structure determination. As X-ray free electron laser (XFEL) facilities advance toward MHz data rates (1 million images per second), traditional peak finding algorithms that require manual parameter tuning or exhaustive grid searches across multiple experiments become increasingly impractical. While deep learning approaches offer promising solutions, their deployment in high-throughput environments presents significant challenges in automated dataset labeling, model scalability, edge deployment efficiency, and distributed inference capabilities. We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. Using this integrated approach, our pipeline achieves accuracy comparable to traditional methods tuned by human experts while eliminating the need for experiment-specific parameter tuning. Although current throughput requires optimization for MHz facilities, our system's scalable architecture and demonstrated model compression capabilities provide a foundation for future high-throughput XFEL deployments.

Wang, Cong↗

DOE OSTI2025

Application of Cyber-Informed Engineering for Protecting BESS

This white paper synthesizes an array of crucial grid services provided by BESS technology, assesses its architecture and communications, and presents a case study for analysis against the principles introduced by Cyber-Informed Engineering (CIE). Furthermore, in walking through the analysis, this paper presents a framework to evaluate risks and solutions when considering BESS components. Asset owners and buyers could perform this analysis to assess their BESS product implementations, alternative inverter-based resources (IBR), and energy management systems (EMS). Battery systems fulfill various roles contingent on the unique market demands and the specific challenges presented by regional grid infrastructures. These roles also vary due to the differing utility models for ownership and operation, which are adapted to meet regional and local capabilities and requirements. Concerns have been raised regarding the potential for adversaries to exploit knowledge of battery operational patterns to orchestrate decisive attacks. However, the security of operational data for these systems may not be the primary vulnerability, as much of this information is already well-understood within the community. Applying a modest degree of subject matter expertise can often yield valuable predictions regarding how a battery will respond under certain conditions, such as grid emergencies, high or low-temperature days, Public Safety Power Shutoff (PSPS) events, and outages. The operational characteristics of batteries are well-documented, and their capabilities, including the risks associated with misoperation and the resulting consequences, are published and understood within the industry. CIE practices represent the next step in gaining functional assurance and providing an acceptable level of risk, regardless of whether a battery vendor can support a trusted and validated supply chain. While this issue has exacerbated supply chain challenges, it is not an isolated condition. This foreign supply route is the primary source of BESS for the U.S. market. Significant efforts are underway through the Bipartisan Infrastructure Law (BIL) to change that. Still, strategic short-term operational mitigations are needed to ensure the security of our operational technology (OT) systems, which are enhanced by instilling trust and are separate from vendors implementing CIE principles.

25 ENERGY STORAGE↗

DOE OSTI2020

Redox cycling-based detection of phenazine metabolites secreted from Pseudomonas aeruginosa in nanopore electrode arrays

The opportunistic pathogen Pseudomonas aeruginosa (P. aeruginosa) produces several redox-active phenazine metabolites, including pyocyanin (PYO) and phenazine-1-carboxamide (PCN), which are electron carrier molecules that also aid in virulence. In particular, PYO is an exclusive metabolite produced by P. aeruginosa, which acts as a virulence factor in hospital-acquired infections and is therefore a good biomarker for identifying early stage colonization by this pathogen. Here, we describe the use of nanopore electrode arrays (NEAs) exhibiting metal–insulator–metal ring electrode architectures for enhanced detection of these phenazine metabolites. The size of the nanopores allows phenazine metabolites to freely diffuse into the interior and access the working electrodes, while the bacteria are excluded. Consequently, highly efficient redox cycling reactions in the NEAs can be accessed by free diffusion unhindered by the presence of bacteria. This strategy yields low limits of detection, i.e. 10.5 and 20.7 nM for PYO and PCN, respectively, values far below single molecule pore occupancy, e.g. at 10.5 nM < n pore > ~ 0.082 per nanopore – a limit which reflects the extraordinary signal amplification in the NEAs. Furthermore, experiments that compared results from minimal medium and rich medium show that P. aeruginosa produces the same types of phenazine metabolites even though growth rates and phenazine production patterns differ in these two media. Here, the NEA measurement strategy developed here should be useful as a diagnostic for pathogens generally and for understanding metabolism in clinically important microbial communities.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Dual Channel Dual Staging: Hierarchical and Portable Staging for GPU-Based In-Situ Workflow

In-situ workflows have emerged as an attractive approach for addressing data movement challenges at very large scales. Since GPU-based architectures dominate the HPC landscapes, porting these in-situ workflows, and, specifically, the inter-application data exchange, to GPU-based systems can be challenging. Technologies such as GPUDirect RDMA (GDR), which is typically used for I/O in GPU applications as an optimization that circumvents the CPU overhead, can be leveraged to support bulk data exchanges between GPU applications. However, current GDR design often lacks performance portability across HPC clusters built with different hardware configurations. Furthermore, the local CPU may also be effectively used as an auxiliary communication mechanism to offload data exchanges. In this paper, we present a dual channel dual staging approach for efficient, scalable, and performance-portable inter-application data exchange for in-situ workflows. This approach exploits the data access pattern within in-situ workflows along with the inherent execution asynchrony to accelerate data exchanges and, at the same time, improve performance portability. Specifically, the dual channel dual staging method leverages both the local CPU and the remote data staging server to build a hierarchical joint staging area and uses this staging area to transform blocking inter-application bulk data exchanges into best-effort local data movements between GPU and CPU. The dual channel dual staging is implemented as a portability extension of the Dataspaces-GPU staging framework. We present an experimental evaluation of its performance, portability, and scalability using this implementation on three leadership GPU clusters. The evaluation results demonstrate that the dual channel dual staging method saves up to 75% in data-exchange time compared to host-based, GDR, and alternate portable designs, while maintaining scalability (up to 512 GPUs) and performance portability across the three platforms.

Zhang, Bo [University of Utah]↗