Search NASA⌕ Search

SEARCH · Search NASA

Results for “heterogeneous architectures”

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 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Metal–Organic Frameworks as a Tunable Platform to Deconvolute Stereoelectronic Effects on the Catalytic Activity of Thioanisole Oxidation

The local environment of a metal active site plays an important role in affecting catalytic activity and selectivity. In re-cent studies, tailoring the behavior of a molybdenum-based active site via modulation of the first coordination sphere has led to improved thioanisole oxidation performance, but disentangling electronic effects from steric influences that arise from these modifications is nontrivial, especially in heterogeneous systems. To this end, the tunability of metal–organic frameworks (MOFs) makes them promising scaffolds for controlling the coordination sphere of a heterogene-ous, catalytically-active metal site while offering additional, attractive features such as crystallinity and high porosity. Herein, we report a variety of MOF-supported Mo species, which were investigated for catalytic thioanisole oxidation to methyl phenyl sulfoxide and/or methyl phenyl sulfone using tert-butyl hydroperoxide (tBHP) as the oxidant. In particular, MOFs of contrasting node architectures were targeted, presenting a unique opportunity to investigate ste-reoelectronic control of Mo active sites in a systematic manner. A Zr 6 -based MOF, NU-1000, was employed along with its sulfated analog Zr 6 -based NU-1000-SO 4 to anchor a dioxymolybdenum species, which enabled examination of sup-port-mediated active site polarizability on catalytic performance. In addition, a MOF containing a mixed metal node, Mo-MFU-4l, was used to probe the stereoelectronic impact of an N-donor ligand environment on the catalytic activity of the transmetalated Mo center. Furthermore, characterization techniques including single crystal X-ray diffraction, were concomi-tantly used with reaction kinetic profiles to better comprehend the dynamics of different Mo active sites, thus correlat-ing structural change with activity.

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

DONUT: physics-aware machine learning for real-time X-ray nanodiffraction analysis

Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample’s local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

Materials science↗
DOE OSTI2025

DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis

SF-25-088 Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample’s local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

Zhou, Tao [Argonne National Laboratory (ANL), Argo↗
DOE OSTI2025

Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage

Subsurface flow research is essential for the sustainable management of natural resources and the environment. Deep learning (DL) has significantly advanced this field by developing efficient and accurate surrogate models to replace computationally expensive physics‐based simulations. These surrogate models are commonly used to predict the spatiotemporal evolution of state variables, such as gas saturation and reservoir pressure, in heterogeneous geological formations. Despite the various DL models applied to this task, there is a lack of studies systematically comparing their performance. This absence of comparative analysis leads to somewhat arbitrary DL model selection in subsurface flow research, resulting in suboptimal performance and potentially inaccurate predictions. To bridge this gap, we conduct a systematic comparison study of three popular DL architectures—U‐Net, Fourier Neural Operators (FNO), and Segmentation Transformer (SETR)—in surrogate modeling of underground hydrogen storage (UHS). We focus on UHS due to its promise of enhancing clean energy resilience and its cyclic operational conditions that represent common scenarios in various subsurface applications. We evaluate the models based on accuracy, training cost, and inference speed. The comparison shows that U‐Net achieves the highest accuracy, followed by SETR and FNO. Despite its lower accuracy, FNO has the highest inference speed. SETR offers competitive accuracy with the least training memory usage, demonstrating the potential of transformers in learning subsurface flow. Our results provide guidance for selecting DL models for surrogate modeling in a wide range of subsurface flow problems.

42 ENGINEERING↗
DOE OSTI2023

Development of Analysis Methods that Integrate Numeric and Textual Equipment Reliability Data

Within the Light Water Reactor Sustainability (LWRS) program, the Risk-Informed Systems Analysis (RISA) Pathway is performing collaborative research on the development and deployment of technologies designed to assist operating nuclear power plants (NPPs) to reduce operating costs improve plant reliability and availability. One of the RISA research areas is focusing on the development of methods and tools designed to optimize plant operations (e.g., maintenance/replacement schedules, optimal maintenance postures for plant structures, systems, and components [SSCs]) in a manner that is more cost effective than current approaches and makes better use of available SSC health data. The Risk-Informed Asset Management (RIAM) project targets this research area by creating a direct bridge between component equipment reliability (ER) data and system engineer decision making regarding maintenance activity scheduling and component aging management. In this respect, one challenge that NPP system engineers are facing is that the amount of ER data being continuously generated is not only extremely large in size, but it comes in different forms: textual (e.g., condition or maintenance reports) and numeric (e.g., generated by monitoring systems). All these data elements provide them with valuable insights and information regarding: 1) the discovery of anomalous behaviors or degradation trends, 2) the identification of the possible causes behind such behaviors/trends, and 3) the prediction of their direct consequences. However, several challenges have proved to be roadblocks to this process. While some of these challenges are technical in nature (i.e., data are often distributed over several physical servers/databases), others are conceptual in nature: data elements come in different formats (e.g., numeric or textual), and measured values have different scales (e.g., vibration spectra and oil temperature). The activities performed by the RIAM project during FY23 directly tackles the need to simultaneously integrate the analysis of ER data in all its forms, numeric and textual. Note that such task has never been performed before due to the complexity of the systems under consideration but, most importantly, because of the technical challenges behind the harmonization of ER data formats and the lack of adequate computational methods to analyze them. Our approach borrows ideas and concepts from the medical field where integration of several data sources is vital to assist medical practitioners to perform correct diagnosis and indicate optimal treatments. In our view a NPP asset is equivalent to a patient in a medical context. The main difference is the complexity of a human body is a magnitude more complex when compared to typical assets commonly present in NPPs (e.g., centrifugal pumps, or motor operated valves). This simplifies our first requirement when analyzing heterogenous ER data formats: to put data into “context”. Context is here intended as the additional piece of information that is needed by ER data analysis tools to understand what these data elements are referring to, i.e., which king of knowledge they are generating. In our context, this knowledge can be translated into models that capture the form and functional architecture of assets/systems, their dependencies, and how they interact. These models actually emulate the knowledge that that NPP system engineers possess about assets and systems; this is their key of success when analyzing ER data, their challenge is ability to handle large amount of data. Here, we employ model-based system engineering (MBSE) models of systems and assets to represent and capture their architecture and functional, i.e. cause-effect, relations. Then, ER data elements are processed by identifying first of all which elements of the developed MBSE elements they are referring to. For numeric ER data this task is fairly easy since it is possible to precisely pinpoint what MBSE elements the corresponding sensor are observing (e.g., bearing temperature of a centrifugal pump). Task is much harder for textual data since the information contained in issue or maintenance reports needs to “be understood” by a computational tool. Here we called this process as “knowledge extraction”. Once again, we borrow the experience in the medical field where methods to extract knowledge from textual data have been developed in the past decade. The missing element for us is the availability of a complete dictionary of NPP related concepts (in addition to the MBSE models presented earlier) that can put “text into context”. In FY23, such dictionary has been developed along with all the computational elements required for knowledge extraction. Lastly, once numeric and textual ER data elements have been processed and “understood”, then the last step is the discovery of possible cause-effect relations among them. This is performed by observing if a logical connection through the MBSE models exists, and if the

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

A tool and a methodology to use macros for abstracting variations in code for different computational demands

Scientific software used on high-performance computing platforms is in a phase of transformation because of the combined increase in the heterogeneity and complexity of models and hardware platforms. Having separate implementations for different platforms can easily lead to combinatorial explosions; therefore, the computational science community has been looking for mechanisms to express code through abstractions that can be specialized for different platforms. Most existing approaches use template meta-programming in C++, and are, therefore language specific. Here, we have developed a tool that uses customized expansion of macros to mimic some of C++ behavior in other languages. It enables unification of any code variants that may be necessary to run efficiently on different target architectures and different computational environments through use of macros with multiple alternative definitions and ability to arbitrate on definition selection for expansion. Combined with two other tools, a custom runtime, and a user specified recipe translator, our custom macroprocessor becomes a part of an overall performance portability solution that does not depend on any specific programming language. We also use macros as code-shorthand that lets code snippets become building blocks that allow variations in control flow to explore performance options. We demonstrate use of macros in Flash-X, a multiphysics multicomponent code with many Fortran legacy components derived from an earlier community code FLASH.

Heterogenous computing↗
DOE OSTI2026

Promotion of CaCO 3 Nucleation by Carboxyl- and Amine-Terminated Peptoid Nanotubes

The use of surfaces to promote heterogeneous nucleation of CaCO 3 has been extensively studied to better understand natural processes of biomineralization, to develop bioinspired approaches for synthesizing composite materials with diverse functionalities, and as a route toward accelerating CO 2 mineralization. Peptoids have emerged as a material of particular interest, because they offer tunable side chain chemistry while maintaining a constant long-range self-assembled architecture. Here, in this work, we investigate the ability of films of self-assembled -NH 2 and −COOH terminated peptoid nanotubes to promote the nucleation of CaCO 3 . Using a combination of atomic force, scanning electron, and optical microscopy, we find that interwoven films of nanotubes formed from peptoids with -NH 2 side chains promote the preferential formation of vaterite with the (001) plane parallel to the film and exhibit a lower interfacial energy than that reported for inorganic surfaces. In contrast, the film of −COOH-functionalized peptoid nanotubes is a much stronger promoter, giving a particle density 5 orders of magnitude larger than for the -NH 2 terminated peptoid nanotubes and enabling complete coverage of individual peptoid tubes with CaCO 3 nanoparticles that results in a composite material with a 50-fold increase in Young’s modulus. Thus, interwoven films of peptoid nanotubes provide a useful platform for investigating the impact of specific chemical groups on nucleation and offer potential application to accelerated mineralization of CO 2 for removal from the environment or modulation of mineralogy and properties of carbonate-based building materials.

carbon nanotubes↗
DOE OSTI2023

Hard–Soft Core–Shell Architecture Formation from Cubic Cobalt Ferrite Nanoparticles

Cubic bi-magnetic hard–soft core–shell nanoarchitectures were prepared starting from cobalt ferrite nanoparticles, prevalently with cubic shape, as seeds to grow a manganese ferrite shell. The combined use of direct (nanoscale chemical mapping via STEM-EDX) and indirect (DC magnetometry) tools was adopted to verify the formation of the heterostructures at the nanoscale and bulk level, respectively. The results showed the obtainment of core–shell NPs (CoFe 2 O 4 @MnFe 2 O 4 ) with a thin shell (heterogenous nucleation). In addition, manganese ferrite was found to homogeneously nucleate to form a secondary nanoparticle population (homogenous nucleation). This study shed light on the competitive formation mechanism of homogenous and heterogenous nucleation, suggesting the existence of a critical size, beyond which, phase separation occurs and seeds are no longer available in the reaction medium for heterogenous nucleation. These findings may allow one to tailor the synthesis process in order to achieve better control of the materials’ features affecting the magnetic behaviour, and consequently, the performances as heat mediators or components for data storage devices.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Dimensionality effect of conductive carbon fillers in LiNi 1/3 Mn 1/3 Co 1/3 O 2 cathode

Developing advanced electrode architectures through modifying active materials, conductive fillers, binders, and electrolytes as well as processing methods has drawn significant research interest. Due to the insufficient electrical conductivity of many active materials, adding conductive carbon fillers to composite electrodes provides the necessary electrical conductivity. The dimensionality effect among different conductive fillers has a significant impact on electrochemistry, which can be associated with morphological and chemical heterogeneities of electrodes. In this study, synchrotron X-ray mosaic nanotomography and X-ray spectroscopy nanoimaging provided direct three-dimensional (3D) visualization and quantification capabilities to investigate the dimensionality effects of Super P (SP) and single-walled carbon nanotube (SWCNT) fillers on the capacity retention of LiNi 1/3 Mn 1/3 Co 1/3 O 2 (NMC111). The results indicate that NMC/SWCNT electrodes, with a wrapping effect from the SWCNTs, exhibited more homogeneous particle size distributions, morphological changes, and chemical states than NMC/SP electrodes, without the wrapping effect. This work developed a framework of 3D quantification methods to study the capacity fading behavior associated with morphological and chemical heterogeneities and paved the way toward designing electrodes for high rate energy storage applications.

25 ENERGY STORAGE↗
DOE OSTI2024

Griffin: A MOOSE-based reactor physics application for multiphysics simulation of advanced nuclear reactors

Griffin is a Multiphysics Object-Oriented Simulation Environment (MOOSE) based reactor physics application for multiphysics simulations of advanced reactor designs jointly developed by Idaho National Laboratory and Argonne National Laboratory. This paper summarizes the motivation, significance, architecture, design, and features of Griffin. Griffin offers flexible and extensible features to address the challenges associated with advanced reactor designs. These features range from fundamental particle transport to specific reactor physics tasks. The features cover a wide range including on-the-fly and traditional two-step cross-section generation methods, steady-state and transient transport solvers suitable for both heterogeneous and homogeneous models, high-fidelity depletion where thousands of isotopes can be tracked and low-fidelity depletion characterized by burnup, etc. The most fundamental aspect that sets Griffin apart from other reactor analysis codes is that it is developed based on the MOOSE framework. A modular development approach is strongly enforced, with multiphysics being an essential element considered since the beginning of Griffin’s development. Griffin links various MOOSE physics modules and couples to other MOOSE-based applications and non-MOOSE-based applications for multiphyiscs simulations. Griffin includes three modules: ISOXML for preparing and managing multigroup cross sections, radiation transport for solving the neutron transport equation, and reactor analysis for user-oriented reactor physics analysis functionalities. Griffin uses various finite element methods for spatial discretization, multigroup approximation for energy discretization and discrete ordinates method, spherical harmonics expansion method, and diffusion approximation for streaming direction discretization to solve the neutron transport equation. Griffin’s flexibility is evidenced through Griffin’s various applications to fast reactor, high-temperature reactor, pebble bed reactor, molten salt reactor, and microreactor designs. Griffin development follows the software quality assurance procedure for MOOSE-based applications and with software requirements consistent with the ASME NQA-1 standard. Griffin has been adopted into the reactor analysis system for the U.S. NRC and is in use at U.S. companies, universities and national laboratories.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

HIPLZ: Enabling performance portability for exascale systems

While heterogeneous computing has emerged as a dominant trend in current and future High-Performance Computing (HPC) systems, it is also widely recognized that this shift has led to increased software complexity due to a proliferation of programming systems for different heterogeneous processors. One such example is the Heterogeneous-Compute Interface for Portability from AMD (HIP ), which is composed of a C Runtime API and C++ Kernel Language. Many HPC applications will likely use HIP on future exascale systems (e.g., Frontier and El Capitan), but HIP currently only targets AMD and NVIDIA processors. This limitation creates challenges for users who would also like to run their applications on exascale systems based on other architectures (e.g., Aurora, which is based on Intel hardware) that are currently not targeted by HIP . In this paper, we introduce the design and implementation of HIPLZ , a compiler and runtime system that uses the Intel Level Zero API to support HIP on Intel GPU architectures. We discuss the design of HIPLZ , derived from HIPCL (an implementation of HIP on top of OpenCL ), and portability issues that occur from using the Level Zero runtime as a backend. We evaluate our implementation by running several performance benchmarks and mini-apps written in HIP on Intel architectures using HIPLZ . Our results show that this approach provides competitive performance relative to Intel's OpenCL implementations on Intel Gen9 and UHD Graphics 770 GPUs, while providing good coverage of features needed by HPC applications. Overall, this approach is a promising demonstration of enabling performance portability for exascale systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Designing resilient IoT and Edge Computing with federated tinyML

The rapid growth of the Internet of Things (IoT) and Edge Computing (EC) has brought significant conveniences to modern society but has also greatly expanded the cyber attack surfaces, particularly as these technologies are being increasingly integrated into critical systems such as power grids, healthcare, and smart homes. Here, to improve IoT/EC’s cybersecurity posture, we leveraged Artificial Intelligence (AI) and Machine Learning (ML) by employing tinyML to monitor voluminous IoT data for cyber threats while addressing devices’ resource constraints, and utilizing Federated Learning (FL) to share local detection knowledge across the system while preserving privacy. Building on our three-layer architecture combining tinyML and FL to enhance autonomous cyber attack detection, this paper demonstrated that the architecture improves detection accuracy, reduces resource consumption, and enables lightweight, secure IoT device monitoring. These results were validated using the public N-BaIoT dataset as well as real IoT network traffic data collected under multiple attack scenarios from our testbeds. Additionally, we introduced an enhanced FL methodology with a novel preprocessing stage, including federated feature selection and global preprocessor construction, to address IoT/EC data heterogeneity. We developed a physical IoT testbed for attack simulations and data collection, implemented a tinyML-powered detector for realistic model validation, and also built a virtual testbed for scalable evaluations of FL models across diverse network environments.

Cognitive cyber↗
DOE OSTI2024

Magnetic resonance insights into the heterogeneous, fractal-like kinetics of chemically recyclable polymers

Moving toward a circular plastics economy is a vital aspect of global resource management. Chemical recycling of plastics ensures that high-value monomers can be recovered from depolymerized plastic waste, thus enabling circular manufacturing. However, to increase chemical recycling throughput in materials recovery facilities, the present understanding of polymer transport, diffusion, swelling, and heterogeneous deconstruction kinetics must be systematized to allow industrial-scale process design, spanning molecular to macroscopic regimes. To develop a framework for designing depolymerization processes, we examined acidolysis of circular polydiketoenamine elastomers. We used magnetic resonance to monitor spatially resolved observables in situ and then evaluated these data with a fractal method that treats nonlinear depolymerization kinetics. This approach delineated the roles played by network architecture and reaction medium on depolymerization outcomes, yielding parameters that facilitate comparisons between bulk processes. These streamlined methods to investigate polymer hydrolysis kinetics portend a general strategy for implementing chemical recycling on an industrial scale.

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

Molecular Design Principles for Photosystem I-Based Biohybrid Solar Fuel Catalysts

Direct solar-to-chemical conversion offers a compelling route to clean, dispatchable energy. Photosystem I (PSI), an evolutionarily optimized light-driven oxidoreductase, can be repurposed for solar-fuel production by coupling its photochemistry to catalytic interfaces. However, the molecular determinants that govern productive electron transfer to abiotic catalysts remain poorly understood. Here, we present molecular structures of active PSI-Pt nanoparticle (PtNP) biohybrids that reveal how protein architecture controls catalyst access, binding geometry, and photocatalytic efficiency. Removal of stromal subunits exposes the electron transfer chain and enables PtNP binding proximal to the F X cluster, demonstrating that steric occlusion limits access to native acceptor regions in PSI. In contrast, in trimeric PSI, PtNPs bind at multiple sites per monomer, but only a subset are positioned within electron transfer distance of terminal cofactors, resulting in a heterogeneous population of productive and nonproductive configurations. Structural analyses and molecular dynamics simulations define the interface topology, electrostatics, and cofactor-to-nanoparticle distances that govern catalyst binding and electron transfer. These results establish that catalytic inefficiency arises not only from intrinsic electron transfer constraints but also from the distribution of binding geometries imposed by the protein scaffold. Together, these findings provide a molecular framework linking protein structure to biohybrid function and define design principles for engineering PSI-based solar fuel systems and protein-nanomaterial interfaces for light-driven catalysis.

biohybrid↗
DOE OSTI2022

Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml

In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Efficient solutions of fermionic systems using artificial neural networks

In this study, we explore the similarities and differences between variational Monte Carlo techniques that employ conventional and artificial neural network representations of the ground-state wave function for fermionic systems. Our primary focus is on shallow neural network architectures, specifically the restricted Boltzmann machine, and we examine unsupervised learning algorithms that are appropriate for modeling complex many-body correlations. We assess the advantages and drawbacks of conventional and neural network wave functions by applying them to a range of circular quantum dot systems. Our findings, which include results for systems containing up to 90 electrons, emphasize the efficient implementation of these methods on both homogeneous and heterogeneous high-performance computing facilities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits

In the span of four decades, quantum computation has evolved from an intellectual curiosity to a potentially realizable technology. Today, small-scale demonstrations have become possible for quantum algorithmic primitives on hundreds of physical qubits and proof-of-principle error-correction on a single logical qubit. Nevertheless, despite significant progress and excitement, the path toward a full-stack scalable technology is largely unknown. There are significant outstanding quantum hardware, fabrication, software architecture, and algorithmic challenges that are either unresolved or overlooked. These issues could seriously undermine the arrival of utility-scale quantum computers for the foreseeable future. Here, we provide a comprehensive review of these scaling challenges. We show how the road to scaling could be paved by adopting existing semiconductor technology to build much higher-quality qubits, employing system engineering approaches, and performing distributed quantum computation within heterogeneous high-performance computing infrastructures. These opportunities for research and development could unlock certain promising applications, in particular, efficient quantum simulation/learning of quantum data generated by natural or engineered quantum systems. To estimate the true cost of such promises, we provide a detailed resource and sensitivity analysis for classically hard quantum chemistry calculations on surface-code error-corrected quantum computers given current, target, and desired hardware specifications based on superconducting qubits, accounting for a realistic distribution of errors. Furthermore, we argue that, to tackle industry-scale classical optimization and machine learning problems in a cost-effective manner, heterogeneous quantum-probabilistic computing with custom-designed accelerators should be considered as a complementary path toward scalability.

Mohseni, Masoud↗
DOE OSTI2026

Evaluating Application Characteristics for GPU Portability Layer Selection

GPUs have become the dominant source of computing power for high performance computing and are increasingly being used across the High Energy Physics computing landscape for a wide variety of tasks. Though NVIDIA is currently the main provider of GPUs, AMD and Intel are rapidly increasing their market share. As a result, programming using a vendor-specific language such as CUDA can significantly reduce deployment choices. There are a number of portability layers such as Kokkos, Alpaka, SYCL, OpenMP and std::par that permit execution on a broad range of GPU and CPU architectures, significantly increasing the flexibility of application programmers. However, each of these portability layers has its own characteristics, performing better at some tasks and worse at others, or placing limitations on aspects of the application. In this presentation, we report on a study of application and kernel characteristics that can influence the choice of a portability layer and show how each layer handles these characteristics. We have analyzed representative heterogeneous applications from CMS (patatrack and p2r), DUNE (Wire-Cell Toolkit), and ATLAS (FastCaloSim) to identify key application characteristics that have different behaviors for the various portability technologies. Using these results, developers can make more informed decisions on which GPU portability technology is best suited to their application.

Atif, Mohammad [Brookhaven]↗