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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Orchestration of materials science workflows for heterogeneous resources at large scale

In the era of big data, materials science workflows need to handle large-scale data distribution, storage, and computation. Any of these areas can become a performance bottleneck. We present a framework for analyzing internal material structures (e.g., cracks) to mitigate these bottlenecks. We demonstrate the effectiveness of our framework for a workflow performing synchrotron X-ray computed tomography reconstruction and segmentation of a silica-based structure. Our framework provides a cloud-based, cutting-edge solution to challenges such as growing intermediate and output data and heavy resource demands during image reconstruction and segmentation. Specifically, our framework efficiently manages data storage, scaling up compute resources on the cloud. The multi-layer software structure of our framework includes three layers. A top layer uses Jupyter notebooks and serves as the user interface. A middle layer uses Ansible for resource deployment and managing the execution environment. A low layer is dedicated to resource management and provides resource management and job scheduling on heterogeneous nodes (i.e., GPU and CPU). At the core of this layer, Kubernetes supports resource management, and Dask enables large-scale job scheduling for heterogeneous resources. The broader impact of our work is four-fold: through our framework, we hide the complexity of the cloud’s software stack to the user who otherwise is required to have expertise in cloud technologies; we manage job scheduling efficiently and in a scalable manner; we enable resource elasticity and workflow orchestration at a large scale; and we facilitate moving the study of nonporous structures, which has wide applications in engineering and scientific fields, to the cloud. While we demonstrate the capability of our framework for a specific materials science application, it can be adapted for other applications and domains because of its modular, multi-layer architecture.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A Performance-Portable MultiGPU Implementation of 3D Euler Equations using ProtoX and IRIS

Computational scientists often face challenges when developing and optimizing code for high-performance computing (HPC), especially when trying to leverage GPUs. Given the heterogeneity of the nodes that comprise many modern HPC facilities, considerable demand exists for performance portable solutions for the core computational kernels used in many scientific computing libraries. In this work, we demonstrate a fourth-order finite volume method–based implementation of the Euler equations, which are an integral part of computational fluid dynamics. Our performance-portable multiGPU implementation for Euler equations uses ProtoX to generate kernels and IRIS for portability. ProtoX is a domain-specific language that uses a structured-grid partial differential equation library called Proto as its front end and the SPIRAL code generation system as its back end to generate optimized kernels for different architectures. Optimized kernels generated by ProtoX are orchestrated through the IRIS intelligent runtime system to provide portability. Two levels of optimizations within the IRIS runtime— directed acyclic graph fusion and task fusion—are explored to efficiently utilize computing resources in a multiGPU environment. Performance improvement through these optimizations is showcased by comparing the base ProtoX-IRIS implementation on AMD GPUs (Frontier node) and on NVIDIA GPUs (NVIDIA DGX-1).

Mankad, Het↗
DOE OSTI2023

Effect of Electrode/Electrolyte Coupling on Birnessite (δ-MnO 2 ) Mechanical Response and Degradation

Understanding the deformation of energy storage electrodes at a local scale and its correlation to electrochemical performance is crucial for designing effective electrode architectures. In this work, the effect of electrolyte cation and electrode morphology on birnessite (δ-MnO 2 ) deformation during charge storage in aqueous electrolytes was investigated using a mechanical cyclic voltammetry approach via operando atomic force microscopy (AFM) and molecular dynamics (MD) simulation. In both K 2 SO 4 and Li 2 SO 4 electrolytes, the δ-MnO 2 host electrode underwent expansion during cation intercalation, but with different potential dependencies. When intercalating Li + , the δ-MnO 2 electrode presents a nonlinear correlation between electrode deformation and electrode height, which is morphologically dependent. Further, these results suggest that the stronger cation–birnessite interaction is the reason for higher local stress heterogeneity when cycling in Li 2 SO 4 electrolyte, which might be the origin of the pronounced electrode degradation in this electrolyte.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Surface vs Homogeneous Organo-Hafnium Catalyst Ion-Pairing and Ligand Effects on Ethylene Homo- and Copolymerizations

Heterogeneous catalysts have long dominated polyethylene and polypropylene production, but understanding their catalysis is challenged by uncertainties in active site structures and percentages. Surface-bound organometallic catalysts are an emerging strategy to combine successful homogeneous catalysts having well-understood structures, relatively high percentages of active sites, and exceptional control of selectivity, with the attractions of surface catalysts, to transition promising homogeneous systems to large-scale heterogeneous ones. Nevertheless, surface-bound olefin polymerization catalysts typically produce ultrahigh M w ’s but with low activity and comonomer selectivity. Here, we report the systematic synthesis and characterization of a series of pyridylamido–Hf complexes and their corresponding surface catalysts chemisorbed on sulfated alumina (AlS) and zirconia (ZrS). Comparative ethylene homo- and 1-octene copolymerizations reveal similar activity and 1-octene selectivity trends in the homogeneous and heterogeneous systems. For the surface pyridylamido–Hf catalyst series, large variations in activity (up to 10×) and 1-octene incorporation (up to 28×) are achieved by ligand and support manipulation. Interestingly, while the homogeneous catalysts exhibit positive comonomer effects in ethylene/1-octene copolymerization, the surface catalysts behave oppositely. Extended X-ray absorption fine structure (EXAFS) reveals significantly elongated Hf···O bond distances vs typical Hf–O covalent bonds (2.06 vs 1.97 Å). Furthermore, density functional theory (DFT) analysis of the heterolytic ion pair separation enthalpies, olefin insertion energetics, and NBO/Bader charges also suggest electrostatic Hf cation–anionic support binding and catalytic patterns, which are modulated by the ion-pairing energetics and ligand architecture.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Modeling Analog Tile-Based Accelerators Using SST

Analog computing has been widely proposed to improve the energy efficiency of multiple important workloads including neural network operations, and other linear algebra kernels. To properly evaluate analog computing and explore more complex workloads such as systems consisting of multiple analog data paths, system level simulations are required. Moreover, prior work on system architectures for analog computing often rely on custom simulators creating signficant additional design effort and complicating comparisons between different systems. To remedy these issues, this report describes the design and implementation of a flexible tile-based analog accelerator element for the Structural Simulation Toolkit (SST). The element focuses on heavily on the tile controller—an often neglected aspect of prior work—that is sufficiently versatile to simulate a wide range of different tile operations including neural network layers, signal processing kernels, and generic linear algebra operations without major constraints. The tile model also interoperates with existing SST memory and network models to reduce the overall development load and enable future simulation of heterogeneous systems with both conventional digital logic and analog compute tiles. Finally, both the tile and array models are designed to easily support future extensions as new analog operations and applications that can benefit from analog computing are developed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Combustion-assisted ink-jet printing of nuclear targets

Advances in target fabrication are critical to high-precision measurements in nuclear physics. This work details the preparation of patterned CeO 2 and ThO 2 architectures and thin-film targets via ink-jet deposition of combustible solutions. The produced targets were characterized by scanning electron microscopy (SEM), and by alpha-particle spectroscopy for radioactive targets to determine densities. Ink jet printing of the targets, used both ethanol and 2-methoxyethanol as solvents, with cerium or thorium nitrate as the oxidizer and acetylacetone as the fuel. Additionally, we found that the distance between each droplet dispersion (step size) played the most significant role in determining the final pattern uniformity and thickness. A 50 μm step size leads to relatively thick targets with a density of 350 μg/cm 2 . Significant overlap in droplet sizes leads to a heterogeneous target with an undesirable cracked surface structure. In contrast, 150 μm spacing yields thinner (20 μg/cm 2 ) patterned structures with excellent surface coverage. This method of Ink-jet printing provides a straightforward, scalable, and high-efficiency pathway to prepare custom made, high-quality targets for nuclear physics experiments.

CeO2↗
DOE OSTI2020

Supported Oxygen Evolution Catalysts by Design: Toward Lower Precious Metal Loading and Improved Conductivity in Proton Exchange Membrane Water Electrolyzers

Reducing the precious metal content of water oxidation catalysts for proton-exchange-membrane water electrolyzers remains a critical barrier to their large-scale deployment. Herein, we present an engineered architecture for supported iridium catalysts, which enables decreased precious metal content and improved activity and conductivity. The improvement in performance at lower precious metal loading is realized by the deposition of a conformal layer of platinum nanoparticles on titanium dioxide (TiO 2 ) using a facile photoreduction method to prepare conductive layer coated supports (CCSs). Platinum nanoparticles are homogeneously dispersed on TiO 2 , and the conductivity of the subsequent catalysts with 39 wt % precious group metal loadings is significantly higher than the commercial 75 wt % loaded IrO 2 -TiO 2 catalysts. The conformal conductive layer also maintains an enhanced conductivity and electrochemical activity upon thermal annealing when compared to catalysts without the conductive layer and nonconformal heterogeneous conductive layer. The iridium mass activity from half-cell studies shows a 141% improvement for CCS supported catalysts at 42% lower loadings compared to the commercial catalysts. The conductive layer also improves the single cell electrolyzer performance at a similar catalyst loading in comparison to a commercial state-of-the-art catalyst. Here, we correlate the physical properties of the engineered catalysts with their electrochemical performance in electrolyzers to understand structure-activity relationships, and we anticipate further performance improvements upon synthesis and materials optimizations.

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

OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC

Federated Learning (FL) is critical for edge and High Performance Computing (HPC) where data is not centralized and privacy is crucial. We present OmniFed, a modular framework designed around decoupling and clear separation of concerns for configuration, orchestration, communication, and training logic. Its architecture supports configuration-driven prototyping and code-level override-what-you-need customization. We also support different topologies, mixed communication protocols within a single deployment, and popular training algorithms. It also offers optional privacy mechanisms including Differential Privacy (DP), Homomorphic Encryption (HE), and Secure Aggregation (SA), as well as compression strategies. These capabilities are exposed through well-defined extension points, allowing users to customize topology and orchestration, learning logic, and privacy/compression plugins, all while preserving the integrity of the core system. We evaluate multiple models and algorithms to measure various performance metrics. By unifying topology configuration, mixed-protocol communication, and pluggable modules in one stack, OmniFed streamlines FL deployment across heterogeneous environments. Github repository is available at https://github.com/at-aaims/OmniFed.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)↗
DOE OSTI2020

Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows

Reduced rank nonlinear filters are increasingly utilized in data assimilation of geophysical flows, but often require a set of ensemble forward simulations to estimate forecast covariance. On the other hand, predictor-corrector type nudging approaches are still attractive due to their simplicity of implementation when more complex methods need to be avoided. However, optimal estimate of nudging gain matrix might be cumbersome. In this paper, we put forth a fully nonintrusive recurrent neural network approach based on a long short-term memory (LSTM) embedding architecture to estimate the nudging term, which plays a role not only to force the state trajectories to the observations but also acts as a stabilizer. Furthermore, our approach relies on the power of archival data and the trained model can be retrained effectively due to power of transfer learning in any neural network applications. In order to verify the feasibility of the proposed approach, we perform twin experiments using Lorenz 96 system. Our results demonstrate that the proposed LSTM nudging approach yields more accurate estimates than both extended Kalman filter (EKF) and ensemble Kalman filter (EnKF) when only sparse observations are available. With the availability of emerging AI-friendly and modular hardware technologies and heterogeneous computing platforms, we articulate that our simplistic nudging framework turns out to be computationally more efficient than either the EKF or EnKF approaches.

42 ENGINEERING↗
DOE OSTI2025

Capturing Historic Reliability Performance Through Graph Databases: A Model Based System Engineering Approach

With the goal of improving the performance and reliability of high dependable technological systems such as nuclear power plants, advanced monitoring and health management systems are employed to inform system engineers on observed degradation processes and anomalous behaviors of assets and components. This information is captured in the form of large amount of data which can be heterogenous in nature (e.g., numeric, textual). Such large data availability poses challenges when system engineers are required to parse and analyze them in order to track historic reliability performance of assets and components. This paper tackles directly this challenge by providing means to organize data in the form of a graph: a knowledge graph. The presented approach distinguish itself from current knowledge graph-based methods by the fact that model-based system engineering (MBSE) models are used to “put data into context”. In particular, MBSE models are used as skeleton of a knowledge graph; numeric and textual data elements, once processed, are associated to MBSE model elements. Thus, a knowledge graph captures both system architecture (though MBSE models) and health/performance data. Such feature opens the door to new data analytics methods designed to identify causal relations between observed phenomena.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Understanding the Performance Gap between Polycrystalline and Single-Crystal Nickel-Rich Layered Oxide Cathodes

Singe-crystal (SC) nickel-rich layered oxide cathodes, composed of boundary-free particles with high tap density, offer significant advantages in volumetric energy density and mechanical strength compared with polycrystalline (PC) cathode materials. However, as the nickel content increases (≥80%), SC Ni-rich cathodes often suffer from faster performance degradation than PC cathodes of the same composition, and the underlying causes of this discrepancy remain poorly understood. Herein, we reveal the distinct Ni redox behaviors that govern the electrochemical performance of SC and PC Ni-rich cathodes using multiscale and operando characterization techniques. Our results indicate that the increasingly heterogeneous Ni oxidation process in SC cathodes leads to the additional irreversible oxygen redox activity that deteriorates both the mechanical and chemical structures. In contrast, PC cathodes, despite with more pronounced surface reconstruction, exhibit greater chemomechanical stability due to homogeneous redox reactions during charging. Consequently, we find that bulk degradation, more than surface reactions, ultimately leads to fast capacity decay of SC Ni-rich cathodes during cycling. In conclusion, this work offers a comprehensive view on the impact of Ni redox evolutions on the chemomechanical stability in Ni-rich layered oxide cathodes, providing new insights into the longstanding performance gap between SC and PC cathodes, and guiding the rational design of Ni-rich cathode architectures.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Synchronization in electric power networks with inherent heterogeneity up to 100% inverter-based renewable generation

The synchronized operation of power generators is the foundation of electric power network stability and a key to the prevention of undesired power outages and blackouts. Here, we derive the conditions that guarantee synchronization in power networks with inherent generator heterogeneity when subjected to small perturbations, and perform a parametric sensitivity analysis to understand synchronization with varied types of generators. As inverter-based resources, which are the primary interfacing technology for many renewable sources of energy, have supplanted synchronous generators in ever growing numbers, the center of attention on associated integration challenges have resided primarily on the role of declining system inertia. Our results instead highlight the critical role of generator damping in achieving a stable state of synchronization. Additionally, we report the feasibility of operating interconnected electric grids with up to 100% power contribution from inverter-based renewable generation technologies. Our study has important implications as it sets the basis for the development of advanced control architectures and grid optimization methods that ensure synchronization and further pave the path towards the decarbonization of the electric power sector.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Potential-induced wetting and dewetting in pH-responsive block copolymer membranes for mass transport control

Wetting and dewetting behavior in channel-confined hydrophobic volumes is used in biological membranes to effect selective ion/molecular transport. Artificial biomimetic hydrophobic nanopores have been devised utilizing wetting and dewetting, however, tunable mass transport control utilizing multiple transport modes is required for applications such as controllable release/transport, water separation/purification and energy conversion. Here, we investigate the potential-induced wetting and dewetting behavior in a pH-responsive membrane composed of a polystyrene-b-poly(4-vinylpyridine) (PS-b-P4VP) block copolymer (BCP) when fabricated as a hierarchically-organized sandwich structure on a nanopore electrode array (NEA), i.e. BCP@NEA. At pH < pK a (P4VP) (pK a ~ 4.8), the BCP acts as an anion-exchange membrane due to the hydrophilic, protonated P4VP cylindrical nanodomains, but at pH > pK a (P4VP), the P4VP domains exhibit charge-neutral, hydrophobic and collapsed structures, blocking mass transport via the hydrophobic membrane. However, when originally prepared in a dewetted condition, mass transport in the BCP membrane may be switched on if sufficiently negative potentials are applied to the BCP@NEA architecture. When the hydrophobic BCP membrane is introduced on top of 2-electrode-embedded nanopore arrays, electrolyte solution in the nanopores is introduced, then isolated, by exploiting the potential-induced wetting and dewetting transitions in the BCP membrane. The potential-induced wetting/dewetting transition and the effect on cyclic voltammetry in the BCP@NEA structures is characterized as a function of the potential, pH and ionic strength. Additionally chronoamperometry and redox cycling experiments are used to further characterize the potential response. The multi-modal mass transport system proposed in this work will be useful for ultrasensitive sensing and single-molecule studies, which require long-time monitoring to explore reaction dynamics as well as molecular heterogeneity in nanoconfined volumes.

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

TAMM: Tensor algebra for many-body methods

Tensor algebra operations such as contractions in computational chemistry consume a significant fraction of the computing time on large-scale computing platforms. The widespread use of tensor contractions between large multi-dimensional tensors in describing electronic structure theory has motivated the development of multiple tensor algebra frameworks targeting heterogeneous computing platforms. In this paper, we present Tensor Algebra for Many-body Methods (TAMM), a framework for productive and performance-portable development of scalable computational chemistry methods. TAMM decouples the specification of the computation from the execution of these operations on available high-performance computing systems. With this design choice, the scientific application developers (domain scientists) can focus on the algorithmic requirements using the tensor algebra interface provided by TAMM, whereas high-performance computing developers can direct their attention to various optimizations on the underlying constructs, such as efficient data distribution, optimized scheduling algorithms, and efficient use of intra-node resources (e.g., graphics processing units). The modular structure of TAMM allows it to support different hardware architectures and incorporate new algorithmic advances. We describe the TAMM framework and our approach to the sustainable development of scalable ground- and excited-state electronic structure methods. We present case studies highlighting the ease of use, including the performance and productivity gains compared to other frameworks.

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

Studying CPU and memory utilization of applications on Fujitsu A64FX and Nvidia Grace Superchip

ARM-based manycore CPU architectures are well-positioned to provide the rising memory throughput requirements of modern data intensive scientific applications in High Performance Computing (HPC). The Fujitsu A64FX CPU platform is based on the ARM v8.2A architecture, and is the processor of the flagship Japanese supercomputer - "Fugaku", which was previously ranked as the #1 supercomputer in the world according to the Top500 list. The Nvidia Grace superchip features 144 Neoverse V2 cores based on the ARMv9 architecture with 4x128b SVE2, providing exceptional computational power. The chip supports up to 480GB of memory, making it ideal for AI, machine learning, and scientific computing workloads. In this paper, we conduct a thorough performance exploration of a variety of parallel bandwidth-sensitive benchmarks and applications compiled with the native Fujitsu compiler on a Fugaku A64FX compute node and ARM (LLVM) Compiler on an NVIDIA Grace superchip compute node, engaging all the computational cores per cluster using OpenMP multithreading (assuming the cores can drive the available bandwidth). Our ultimate goals are to study the resource utilization of scientific applications and benchmarks on A64FX and Grace superchip, considering graph application scenarios ( GAP Benchmark suite) and eleven appli- cation proxies from the Rodinia heterogeneous benchmark suite (considering domains such as Data Mining, Bioinformatics, Fluid Dynamics, Pattern Recognition, etc.). Through exhaustive performance monitoring, we quantify the resource utilization of diverse OpenMP-based HPC applications on both the Fujitsu A64FX and the Nvidia Grace Superchip platforms.

benchmarking, Performance Analysis, High performan↗
DOE OSTI2026

Imaging from Macro to Nanoscale: Multimodal Advances in Chemical and Biomedical Imaging

Imaging increasingly serves as a multiscale framework for linking molecular mechanisms to cellular behavior, tissue architecture, and organ phenotypes in biology and unraveling fundamental processes in chemistry, physics and materials science. This Perspective highlights recent advances in chemical and biomedical imaging across macro-, micro-, and nanoscales, using representative examples published in Chemical and Biomedical Imaging (CBMI). At the macroscale, we discuss chemically selective MRI, including endogenous and exogenous CEST strategies, together with photoacoustic imaging as a hybrid modality with functional and chemical contrast. At the microscale, we consider fluorescence, label-free optical and vibrational imaging, and selected X-ray approaches that expand sensitivity, specificity, and temporal resolution in biological and materials systems. At the nanoscale, we highlight super-resolution fluorescence microscopy, single-molecule methods, tip-enhanced Raman spectroscopy, and correlative imaging strategies that resolve local heterogeneity and molecular organization. Across scales, a common theme emerges that advances in probes, contrast mechanisms, instrumentation, and sample handling are enabling chemically informed imaging that connects molecular specificity with biological context.

multiscale imaging↗
DOE OSTI2021

Performance Portability of Molecular Docking Miniapp On Leadership Computing Platforms

Rapidly changing computer architectures, such as those found at high-performance computing (HPC) facilities, present the need for mini-applications (miniapps) that capture essential algorithms used in large applications to test program performance and portability, aiding transitions to new systems. The COVID-19 pandemic has fueled a flurry of activity in computational drug discovery, including the use of supercomputers and GPU acceleration for massive virtual screens for therapeutics. Recent work targeting COVID-19 at the Oak Ridge Leadership Computing Facility (OLCF) used the GPU-accelerated program AutoDock-GPU to screen billions of compounds on the Summit supercomputer. In this paper we present the development of a new miniapp, miniAutoDock-GPU, that can be used to evaluate the performance and portability of GPU-accelerated protein-ligand docking programs on different computer architectures. These tests are especially relevant as facilities transition from petascale systems and prepare for upcoming exascale systems that will use a variety of GPU vendors. The key calculations, namely, the Lamarckian genetic algorithm combined with a local search using a Solis-Wets based random optimization algorithm, are implemented. We developed versions of the miniapp using several different programming models for GPU acceleration, including a version using the CUDA runtime API for NVIDIA GPUs, and the Kokkos middle-ware API which is facilitated by C++ template libraries. A third version, currently in progress, uses the HIP programming model. These efforts will help facilitate the transition to exascale systems for this important emerging HPC application, as well as its use on a wide range of heterogeneous platforms.

Thavappiragasam, Mathialakan↗
DOE OSTI2025

AI Benchmark Democratization and Carpentry

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model architectures, scale, datasets, and deployment contexts makes evaluation a moving target. Large language models often memorize static benchmarks, causing a gap between benchmark results and real-world performance. Beyond traditional static benchmarks, continuous adaptive benchmarking frameworks are needed to align scientific assessment with deployment risks. This calls for skills and education in AI Benchmark Carpentry. From our experience with MLCommons, educational initiatives, and programs like the DOE's Trillion Parameter Consortium, key barriers include high resource demands, limited access to specialized hardware, lack of benchmark design expertise, and uncertainty in relating results to application domains. Current benchmarks often emphasize peak performance on top-tier hardware, offering limited guidance for diverse, real-world scenarios. Benchmarking must become dynamic, incorporating evolving models, updated data, and heterogeneous platforms while maintaining transparency, reproducibility, and interpretability. Democratization requires both technical innovation and systematic education across levels, building sustained expertise in benchmark design and use. Benchmarks should support application-relevant comparisons, enabling informed, context-sensitive decisions. Dynamic, inclusive benchmarking will ensure evaluation keeps pace with AI evolution and supports responsible, reproducible, and accessible AI deployment. Community efforts can provide a foundation for AI Benchmark Carpentry.

von Laszewski, Gregor [Virginia U.]↗