Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scalable performance”

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 667 records · Page 37
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Optimizing the hypre solver for manycore and GPU architectures

The solution of large-scale combustion problems with codes such as Uintah on modern computer architectures requires the use of multithreading and GPUs to achieve performance. Uintah uses a low-Mach number approximation that requires iteratively solving a large system of linear equations. The Hypre iterative solver has solved such systems in a scalable way for Uintah, but the use of OpenMP with Hypre leads to at least slowdown due to OpenMP overheads. The proposed solution uses the MPI Endpoints within Hypre, where each team of threads acts as a different MPI rank. This approach minimizes OpenMP synchronization overhead and performs as fast or (up to 1.44) faster than Hypre's MPI-only version, and allows the rest of Uintah to be optimized using OpenMP. The profiling of the GPU version of Hypre shows the bottleneck to be the launch overhead of thousands of micro-kernels. The GPU performance was improved by fusing these micro-kernels and was further optimized by using Cuda-aware MPI, resulting in an overall speedup of 1.16—1.44 compared to the baseline GPU implementation. The above optimization strategies were published in the International Conference on Computational Science 2020 [1]. This work extends the previously published research by carrying out the second phase of communication-centered optimizations in Hypre to improve its scalability on large-scale supercomputers. Additionally, this includes an efficient non-blocking inter-thread communication scheme, communication-reducing patch assignment, and expression of logical communication parallelism to a new version of the MPICH library that utilizes the underlying network parallelism [2]. The above optimizations avoid communication bottlenecks previously observed during strong scaling and improve performance by up to 2 on 256 nodes of Intel Knight's Landing processor.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A Recipe for a Great Meal: A Benchtop Route from Elemental Se to Superior Thermoelectric β-Ag 2 Se

The low-temperature modification of β-Ag 2 Se has proven to be useful as a near-room-temperature thermoelectric material. Over the past years, research has been devoted to interstitial, vacancy, and substitutional doping into the parent β-Ag 2 Se structure, aiming at tuning the material’s charge and heat transport properties to enhance thermoelectric performance. The transformation of β-Ag 2 Se into α-Ag 2 Se at ~134 °C and the low solubility of dopants are the main obstacles for the doping approach. Herein, we report a facile, safe, scalable, and cost-effective benchtop approach to successfully produce metal-doped β-Ag 2 Se. The doped materials display a remarkable enhancement of thermoelectric performance with a record-high peak zT of 1.30 at 120 °C and an average zT of ~1.15 in the 25–120 °C range for 0.2 at. % Zn-doped Ag 2 Se. The enhancement in zT is attributed to point defects created by Zn doping into Ag vacancies/interstitials, which enhances the scattering of phonons and tunes the charge carrier properties, leading to the significant suppression of thermal conductivity. In conclusion, the simplicity of the synthetic method developed herein and the high performance of the final products provide an avenue to produce high-quality Ag 2 Se-based thermoelectric materials.

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

Scalable foundation models for numerical simulations on HPC platforms

In recent years, foundation models (FMs) have begun to reshape numerical simulations on high-performance computing (HPC) platforms. These large, pre-trained AI models enable rapid predictions across a broad range of physical domains, including Earth system modeling, fluid dynamics, materials science, as well as complex multi-modal simulations in aerospace engineering and fusion research. By training on diverse datasets, FMs learn intricate relationships and underlying physical behavior while also enabling the quantification of uncertainty in their predictions. This capability allows simulations that once required days of numerical calculation to be completed in minutes (FM inference), supporting real-time design optimization, uncertainty-aware decision making, and more comprehensive exploration of complex scenarios.

AI↗
DOE OSTI2023

Structural and Chemical Evolution of Highly Fluorinated Li‐Rich Disordered Rocksalt Oxyfluorides as a Function of Temperature

Abstract Li‐rich disordered rocksalt (DRS) oxyfluorides have emerged as promising high‐energy cathode materials for lithium‐ion batteries. While a high level of fluorination in DRS materials offers performance advantages, it can only be achieved via mechanochemical synthesis, which poses challenges of reproducibility and scalability. The definition of relationships between fluorination and structural stability is required to devise alternative methods that overcome these challenges. In this study, the thermal evolution of three highly fluorinated phases, Li 2 TMO 2 F (TM = Mn, Co, and Ni), is investigated in an inert atmosphere. Diffraction and spectroscopic techniques are utilized to examine their electronic and chemical states up until conditions of decomposition. The analysis reveals that the materials phase‐separate above 400 °C, at most. It is also observed that heat‐treated DRS materials exhibit intricate changes in the local coordination of the metals, including their spin, and ordering compared to the pristine states. The changes upon annealing are accompanied by a modulation of the voltage profile, including reduced hysteresis, when used as electrodes. These results provide an in‐depth understanding of the fundamental crystal chemistry of DRS oxyfluorides in view of their promising role as the next generation of Li‐ion cathodes.

25 ENERGY STORAGE↗
DOE OSTI2025

Preserving the Josephson Coupling of Twisted Cuprate Junctions via Tailored Silicon Nitride Circuits Boards

Controlled fabrication of twisted van der Waals heterostructures is essential to unlock the full potential of moiré materials. However, achieving reproducibility remains a major challenge, particularly for air-sensitive materials such as Bi 2 Sr 2 CaCu 2 O 8 + δ (BSCCO), where it is crucial to preserve the intrinsic and delicate superconducting properties of the interface throughout the entire fabrication process. Here, a dry, inert and cryogenic assembly method is presented that combines silicon nitride nanomembranes (NMBs) with pre-patterned electrodes and the cryogenic stacking technique (CST) to fabricate high-quality twisted BSCCO Josephson junctions (JJs). This protocol prevents thermal and chemical degradation during both interface formation and electrical contact integration. It is also found that asymmetric membrane designs, such as a double cantilever, effectively suppress vibration-induced disorder due to wire bonding, resulting in sharp and hysteretic current–voltage characteristics. The junctions exhibit a twist-angle-dependent Josephson coupling with magnitudes comparable to the highest-performing devices reported to date, but achieved through a straightforward and versatile contact method, offering a scalable and adaptable platform for future applications. These findings highlight the importance of both interface and contact engineering in addressing reproducibility in superconducting van der Waals heterostructures.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

Few-cycle atomic layer deposition to nanoengineer polybenzimidazole for H 2 /CO 2 separation

Atomic layer deposition (ALD) creates uniform sub-nanometer films on a variety of surfaces and nanopore walls and has been used to modify polymers to improve surface affinity towards specific molecules, solvent resistance, and barrier properties to gases and vapors. Here, for the first time, we demonstrate that few-cycle ALD can be used to engineer functional polymers at a sub-nanometer scale to improve both molecular size-sieving ability and counterintuitively, gas permeability. Particularly, 1-cycle ALD treatment of polybenzimidazole (PBI) by sequential exposure to trimethylaluminum (TMA) and water vapor remarkably increases H 2 permeability by 120% - 270% and H 2 /CO 2 selectivity by 30% at 35–200 °C. The ALD not only deposits an AlOx layer on the surface but also enables the TMA to infiltrate and react with the bulk PBI to form an AlO x network, disrupting polymer chain packing and increasing chain rigidity. The membrane exhibits excellent stability when challenged with simulated syngas, overcoming the permeability/selectivity tradeoff for H 2 /CO 2 separation. In conclusion, this study showcases a facile and scalable way of engineering polymeric membranes at a sub-nanometer level to improve molecular separation performance.

36 MATERIALS SCIENCE↗
DOE OSTI2025

2,3-Butanediol recovery from fermentation broth using membrane pertraction

2,3-Butanediol (BDO) has gained immense interest for use as a platform chemical in the production of many important chemicals such as synthetic rubber, plasticizer, and octane boosters. Using BDO as a precursor for sustainable aviation fuel production may significantly reduce the carbon footprint of the airline industry. However, recovery of BDO is challenging due to its relatively low concentration (∼10 wt %) in fermentation broth and its high affinity for water. In this work, we developed a membrane pertraction process for BDO recovery from biomass derived fermentation broth. Different organic solvents such as hexanol and oleyl alcohol were investigated. With traditional solvent extraction, hexanol required a solvent to feed ratio of 10 to recover >90 % BDO, and oleyl alcohol could recover 35 % of BDO at the same ratio. BDO recovery of >90 % was demonstrated with pertraction; a BDO extraction rate of 15 g 1 m −2 h −1 was achieved using hexanol, and an extraction rate of 10 g 1 m −2 h −1 was achieved using oleyl alcohol. Impurities commonly found in fermentation broth did not affect the separation performance of the pertraction process. In conclusion, this work demonstrates pertraction as a low-footprint, scalable method for recovery of high-purity BDO from fermentation broth.

2,3 butanediol↗
DOE OSTI2022

Opening twisted polymer chains for simultaneously high printability and battery fast-charge

Fast-charging is key to the widespread adoption of battery-based electric vehicles. However, improving fast-charging through architecture optimization is expensive. To reduce costs and expand to commercialization, we applied roll-to-roll screen printing technology to create channels and decrease the tortuosity of electrodes. For the first time, this work successfully opened twisted polymer chains within high-solid-content inks to improve their screen printability and battery performance of as-printed electrodes. With LiNi 0.6 Mn 0.2 Co 0.2 O 2 as active materials, the 60% solid content ink presents superior screen printability after opening the twisted binder chains. As-printed electrode exhibits 33% higher charge capacity at 6 C than printed electrode with chains twisted ink at mass loading of 6.5 mg/cm 2 . Furthermore, coarse-grained molecular dynamics simulations are performed to study the underlying mechanism systematically. In conclusion, the new ink preparation procedure provides a scalable, effective strategy for manufacturing screen-printable battery ink and promotes screen-printed electrode technology.

25 ENERGY STORAGE↗
DOE OSTI2025

Improving Conversion of Captured CO 2 on Mixed-Oxide Dual-Function Materials by Low-Concentration Metal Promotion

Reactive carbon capture (RCC) is a promising nascent approach to harness the untapped resource of waste CO 2 to produce fuels and platform chemicals. However, process economics relies on the design of dual-function materials (DFMs) that exhibit maximal conversion of captured CO 2 and high selectivity toward valuable carbon products (e.g., CO). Herein, we report the use of low-concentration (ca. 0.5 wt %) metal promotors (Pt and Au) to improve the conversion of captured CO 2 on a Zn-Al mixed-oxide DFM by >30%, while also more than doubling per-cycle CO yield due to enhanced retention of captured CO 2 and H 2 activation. In situ DRIFTS of bound CO 2 on the DFMs showed distinctions in surface carbonate formation for the Pt- and Au-modified materials that were correlated with product evolution during the reactive desorption step of RCC. Particularly, Pt afforded superior H 2 activation but formed irreversibly-bound bicarbonates, compromising overall productivity, while the Na/Au/ZA DFM predominantly adsorbed CO 2 on Na sites, resulting in polydentate carbonates that are retained until higher temperatures before conversion to CO. In conclusion, these results indicate that adding a low concentration of oxidation-resistant noble metals, especially Au, is an effective strategy for improving key performance metrics of Zn-Al mixed-oxide DFMs to further advance the development of scalable RCC technologies.

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

Fast Tuning-Free Distributed Algorithm for Solving the Network-Constrained Economic Dispatch

With the increasing penetration of distributed energy resources (DERs) and their participation in the electricity market, it becomes more desirable to apply distributed algorithms for resource allocation in order to address the resulting computational and communicational challenges. Most of the existing distributed algorithms for solving the network-constrained economic dispatch (NCED) problem require the tuning of certain auxiliary parameters. As a result, the robustness of these algorithms against the varieties in DERs is greatly undermined. In this paper, a new distributed algorithm, optimality condition consensus (OCC), is proposed to solve the NCED problem by using distributed power flow (DPF) and ratio consensus as fundamental tools. It inherits the advantages of existing distributed algorithms for the NCED problem but removes the need for parameter tuning to improve performance in practice. In conclusion, the effectiveness of the proposed distributed algorithm in terms of efficiency, scalability, and robustness is demonstrated through detailed case studies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

MuyGPyS

MuyGPs is a GP estimation method that affords fast hyperparameter optimization by way of performing leave-one-out cross-validation. MuyGPs achieves best-in-class speed and scalability by limiting inference to the information contained in k nearest neighborhoods for prediction locations for both hyperparameter optimization and tuning. This feature affords the optimization of hyperparameters by way of leave-one-out cross-validation, as opposed to the more expensive loglikelihood evaluations requires by similar sparse methods

Priest, BenjaminW.↗
DOE OSTI2025

Eureka: Enabling Fine-Grained Access and Range Queries on Compressed Scientific Data via Data-Index Co-Compression

Handling large-scale scientific data in high-performance computing (HPC) environments poses significant challenges, including excessive I/O, high storage costs, and slow query performance. Traditional approaches often require full data decompression and scans, making them impractical for real-time or interactive analysis. To address these limitations, we introduce Eureka, a unified data-index co-compression framework that enables fine-grained access and efficient range queries on compressed scientific datasets. Eureka integrates spatial domain decomposition with block-wise error-bounded lossy compression to support selective decompression. It constructs a hierarchical AVL-tree index during compression to capture block-level value ranges, enabling fast pruning during query execution. To reduce metadata overhead, the index itself is also compressed while ensuring recall-preserving results. Experiments on six diverse HPC simulation datasets show that Eureka achieves up to 25x data compression and over 300x index compression, surpassing state-of-the-art compressors such as SZ3 and ZFP in rate-distortion performance. Additionally, Eureka delivers over 30x speedup for low-selectivity range queries, making it a scalable and efficient solution for modern scientific data analysis.

Yan, Ning↗
DOE OSTI2021

A Computationally Improved Heuristic Algorithm for Transmission Switching Using Line Flow Thresholds for Load Shed Reduction

We present a computationally improved heuristic algorithm for transmission switching (TS) to recover load shed. Research from the past showed that changing power system topology may control power flows and remove line congestion. Hence, TS may reduce the required load shed. One of the main challenges is to find a potential TS candidate in a suitable time. Here, we propose a novel heuristic method that is capable of finding the potential TS candidate faster than existing algorithms in literature. The proposed method is compatible with both the AC and DC optimal power flows (OPF). Three metrics are used to compare the proposed algorithm with the state-of-the-art from literature to show the speedup and accuracy achieved. The proposed method is implemented on the IEEE 30-bus system, PEGASE 89-bus system, IEEE 118-bus system, and Polish 2383- bus system. The results on the large-scale Polish 2383-bus system shows that the proposed algorithm is scalable to large real-world systems. Parallel computing is implemented to further improve the computational performance of the proposed algorithm.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Non-Electricity Based Renewable Fuels: Theory and Computation for Solar Thermochemical Hydrogen

Dominated by photovoltaics and wind, current renewable energy sources generate mostly electricity, but 80% of the global final energy consumption occurs in form of fuels. Therefore, direct solar fuel generation would be a major breakthrough for the energy transition. Solar thermochemical hydrogen (STCH) is one of the very few potential routes towards scalable renewable fuels, but currently suffers from lack of an oxide working material that could optimally perform energy conversion within the thermodynamic boundary conditions. Theory and computation can contribute in two distinct ways, through materials search and discovery, but also by providing detailed mechanistic models for specific systems so to advance our understanding of possible design strategies. To enable high-throughput materials screening, we developed a defect graph neural network (dGNN) machine learning approach,[1] which accelerates the prediction of defect formation energies by replacing the tedious density functional theory (DFT) supercell calculations for all possible defect sites. This approach enables high-throughput database screening of oxides, which was integrated with thermodynamic modeling to extract the reduction entropies as additional selection criterion for STCH. Once potential candidate materials are identified, detailed models can guide materials design by predicting performance characteristics. One challenge is to quantitatively predict thermochemical equilibria at high concentrations when the redox active defects start to interact with each other, thereby impeding the formation of additional defects. Introducing a model for the free energy of defect interaction, parametrized on the basis of DFT data, we simulated the complete STCH redox cycle for (Sr,Ce)MnO3 alloys, achieving near-quantitative agreement with experimental data.[2] The analysis of these simulations reveals how defect interactions diminish the reduction entropy and H2 yield, suggesting to include these interactions in design considerations. Finally, we revisit the popular van't Hoff method for analyzing reduction enthalpies and entropies. This method is not ideal, as it involves a temperature-dependent convolution of gas-phase and solid-state entropies, causing uncertainties in the same order of magnitude as the physical quantities of interest. To avoid this problem, we suggest a simple alternative approach which can be applied to experimental and simulated data alike.

first-principles calculations↗
DOE OSTI2020

Hybrid Sorbents for 129 I Capture from Contaminated Groundwater

Radioiodine ( 129 I) poses a risk to the environment due to its long half-life, toxicity, and mobility. It is found at the U.S. Department of Energy Hanford Site due to legacy releases of nuclear wastes to the subsurface where 129 I is predominantly present as iodate (IO 3 – ). To date, a cost-effective and scalable cleanup technology for 129 I has not been identified, with hydraulic containment implemented as the remedial approach. Here, novel high-performing sorbents for 129 I remediation with the capacity to reduce 129 I concentrations to or below the US Environmental Protection Agency (EPA) drinking water standard and procedures to deploy them in an ex-situ pump and treat (P&T) system are introduced. Furthermore, this includes implementation of hybridized polyacrylonitrile (PAN) beads for ex-situ remediation of IO 3 – -contaminated groundwater for the first time. Iron (Fe) oxyhydroxide and bismuth (Bi) oxyhydroxide sorbents were deployed on silica substrates or encapsulated in porous PAN beads. In addition, Fe–, cerium (Ce)–, and Bi–oxyhydroxides were encapsulated with anion-exchange resins. The PAN–bismuth oxyhydroxide and PAN–ferrihydrite composites along with Fe- and Ce-based hybrid anion-exchange resins performed well in batch sorption experiments with distribution coefficients for IO 3 – of >1000 mL/g and rapid removal kinetics. Of the tested materials, the Ce-based hybrid anion-exchange resin was the most efficient for removal of IO 3 – from Hanford groundwater in a column system, with 50% breakthrough occurring at 324 pore volumes. The functional amine groups on the parent resin and amount of active sorbent in the resin can be customized to improve the iodine loading capacity. These results highlight the potential for IO 3 – remediation by hybrid sorbents and represent a benchmark for the implementation of commercially available materials to meet EPA standards for cleanup of 129 I in a large-scale P&T system.

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

Porting hypre to heterogeneous computer architectures: Strategies and experiences

We report that linear systems are occurring in many applications, and solving them can take a large amount of the total simulation time. The high performance library hypre provides a variety of interfaces and linear solvers, including various multigrid methods, that have achieved good scalability on a variety of homogeneous parallel computer architectures. Heterogeneous architectures with nodes that have both CPUs and accelerators provide new challenges, since they require more fine-grained parallelism and reduced data movement between different memories on a single node as well as across nodes. We will discuss our experiences and strategies to port hypre to heterogeneous computers with accelerators, including the design of a new memory model, the use of abstractions, the BoxLoop macros in the structured and semi-structured interfaces, and the restructuring of algebraic multigrid (AMG) into modular components. We present numerical experiments comparing CPU and GPU performance for several test problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.

Wang, Tianqi↗
DOE OSTI2025

Asynchronous-many-task systems: Challenges and opportunities - Scaling an AMR astrophysics code on exascale machines using Kokkos and HPX

Dynamic and adaptive mesh refinement is pivotal in high-resolution, multi-physics, multi-model simulations, necessitating precise physics resolution in localized areas across expansive domains. Today’s supercomputers’ extreme heterogeneity presents a significant challenge for dynamically adaptive codes, highlighting the importance of achieving performance portability at scale. Our research focuses on astrophysical simulations, particularly stellar mergers, to elucidate early universe dynamics. Here, we present Octo-Tiger, leveraging Kokkos, HPX, and SIMD for portable performance at scale in complex, massively parallel adaptive multi-physics simulations. Octo-Tiger supports diverse processors, accelerators, and network backends. Experiments demonstrate exceptional scalability across several heterogeneous supercomputers including Perlmutter, Frontier, and Fugaku, encompassing major GPU architectures and x86, ARM, and RISC-V CPUs. Parallel efficiency of 47.59% (110,080 cores and 6880 hybrid A100 GPUs) on a full-system run on Perlmutter (26% HPCG peak performance) and 51.37% (using 32,768 cores and 2048 MI250X) on Frontier are achieved.

97 MATHEMATICS AND COMPUTING↗