Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “YIn”

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 1,297 records · Page 72
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

A Sparse Distributed Gigascale Resolution Material Point Method

In this paper, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

FORGE: Pre-Training Open Foundation Models for Science

Large language models (LLMs) are poised to revolutionize the way we conduct scientific research. However, both model complexity and pre-training cost are impeding effective adoption for the wider science community. Identifying suitable scientific use cases, finding the optimal balance between model and data sizes, and scaling up model training are among the most pressing issues that need to be addressed. In this study, we provide practical solutions for building and using LLM-based foundation models targeting scientific research use cases. We present an end-to-end examination of the effectiveness of LLMs in scientific research, including their scaling behavior and computational requirements on Frontier, the first Exascale supercomputer. We have also developed for release to the scientific community a suite of open foundation models called FORGE with up to 26B parameters using 257B tokens from over 200M scientific articles, with performance either on par or superior to other state-of-the-art comparable models. We have demonstrated the use and effectiveness of FORGE on scientific downstream tasks. Our research establishes best practices that can be applied across various fields to take advantage of LLMs for scientific discovery.

Yin, Junqi↗
DOE OSTI2025

QECC-Synth: A Layout Synthesizer for Quantum Error Correction Codes on Sparse Architectures

Quantum Error Correction (QEC) codes are essential for achieving fault-tolerant quantum computing (FTQC). However, their implementation faces significant challenges due to disparity between required dense qubit connectivity and sparse hardware architectures. Current approaches often either underutilize QEC circuit features or focus on manual designs tailored to specific codes and architectures, limiting their capability and generality. In response, we introduce QECC-Synth, an automated compiler for QEC code implementation that addresses these challenges. We leverage the ancilla bridge technique tailored to the requirements of QEC circuits and introduces a systematic classification of its design space flexibilities. We then formalize this problem using the MaxSAT framework to optimize these flexibilities. Evaluation shows that our method significantly outperforms existing methods while demonstrating broader applicability across diverse QEC codes and hardware architectures.

Yin, Keyi [University of California, San Diego]↗
DOE OSTI2024

The Case for Co-Designing Model Architectures with Hardware

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL model to be more amenable to the target hardware can significantly improve the runtime performance of DL training and inference. In this paper, we provide a set of guidelines for users to maximize the runtime performance of their transformer models. These guidelines have been created by carefully considering the impact of various model hyperparameters controlling model shape on the efficiency of the underlying computation kernels executed on the GPU. We find the throughput of models with “efficient” model shapes is up to 39% higher while preserving accuracy compared to models with a similar number of parameters but with unoptimized shapes.

Yin, Junqi↗
DOE OSTI2025

CaliQEC: In-situ Qubit Calibration for Surface Code Quantum Error Correction

Quantum Error Correction (QEC) is essential for fault-tolerant, large-scale quantum computation. However, error drift in qubits undermines QEC performance during long computations, necessitating frequent calibration. Conventional calibration methods disrupt quantum states, requiring system downtime and rendering in situ calibration impractical. To address this challenge, we propose QECali, a novel framework that enables in situ calibration for surface codes. Our evaluation demonstrates that QECali introduces modest qubit overhead and negligible increases in execution time, offering the first practical solution for in situ calibration in surface code based quantum computation.

Fang, Xiang [University of California, Santa Barba↗
DOE OSTI2025

RingX: Scalable Parallel Attention for Long-Context Learning on HPC

The attention mechanism has become foundational for remarkable AI breakthroughs since the introduction of the Transformer, driving the demand for increasingly longer context to power frontier models such as large-scale reasoning language models and high-resolution image/video generators. However, its quadratic computational and memory complexities present substantial challenges. Current state-of-the-art parallel attention methods, such as ring attention, are widely adopted for long-context training but utilize a point-to-point communication strategy that fails to fully exploit the capabilities of modern HPC network architectures. In this work, we propose ringX, a scalable family of parallel attention methods optimized explicitly for HPC systems. By enhancing workload partitioning, refining communication patterns, and improving load balancing, ringX achieves up to 3.4 × speedup compared to conventional ring attention on the Frontier supercomputer. Optimized for both bi-directional and causal attention mechanisms, ringX demonstrates its effectiveness through training benchmarks of a Vision Transformer (ViT) on a climate dataset and a Generative Pre-Trained Transformer (GPT) model, Llama3 8B. Our method attains an end-to-end training speedup of approximately 1.5 × in both scenarios. To our knowledge, the achieved 38% model FLOPs utilization (MFU) for training Llama3 8B with a 1M-token sequence length on 4,096 GPUs represents one of the highest training efficiencies reported for long-context learning on HPC systems. Our code implementation is available at https://github.com/jqyin/ringX-attention.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗
DOE OSTI2026

FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving

Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent replicas, while tensor parallelism (TP) reduces per-request latency and pools memory for long-context inference. However, existing serving stacks typically commit to a static parallelism configuration at deployment; adapting to bursts, priorities, or long-context requests is often disruptive and slow. We present Flying Serving, a vLLM-based system that enables online DP-TP switching without restarting engine workers. Flying Serving makes reconfiguration practical by virtualizing the state that would otherwise force data movement: (i) a zero-copy Model Weights Manager that exposes TP shard views on demand, (ii) a KV Cache Adaptor that preserves request KV state across DP/TP layouts, (iii) an eagerly initialized Communicator Pool to amortize collective setup, and (iv) a deadlock-free scheduler that coordinates safe transitions under execution skew. Across three popular LLMs and realistic serving scenarios, Flying Serving improves performance by up to 4.79 × under high load and 3.47 × under low load while supporting latency- and memory-driven requests.

Gao, Shouwei [ORNL]↗
DOE OSTI2020

Improved Stability and Cyclability of Ceramic Solid Electrolyte by Coating Polymer

Rechargeable all-solid-state lithium (Li) metal batteries show better safety and energy density compared to commercial Li-ion batteries using liquid electrolyte. As the key component of Li metal batteries, ceramic solid-state electrolyte has attracted great interest because of its high ion conductivity and great potential in interfacing with Li metal. Ceramic electrolyte has a more stable interface with Li metal than liquid electrolyte, but chemical reaction and Li dendrite growth at the electrolyte/Li interface are still significant, which causes device degradation and failure by cycling of Li plating and stripping. Unlike ceramic electrolyte, polymer electrolyte has a relatively stable interface with Li metal and better mechanical flexibility. Therefore, we introduced a polymer electrolyte coating to protect the ceramic electrolyte from direct contact with Li metal. The galvanotactic cycling Li plating/striping data on the devices with (without) the coating illustrates increased (decreased) overall conductivity and cyclability of the test cell by the cycling. Nanometer-scale ionic-transport imaging, based on atomic force microscopy, shows that cycling degrades the ceramic-only electrolyte by partially blocking ionic transport in areas; in contrast, cycling on the polymer-coated electrolyte improves ionic conductivity. Compared with the ceramic-only electrolyte, this novel polymer electrolyte coating on ceramic electrolyte shows less degradation when in contact with Li metal.

25 ENERGY STORAGE↗
DOE OSTI2020

Redox Potential Measurements of Cr(II)/Cr Ni(II)/Ni and Mg(II)/Mg in Molten MgCl 2 –KCl–NaCl Mixture

The redox potential of Ni(II)/Ni, Cr(II)/Cr, and Mg(II)/Mg in MgCl 2 –KCl–NaCl (Magnak chloride) were studied utilizing chronopotentiometry (CP) method in a three-electrode electrochemical cell. Four different CrCl 2 concentrations from 873 K to 1073 K, three NiCl 2 concentrations from 773 K to 1073 K, and two MgCl 2 concentrations from 823 K to 1073 K have been measured. The activity coefficients were calculated referring to a supercooled potential accordingly. The empirical equation of formal potential will be of great significance for the fundamental thermodynamic prediction in high-temperature Magnak chloride systems where corrosion product impurities are present.

14 SOLAR ENERGY↗
DOE OSTI2020

Communication—On the Lack of Correlation between the Voltammetric Redox Couple and ORR Activity of Fe-N-C Catalysts

Platinum group metal-free catalysts for polymer electrolyte fuel cells are analyzed in different electrolytes (H 2 SO 4 and HClO 4 ) and at different pH values to gain insight into the oxygen reduction reaction (ORR) mechanism. Two Fe-N-C type catalysts showing a reversible voltammetric redox couple around 0.77 V vs RHE in HClO 4 electrolyte are investigated. A notable cathodic shift of the redox couple to 0.62 V is observed in H 2 SO 4 and is assigned to bisulfate adsorption. Concurrently, the ORR activity of the catalysts is unaffected, suggesting an independent nature of the reductive mechanism with the redox peak species.

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

Operando Synchrotron Studies of Inhomogeneity during Anode-Free Plating of Li Metal in Pouch Cell Batteries

Operando synchrotron X-ray diffraction (XRD) studies have not previously been used to directly characterize Li metal in standard batteries due to the extremely weak scattering from Li atoms. In this work, it is demonstrated the stripping and plating of Li metal can be effectively quantified during battery cycling in appropriately designed synchrotron XRD experiments that utilize an anode-free battery configuration in which a Li-containing cathode material of LiNi 0.6 Mn 0.2 Co 0.2 O 2 (NMC622) is paired with a bare anode current collector consisting of either Cu metal (Cu/NMC) or Mo metal (Mo/NMC). In this configuration, it is possible to probe local variations in the deposition and stripping of Li metal with sufficient spatial sensitivity to map the inhomogeneity in pouch cells and to follow these processes with sufficient time resolution to track state-of-charge-dependent variations in the rate of Li usage at a single point. For the Cu/NMC and Mo/NMC batteries, it was observed that the initial plating of Li occurred in a very homogeneous manner but that severe macroscopic inhomogeneity arose on a mm-scale during the subsequent stripping of Li, contrasting with the conventional wisdom that the greatest challenges in Li metal batteries are associated with Li deposition.

25 ENERGY STORAGE↗
DOE OSTI2023

The Impact of Fluoroethylene Carbonate Additive on Charged Sodium Ion Electrodes/Electrolyte Reactivity Studied Using Accelerating Rate Calorimetry

The effects of fluoroethylene carbonate (FEC) electrolyte additive on charged sodium ion electrode/electrolyte reactivity at elevated temperatures were investigated using accelerating rate calorimetry (ARC). The beneficial effect of FEC on cell lifetime was demonstrated using Na 0.97 Ca 0.03 [Mn 0.39 Fe 0.31 Ni 0.22 Zn 0.08 ]O 2 (NCMFNZO)/hard carbon (HC) pouch cells first prior to ARC measurements. Electrodes from these pouch cells were utilized as sample materials and 1.0 M NaPF 6 in propylene carbonate (PC):ethyl methyl carbonate (EMC) (1:1 by vol.) was chosen as control electrolyte. Adding 2 wt% and 5 wt% FEC to the electrolyte does not significantly affect the reactivity of de-sodiated NCMFNZO compared to the control electrolyte. However, the addition of FEC obviously changed the reactivity between sodiated HC and electrolytes, especially by showing a suppression on the exothermal behavior between 160 °C and 230 °C. These results give a head to head comparison of the reactivity of FEC additive containing electrolytes with charged sodium ion electrode materials at elevated temperatures and show that the use of FEC at additive levels should not compromise the cell safety when extending cell lifetime.

25 ENERGY STORAGE↗
DOE OSTI2021

Research on the Influence Mechanism of the High‐Steep Slope on the Deformation Characteristics of Bridge Substructure

With the development of the Chinese railway, the high‐steep slope is irreversible to be faced; especially under severe conditions such as heavy rainfall and earthquake, this kind of slope is prone to geological disasters, which seriously affects the safety and stability of the bridge substructure. Aiming to this, long‐term monitorization and numerical analysis were carried out in this research, and the influence mechanism of the high‐steep slopes on the stress and deformation characteristics of the bridge structure was studied. The research results show that under the effect of rainfall and earthquake, the original stress balance in the high‐steep slope is broken, and the possibility of landslide thrust increases; under the comprehensive impact of residual landslide thrust, traction force at slope foot, vertical gravity of bridge slab and vehicle, and the bridge cap will deform. Besides, the deformation of the bridge pier exceeds the allowable lateral displacement of the top of the bridge pier, reaching 111.7%∼112.4% of the limit, which seriously affects the stability of the bridge structure and the safety of the railway service. Therefore, by increasing the support strength of the slope foot and the diameter of the bridge pile foundation, the traction force of the slope foot can be reduced, and the sliding resistance of the bridge pile foundation can be improved so as the safety of the bridge structure can be promoted.

Zhang, Yufang (ORCID:0000000348912060)↗
DOE OSTI2022

MSASGCN : Multi-Head Self-Attention Spatiotemporal Graph Convolutional Network for Traffic Flow Forecasting

Traffic flow forecasting is an essential task of an intelligent transportation system (ITS), closely related to intelligent transportation management and resource scheduling. Dynamic spatial-temporal dependencies in traffic data make traffic flow forecasting to be a challenging task. Most existing research cannot model dynamic spatial and temporal correlations to achieve well-forecasting performance. The multi-head self-attention mechanism is a valuable method to capture dynamic spatial-temporal correlations, and combining it with graph convolutional networks is a promising solution. Therefore, we propose a multi-head self-attention spatiotemporal graph convolutional network (MSASGCN) model. It can effectively capture local correlations and potential global correlations of spatial structures, can handle dynamic evolution of the road network, and, in the time dimension, can effectively capture dynamic temporal correlations. Experiments on two real datasets verify the stability of our proposed model, obtaining a better prediction performance than the baseline algorithms. The correlation metrics get significantly reduced compared with traditional time series prediction methods and deep learning methods without using graph neural networks, according to MAE and RMSE results. Compared with advanced traffic flow forecasting methods, our model also has a performance improvement and a more stable prediction performance. We also discuss some problems and challenges in traffic forecasting.

Cao, Yang↗
DOE OSTI2022

Research on Deformation Law of Deep Foundation Pit of Station in Core Region of Saturated Soft Loess Based on Monitoring

Saturated soft loess has a large pore structure, high compressibility, low strength, fluid plastic state, and poor engineering properties. It is still one of the key problems that engineering needs to solve. In order to study the influence of deep foundation pit excavation in the saturated soft loess area on the deformation of foundation pits, the deformation laws of ground settlement, enclosure structure, and supporting axial force were clarified based on the field tests on the deformation characteristics of deep foundation pits in areas with the high-water level in saturated soft loess, combined with geological conditions and on-site construction procedures. The results indicate the following: water supply and construction process were found to be the main factor in changing the surface settlement curve of deep foundation pits in saturated soft loess; increasing the construction speed of the pit bottom floor, inverted braces, floor frame beams, and sidewall frame beams to close the structure, which is conducive to restraining the deformation of the continuous underground wall and foundation pits in similar areas. In the initial stage of support layout, the axial force of steel support tends to increase too fast or even exceed the standard control value. Therefore, a reasonable preadding axial force is an effective means to control the deformation of the continuous underground wall and the axial force of the steel support. The current research results may provide a reference for constructing deep foundation pits in similar areas.

Wang, Xueyan↗
DOE OSTI2022

DistGANS- Distributed Generative Adversarial Neural Networks

DistGANs is a Python package to perform distributed training of conditional generative adversarial neural networks for multi-class labeled image data. DistGANs partitionins the training data according to data labels, and enhances scalability by performing a parallel training where multiple generators are concurrently trained, each one of them focusing on a single data label.

Lupo Pasini, Massimiliano [Oak Ridge National Lab.↗