Search NASA⌕ Search

SEARCH · Search NASA

Results for “Speedup model”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Predicting impurity spectral functions using machine learning

The Anderson Impurity Model (AIM) is a canonical model of quantum many-body physics. Here we investigate whether machine learning models, both neural networks (NN) and kernel ridge regression (KRR), can accurately predict the AIM spectral function in all of its regimes, from empty orbital, to mixed valence, to Kondo. To tackle this question, we construct two large spectral databases containing approximately 410 000 and 600 000 spectral functions of the single-channel impurity problem. We show that the NN models can accurately predict the AIM spectral function in all of its regimes, with pointwise mean absolute errors down to 0.003 in normalized units. We find that the trained NN models outperform models based on KRR and enjoy a speedup on the order of 10 5 over traditional AIM solvers. Finally, the required size of the training set of our model can be significantly reduced using farthest point sampling in the AIM parameter space, which is important for generalizing our method to more complicated multichannel impurity problems of relevance to predicting the properties of real materials.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

Accelerating multicanonical sampling with irreversibility

Flat-histogram Monte Carlo simulations are well-established, robust methods to perform random walks in a physical observable or parameter space, making them suitable for finding ground states or studying phase transitions in complex systems in statistical physics. However, their efficiency can be limited by the time to attain the desired flat distribution, which is generally unknown prior to the simulations. In particular, they might suffer from slowing down towards the end of a simulation due to the diffusive nature of random walks. In this work we apply irreversibility to the multicanonical Monte Carlo method via the lifting approach to alleviate this behavior. We achieve a 2–4 times speedup in ground-state search for a two-dimensional (2D) Ising model, and up to an order of magnitude of speedup for finding the ground-state energy in an Edwards–Anderson spin glass, compared to traditional multicanonical sampling. In conclusion, the round-trip times between ground states show a narrower distribution and are significantly shorter compared to the reversible counterpart, suggesting that a lower convergence time with a smaller time variance is feasible.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2020

Solution of the Nonlinear High-Fidelity Generalized Method of Cells Micromechanics Relations via Order-Reduction Techniques

The High-Fidelity Generalized Method of Cells (HFGMC) is one technique, distinct from traditional finite element approaches, for accurately simulating nonlinear composite material behavior. In this work, the HFGMC global system of equations for doubly-periodic repeating unit cells with nonlinear constituents has been reduced in size through the novel application of a Petrov-Galerkin Proper Orthogonal Decomposition order-reduction scheme in order to improve its computational efficiency. Order-reduced models of an E-glass/Nylon 12 composite led to a 4.8 to 6.3x speedup in the equation assembly/solution runtime while maintaining model accuracy. This corresponded to a 21 to 38 percent reduction in total runtime. The significant difference in assembly/solution and total runtimes was attributed to the evaluation of integration point inelastic field quantities; this step was identical between the unreduced and order-reduced models. Nonetheless, order-reduced techniques offer the potential to significantly improve the computational efficiency of multiscale calculations.

Ricks, Trenton M.↗
DOE OSTI2022

The Schwarz Alternating Method for the Seamless Coupling of Nonlinear Reduced Order Models and Full Order Models

Projection-based model order reduction allows for the parsimonious representation of full order models (FOMs), typically obtained through the discretization of a set of partial differential equations (PDEs) using conventional techniques (e.g., finite element, finite volume, finite difference methods) where the discretization may contain a very large number of degrees of freedom. As a result of this more compact representation, the resulting projection-based reduced order models (ROMs) can achieve considerable computational speedups, which are especially useful in real-time or multi-query analyses. One known deficiency of projection-based ROMs is that they can suffer from a lack of robustness, stability and accuracy, especially in the predictive regime, which ultimately limits their useful application. Another research gap that has prevented the widespread adoption of ROMs within the modeling and simulation community is the lack of theoretical and algorithmic foundations necessary for the “plug-and-play” integration of these models into existing multi-scale and multi-physics frameworks. This paper describes a new methodology that has the potential to address both of the aforementioned deficiencies by coupling projection-based ROMs with each other as well as with conventional FOMs by means of the Schwarz alternating method [41]. Leveraging recent work that adapted the Schwarz alternating method to enable consistent and concurrent multiscale coupling of finite element FOMs in solid mechanics [35, 36], we present a new extension of the Schwarz framework that enables FOM-ROM and ROM-ROM coupling, following a domain decomposition of the physical geometry on which a PDE is posed. In order to maintain efficiency and achieve computation speed-ups, we employ hyper-reduction via the Energy-Conserving Sampling and Weighting (ECSW) approach [13]. We evaluate the proposed coupling approach in the reproductive as well as in the predictive regime on a canonical test case that involves the dynamic propagation of a traveling wave in a nonlinear hyper-elastic material.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A GPU‐Accelerated Generative Adversarial Model for Causal Inference

We develop a GPU-accelerated machine learning generative adversarial model designed to facilitate causal inferences from observational data. Our model's theoretical framework is conceptualized in a manner that is amenable to being operable and scalable for high-performance computing platforms. We leverage GPU acceleration to develop a parallel evolutionary algorithm to achieve large-scale parallel computation of the model within a now widely accessible computing platform. This capability both enhances computational speedup and efficiency and also extends the use of the model to a broader range of substantive research domains while maintaining the underlying theoretical properties of the model.

GPU↗
DOE OSTI2023

A reduced-order model of concentration polarization in reverse osmosis systems with feed spacers

Feed spacers in reverse osmosis systems generate complex fluid flows that limit computational fluid dynamics (CFD) simulations to small length and time scales. That limits our ability to simulate mineral scaling and other membrane fouling phenomena, which occur over longer length and time scales. Thus motivated, we develop a reduced model that replaces the CFD simulation of the velocity field with an analytical model that mimics spacers. This focuses the remaining numerical effort on simulating the advection–diffusion equation governing solute transport. We motivate and validate the model with CFD simulations and bench-scale experiments of spacer filaments in three different arrangements, including cases of unsteady vortex shedding. We show that the model produces a roughly 10,000-fold speedup compared to CFD, and accurately reproduces CFD predictions of not only the average and maximum concentrations, but also the local concentration distribution along the membrane. Here, we also demonstrate the model for simulating a feed channel with a length-to-height ratio of 200. The model provides a simple testbed for exploratory studies of multispecies transport, precipitation, and membrane fouling phenomena for which simulating spacers is often prohibitive.

Computational fluid dynamics↗
DOE OSTI2024

Aggregate data‐driven dynamic modeling of active distribution networks with DERs for voltage stability studies

Abstract Electric distribution networks increasingly host distributed energy resources based on power electronic converter (PEC) toward active distribution networks (ADN). Despite advances in computational capabilities, electromagnetic transient models are limited in scalability because of their reliance on exact data about the distribution system and each of its components. Similarly, the use of the DER_A model, which is intended to examine the combined dynamic behavior of many DERs, is limited by the difficulty in parameterization. There is a need for improved dynamic models of DERs for use in large power system simulations for stability analysis. This paper proposes an aggregate model‐free, data‐driven approach for deriving a dynamic partitioned model (DPM) of ADNs. Detailed residential distribution feeders were first developed, including PEC‐based DERs and composite load models (CMLDs), from which the aggregated DPM was derived. The performance was evaluated through various case studies and validated against the detailed ADN model and state‐of‐the‐art DER_A model with CMLD. The data‐driven DPM achieved a of over 90%, accurately representing the aggregated dynamic behavior of ADNs. Furthermore, the DPM significantly accelerated the simulation process with a computational speedup of 68 times compared to the detailed ADN and a 3.5 times speedup compared to the DER_A CMLD model.

42 ENGINEERING↗
DOE OSTI2016

Visualizing Wind Farm Wakes Using SCADA Data

As wind farms scale to include more and more turbines, questions about turbine wake interactions become increasingly important. Turbine wakes reduce wind speed and downwind turbines suffer decreased performance. The cumulative effect of the wakes throughout a wind farm will therefore decrease the performance of the entire farm. These interactions are dynamic and complicated, and it is difficult to quantify the overall effect of the wakes. This problem has attracted some attention in terms of computational modelling for siting turbines on new farms, but less attention in terms of empirical studies and performance validation of existing farms. In this report, Supervisory Control and Data Acquisition (SCADA) data from an existing wind farm is analyzed in order to explore methods for documenting wake interactions. Visualization techniques are proposed and used to analyze wakes in a 67 turbine farm. The visualizations are based on directional analysis using power measurements, and can be considered to be normalized capacity factors below rated power. Wind speed measurements are not used in the analysis except for data pre-processing. Four wake effects are observed; including wake deficit, channel speed up, and two potentially new effects, single and multiple shear point speed up. In addition, an attempt is made to quantify wake losses using the same SCADA data. Power losses for the specific wind farm investigated are relatively low, estimated to be in the range of 3-5%. Finally, a simple model based on the wind farm geometrical layout is proposed. Key parameters for the model have been estimated by comparing wake profiles at different ranges and making some ad hoc assumptions. A preliminary comparison of six selected profiles shows excellent agreement with the model. Where discrepancies are observed, reasonable explanations can be found in multi-turbine speedup effects and landscape features, which are yet to be modelled.

17 WIND ENERGY↗
NASA NTRSDate not supplied

Accuracy Assessment of Two Gps Fidelity Prediction Services in Urban Terrain

Low altitude flight in urban areas is susceptible to degraded GNSS-based navigation system performance due to terrain interference with radio signals from orbital positioning satellites. Predictive navigation performance fidelity tools are needed a) in preflight planning to assist in the creation of safe flight paths and b) in-flight to provide contingency management agents with the navigation risk of proximal flight corridors. Two navigation fidelity prediction services are validated by comparison with over 6000 readings from GNSS sensors collected along a five-mile path through urban areas of Corpus Christi, Texas, on three dates in 2022. Predictions are based on satellite line of sight through 3D terrain data collected in 2018. Each service predicts a set of navigation fidelity metrics over a user-specified time period. One metric estimated by both is the number of visible satellites. A direct comparison of the number of predicted visible satellites with the number sensed by the receiver is used to validate the prediction services. Results show an exact match in the number of predicted satellites for 60% of the measurements, and a match within +/- 4 satellites for 95% of the measurements. As expected, agreement improves away from vertical blocking terrain. Most cases of mismatch are due a lower predicted count than measured (false negatives), and can be accounted for by receiver pickup of stray signals caused by multipath propagation. About 10% of mismatches are false positives and are mostly accounted for by foliage effects. The two services predict visibility of the same set of satellites 80% of the time, differ by two or less satellites 95% of the time, and can compute predictions for one hour of observations in one minute or less. Validation is analyzed statistically and in detailed case studies of selected observation times. The prediction services validated in this study run fast enough for preflight safety planning. The more stringent challenge of inflight navigation fidelity prediction for contingency management requires both a speedup of the current level of modeling and equally fast stray signal modeling.

Andrew Moore↗
NASA NTRSDate not supplied

Accuracy Assessment of Two GPS Fidelity Prediction Services in Urban Terrain

Low altitude flight in urban areas is susceptible to degraded GNSS-based navigation system performance due to terrain interference with radio signals from orbital positioning satellites. Predictive navigation performance fidelity tools are needed a) in preflight planning to assist in the creation of safe flight paths and b) in-flight to provide contingency management agents with the navigation risk of proximal flight corridors. Two navigation fidelity prediction services are validated by comparison with over 6000 readings from GNSS sensors collected along a five-mile path through urban areas of Corpus Christi, Texas, on three dates in 2022. Predictions are based on satellite line of sight through 3D terrain data collected in 2018. Each service predicts a set of navigation fidelity metrics over a user-specified time period. One metric estimated by both is the number of visible satellites. A direct comparison of the number of predicted visible satellites with the number sensed by the receiver is used to validate the prediction services. Results show an exact match in the number of predicted satellites for 60% of the measurements, and a match within +/- 4 satellites for 95% of the measurements. As expected, agreement improves away from vertical blocking terrain. Most cases of mismatch are due a lower predicted count than measured (false negatives), and can be accounted for by receiver pickup of stray signals caused by multipath propagation. About 10% of mismatches are false positives and are mostly accounted for by foliage effects. The two services predict visibility of the same set of satellites 80% of the time, differ by two or less satellites 95% of the time, and can compute predictions for one hour of observations in one minute or less. Validation is analyzed statistically and in detailed case studies of selected observation times. The prediction services validated in this study run fast enough for preflight safety planning. The more stringent challenge of inflight navigation fidelity prediction for contingency management requires both a speedup of the current level of modeling and equally fast stray signal modeling.

Andrew J. Moore↗
DOE OSTI2020

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗
DOE OSTI2022

Sparse Deep Neural Network Inference using different Programming Models

Sparse deep neural networks have gained increasing attention recently in achieving speedups on inference with reduced memory footprints. However, the real-world applications are little shown with specialized optimizations, yet a wide variety of DNN tasks remain dense without exploiting the advantages of sparsity in networks. Recent work presented by MIT/IEEE/Amazon GraphChallenge has demonstrated significant speedups and various techniques. Still, we find that there is limited investigation of the impact of various Python and C\slash C++ based programming models to explore new opportunities in general cases. In this work, we provide performance evaluation through different programming models using CuPy, cuSPARSE, and OpenMP to discuss the advantages and disadvantages of our sparse implementations on single-GPU and multiple GPUs of NVIDIA DGX-A100 40GB/80GB platforms.

machine learning, HPC↗
DOE OSTI2022

From PeleC to PeleACC, to PeleC++

PeleC is an Exascale Computing Project application for simulating compressible combustion in complex geometries. It has been built on top of the popular AMReX library. In the beginning of the Exascale Computing Project, PeleC was focused on KNL. It uses a mixture of C++, C, and kernels written in Fortran to obtain performance by focusing on vectorization. Recently we have taken two approaches in deciding PeleC's future for obtaining performance on exascale GPU machines. In the first programming model, we decorated the Fortran kernels with OpenACC directives. This expedited our ability to run at large scales on Summit's GPUs, where we achieved a significant speedup over the CPUs on Summit. The second programming model involved rewriting the Fortran kernels in C++ and using AMReX's Kokkos-like lambda abstractions for running on the GPU. This resulted in similar speedups on Summit's GPUs over merely utilizing the CPUs. Both approaches involved AMReX's management of memory transfers between the device and host. In this work, we compare and contrast the benefits and pitfalls to both programming approaches regarding performance, performance portability, and productivity. We also discuss advantages we have found in taking the time to modernize our code and why have chosen a specific pathway to prepare our code for the future DOE exascale machines.

exascale computing↗
DOE OSTI2025

Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State

We present a novel machine learning (ML)-based method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch (2.0+) and optimized for GPU inference using NVIDIA TensorRT (8.4.1), achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves 𝐿 1 and 𝐿 ∞ errors of 4.54 × 10 −7 and 3.44 × 10−6, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (dual AMD 64-core 2.45 GHz Milan processors and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. By exploiting the underlying symmetries within the equation of state, these findings highlight the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations.

conservative-to-primitive conversion↗
NASA NTRS2019

Accelerated Simulation of Air Pollution Using NVIDIA RAPIDS

Atmospheric chemistry models are a central tool to study and forecast the impact of air pollution on the environment, vegetation, and human health. However, the numerical simulation of chemical kinetics is computationally expensive due to the stiffness of the system of ordinary differential equations that describes atmospheric chemistry. Here we present an alternative approach to the computation of atmospheric chemistry based on machine learning. Our training data set is produced using the NASA Goddard Earth Observing System (GEOS) model with GEOS-Chem chemistry, run on the NASA Center for Climate Simulation (NCCS) Discover supercomputing cluster on 384 Intel Xeon Haswell cores. This model spends more than 50% of total run time on solving atmospheric chemistry. The data set contains as input features the air pollution concentrations before solving the differential equations, together with some key physical parameters such as temperature and sun intensity. As target variables we define the air pollution concentrations after solving the differential equations. Using Dask-cuDF and Dask-XGBoost on the NVIDIA RAPIDS platform on 8 Tesla V100 GPUs, we generate from this training set gradient boosted decision tree models that can reproduce the simulation of chemical kinetics. We do this on the NCCS Advanced Data Analytics Platform (ADAPT) science cloud environment. Our application takes full advantage of recent advances in Dask-XGBoost, such as multi-node and multi-GPU scaling for distributed training with large data sets. The increase in training data size enabled by this is critical to capture the full range of chemical environments encountered across the globe and all annual seasons.The boosted tree models offer good predictability and show many of the features of the full chemistry reference simulation. Further improvements can be achieved through mass balance considerations and by accounting for error correlations. We incorporate the boosted tree models into the GEOS reference model using XGBoost's C API. This enables a seamless integration of the GPU trained models into GEOS-Chem, which is written in Fortran and optimized for use in a massively parallel CPU environment. We show the benefits of this approach and discuss the potential speedup of this machine learning accelerated atmospheric chemistry model.

Keller, Christoph A.↗
NASA NTRS1990

DSIM: A distributed simulator

Discrete event-driven simulation makes it possible to model a computer system in detail. However, such simulation models can require a significant time to execute. This is especially true when modeling large parallel or distributed systems containing many processors and a complex communication network. One solution is to distribute the simulation over several processors. If enough parallelism is achieved, large simulation models can be efficiently executed. This study proposes a distributed simulator called DSIM which can run on various architectures. A simulated test environment is used to verify and characterize the performance of DSIM. The results of the experiments indicate that speedup is application-dependent and, in DSIM's case, is also dependent on how the simulation model is distributed among the processors. Furthermore, the experiments reveal that the communication overhead of ethernet-based distributed systems makes it difficult to achieve reasonable speedup unless the simulation model is computation bound.

Goswami, Kumar K.↗
DOE OSTI2022

Reduced-Order Modeling Method for Phase-Change Thermal Energy Storage Heat Exchangers

Thermal energy storage can facilitate the effective utilization of renewable energy. To speed up the design process of thermal energy storage devices, it is critical to develop fast and accurate modeling methods for phase change material embedded heat exchangers (PCM HXs). This study developed and compared two approximation-assisted reduced-order PCM HX models for the simulation of thermal storage components and systems, which were verified against a validated finite-volume model. They are a pure black-box model, and a grey-box model based on the Number of Transfer Units (or effectiveness-NTU) approach. We used the reduced-order models to predict the performance of standalone PCM HX for 1000 cases with different fluid inlet conditions and HX designs. We also integrated the models with a vapor compression system to predict the compressor energy consumption and total charging time under various conditions. The results show that overall, the black-box model gave more accurate results than the grey-box model. On average, the mean absolute deviation in the PCM HX fluid outlet temperature was 0.05 K and 0.1 K for the black-box model and grey-box model, respectively. The grey-box model gave larger temperature deviation toward the end of the phase change process, due to the simplified two-node PCM representation. On the system level, the mean absolute deviation in compressor energy consumption was 0.2% and 0.3% for the black-box model and grey-box model, respectively. Their mean absolute deviation in total charging time was 1.1% and 2.6%, respectively. In terms of computation efficiency, the system simulation speedup ratio gained by using the reduced-order models was 11 to 57. System simulation time was decreased from an average of 1465 s to an average of 59 s. This shows that the proposed reduced-order modeling methods can be used to predict system performance of PCM HXs with less than 3% accuracy penalty, and 25 times less computational time than finite-volume models, enabling faster design and evaluation of PCM thermal storage devices.

25 ENERGY STORAGE↗
NASA NTRS2002

Opportunities for Breakthroughs in Large-Scale Computational Simulation and Design

Opportunities for breakthroughs in the large-scale computational simulation and design of aerospace vehicles are presented. Computational fluid dynamics tools to be used within multidisciplinary analysis and design methods are emphasized. The opportunities stem from speedups and robustness improvements in the underlying unit operations associated with simulation (geometry modeling, grid generation, physical modeling, analysis, etc.). Further, an improved programming environment can synergistically integrate these unit operations to leverage the gains. The speedups result from reducing the problem setup time through geometry modeling and grid generation operations, and reducing the solution time through the operation counts associated with solving the discretized equations to a sufficient accuracy. The opportunities are addressed only at a general level here, but an extensive list of references containing further details is included. The opportunities discussed are being addressed through the Fast Adaptive Aerospace Tools (FAAST) element of the Advanced Systems Concept to Test (ASCoT) and the third Generation Reusable Launch Vehicles (RLV) projects at NASA Langley Research Center. The overall goal is to enable greater inroads into the design process with large-scale simulations.

Alexandrov, Natalia↗