Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “accelerated computing”

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 1,405 records · Page 78
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Cathode to Target Simulations for Scorpius: I. Simulation Codes and Models

The new Scorpius linear induction electron accelerator is under development for multi-pulse flash radiography of large, explosively-driven hydrodynamic experiments. Beam physics from the cathode to the target was examined with computer simulations, including envelope, ray-trace, and particle-in cell (PIC) codes. Beam instabilities investigated included beam breakup (BBU), image displacement, diocotron, parametric envelope, ion hose, and the resistive wall instability. Beam corkscrew motion and emittance growth from beam mismatch were also studied. The results of these simulations is documented in a series of reports. In this report the computer codes and physical models used for these simulations are described. The conclusion of this study is that Scorpius will produce and accelerate a beam with radiographic quality equivalent to the present accelerators at Los Alamos National Laboratory if the same engineering standards and construction details are upheld.

43 PARTICLE ACCELERATORS↗
DOE OSTI2026

Parallel-in-Time Solution of Allen-Cahn Equations by Integrating Operator Learning into the Parareal Method

While recent advances in deep learning have shown promising efficiency gains in solving time-dependent partial differential equations (PDEs), matching the accuracy of conventional numerical solvers still remains a challenge. One strategy to improve the accuracy of deep learning-based solutions for time-dependent PDEs is to use the learned model as the coarse propagator in the Parareal method and a traditional numerical method as the fine solver. However, successful integration of deep learning into the Parareal method requires consistency between the coarse and fine solvers, particularly for PDEs exhibiting rapid changes such as sharp transitions. Here, to ensure this consistency, we propose using convolutional neural networks (CNNs) to learn the fully discrete time-stepping operator defined by the same numerical scheme employed as the fine solver. We demonstrate the effectiveness of the proposed method in solving the classical and mass-conservative Allen–Cahn (AC) equations. Through iterative updates in the Parareal algorithm, our approach achieves a significant computational speedup compared to traditional fine solvers while converging to high-accuracy solutions. Our results highlight that the proposed hybrid Parareal algorithm effectively accelerates simulations, particularly when implemented on multiple GPUs, and converges to the desired accuracy in only a few iterations. Another advantage of our method is that the CNN model is trained on trajectory-based data generated from random initial conditions, such that the trained model can be used to solve the AC equations with various initial conditions without retraining. This work demonstrates the potential of integrating neural network methods into parallel-in-time frameworks for efficient and accurate simulations of time-dependent PDEs.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2000

Acceleration of the Fast Solar Wind by Solitary Waves in Coronal Holes

The purpose of this investigation is to develop a new model for the acceleration of the fast solar wind by nonlinear, time-dependent multidimensional MHD simulations of waves in solar coronal holes. Preliminary computational studies indicate that solitary-like waves are generated in coronal holes nonlinearly by torsional Alfven waves. These waves in addition to thermal conduction may contribute considerably to the accelerate the solar wind. Specific goals of this proposal are to investigate the generation of nonlinear solitary-like waves and their effect on solar wind acceleration by numerical 2.5D MHD simulation of coronal holes with a broad range of plasma and wave parameters; to study the effect of random disturbances at the base of a solar coronal hole on the fast solar wind acceleration with a more advanced 2.5D MHD model and to compare the results with the available observations; to extend the study to a full 3D MHD simulation of fast solar wind acceleration with a more realistic model of a coronal hole and solar boundary conditions. The ultimate goal of the three year study is to model the fast solar wind in a coronal hole, based on realistic boundary conditions in a coronal hole near the Sun, and the coronal hole structure (i.e., density, temperature, and magnetic field geometry) that will become available from the recently launched SOHO spacecraft.

Ofman, Leon↗
DOE OSTI2023

Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware

In-memory computing with emerging non-volatile memory devices (eNVMs) has shown promising results in accelerating matrix-vector multiplications. However, activation function calculations are still being implemented with general processors or large and complex neuron peripheral circuits. Here, we present the integration of Ag-based conductive bridge random access memory (Ag-CBRAM) crossbar arrays with Mott rectified linear unit (ReLU) activation neurons for scalable, energy and area-efficient hardware (HW) implementation of deep neural networks. We develop Ag-CBRAM devices that can achieve a high ON/OFF ratio and multi-level programmability. Compact and energy-efficient Mott ReLU neuron devices implementing ReLU activation function are directly connected to the columns of Ag-CBRAM crossbars to compute the output from the weighted sum current. We implement convolution filters and activations for VGG-16 using our integrated HW and demonstrate the successful generation of feature maps for CIFAR-10 images in HW. Our approach paves a new way toward building a highly compact and energy-efficient eNVMs-based in-memory computing system.

Mott insulators↗
DOE OSTI2025

Bayesian Calibration of Stochastic Agent Based Model via Random Forest

Agent-based models (ABM) provide an excellent framework for modeling outbreaks and interventions in epidemiology by explicitly accounting for diverse individual interactions and environments. However, these models are usually stochastic and highly parametrized, requiring precise calibration for predictive performance. When considering realistic numbers of agents and properly accounting for stochasticity, this high-dimensional calibration can be computationally prohibitive. This paper presents a random forest-based surrogate modeling technique to accelerate the evaluation of ABMs and demonstrates its use to calibrate an epidemiological ABM named CityCOVID via Markov chain Monte Carlo (MCMC). The technique is first outlined in the context of CityCOVID's quantities of interest, namely hospitalizations and deaths, by exploring dimensionality reduction via temporal decomposition with principal component analysis (PCA) and via sensitivity analysis. The calibration problem is then presented, and samples are generated to best match COVID-19 hospitalization and death numbers in Chicago from March to June in 2020. Further, these results are compared with previous approximate Bayesian calibration (IMABC) results, and their predictive performance is analyzed, showing improved performance with a reduction in computation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Can exascale computing and explainable artificial intelligence applied to plant biology deliver on the United Nations sustainable development goals?

Human population growth and accelerated climate change necessitate agricultural improvements using designer crop ideotypes (idealized plants that can grow in niche environments). Diverse and highly skilled research groups must integrate efforts to bridge the gaps needed to achieve international goals toward sustainable agriculture. Given the scale of global agricultural needs and the breadth of multiple types of omics data needed to optimize these efforts, explainable artificial intelligence (AI with a decipherable decision making process that provides a meaningful explanation to humans) and exascale computing (computers that can perform 1018 floating-point operations per second, or exaflops) are crucial. Accurate phenotyping and daily-resolution climatype associations are equally important for refining ideotype production to specific environments at various levels of granularity. In this article, we review advances toward tackling technological hurdles to solve multiple United Nations Sustainable Development Goals and discuss a vision to overcome gaps between research and policy.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Iterative methods in GPU-resident linear solvers for nonlinear constrained optimization

Linear solvers are major computational bottlenecks in a wide range of decision support and optimization computations. The challenges become even more pronounced on heterogeneous hardware, where traditional sparse numerical linear algebra methods are often inefficient. For example, methods for solving ill-conditioned linear systems have relied on conditional branching, which degrades performance on hardware accelerators such as graphical processing units (GPUs). To improve the efficiency of solving ill-conditioned systems, our computational strategy separates computations that are efficient on GPUs from those that need to run on traditional central processing units (CPUs). Our strategy maximizes the reuse of expensive CPU computations. Iterative methods, which thus far have not been broadly used for ill-conditioned linear systems, play an important role in our approach. In particular, we extend ideas from Arioli et al., (2007) to implement iterative refinement using inexact LU factors and flexible generalized minimal residual (FGMRES), with the aim of efficient performance on GPUs. In conclusion, we focus on solutions that are effective within broader application contexts, and discuss how early performance tests could be improved to be more predictive of the performance in a realistic environment.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2012

On Shaft Data Acquisition System (OSDAS)

On Shaft Data Acquisition System (OSDAS) is a rugged, compact, multiple-channel data acquisition computer system that is designed to record data from instrumentation while operating under extreme rotational centrifugal or gravitational acceleration forces. This system, which was developed for the Heritage Fuel Air Turbine Test (HFATT) program, addresses the problem of recording multiple channels of high-sample-rate data on most any rotating test article by mounting the entire acquisition computer onboard with the turbine test article. With the limited availability of slip ring wires for power and communication, OSDAS utilizes its own resources to provide independent power and amplification for each instrument. Since OSDAS utilizes standard PC technology as well as shared code interfaces with the next-generation, real-time health monitoring system (SPARTAA Scalable Parallel Architecture for Real Time Analysis and Acquisition), this system could be expanded beyond its current capabilities, such as providing advanced health monitoring capabilities for the test article. High-conductor-count slip rings are expensive to purchase and maintain, yet only provide a limited number of conductors for routing instrumentation off the article and to a stationary data acquisition system. In addition to being limited to a small number of instruments, slip rings are prone to wear quickly, and introduce noise and other undesirable characteristics to the signal data. This led to the development of a system capable of recording high-density instrumentation, at high sample rates, on the test article itself, all while under extreme rotational stress. OSDAS is a fully functional PC-based system with 48 channels of 24-bit, high-sample-rate input channels, phase synchronized, with an onboard storage capacity of over 1/2-terabyte of solid-state storage. This recording system takes a novel approach to the problem of recording multiple channels of instrumentation, integrated with the test article itself, packaged in a compact/rugged form factor, consuming limited power, all while rotating at high turbine speeds.

Pedings, Marc↗
DOE OSTI2024

Accelerated Constrained Sparse Tensor Factorization on Massively Parallel Architectures

This study presents the first constrained sparse tensor factorization (cSTF) framework that optimizes and fully offloads computation to massively parallel GPU architectures, and the first performance characterization of cSTF on GPU architectures. In contrast to prior work on tensor factorization, where the matricized tensor times Khatri-Rao product (MTTKRP) is the primary performance bottleneck, our systematic analysis of the cSTF algorithm on GPUs reveals that adding constraints creates an additional bottleneck in the update operation for many real-world sparse tensors. While executing the update operation on the GPU brings significant speedup over its CPU counterpart, it remains a significant bottleneck. To further accelerate the update operation, we propose cuADMM, a new update algorithm that leverages algorithmic and code optimization strategies to minimize both computation and data movement on GPUs. As a result, our framework delivers significantly improved performance compared to prior state-of-the-art. On 10 real-world sparse tensors, our framework achieves geometric mean speedup of 5.1 × (max 41.59 ×) and 7.01 × (max 58.05 ×) on the NIVIDA A100 and H100 GPUs, respectively, over the state-of-the-art SPLATT library running on a 26-core Intel Ice Lake Xeon CPU.

Soh, Yongseok↗
NASA NTRS1975

Man-Computer Interactive Data Access System (McIDAS). Continued development of McIDAS and operation in the GARP Atlantic tropical experiment

The complete output of the Synchronous Meteorological Satellite was recorded on one inch magnetic tape. A quality control subsystem tests cloud track vectors against four sets of criteria: (1) rejection if best match occurs on correlation boundary; (2) rejection if major correlation peak is not distinct and significantly greater than secondary peak; (3) rejection if correlation is not persistent; and (4) rejection if acceleration is too great. A cloud height program determines cloud optical thickness from visible data and computer infrared emissivity. From infrared data and temperature profile, cloud height is determined. A functional description and electronic schematics of equipment are given.

Suomi, V. E.↗
DOE OSTI2025

SA-GAT-SR: self-adaptable graph attention networks with symbolic regression for high-fidelity material property prediction

Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These methods have emerged as powerful tools for high-throughput prediction of material properties, offering a compelling enhancement and alternative to traditional first-principles calculations. While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy, such approaches often lack physical interpretability and insights into materials behavior. Here, we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression (SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression. Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintaining O(n) computational scaling. The integrated SR module subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships, achieving 23 × acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input. This work suggests a new framework in computational materials science, bridging the gap between predictive accuracy and physical interpretability, offering valuable physical insights into material behavior.

36 MATERIALS SCIENCE↗
NASA NTRS2003

Accelerating the Design of Space Vehicles

One of NASA's key goals is to increase the safety and reduce the cost of space transportation. Thus, a key element of NASA's new Integrated Space Transportation Plan is to develop new propulsion, structures, and operations for future generations of reusable launch vehicles (RLVs). As part of this effort to develop the next RLV, the ClCT Program's Computing, Networking, and Information Systems (CNIS) Project is developing and demonstrating collaborative software technologies that use the collective power of the NASA Grid to accelerate spacecraft design. One of these technologies, called AeroDB, automates the execution and monitoring of computational fluid dynamics (CFD) parameter studies on the NASA Grid. About the NASA Grid The NASA Grid, or Information Power Grid,. is being developed to leverage the distributed resources of NASA's many computers. instruments, simulators, and data storage systems. The goal is to use these combined resources to sdve difficult NASA challenges, such as iimulating the entire flight of a space vehicle from ascent to descent.To realize the vision of the NASA Grid, the CNIS Project is developing the software framework and protocols for building domain-specific environments and interfaces, new Grid services based on emerging industry standards, and advanced networking and computing testbeds to support new Grid-based applications such as AeroDB.

Laufenberg, Larry↗
NASA NTRS1989

Convergence acceleration of viscous and inviscid hypersonic flow calculations

The convergence of inviscid and viscous hypersonic flow calculations using a two-dimensional flux-splitting code is accelerated by applying a Richardson-type overrelaxation method. Successful results are presented for various cases; and a 50 percent savings in computer time is usually achieved. An analytical formula for the overrelaxation factor is derived, and the performance of this scheme is confirmed numerically. Moreover, application of this overrelaxation scheme produces a favorable preconditioning for Wynn's epsilon-algorithm. Both techniques have been extended to viscous three-dimensional flows and applied to accelerate the convergence of the compressible Navier-Stokes code. A savings of 40 percent in computer time is achieved in this case.

Cheer, A.↗
DOE OSTI2025

Design-to-Deployment Continuum Platform for Microscopes and Computing Ecosystems

Science ecosystems with networked computing systems and physical instruments are increasingly being deployed with a goal to achieve the productivity promised by AI-supported remote automation. In support of these efforts, the virtual infrastructure twins (VITs) have been successfully utilized to develop the orchestration codes for these ecosystems without requiring physical access to expensive instruments, such as electron microscopes. Currently, the utility of such a VIT is severely limited by the computing capacity and capability of the computing system used as its host. Furthermore, codes developed on the VIT typically need to be transferred and refactored for production use, particularly, on high-performance systems with accelerators. In response, we develop a design-to-deployment continuum platform wherein a VIT runs natively on the ecosystem's own computing system, and thereby facilitates the continual in-situ testing and transition of codes for production use. Here, we describe the development and testing of software for remote microscope steering and GPU-based image reconstruction using this platform on a multi-GPU computing system networked to Nion microscopes. We demonstrate a continual transition of steering and reconstruction codes developed under VIT platform to production ecosystem deployment.

Al-Najjar, Anees [Oak Ridge National Laboratory (O↗
NASA NTRS1995

Dynamic analysis of astronaut motions in microgravity: Applications for Extravehicular Activity (EVA)

Simulations of astronaut motions during extravehicular activity (EVA) tasks were performed using computational multibody dynamics methods. The application of computational dynamic simulation to EVA was prompted by the realization that physical microgravity simulators have inherent limitations: viscosity in neutral buoyancy tanks; friction in air bearing floors; short duration for parabolic aircraft; and inertia and friction in suspension mechanisms. These limitations can mask critical dynamic effects that later cause problems during actual EVA's performed in space. Methods of formulating dynamic equations of motion for multibody systems are discussed with emphasis on Kane's method, which forms the basis of the simulations presented herein. Formulation of the equations of motion for a two degree of freedom arm is presented as an explicit example. The four basic steps in creating the computational simulations were: system description, in which the geometry, mass properties, and interconnection of system bodies are input to the computer; equation formulation based on the system description; inverse kinematics, in which the angles, velocities, and accelerations of joints are calculated for prescribed motion of the endpoint (hand) of the arm; and inverse dynamics, in which joint torques are calculated for a prescribed motion. A graphical animation and data plotting program, EVADS (EVA Dynamics Simulation), was developed and used to analyze the results of the simulations that were performed on a Silicon Graphics Indigo2 computer. EVA tasks involving manipulation of the Spartan 204 free flying astronomy payload, as performed during Space Shuttle mission STS-63 (February 1995), served as the subject for two dynamic simulations. An EVA crewmember was modeled as a seven segment system with an eighth segment representing the massive payload attached to the hand. For both simulations, the initial configuration of the lower body (trunk, upper leg, and lower leg) was a neutral microgravity posture. In the first simulation, the payload was manipulated around a circular trajectory of 0.15 m radius in 10 seconds. It was found that the wrist joint theoretically exceeded its ulnal deviation limit by as much as 49. 8 deg and was required to exert torques as high as 26 N-m to accomplish the task, well in excess of the wrist physiological limit of 12 N-m. The largest torque in the first simulation, 52 N-m, occurred in the ankle joint. To avoid these problems, the second simulation placed the arm in a more comfortable initial position and the radius and speed of the circular trajectory were reduced by half. As a result, the joint angles and torques were reduced to values well within their physiological limits. In particular, the maximum wrist torque for the second simulation was only 3 N-m and the maximum ankle torque was only 6 N-m.

Newman, Dava J.↗
DOE OSTI2025

Accelerating multilevel Markov Chain Monte Carlo using machine learning models

Here, this work presents an efficient approach for accelerating multilevel Markov Chain Monte Carlo (MCMC) sampling for large-scale problems using low-fidelity machine learning models. While conventional techniques for large-scale Bayesian inference often substitute computationally expensive high-fidelity models with machine learning models, thereby introducing approximation errors, our approach offers a computationally efficient alternative by augmenting high-fidelity models with low-fidelity ones within a hierarchical framework. The multilevel approach utilizes the low-fidelity machine learning model (MLM) for inexpensive evaluation of proposed samples thereby improving the acceptance of samples by the high-fidelity model. The hierarchy in our multilevel algorithm is derived from geometric multigrid hierarchy. We utilize an MLM to accelerate the coarse level sampling. Training machine learning model for the coarsest level significantly reduces the computational cost associated with generating training data and training the model. We present an MCMC algorithm to accelerate the coarsest level sampling using MLM and account for the approximation error introduced. We provide theoretical proofs of detailed balance and demonstrate that our multilevel approach constitutes a consistent MCMC algorithm. Additionally, we derive the expression for cost reduction due to machine learning model to facilitate cost analysis of the hierarchical sampling algorithm. Our technique is demonstrated on a standard benchmark inference problem in groundwater flow, where we estimate the probability density of a quantity of interest using a four-level MCMC algorithm. Our proposed algorithm accelerates multilevel sampling by a factor of two while achieving similar accuracy compared to sampling using the standard multilevel algorithm.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1992

An installed nacelle design code using a multiblock Euler solver. Volume 1: Theory document

An efficient multiblock Euler design code was developed for designing a nacelle installed on geometrically complex airplane configurations. This approach employed a design driver based on a direct iterative surface curvature method developed at LaRC. A general multiblock Euler flow solver was used for computing flow around complex geometries. The flow solver used a finite-volume formulation with explicit time-stepping to solve the Euler Equations. It used a multiblock version of the multigrid method to accelerate the convergence of the calculations. The design driver successively updated the surface geometry to reduce the difference between the computed and target pressure distributions. In the flow solver, the change in surface geometry was simulated by applying surface transpiration boundary conditions to avoid repeated grid generation during design iterations. Smoothness of the designed surface was ensured by alternate application of streamwise and circumferential smoothings. The capability and efficiency of the code was demonstrated through the design of both an isolated nacelle and an installed nacelle at various flow conditions. Information on the execution of the computer program is provided in volume 2.

Chen, H. C.↗
NASA NTRS1993

An installed nacelle design method using multiblock Euler solver

An efficient multiblock Euler design method was developed for designing a nacelle installed on geometrically complex airplane configurations. This approach employed a design module based on a direct iterative surface curvature method developed at NASA-Langley. A multiblock Euler flow solver was used for computing flow around complex geometries. The flow solver used a finite-volume formulation with explicit time-stepping to solve the Euler equations. It used a multiblock version of the multigrid method to accelerate the convergence of the calculations. The design module successively updated the surface geometry to reduce the difference between the computed and target pressure distributions. In the flow solver, the change in surface geometry was simulated by applying surface transpiration boundary conditions to avoid repeated grid generation during design iterations. Smoothness of the designed surface was ensured by alternate application of streamwise and circumferential smoothings.

Chen, H. C.↗