Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computer system benchmarking”

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 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Fast and robust all-electron density functional theory calculations in solids using orthogonalized enriched finite elements

Here, we present a computationally efficient approach to perform systematically convergent real-space all-electron Kohn-Sham density functional theory calculations for solids using an enriched finite element (FE) basis. The enriched FE basis is constructed by augmenting the classical FE basis with atom-centered numerical basis functions, comprising of atomic solutions to the Kohn-Sham problem. Notably, to improve the conditioning, we orthogonalize the enrichment functions with respect to the classical FE basis, without sacrificing the locality of the resultant basis. In addition to improved conditioning, this orthogonalization procedure also renders the overlap matrix block diagonal, greatly simplifying its inversion. Subsequently, we use a Chebyshev polynomial based filtering technique to efficiently compute the occupied eigenspace in each self-consistent field iteration. We demonstrate the accuracy and efficiency of the proposed approach on periodic unit cells and supercells. The benchmark studies show a staggering 130× speedup of the orthogonalized enriched FE basis over the classical FE basis. We also present a comparison of the orthogonalized enriched FE basis with the linearized augmented plane-wave + local orbitals basis, both in terms of accuracy and efficiency. Notably, we demonstrate that the orthogonalized enriched FE basis can handle large system sizes of ~10 000 electrons. Finally, we observe good parallel scalability of our implementation with 92% efficiency at 22× speedup for a system with 620 electrons

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

Efficient Learning of Accurate Surrogates for Simulations of Complex Systems

Machine learning methods are increasingly deployed to construct surrogate models for complex physical systems at a reduced computational cost. However, the predictive capability of these surrogates degrades in the presence of noisy, sparse, or dynamic data. We introduce an online learning method empowered by optimizer-driven sampling that has two advantages over current approaches: it ensures that all local extrema (including endpoints) of the model response surface are included in the training data and it employs a continuous validation and update process in which surrogates undergo retraining when their performance falls below a validity threshold. We find, using benchmark functions, that optimizer-directed sampling generally outperforms traditional sampling methods in terms of accuracy around local extrema even when the scoring metric is biased towards assessing overall accuracy. Finally, the application to dense nuclear matter demonstrates that highly accurate surrogates for a nuclear equation of state model can be reliably auto-generated from expensive calculations using few model evaluations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Wilkins: HPC in situ workflows made easy

In situ approaches can accelerate the pace of scientific discoveries by allowing scientists to perform data analysis at simulation time. Current in situ workflow systems, however, face challenges in handling the growing complexity and diverse computational requirements of scientific tasks. In this work, we present Wilkins, an in situ workflow system that is designed for ease-of-use while providing scalable and efficient execution of workflow tasks. Wilkins provides a flexible workflow description interface, employs a high-performance data transport layer based on HDF5, and supports tasks with disparate data rates by providing a flow control mechanism. Wilkins seamlessly couples scientific tasks that already use HDF5, without requiring task code modifications. We demonstrate the above features using both synthetic benchmarks and two science use cases in materials science and cosmology.

HPC↗
NASA NTRS1993

Efficiently modeling neural networks on massively parallel computers

Neural networks are a very useful tool for analyzing and modeling complex real world systems. Applying neural network simulations to real world problems generally involves large amounts of data and massive amounts of computation. To efficiently handle the computational requirements of large problems, we have implemented at Los Alamos a highly efficient neural network compiler for serial computers, vector computers, vector parallel computers, and fine grain SIMD computers such as the CM-2 connection machine. This paper describes the mapping used by the compiler to implement feed-forward backpropagation neural networks for a SIMD (Single Instruction Multiple Data) architecture parallel computer. Thinking Machines Corporation has benchmarked our code at 1.3 billion interconnects per second (approximately 3 gigaflops) on a 64,000 processor CM-2 connection machine (Singer 1990). This mapping is applicable to other SIMD computers and can be implemented on MIMD computers such as the CM-5 connection machine. Our mapping has virtually no communications overhead with the exception of the communications required for a global summation across the processors (which has a sub-linear runtime growth on the order of O(log(number of processors)). We can efficiently model very large neural networks which have many neurons and interconnects and our mapping can extend to arbitrarily large networks (within memory limitations) by merging the memory space of separate processors with fast adjacent processor interprocessor communications. This paper will consider the simulation of only feed forward neural network although this method is extendable to recurrent networks.

Farber, Robert M.↗
DOE OSTI2024

Efficient learning of accurate surrogates for simulations of complex systems

Machine learning methods are increasingly deployed to construct surrogate models for complex physical systems at a reduced computational cost. However, the predictive capability of these surrogates degrades in the presence of noisy, sparse or dynamic data. Here, we introduce an online learning method empowered by optimizer-driven sampling that has two advantages over current approaches: it ensures that all local extrema (including endpoints) of the model response surface are included in the training data, and it employs a continuous validation and update process in which surrogates undergo retraining when their performance falls below a validity threshold. We find, using benchmark functions, that optimizer-directed sampling generally outperforms traditional sampling methods in terms of accuracy around local extrema even when the scoring metric is biased towards assessing overall accuracy. Finally, the application to dense nuclear matter demonstrates that highly accurate surrogates for a nuclear equation-of-state model can be reliably autogenerated from expensive calculations using few model evaluations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

PyCMG-based Simulation of Volumetric Concrete Microstructure

Concrete is a complex, heterogeneous material with a microstructure composed of aggregates, cement paste, and pores spanning multiple length scales. Understanding this microstructure is critical for advancing the performance, durability, and modeling of concrete-based systems. While experimental imaging such as X-ray computed tomography (XCT) provides valuable insights, generating large datasets with detailed ground truth annotations is both costly and labor-intensive due to challenges in segmenting similar phases, such as aggregates and cement paste, that often share similar attenuation properties. To address this, we developed a pipeline to simulate realistic 3D concrete microstructures using the open-source Python package PyCMG. This simulation effort focuses on generating high-fidelity, annotated microstructures that can serve as training or benchmarking datasets for image analysis, segmentation algorithms, and machine learning models, particularly in scenarios where experimental data is scarce.

Ziabari, Amir [Oak Ridge National Laboratory; ORNL↗
DOE OSTI2020

Computing Bottleneck Structures at Scale for High-Precision Network Performance Analysis

The Theory of Bottleneck Structures is a recently-developed framework for studying the performance of data networks. It describes how local perturbations in one part of the network propagate and interact with others. This framework is a powerful analytical tool that allows network operators to make accurate predictions about network behavior and thereby optimize performance. Previous work implemented a software package for bottleneck structure analysis, but applied it only to toy examples. In this work, we introduce the first software package capable of scaling bottleneck structure analysis to production-size networks. Here, we benchmark our system using logs from ESnet, the Department of Energy's high-performance data network that connects research institutions in the U.S. Using the previously published tool as a baseline, we demonstrate that our system achieves vastly improved performance, constructing the bottleneck structure graphs in 0.21 s and calculating link derivatives in 0.09 s on average. We also study the asymptotic complexity of our core algorithms, demonstrating good scaling properties and strong agreement with theoretical bounds. These results indicate that our new software package can maintain its fast performance when applied to even larger networks. They also show that our software is efficient enough to analyze rapidly changing networks in real time. Overall, we demonstrate the feasibility of applying bottleneck structure analysis to solve practical problems in large, real-world data networks.

benchmark↗
DOE OSTI2022

Nuclide inventory validation: radiochemical assay data quality and modeling challenges in benchmark models development

Oak Ridge National Laboratory is conducting radiochemical assay experiments, using high-precision analytical protocols validated with a comprehensive quality assurance plan, to expand the nuclide inventory validation basis for high burnup spent nuclear fuel. Preliminary measurement data for key actinides and fission products in two pressurized water reactor spent fuel samples are being used to investigate the impact of measurement data uncertainty on the sample burnup estimation. These measurement data are also being used to examine the impact of assumptions applied when developing best-estimate computational models to simulate fuel irradiation history. The simulations are being performed using depletion capabilities in the SCALE code system. Comparison of calculated and measured nuclide concentrations shows good agreement for the considered nuclides. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Pseudospectral convex optimization for on-ramp merging control of connected vehicles

It can be a daunting task for human drivers to merge into highways because of the intricate vehicle negotiations and potential risk within limited time and space. Connected vehicle (CV) technologies could be a solution to this problem and offer many benefits to the road safety, traffic mobility, and energy efficiency. However, real-time optimal control of CVs is still an open challenge, due to the nonlinear vehicle dynamics, non-convex fuel consumption model, and highly dynamic uncertain inter-vehicle interactions. To tackle these issues, a novel real-time optimal control approach that balances the computational efficiency and solution optimality is proposed for the purpose of onboard application. To this end, the pseudospectral collocation method is integrated with a sequential convex programming approach to develop two new optimization algorithms, which are implemented within a model predictive control (MPC) framework to allow for real-time generation of optimal merging speed profiles. One algorithm leverages the line search technique to improve convergence, and the other benefits from the trust region method for better computational efficiency. The optimality and convergence process of both proposed algorithms are investigated by comparing their solutions with a popular non-linear solver. Furthermore, simulation results show that the proposed methods outperform the benchmark in terms of computational cost, fuel consumption, and traffic efficiency. In particular, the proposed fuel-economy merging rule can save 57.1% fuel consumption on average on four different traffic volumes. Meanwhile, the proposed optimal control algorithms can reduce 2.2% travel time on average comparing to the “first-in-first-out” merging rule.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

A parallel-kinetic-perpendicular-moment model for magnetised plasmas

We describe a new model for the study of weakly collisional, magnetised plasmas derived from exploiting the separation of the dynamics parallel and perpendicular to the magnetic field. This unique system of equations retains the particle dynamics parallel to the magnetic field while approximating the perpendicular dynamics through a spectral expansion in the perpendicular degrees of freedom, analogous to moment-based fluid approaches. In so doing, a hybrid approach is obtained that is computationally efficient enough to allow for larger-scale modelling of plasma systems while eliminating a source of difficulty in deriving fluid equations applicable to magnetised plasmas. We connect this system of equations to historical asymptotic models and discuss advantages and disadvantages of this approach, including the extension of this parallel-kinetic-perpendicular moment beyond the typical region of validity of these more traditional asymptotic models. This paper forms the first of a multi-part series on this new model, covering the theory and derivation, alongside demonstration benchmarks of this approach that include shocks and magnetic reconnection.

astrophysical plasmas↗
DOE OSTI2021

Reduced Complexity Model Intercomparison Project Phase 2: Synthesizing Earth System Knowledge for Probabilistic Climate Projections

Abstract Over the last decades, climate science has evolved rapidly across multiple expert domains. Our best tools to capture state‐of‐the‐art knowledge in an internally self‐consistent modeling framework are the increasingly complex fully coupled Earth System Models (ESMs). However, computational limitations and the structural rigidity of ESMs mean that the full range of uncertainties across multiple domains are difficult to capture with ESMs alone. The tools of choice are instead more computationally efficient reduced complexity models (RCMs), which are structurally flexible and can span the response dynamics across a range of domain‐specific models and ESM experiments. Here we present Phase 2 of the Reduced Complexity Model Intercomparison Project (RCMIP Phase 2), the first comprehensive intercomparison of RCMs that are probabilistically calibrated with key benchmark ranges from specialized research communities. Unsurprisingly, but crucially, we find that models which have been constrained to reflect the key benchmarks better reflect the key benchmarks. Under the low‐emissions SSP1‐1.9 scenario, across the RCMs, median peak warming projections range from 1.3 to 1.7°C (relative to 1850–1900, using an observationally based historical warming estimate of 0.8°C between 1850–1900 and 1995–2014). Further developing methodologies to constrain these projection uncertainties seems paramount given the international community's goal to contain warming to below 1.5°C above preindustrial in the long‐term. Our findings suggest that users of RCMs should carefully evaluate their RCM, specifically its skill against key benchmarks and consider the need to include projections benchmarks either from ESM results or other assessments to reduce divergence in future projections.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Logic in Memory Emulator

Logic in Memory Emulator (LiME) is a hardware/software tool specially designed for memory system evaluation and experiment. Emerging memories display a wide range of bandwidths, latencies, and capacities, making it challenging for the computer architect to navigate the design space of potential memory configurations, and for the application developer to assess performance implications of using such memories. With the LiME framework, architectural ideas can be prototyped in great detail yet with sufficient performance to support realistic evaluation on long running applications. LiME consists of two fundamental components: 1) the hardware and OS infrastructure for the emulator, and 2) a suite of benchmark applications to assist in characterizing the performance of current and future computer architectures. Some of the applications have been collected from other open source projects. Uses: Logging, replay and analysis of an application's memory behavior Evaluate impact of emerging memory technology on application performance. Emulate complex memory interactions in whole applications orders of magnitude faster than software simulation. Emulate acceleration hardware co-located with the memory subsystem. Features: Capture and log external memory accesses to a separate off-chip memory device without affecting application execution. Memory traces include the address, length, timestamp, and optionally the data for each transaction. Captured trace data can be saved to an SD card for off-line analysis. Configure a wide range of memory latencies in sub-nanosecond increments that encompass highbandwidth and storage class memories. Specify regions of interest (ROI) in applications to reduce the amount of trace data captured for analysis. Currently supports execution on Xilinx Zynq SoC which integrates an ARM processor with FPGA logic on a single device. Applications can be run under Linux or in bare metal mode on the ARM cores.

Jain, AbhishekK↗
DOE OSTI2024

Forward variable selection enables fast and accurate dynamic system identification with Karhunen-Loève decomposed Gaussian processes

A promising approach for scalable Gaussian processes (GPs) is the Karhunen-Loève (KL) decomposition, in which the GP kernel is represented by a set of basis functions which are the eigenfunctions of the kernel operator. Such decomposed kernels have the potential to be very fast, and do not depend on the selection of a reduced set of inducing points. However KL decompositions lead to high dimensionality, and variable selection thus becomes paramount. This paper reports a new method of forward variable selection, enabled by the ordered nature of the basis functions in the KL expansion of the Bayesian Smoothing Spline ANOVA kernel (BSS-ANOVA), coupled with fast Gibbs sampling in a fully Bayesian approach. It quickly and effectively limits the number of terms, yielding a method with competitive accuracies, training and inference times for tabular datasets of low feature set dimensionality. Theoretical computational complexities are O ( N P 2 ) in training and O ( P ) per point in inference, where N is the number of instances and P the number of expansion terms. The inference speed and accuracy makes the method especially useful for dynamic systems identification, by modeling the dynamics in the tangent space as a static problem, then integrating the learned dynamics using a high-order scheme. The methods are demonstrated on two dynamic datasets: a ‘Susceptible, Infected, Recovered’ (SIR) toy problem, along with the experimental ‘Cascaded Tanks’ benchmark dataset. Comparisons on the static prediction of time derivatives are made with a random forest (RF), a residual neural network (ResNet), and the Orthogonal Additive Kernel (OAK) inducing points scalable GP, while for the timeseries prediction comparisons are made with LSTM and GRU recurrent neural networks (RNNs) along with the SINDy package.

Hayes, Kyle↗
NASA NTRS1996

I/O-Efficient Scientific Computation Using TPIE

In recent years, input/output (I/O)-efficient algorithms for a wide variety of problems have appeared in the literature. However, systems specifically designed to assist programmers in implementing such algorithms have remained scarce. TPIE is a system designed to support I/O-efficient paradigms for problems from a variety of domains, including computational geometry, graph algorithms, and scientific computation. The TPIE interface frees programmers from having to deal not only with explicit read and write calls, but also the complex memory management that must be performed for I/O-efficient computation. In this paper we discuss applications of TPIE to problems in scientific computation. We discuss algorithmic issues underlying the design and implementation of the relevant components of TPIE and present performance results of programs written to solve a series of benchmark problems using our current TPIE prototype. Some of the benchmarks we present are based on the NAS parallel benchmarks while others are of our own creation. We demonstrate that the central processing unit (CPU) overhead required to manage I/O is small and that even with just a single disk, the I/O overhead of I/O-efficient computation ranges from negligible to the same order of magnitude as CPU time. We conjecture that if we use a number of disks in parallel this overhead can be all but eliminated.

Vengroff, Darren Erik↗
DOE OSTI2023

Assessment of Sodium Thermal Stratification Models Utilizing the TSTF Benchmark

As a result of certain transient scenarios, a thermally stratified layer of liquid sodium can develop in the bulk coolant volumes of a sodium-cooled fast reactor (SFR). In addition to the effects a stratification layer has on the temperature of the heat transport system, a stratification layer can also influence the transition to and establishment of natural circulation flow, which plays an important role in passive cooling and the inherent safety of a pool-type SFR. Therefore, the ability to accurately capture thermal stratification phenomena is important when demonstrating the safety basis of a pool-type SFR during transient sequences. The present work assesses various computational models with different fidelities in their ability to predict thermal stratification in the upper plenum of an SFR. Each computational model will be assessed using the data generated at the Thermal Stratification Test Facility (TSTF) located at the University of Wisconsin-Madison. Using measured flow rate and inlet temperature data, the measured temperature distributions of the tests are compared to the predictions of the lumped volume-based models in SAS4A/SASSYS-1, a 1D-based model in SAM, and a 3-D computational fluid dynamics (CFD) model using STAR-CCM+. The relative performance of the various computational methods is assessed with respect to key metrics such as bulk coolant temperature distribution and plenum exit temperature. A total of eight tests are analyzed, covering different combinations of flow rates (3 and 10 GPM) and upper internal structure (UIS) configurations (none, solid, porous, and open) The perfect mixing model of SAS4A/SASSYS-1 provides the highest accuracy when the flow rate is high and there is no UIS in the test vessel, as high flow rate injection promotes thermal mixing of the sodium in the test vessel. For most of the analyzed tests, the stratified volume model of SAS4A/SASSYS-1 is able to predict the delay in the outlet temperature drop and temperature distribution in the test vessel by a small number of layers to represent thermal stratification. However, the stratified volume model can only simulate a maximum of three temperature layers within a volume and when a layer approaches the elevation of the outlet, the predicted outlet temperature can demonstrate rapid, non-physical changes. The 1-D axial mixing model of SAM provides results that agree reasonably well with the measured data in the prediction of the temporal evolution of the outlet temperature with the exception of the case with a high flow rate and no UIS. The SAM 1-D model has a similar level of accuracy to CFD results when it comes to predicting the outlet temperature. CFD shows overall good agreement in predicting the temperature distribution in the test vessel and outlet temperature. As CFD can model the test vessel geometry in detail, it performs well in the cases of complex geometries such as tests that included a UIS and internal flow through the UIS resulting in active mixing of the coolant in the test vessel. Each of the models discussed in the present work has the potential to be useful during the various stages of reactor design, analysis, and licensing. The lumped-volume approach can be applied for fast turnaround safety calculations to obtain overall reactor behavior during transients. The 1-D models provide improved accuracy when stratification is expected for a relatively low increase in the computational cost. The CFD model can be utilized for confirmatory analysis of the 1-D model, when experimental measurements are not available.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

A physics-informed multi-agents model to predict thermo-oxidative/hydrolytic aging of elastomers

This paper introduces a novel physics-informed multi-agents constitutive model to propose prediction in quasi-static constitutive behavior of cross-linked elastomer and the loss of mechanical performance during environmental aging. The presented model is used to simulate the effect of single-mechanism chemical aging (i.e. thermal-inducedor hydrolytic aging) on the behavior of the material in this hybrid framework. Those environmental single-mechanism damages change the polymer matrix over time due to massive chain scission, chain formations, and changing the arrangement of molecules in the polymer matrix. Here we propose a data-driven super-constrained machine-learned engine to represent damage in the polymer matrix and capture the changes in material behavior, including its inelastic features such as Mullins effect and permanent set in the course of aging. We have simplified the 3D stress–strain tensor mapping problem into a small number of super-constrained 1D mapping problems by means of a sequential order reduction. An assembly of multiple replicated conditional neural-network learning-agents (L-agents) is trained to systematically simplify the high-dimensional mapping problem into multiple 1D problems, each represented by a different type of agent. Our hybrid framework is designed to capture the effect of deformation history, aging time, and aging temperature. The model is validated with respect to a comprehensive set of experiments specifically designed to benchmark model capabilities and also against available data in the literature. Thermodynamic consistency and frame independency have been verified. Besides acceptable predictive abilities, a significant reduction of computational cost to predict behavior at multiple states of deformation is the most significant feature of this model.

42 ENGINEERING↗
DOE OSTI2023

GPU acceleration of Swendsen–Wang dynamics

When simulating a lattice system near its critical temperature, local algorithms for modeling the system’s evolution can introduce very large autocorrelation times into sampled data. Here, this critical slowing down places restrictions on the analysis that can be completed in a timely manner of the behavior of systems around the critical point. Because it is often desirable to study such systems around this point, a new algorithm must be introduced. Therefore, we turn to cluster algorithms, such as the Swendsen–Wang algorithm and the Wolff clustering algorithm. They incorporate global updates which generate new lattice configurations with little correlation to previous states, even near the critical point. We look to accelerate the rate at which these algorithm are capable of running by implementing and benchmarking a parallel implementation of each algorithm designed to run on GPUs under NVIDIA’s CUDA framework. A 17 and 90 fold increase in the computational rate was, respectively, experienced when measured against the equivalent algorithm implemented in serial code.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS2021

Reduced Complexity Model Intercomparison Project Phase 2: Synthesizing Earth System Knowledge for Probabilistic Climate Projections

Over the last decades, climate science has evolved rapidly across multiple expert domains. Our best tools to capture state-of-the-art knowledge in an internally self-consistent modelling framework are the increasingly complex fully coupled Earth System Models (ESMs). However, computational limitations and the structural rigidity of ESMs mean that the full range of uncertainties across multiple domains are difficult to capture with ESMs alone. The tools of choice are instead more computationally efficient reduced complexity models (RCMs), which are structurally flexible and can span the response dynamics across a range of domain-specific models and ESM experiments. Here we present Phase 2 of the Reduced Complexity Model Intercomparison Project (RCMIP Phase 2), the first comprehensive intercomparison of RCMs that are probabilistically calibrated with key benchmark ranges from specialized research communities. Unsurprisingly, but crucially, we find that models which have been constrained to reflect the key benchmarks better reflect the key benchmarks. Under the low-emissions SSP1-1.9 scenario, across the RCMs, median peak warming projections range from 1.3 to 1.7°C (relative to 1850-1900, using an observationally-based historical warming estimate of 0.8°C between 1850-1900 and 1995-2014). Further developing methodologies to constrain these projection uncertainties seems paramount given the international community's goal to contain warming to below 1.5°C above pre-industrial in the long-term. Our findings suggest that users of RCMs should carefully evaluate their RCM, specifically its skill against key benchmarks and consider the need to include projections benchmarks either from ESM results or other assessments to reduce divergence in future projections.

Climate↗