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 253 records · Page 14

Coherence Properties of the LCLS

The LINAC Coherent Light Source (LCLS), an X-Ray free-electron laser(FEL) based on the self amplified spontaneous emission principle, has recently come on-line. For many users it is desirable to have an idea of the level of transverse coherence of the X-Ray beam produced. In this paper, we analyze the output of GENESIS simulations of electrons traveling through the FEL. We first test the validity of an approach that ignores the details of how the beam was produced, and instead, by assuming a Gaussian-Schell model of transverse coherence, predicts the level of transverse coherence simply through looking at the beam radius at several longitudinal slices. We then develop a Markov chain Monte Carlo approach to calculating the degree of transverse coherence, which offers a {approx}100-fold speedup compared to the brute-force algorithm previously in use. We find the beam highly coherent. Using a similar Markov chain Monte Carlo approach, we estimate the reasonability of assuming the beam to have a Gaussian-Schell model of transverse coherence, with inconclusive results.

Ocko, Samuel↗

Damage Accelerates Ice Shelf Instability and Mass Loss in Amundsen Sea Embayment

Pine Island Glacier and Thwaites Glacier in the Amundsen Sea Embayment are among the fastest changing outlet glaciers in West Antarctica with large consequences for global sea level. Yet, assessing how much and how fast both glaciers will weaken if these changes continue remains a major uncertainty as many of the processes that control their ice shelf weakening and grounding line retreat are not well understood. Here, we combine multisource satellite imagery with modeling to uncover the rapid development of damage areas in the shear zones of Pine Island and Thwaites ice shelves. These damage areas consist of highly crevassed areas and open fractures and are first signs that the shear zones of both ice shelves have structurally weakened over the past decade. Idealized model results reveal moreover that the damage initiates a feedback process where initial ice shelf weakening triggers the development of damage in their shear zones, which results in further speedup, shearing, and weakening, hence promoting additional damage development. This damage feedback potentially preconditions these ice shelves for disintegration and enhances grounding line retreat. The results of this study suggest that damage feedback processes are key to future ice shelf stability, grounding line retreat, and sea level contributions from Antarctica. Moreover, they underline the need for incorporating these feedback processes, which are currently not accounted for in most ice sheet models, to improve sea level rise projections.

glaciology↗

Machine learning surrogates for ion energy–angle distributions in thermal and RF plasma sheaths

Ion energy–angle distributions (IEADs) at material surfaces are a critical input for plasma–material interaction (PMI) studies in fusion devices, yet they are computationally expensive to obtain using particle-in-cell (PIC) simulations. In this work, we develop a machine learning surrogate based on a deep deconvolutional neural network (DDeCNN) trained on large databases generated with the hPIC2 code. The surrogate is capable of reconstructing IEADs from sheath parameters for both thermal and radio-frequency (RF) plasmas, including cases with multiple ion species. Across thousands of test cases, the model achieves high accuracy, with over 97 % of predictions classified as good or average based on standard error metrics (MAE, MSE, L2). Even in the more challenging RF and multi-species regimes, the surrogate reliably captures the multi-peak structure of PIC results. Once trained, the surrogate produces IEADs in milliseconds on a common workstation, yielding speedups of six to seven orders of magnitude compared with running a full PIC simulation. This computational gain enables dense parameter scans and direct coupling of IEAD predictions with PMI and erosion models on whole-device scales in fusion-relevant conditions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

ExaCA: A performance portable exascale cellular automata application for alloy solidification modeling

Modeling the as-solidified grain structures that form during alloy processing is a critical component in understanding process-property relationships, particularly for additive manufacturing (AM) where grain structure is very sensitive to processing conditions. While cellular automata (CA)-based models have proven able to predict aspects of microstructure for several alloys and AM process conditions, long run times and large resource sets required limit the utility and the problem size to which existing CA models can be applied. As part of the ExaAM project, an initiative within the Exascale Computing Project (ECP) to develop, test, and optimize an exascale-capable coupled and self-consistent model of AM parts, we developed ExaCA (https://github.com/LLNL/ExaCA) for the liquid–solid phase transformation in the wake of AM melt pools. The CA-based code is parallelized using MPI and the Kokkos programming model, the latter enabling simulation on both CPUs and GPUs within a single-source implementation. Here, we detail the steps taken to transform a baseline, MPI-based CA code into one that is performant on CPUs and GPUs. Performance testing of ExaCA on Summit (a pre-exascale machine at Oak Ridge National Laboratory) was used to quantify CPU–GPU speedup comparing with equal numbers of nodes. Testing showed comparable CPU performance to the MPI-only CA code and a 5-20x speedup when running AM-based test problems using GPUs. The improved performance of CA through GPU utilization and the performance portable nature of ExaCA will enable accurate part-scale modeling by harnessing the power of current and future generations of high performance computing resources. Future work will include improving the strong scaling of ExaCA on GPUs by reducing load imbalance associated with the locality of the problem, and continuing performance optimization across exascale hardware.

36 MATERIALS SCIENCE↗

Parallel discrete event simulation using shared memory

With traditional event-list techniques, evaluating a detailed discrete-event simulation-model can often require hours or even days of computation time. By eliminating the event list and maintaining only sufficient synchronization to ensure causality, parallel simulation can potentially provide speedups that are linear in the numbers of processors. A set of shared-memory experiments, using the Chandy-Misra distributed-simulation algorithm, to simulate networks of queues is presented. Parameters of the study include queueing network topology and routing probabilities, number of processors, and assignment of network nodes to processors. These experiments show that Chandy-Misra distributed simulation is a questionable alternative to sequential-simulation of most queueing network models.

Reed, Daniel A.↗

Surrogate models for linear response

Linear response theory is a well-established method in physics and chemistry for exploring excitations of many-body systems. In particular, the quasiparticle random-phase approximation (QRPA) provides a powerful microscopic framework by building excitations on top of the mean-field vacuum; however, its high computational cost limits model calibration and uncertainty quantification studies. Here, we present two complementary QRPA surrogate models and apply them to study response functions of finite nuclei. One is a reduced-order model that exploits the underlying QRPA structure, while the other utilizes the recently developed parametric matrix model algorithm to construct a map between the system’s Hamiltonian and observables. Our benchmark applications, the calculation of the electric dipole polarizability of 180 Yb and the 𝛽-decay half-life of 80 Ni, show that both emulators can achieve 0.1%–1% accuracy while offering a 6–7 orders of magnitude speedup compared to state-of-the-art QRPA solvers. These results demonstrate that the developed QRPA emulators are well positioned to enable Bayesian calibration and large-scale studies of computationally expensive physics models describing the properties of many-body systems.

Beta decay↗

Stress-constrained topology optimization of lattice-like structures using component-wise reduced order models

We report lattice-like structures can provide a combination of high stiffness with light weight that is useful in many applications, but a resolved finite element mesh of such structures results in a computationally expensive discretization. This computational expense may be particularly burdensome in many-query applications, such as optimization. We develop a stress-constrained topology optimization method for lattice-like structures that uses component-wise reduced order models as a cheap surrogate, providing accurate computation of stress fields while greatly reducing run time relative to a full order model. We demonstrate the ability of our method to produce large reductions in mass while respecting a constraint on the maximum stress in a pair of test problems. The ROM methodology provides a speedup of about 150x in forward solves compared to full order static condensation and provides a relative error of less than 5% in the relaxed stress.

97 MATHEMATICS AND COMPUTING↗

Symplectic multi-particle tracking on GPUs

A symplectic multi-particle tracking model is implemented on the Graphic Processing Units (GPUs) using the Compute Unified Device Architecture (CUDA) language. The symplectic tracking model can preserve phase space structure and reduce non-physical effects in long term simulation, which is important for beam property evaluation in particle accelerators. Though this model is computationally expensive, it is very suitable for parallelization and can be accelerated significantly by using GPUs. In this paper, we optimized the implementation of the symplectic tracking model on both single GPU and multiple GPUs. Using a single GPU processor, the code achieves a factor of 2-10 speedup for a range of problem sizes compared with the time on a single state-of-the-art Central Processing Unit (CPU) node with similar power consumption and semiconductor technology. It also shows good scalability on a multi-GPU cluster at Oak Ridge Leadership Computing Facility. In an application to beam dynamics simulation, the GPU implementation helps save more than a factor of two total computing time in comparison to the CPU implementation.

43 PARTICLE ACCELERATORS↗

Approximation of refrigerant thermophysical properties using neural networks to speed up transient thermofluid simulations

Accurate and efficient evaluations of refrigerant thermophysical properties and their partial derivatives are essential for transient simulations of thermofluid systems, where several computations need to be executed at each integration time step. Since the utilization of an Equation of State for retrieving properties based on a pair of independent inputs typically involves numerical iterations in solution procedures, when the input variables differ from the refrigerant state variables employed in dynamic models, a variety of approaches including lookup table interpolation and curve fitting have been developed to explicitly approximate these properties based on the state variables, and consequently eliminate internal iterations. This paper presents an alternative method that exploits derivative-informed neural networks to model refrigerant properties explicitly from inputs of pressure and enthalpy, while ensuring consistent partial derivatives generated by differentiating the neural networks. Computational speed and accuracy of the proposed approach are demonstrated via transient simulations of a discretized heat exchanger model in Modelica, and comparisons against other property evaluation routines. Simulation results indicate that the proposed approach can realize a significant speedup with negligible discrepancies in predicted transients. The method is implemented in an open-source Modelica library.

Ma, Jiacheng↗

Feasibility Study on Implementing a Staggered-Grid Finite Volume Method for System Analysis Code Development Under the MOOSE Framework

Here, this work summarizes a feasibility study on testing numerical algorithms that are suitable and efficient for advanced system analysis code development under the mutli-physics framework, MOOSE. The key to the test bed is the implementation of high-order one-dimensional staggered-grid finite volume method (SG-FVM), and its direct interaction with the linear/nonlinear solver, PETSc. The test bed utilized a more flexible code structure to enable the finite volume method implementation and direct interacting with the solver package, instead of using the natively supported finite element method by the framework. Using a suite of selected test problems with different problem sizes and levels of complexity, the implemented SG-FVM demonstrated superior performance improvement against a direct finite element method implementation through MOOSE. On two computer systems, the speedup was observed to be significant, with at least one order of magnitude of solving time reduction. For a complex reactor model, transient simulation was performed using the newly developed finite volume method code, the results of which agree very well with the reference results from the finite element method code. Overall, this study demonstrates a successful feasibility study on the proposed numerical algorithms and software structure to support advanced system analysis tool development.

MOOSE↗

A model for optimizing file access patterns using spatio-temporal parallelism. In: UltraVis '13 Proceedings of the 8th International Workshop on Ultrascale Visualization, Article No. 4

For many years now, I/O read time has been recognized as the primary bottleneck for parallel visualization and analysis of large-scale data. In this paper, we introduce a model that can estimate the read time for a file stored in a parallel filesystem when given the file access pattern. Read times ultimately depend on how the file is stored and the access pattern used to read the file. The file access pattern will be dictated by the type of parallel decomposition used. We employ spatio-temporal parallelism, which combines both spatial and temporal parallelism, to provide greater flexibility to possible file access patterns. Using our model, we were able to configure the spatio-temporal parallelism to design optimized read access patterns that resulted in a speedup factor of approximately 400 over traditional file access patterns.

Nouanesengsy, Boonthanome↗

A model for optimizing file access patterns using spatio-temporal parallelism

For many years now, I/O read time has been recognized as the primary bottleneck for parallel visualization and analysis of large-scale data. In this paper, we introduce a model that can estimate the read time for a file stored in a parallel filesystem when given the file access pattern. Read times ultimately depend on how the file is stored and the access pattern used to read the file. The file access pattern will be dictated by the type of parallel decomposition used. We employ spatio-temporal parallelism, which combines both spatial and temporal parallelism, to provide greater flexibility to possible file access patterns. Using our model, we were able to configure the spatio-temporal parallelism to design optimized read access patterns that resulted in a speedup factor of approximately 400 over traditional file access patterns.

Boonthanome, Nouanesengsy↗

Comparisons of dosimetric accuracy and calculation time of ARCHER and MCNP5 codes for the Ir-192 brachytherapy case - Paper 1

In the last decade, the graphics processing unit (GPU) technology has emerged as a viable player in high-performance computing. A GPU card is designed to carry out thousands of single instructions simultaneously, showing unprecedented computing power when compared with the traditional CPU technology. It has been proved that some computationally intensive programs can be accelerated drastically on the GPUs including Monte Carlo simulations. Unfortunately, existing production Monte Carlo codes cannot be easily ported to the GPU environment. To address the needs, a new Monte Carlo code ARCHER (Accelerated Radiation-transport Computations in Heterogeneous Environment) is being developed at Rensselaer Polytechnic Institute, employing the latest GPU and the Intel Xeon Phi coprocessor technologies. We can execute the code which was written using C and C++ on both CPU and GPU platforms. The ARCHER GPU code was written in CUDA C 5.0 and was tested on the Tesla M2090. There have been a few studies testing the ARCHER GPU code on several different platforms. In particular, Su et al has tested the ARCHER for external-beam radiation treatment 20 MeV monoenergetic monodirectional parallel electron beam. The comparison of the calculation results between EGSnrc and ARCHERGPU was impressive. A remarkable 224- fold speed-up factor was obtained using a NVIDIA Tesla M2090 GPU compared to a CPU. In this study, we applied the ARCHER code to dose calculation for a relatively new procedure, called accelerated partial breast irradiation (APBI) brachytherapy. The APBI brachytherapy dose calculation was based on RPI-AF phantom which is a 3D heterogeneous patient model. We then compared the dosimetric accuracy and calculation times of ARCHER and MCNP5 to gain insight into the accuracy and speedup of the GPU-based ARCHER code. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗

Turbulent Mixing Simulation via a Quantum Algorithm

Probability density function (PDF) methods have been very useful in describing many physical aspects of turbulent mixing. In applications of these methods, modeled PDF transport equations are commonly simulated via classical Monte Carlo techniques, which provide estimates of moments of the PDF at arbitrary accuracy. In this paper, recently developed techniques in quantum computing and quantum enhanced measurements (quantum metrology) are used to construct a quantum algorithm that accelerates the computation of such estimates. This quantum algorithm provides a quadratic speedup over classical Monte Carlo methods in terms of the number of repetitions needed to achieve the desired precision. This paper illustrates the power of this algorithm by considering a binary scalar mixing process modeled by means of the coalescence/dispersion (C/D) closure. The equation is first simulated using classical Monte Carlo methods, where error estimates for the computation of central moments are provided. Then the quantum algorithm for this problem is simulated by sampling from the same probability distribution as that of the output of a quantum computer, and it is shown that significantly fewer resources are required to achieve the same precision. Finally, the results demonstrate potential applications of future quantum computers for simulation of turbulent mixing, and large classes of related problems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Towards district scale flood simulations using conventional and anisotropic porosity shallow water models with high-resolution topographic information

Current topographic survey technology provides high-resolution (HR) datasets for urban environments. Incorporating this HR information in models aiming to provide flood risk assessment is desirable because the flood wave propagation is depending on the urban topographic features, i.e. buildings, bridges and street networks. Conceptual, numerical and practical challenges arise from the application of shallow water models to HR urban flood modeling. For example, numerical challenges are occurrence of wet-dry fronts, geometric discontinuities in the urban environment and discontinuous solutions, i.e. shock waves. These challenges can be overcome by using a Godunov-type scheme. However, the computational cost of this type of schemes is high, such that HR two-dimensional shallow water simulations with practical relevance have to be run on supercomputers. The porous shallow water model is an alternative approach that aims to reduce computational cost by using a coarse resolution and accounting for unresolved processes by means of the porosity terms. Usually, a speedup between two and three orders of magnitude in comparison to HR simulations can be obtained. This study presents preliminary results of a practical test case concerning pluvial flooding in a district of the city of Nice, France, caused by the intense rainfall event on October 3rd, 2015. HR topography data set on a 1 m resolution is available for the district, whereby street features of infra-metric dimensions have been included. A reference solution is calculated by a HR shallow water model on a 1 m by 1 m structured computational grid. The porous shallow water model is run on a 10 m by 10 m grid and the influence of the drag source term is studied. The model calculations show a large deviation, which is caused by the poor meshing strategy of the porous shallow water (AP) model. The study also summarizes practical challenges that arise during the application of the AP and HR models to a large urban catchment. The main difficulty is to obtain a good mesh. In smaller scale investigations, the mesh is currently constructed by hand such that the cell edges align with buildings. This approach is not feasible for large scale urban catchments with a large number of buildings. Future steps that have to be taken, such as a strategy for automatic mesh generation, are reported on.

42 ENGINEERING↗

The impact of aerosol mixing state on immersion freezing: insights from classical nucleation theory and particle-resolved simulations

Immersion freezing, initiated by ice-nucleating particles (INPs) in supercooled aqueous droplets, plays an important role in the formation of ice crystals within clouds. The efficiency of immersion freezing depends strongly on INP composition and, crucially, on the mixing state – how chemical species are distributed across the particle population. Here, we quantify the impact of aerosol mixing state on immersion freezing using a combined theoretical and particle-resolved modeling approach. We derive analytical expressions for the frozen fraction of internally and externally mixed INP populations based on classical nucleation theory, showing that the frozen fraction is sensitive to whether ice-active species are present in all particles or only in a subset of the population. We introduce a multi-species immersion freezing scheme into the particle-resolved model PartMC, using the water activity-based immersion freezing model (ABIFM) to compute freezing probabilities for mixed-composition particles. To improve computational efficiency, we implement a Binned Tau-Leaping algorithm and demonstrate an order-of-magnitude speedup with minimal accuracy loss. Simulations reproduce the analytical trends in limiting cases and extend the analysis to more general aerosol populations, where mixing state continues to exert a substantial control on frozen fraction. Sensitivity analyses across particle size, species type, and cooling condition reveal that the mixing state effect is most pronounced when small amounts of highly efficient INPs are mixed with less efficient materials. These findings underscore the need to represent aerosol mixing state explicitly in models of heterogeneous ice nucleation to reduce uncertainty in cloud-phase partitioning.

54 ENVIRONMENTAL SCIENCES↗

Towards Enhancing Coding Productivity for GPU Programming Using Static Graphs

The main contribution of this work is to increase the coding productivity of GPU programming by using the concept of Static Graphs. GPU capabilities have been increasing significantly in terms of performance and memory capacity. However, there are still some problems in terms of scalability and limitations to the amount of work that a GPU can perform at a time. To minimize the overhead associated with the launch of GPU kernels, as well as to maximize the use of GPU capacity, we have combined the new CUDA Graph API with the CUDA programming model (including CUDA math libraries) and the OpenACC programming model. We use as test cases two different, well-known and widely used problems in HPC and AI: the Conjugate Gradient method and the Particle Swarm Optimization. In the first test case (Conjugate Gradient) we focus on the integration of Static Graphs with CUDA. In this case, we are able to significantly outperform the NVIDIA reference code, reaching an acceleration of up to 11x thanks to a better implementation, which can benefit from the new CUDA Graph capabilities. In the second test case (Particle Swarm Optimization), we complement the OpenACC functionality with the use of CUDA Graph, achieving again accelerations of up to one order of magnitude, with average speedups ranging from 2x to 4x, and performance very close to a reference and optimized CUDA code. Our main target is to achieve a higher coding productivity model for GPU programming by using Static Graphs, which provides, in a very transparent way, a better exploitation of the GPU capacity. The combination of using Static Graphs with two of the current most important GPU programming models (CUDA and OpenACC) is able to reduce considerably the execution time w.r.t. the use of CUDA and OpenACC only, achieving accelerations of up to more than one order of magnitude. Finally, we propose an interface to incorporate the concept of Static Graphs into the OpenACC Specifications.

58 GEOSCIENCES↗

Generating Massive Scale-free Networks: Novel Parallel Algorithms using the Preferential Attachment Model

Recently, there has been substantial interest in the study of various random networks as mathematical models of complex systems. As real-life complex systems grow larger, the ability to generate progressively large random networks becomes all the more important. This motivates the need for efficient parallel algorithms for generating such networks. Naïve parallelization of sequential algorithms for generating random networks is inefficient due to inherent dependencies among the edges and the possibility of creating duplicate (parallel) edges. In this article, we present message passing interface-based distributed memory parallel algorithms for generating random scale-free networks using the preferential-attachment model. Our algorithms are experimentally verified to scale very well to a large number of processing elements (PEs), providing near-linear speedups. The algorithms have been exercised with regard to scale and speed to generate scale-free networks with one trillion edges in 6 minutes using 1,000 PEs.

97 MATHEMATICS AND COMPUTING↗