SEARCH · Engineering Papers

Results for “Parallel processing”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 739 records · Page 41

All sources NASA NTRS DOE OSTI

DOE OSTI2021

I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization

In this paper, we propose a novel hardware accelerator for GCN inference called I-GCN that significantly improves data locality and reduces unnecessary computation through a new online graph restructuring algorithm we refer to as islandization. The proposed algorithm finds clusters of nodes with strong internal but weak external connections. The islandization process yields two major benefits. First, by processing islands rather than individual nodes, there is better on-chip data reuse and fewer off-chip memory accesses. Second, there is less redundant computation as aggregation for common/shared neighbors in an island can be reused. The parallel search, identification, and leverage of graph islands are all handled purely in hardware at runtime working in an incremental pipelined manner. This is done without any preprocessing of the graph data or adjustment of the GCN model structure.

Geng, Tong↗

DOE OSTI2025

ChatHPC: Building the Foundations for a Productive and Trustworthy AI-Assisted HPC Ecosystem

ChatHPC democratizes large language models for the high-performance computing (HPC) community by providing the infrastructure, ecosystem, and knowledge needed to apply modern generative AI technologies to rapidly create specific capabilities for critical HPC components while using relatively modest computational resources. Our divide-and-conquer approach focuses on creating a collection of reliable, highly specialized, and optimized AI assistants for HPC based on the cost-effective and fast Code Llama fine-tuning processes and expert supervision. We target major components of the HPC software stack, including programming models, runtimes, I/O, tooling, and math libraries. Thanks to AI, ChatHPC provides a more productive HPC ecosystem by boosting important tasks related to portability, parallelization, optimization, scalability, and instrumentation, among others. With relatively small datasets (on the order of KB), the AI assistants, which are created in a few minutes by using one node with two NVIDIA H100 GPUs and the ChatHPC library, can create new capabilities with Meta’s 7-billion parameter Code Llama base model to produce high-quality software with a level of trustworthiness of up to 90% higher than the 1.8-trillion parameter OpenAI ChatGPT-4o model for critical programming tasks in the HPC software stack.

Young, Aaron [ORNL] (ORCID:0000000254484667)↗

DOE OSTI2022

On the Nature of Surface Defects Found in 2/0 N-Doped 9-Cell Cavities

In this contribution, we present a systematic study on the microstructure of 1.3 GHz 9-cell TESLA type SRF cavity, processed with 2/0 Nitrogen-doping surface treatment, to explain the premature quench phenomena commonly observed in N-doping treated cavities. The microstructure characterization was carried out using Secondary electron images, advanced metallurgical techniques such as EBSD in parallel with chemical information obtained from spectroscopic techniques. The most remarkable difference is observed in the ends-cavities (1 and 9), which showed roughening of the surface, revealing a series of morphologies associated with Nb cubic phase. The cell-to-cell analysis also showed standard features such as pits with different geometry and distribution, located in grains and grain boundaries. The defects found in this system suggest that the standard electropolishing chemical etching was insufficient to eliminate history defects produced during the manufacture of the cavity, without discarding the role of the impurities, N and O, that could have induced the growth of these morphologies.

43 PARTICLE ACCELERATORS↗

DOE OSTI2025

Temporal Properties of Compressible Magnetohydrodynamic Turbulence

Describing the temporal properties of compressible magnetohydrodynamic (MHD) turbulence is a fundamental problem that has important implications for particle acceleration and transport in astrophysical plasmas. Here, by carefully analyzing the spatial and temporal properties of compressible MHD turbulence, we derive a new spectral power density function that is supported by simulations. This new function reveals that the low-frequency fluctuations are dominated by modes with small parallel wavenumbers with respect to the mean background magnetic field. Furthermore, for fluctuations with dynamically significant parallel wavenumbers, broadening around their eigenfrequencies is described by this function, which is in close agreement with simulations. We use this formalism to present the scaling properties of individual MHD modes. Such broadening is a direct consequence of nonlinear processes and is different for the three fundamental MHD modes. Our results provide a new window to investigate the temporal properties of turbulence and will enable further studies on the interaction between compressible MHD turbulence and energetic plasmas.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2021

Digital Twin Model for Advanced Manufacture of a Rotating Detonation Engine Injector

A digital twin material model (DTMM) of an additive manufacturing (AM) process was created to advance the state of the art in rotating detonation engine (RDE) injector design. Current RDE injectors are designed with large pressure drops, enabling a stable and repeatable combustion process. However, this comes at the cost of system efficiency. For the technology to transition to commercial fossil-based power generation, it is important to develop injectors with reduced flow losses. Low-loss injectors are difficult to design and manufacture with conventional manufacturing techniques. AM enables new design options, but the AM manufacturing process must be thoroughly understood to result in a robust design. A DTMM provides the necessary insight by defining the cause-effect relationships between process parameters, microstructure features, and properties. Therefore, a DTMM to support the design and manufacturing process was developed and applied to the design of a new additively manufactured low-loss injector. The injector combustion behavior was characterized through hot-fire tests, and mechanical performance was compared to the DTMM predictions. The two project goals were the successful development of the DTMM and the demonstration of an improved RDE injector design. The RDE injector design and DTMM developments occurred on parallel but dependent paths. The injector was designed to reduce pressure drop by increasing the cross-sectional flow area ratio between the injector air passages and the combustor annulus. This resulted in less structural material, raising the concern that thin members would be susceptible to high-cycle fatigue (HCF) under the periodic loading inherent to an RDE. It was most important for the DTMM to predict behavior in these features; therefore, the injector design concept guided the material thicknesses used in fatigue tests. The DTMM development started by manufacturing a series of coupons over the range of possible AM process variations. A design-of-experiment approach was used to select which process variable combinations gave the most efficient coverage relevant to the injector design space. The microstructure in each of these coupons was characterized, and then computational methods were used to create a numerical model of the correlation between process variables and microstructure. Next, a set of HCF samples were tested to calibrate existing models that map microstructure to HCF performance. Together, these two links formed the DTMM that calculates HCF behavior from AM process variables. Two injector prototypes were additively manufactured. The first injector design strategy aggressively pursued low-loss performance by substantially increasing the oxidizer flow area. The combination of manufacturing lead times and the fatigue testing schedule meant that the DTMM was not available when building this first prototype. Therefore, its process parameters were chosen based on a manual review of the available coupon data. This prototype was built successfully and evaluated in 58 combustion tests. Sustained detonation was achieved with remarkably reduced pressure loss, and some tests even displayed pressure loss characteristics similar to conventional gas turbine combustors. This achieved the project goal of improving RDE injector design. The second injector was manufactured according to the optimized parameters predicted by the DTMM. The flow area modifications of this injector were less aggressive than the first injector since demonstrating low pressure loss was not an objective of the second hot-fire test series. Rather, the test objective was to cause high cycle fatigue failure in the part due to periodic loading from the rotating detonation wave. The observed number of cycles to failure was to be compared to the number predicted by the DTMM and thereby assess the utility of the DTMM in component design. However, the required level of vibration was not obtained during combustion. Therefore, high cycle fatigue was not experienced in the hot-fire tests of the second injector. Fatigue data was obtained by further testing the second injector in a conventional HCF test apparatus. The injector demonstrated HCF strength above the DTMM prediction. In fact, it did not fail and testing was only discontinued due to reaching the end of the period of performance. This points to some success in the project’s primary goal of successfully developing and applying the DTMM to a component design. Implementing the DTMM recommendations for optimal processing parameters led to a part with acceptable properties. The DTMM was also shown to be an efficient correlator of data and to provide insight into the relationship between process settings, microstructure, and property performance. However, the failure of the DTMM prediction to match the experimental result of the injector fatigue test also points to the need to include significantly more data in the model development. In this project, coupons made with identical processing parameters exhibited drastically different properties from each other and from the injector part, which clearly influences the accuracy of a model that predicts performance based on parameters. Uncertainties in the build process must be quantified to develop more robust models. A denser and broader matrix of coupon process and geometry variations, several repeated builds of every point, more in-situ build process measurements, and direct observation of tensile and HCF sample microstructure (as opposed to separate microstructure specimens) are recommendations to improve future AM modeling efforts.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2024

The Influence of Residual Stress on Fatigue Crack Growth Rates in Stainless Steel Processed by Different Additive Manufacturing Methods

The properties and microstructure of Type 304L stainless steel produced by two additive manufacturing (AM) methods—directed energy deposition (DED) and powder bed fusion (PBF)—are evaluated and compared. Localized heating and steep temperature gradients of AM processes lead to significant residual stress and distinctive microstructures, which may be process-specific and influence mechanical behavior. Test data show that materials produced by DED and PDF have small differences in tensile strengths but clear differences in residual stress and microstructural features. Measured fatigue crack growth rates (FCGRs) for cracks propagating parallel to and perpendicular to the build directions differ between the two AM materials. To separate the influences of residual stress and microstructure, K-control test procedures with decreasing and constant stress intensity factor ranges are used to measure FCGRs in the near-threshold regime (crack growth rates ≤ 1 × 10 −8 m/cycle). Residual stress is quantified by the residual stress intensity factor, K res , measured by the online crack compliance method. Correcting the FCGR data for differences in K res brings results for specimens of the two AM materials into agreement with each other and with results for wrought specimens, when the latter are corrected for crack closure. Differences in microstructure and tensile strength have an insignificant influence on FCGRs in these tests.

additive manufacturing↗

DOE OSTI2023

Distributed approximate minimal Steiner trees with millions of seed vertices on billion-edge graphs

In this report, we present a parallel 2-approximation Steiner minimal tree algorithm and its MPI-based distributed implementation. In place of expensive distance computations between all pairs of seed vertices, the solution we employ exploits a cheaper Voronoi cell computation. Our design leverages asynchronous processing and message prioritization to accelerate convergence of distance computations, and harnesses vertex and edge centric processing to offer fast time-to-solution. We demonstrate scalability and performance using real-world graphs with up to 128 billion edges and 512 compute nodes, and show the ability to find Steiner trees with up to one million seed vertices. Using 12 data instances, we present comparison with the state-of-the-art exact solver, SCIP-Jack, and two sequential 2-approximate algorithms. We empirically show that, on average, the total distance of the Steiner tree identified by our solution is 1.1290 times greater than the Steiner minimal tree – well within the theoretical approximation bound of 2.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Insights From Dayflow: A Historical Streamflow Reanalysis Dataset for the Conterminous United States

Abstract Reconstructed historical streamflow time series can supplement limited streamflow gauge observations. However, there are common challenges of typical modeling approaches: process‐based hydrologic models can be data/computation‐intensive, and statistics‐based models can be region/stream‐specific. Here we present a nationally scalable modeling framework integrating the simulated runoff from the Variable Infiltration Capacity (VIC) model with the Routing Application for Parallel computatIon of Discharge (RAPID) routing model leveraging high‐performance computing. We demonstrate an efficient method of assimilating streamflow at US Geological Survey (USGS) streamflow monitoring sites using a simple hierarchical approach in the VIC‐RAPID framework. The result is a reconstructed 36‐year (1980–2015) daily and monthly streamflow dataset (Dayflow) at ∼2.7 million NHDPlusV2 stream reaches in the conterminous US (CONUS). We perform a comprehensive evaluation at 7,526 USGS sites and characterize their error statistics. The results demonstrate that 49% of the USGS sites demonstrate Kling–Gupta Efficiency (KGE) > 0.5 and 58% of the sites show percentage bias within ±20% for the daily naturalized streamflow. Streamflow data assimilation across CONUS shows an overall improvement over naturalized streamflow, notably in the western semiarid‐to‐arid regions. Comparison to other national and global streamflow reanalysis datasets such as the National Water Model and Global Reach‐scale A priori Discharge Estimates for SWOT demonstrates improved KGE, reduced bias, and directions for Dayflow improvements. Investigations of error statistics with key hydrologic, hydroclimatic, and geomorphologic basin characteristics reveal region‐specific patterns which may help improve future framework applications. Overall, Dayflow may enable a better understanding of hydrologic conditions in a changing environment, especially in locations currently not represented by streamflow monitoring networks.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

BETO 2021 Peer Review - 1.3.5.270 - Rewiring Algal Carbon Energetics for Renewables (RACER)

Critically needed improvements in biomass and biofuel intermediate productivity can be made by addressing fundamental inefficiencies in algal carbon conversion efficiency (CCE) to biofuel intermediates. Algae photosynthesis is, at best, able to convert 5-7% of incident light energy to biomass, while conversion to fuel intermediates falls 15-25% short of its maximum potential due to inefficiencies along the pathways. Recent progress in the Rewiring Algal Carbon Energetics (RACER) project consortium focused on a means to address the above inefficiencies in a pathway from algal biomass to a trifecta of fuel intermediates, ethanol, 2,3-butane diol, lipids and green biocrude. This project engineered a production-relevant algal species Desmodesmus armatus (SE 00107), to demonstrate biomass productivity improvements, with a doubling of the fuel intermediate yields. The new algae biorefinery paradigm embodied in RACER opens opportunities for algae engineering beyond efforts typically targeted solely at lipid content or improved light harvesting efficiency. Parallel approaches showed improved CCE through elimination of wasted energy during photosynthesis and increased carbon flux to transitory carbohydrate storage in the cells. Outdoor operation and nutrient management strategies with improvements in pretreatment, fermentation and extraction in a Combined Algal Processing approach showed a 40% reduction in MFSP, with a combined biofuel productivity of > 3700 gal/acre.

algal↗

DOE OSTI2024

Accelerating Thermochemical Equilibrium Calculations for Nuclear Reactor Applications

Thermochemical properties play a key role in modeling and simulation of several key phenomena in nuclear reactors. There has been an increasing interest in incorporating CALPHAD-based formulations in multiphysics simulations including for Molten Salt Reactors where knowledge of phase evolution of the salt and the chemical potentials of various elements are of utmost importance in source term analyses and redox control. However, the size of such simulations is often limited by the high computational cost of full thermodynamic equilibrium calculations. This work discusses the current efforts aimed at accelerating thermochemical equilibrium calculations for multiphysics simulations performed using the open-source finite element / finite volume code Multiphysics Object Oriented Simulation Environment (MOOSE) [1]. While several methods have been proposed for accelerating phase equilibrium calculations [2], most focus on relatively small systems and often rely on a- priori knowledge of the state-space of the system. Nuclear materials, however, are often multi-component systems owing to the evolution of composition under irradiation and an approach based on a-priori mapping of phase diagram is often not enough. This work is aimed at demonstrating an on-the-fly surrogate modeling framework that uses active learning to reduce the number of full equilibrium calculations that must be performed. By combining with efficient coupling approaches, the surrogate framework helps in reducing the computational cost of thermodynamic equilibrium informed multiphysics simulations of nuclear materials. The performance is benchmarked against full coupling with the thermochemistry library Thermochimica [3]. This work uses a machine learning based approach for constructing surrogate models to predict the stable phases in a multicomponent system. The surrogates were constructed using neural networks and Gaussian process classification. In this work, we compare the relative performance of the two methods. We also demonstrate the use of caching previous calculations by interpolating the values from nearest neighbors. References [1] Lindsay, A.D., et al. "2.0 – MOOSE: Enabling massively parallel multiphysics simulation", SoftwareX, 20 (2022): 101202. [2] Roos, W.A. and Zietsman J.H. "Accelerating complex chemical equilibrium calculations – A Review", Calphad, 77 (2022): 102380. [3] Piro, M.H.A., et al. "The thermochemistry library Thermochimica", Computational Materials Science, 67 (2013): 266-272.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Progress Report on Performance of A709 and G91 Steels in Sodium

Specimens in six different processing and heat treatment conditions of A709 H58776 were exposed to sodium at 550, 600, and 650°C, respectively for various exposure times. G91 base metal was tested in sodium at 550, 600, and 650°C, and G91 weldment at 550 and 600°C, respectively. Parallel thermal aging experiments were conducted on G91 and A709 to obtain thermal aging data for comparison with sodium exposure results to separate the thermal and sodium effects. The corrosion data obtained on A709 steel continue to show low corrosion rates, which indicate good compatibility of A709 with sodium when oxygen content is controlled. G91 has also shown acceptable corrosion rates over the temperature range of 550-650°C in sodium. Thermal aging or sodium exposures reduced the tensile strength, uniform elongation, and total elongation for A709 ESR, AOD specimens. These specimens consistently showed higher yield stress and tensile strength and lower uniform and total elongations after sodium exposure than after thermal aging under comparable testing conditions. It implies that there was an additional effect of sodium exposure that gave rise to an increase in tensile strength of A709. Dynamic strain aginginduced flow serrations were completely removed by either thermal aging or sodium exposure at 650°C, which imply that carbon or nitrogen in solution was removed from the solution and formed precipitates during aging or sodium exposures. The tensile data ruled out the possibility of decarburization under the sodium exposure conditions. The HOMO specimens behaved somewhat differently from the ESR and AOD specimens in sodium. While thermal aging and sodium exposures at 550 and 600°C decreased the yield stress and the ultimate tensile strength of G91, there was virtually no additional effect resulting from sodium exposures at these two temperatures. In contrast, sodium exposures at 650°C had a drastic effect on the yield stress and the ultimate tensile strength of G91. It is suggested that G91 experienced decarburization in the 650°C sodium environments. Carbon concentrations in sodium in the SMT-1 and SMT-2 loops were determined by a foil equilibration method. The estimated carbon concentration was in the range of 0.8-1.2 ppm in the SMT-1 loop and 0.3-0.7 ppm in the SMT-2 loop. The carbon activity in sodium in the SMT-2 loop was estimated to be 0.03-0.08 at 600°C, and 0.08-0.2 at 550°C. The carbon activity in sodium at 650°C in the SMT-1 loop was 0.04-0.07. Equilibrium simulation of the carburization – decarburization processes was conducted for A709 and G91 steels exposed in sodium environments at temperatures of 550-700°C. The carbon activity-concentration relationship for G91 was re-evaluated by considering four phases in G91, i.e. bcc ferrite, M 23 C 6 , NbC and VC carbides. It was found that the carburization-decarburization process in G91 steel was dictated by M 23 C 6 carbides at high carbon activities, while NbC carbides dominated the process at low carbon activities. Formation of NbC increases the decarburization resistance of G91 steel. It remains to be understood whether the decarburization resistance provided by MC carbides in G91 can be maintained during long-term operations of SFRs. The carbon concentration-activity relationship for A709 was calculated based on the equilibrium of fcc-austenite and M 23 C 6 carbide phase. The calculations showed that A709 decarburizes at 650°C in the SMT-1 loop environments, which is different from the experimental findings. The carbon concentration-activity relationship in A709 was further evaluated by considering four phases, including fcc-austenite, M 23 C 6 , NbC, and TiC carbide phases. TiC is the most stable carbides among the three carbide phases. The carburization-decarburization process in A709 is dictated by M 23 C 6 carbides at high carbon activities and by TiC at low carbon activities. Formation of TiC increases the decarburization resistance of A709 steel. Because of the complexity of the precipitation process in A709 during sodium exposures, detailed characterization of precipitates in sodium-exposed specimens and improved thermodynamic models are needed to understand the carburization-decarburization behavior of A709. Kinetic analysis of carbon transfer will be investigated for G91 and A709 in future work.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2021

Impact of organic acids and sulfate on the biogeochemical properties of soil from urban subsurface environments

Urban subsurface environments are often different from undisturbed subsurface environments due to the impacts of human activities. For example, deterioration of underground infrastructure can introduce elevated levels of Ca, Fe, and heavy metals into subsurface soils and groundwater. Likewise, leakage from sewer systems can lead to contamination by organic C, N, S, and P. However, the impact of these organic and inorganic compounds on biogeochemical processes including microbial redox reactions, mineral transformations, and microbial community transitions in urban subsurface environments is poorly understood. Here we conducted a microcosm experiment with soil samples from an urban construction site to investigate the possible biotic and abiotic processes impacted when sulfate and acetate or lactate were introduced into an urban subsurface environment. In the top-layer soil (0-0.3 m) microcosms, which were highly alkaline (pH > 10), the major impact was on abiotic processes such as secondary mineral precipitation. In the mid-layer (2-3 m) soil microcosms, the rate of Fe(III)-reduction and the amount of Fe(II) produced were greatly impacted by the specific organic acid added, and sulfate-reduction was not observed until after Fe(III)-reduction was complete. Near the end of the incubation, some genera related to syntrophic acetate oxidation and methanogenesis were observed in the lactateamended microcosms. In the bottom-layer (7-8 m) soil microcosms, the rate of Fe(III)-reduction and the amount of Fe(II) produced were affected by the concentration of amended sulfate. Sulfate-reduction was concurrent with Fe(III)-reduction, suggesting that Fe(II) production was likely due to abiotic reduction of Fe(III) by sulfide produced by microbial sulfate reduction. The slightly acidic initial pH (~5.8) of the mid-soil system was a major factor controlling sequential microbial Fe(III) and sulfate reduction versus parallel Fe(III) and sulfate reduction in the bottom soil system, which had a neutral initial pH (~7.2). Finally, 16S rRNA gene-based community analysis revealed a variety of indigenous microbial groups including alkaliphiles, dissimilatory iron and sulfate reducers, syntrophes, and methanogens tightly coupled with, and impacted by, these complex abiotic and biogeochemical processes occurring in urban subsurface environments.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Solidification and crystallographic texture modeling of laser powder bed fusion Ti-6Al-4V using finite difference-monte carlo method

Laser powder bed fusion (LPBF) additive manufacturing makes near-net-shaped parts with reduced material cost and time, rising as a promising technology to fabricate Ti-6Al-4V, a widely used titanium alloy in aerospace and medical industries. However, LPBF Ti-6Al-4V parts produced with 67° rotation between layers, a scan strategy commonly used to reduce microstructure and property inhomogeneity, have varying grain morphologies and weak crystallographic textures that change depending on processing parameters. Here, this study predicts LPBF Ti-6Al-4V solidification at three energy levels using a finite difference-Monte Carlo method and validates the simulations with large-area electron backscatter diffraction (EBSD) scans. The developed model accurately shows that a <001> texture forms at low energy and a <111> texture occurs at higher energies parallel to the build direction but with a lower strength than the textures observed from EBSD. A validated and well-established method of combining spatial correlation and general spherical harmonics representation of texture is developed to calculate a difference score between simulations and experiments. The quantitative comparison enables effective fine-tuning of nucleation density (N 0 ) input, which shows a nonlinear relationship with increasing energy level. Future improvements in texture prediction code and a more comprehensive study of N 0 with different energy levels will further advance the optimization of LPBF Ti-6Al-4V components. These developments contribute a novel understanding of crystallographic texture formation in LPBF Ti-6Al-4V, the development of robust model validation and calibration pipeline methodologies, and provide a platform for mechanical property prediction and process parameter optimization.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2020

Emerging technologies and radical collaboration to advance predictive understanding of watershed hydrobiogeochemistry

Increasing population and resource-intensive lifestyles are driving enhanced demands for clean water, food, and energy. In parallel, land-use change, climate change, and perturbations—including drought, floods, fires, and early snowmelt—are significantly reshaping interactions within watersheds throughout the world. While watersheds are the Earth's key functional unit for assessing and managing water resources, hydrological processes in watersheds also mediate biogeochemical interactions that support terrestrial life on Earth (Kaushal, Gold, Bernal, & Tank, 2018; National Research Council, 2012). Although society is dependent upon clean water availability, tractable prediction of watershed hydrobiogeochemical behavior, including watershed response to perturbations, remains a challenge. Central to the challenge are complex, multiscale interactions between plants, microorganisms, organic matter, minerals, dissolved constituents, and migrating fluids, which occur within and across bedrock-to-canopy compartments and along extensive lateral gradients of a watershed. Several recent community reports have synthesized formidable challenges associated with watershed science and technology (AGU, 2018; Blöschl et al., 2019). Here, we discuss emerging technologies and collaboration modes that are critical for developing generalizable insights about and predictive understanding of complex watershed hydrobiogeochemical behavior, which are important for underpinning optimized natural resource management.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Developing Ultrahigh-Resolution E3SM Land Model for GPU Systems

Designing and refactoring complex scientific code, such as the E3SM land model (ELM), for new computing architectures is challenging. This paper presents design strategies and technical approaches to develop a data-oriented, GPU-ready ELM model using compiler directives (OpenACC/OpenMP). We first analyze the datatypes and processes in the original ELM code. Then we present design considerations for ultrahigh-resolution ELM (uELM) development for massive GPU systems. These techniques include the global data-oriented simulation workflow, domain partition, code porting and data copy, memory reduction, parallel loop restructure and flattening, and race condition detection. We implemented the first version of uELM using OpenACC targeting the NVidia GPUs in the Summit supercomputer at Oak Ridge National Laboratory. During the implementation, we developed a software tool (named SPEL) to facilitate code generation, verification, and performance tuning using these techniques. The first uELM implementation for Nvidia GPUs on Summit delivered promising results: 1) over 98% of the ELM code was automatically generated and tuned by scripts. Most ELM modules had better computational performances than the original ELM code for CPUs. The GPU-ready uELM is more scalable than the CPU code on fully-loaded Summit nodes. Example profiling results from several modules are also presented to illustrate the performance improvements and race condition detection. The lessons learned and toolkit developed in the study are also suitable for further uELM deployment using OpenMP on the first US exascale computer, Frontier, equipped with AMD CPUs and GPUs.

Schwartz, Peter↗

DOE OSTI2020

Pass-efficient methods for compression of high-dimensional turbulent flow data

The future of high-performance computing, specifically on future Exascale computers, will presumably see memory capacity and bandwidth fail to keep pace with data generated, for instance, from massively parallel partial differential equation (PDE) systems. Current strategies proposed to address this bottleneck entail the omission of large fractions of data, as well as the incorporation of in situ compression algorithms to avoid overuse of memory. To ensure that post-processing operations are successful, this must be done in a way that a sufficiently accurate representation of the solution is stored. Moreover, in situations where the input/output system becomes a bottleneck in analysis, visualization, etc., or the execution of the PDE solver is expensive, the number of passes made over the data must be minimized. In the interest of addressing this problem, this work focuses on the utility of pass-efficient, parallelizable, low-rank, matrix decomposition methods in compressing high-dimensional simulation data from turbulent flows. Additionally, a particular emphasis is placed on using coarse representation of the data – compatible with the PDE discretization grid – to accelerate the construction of the low-rank factorization. This includes the presentation of a novel single-pass matrix decomposition algorithm for computing the so-called interpolative decomposition. The methods are described extensively and numerical experiments on two turbulent channel flow data are performed. In the first (unladen) channel flow case, compression factors exceeding 400 are achieved while maintaining accuracy with respect to first- and second-order flow statistics. In the particle-laden case, compression factors of 100 are achieved and the compressed data is used to recover particle velocities. These results show that these compression methods can enable efficient computation of various quantities of interest in both the carrier and disperse phases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

Toward exascale whole-device modeling of fusion devices: Porting the GENE gyrokinetic microturbulence code to GPU

GENE solves the five-dimensional gyrokinetic equations to simulate the development and evolution of plasma microturbulence in magnetic fusion devices. The plasma model used is close to first principles and computationally very expensive to solve in the relevant physical regimes. In order to use the emerging computational capabilities to gain new physics insights, several new numerical and computational developments are required. Here, we focus on the fact that it is crucial to efficiently utilize GPUs (graphics processing units) that provide the vast majority of the computational power on such systems. In this paper, we describe the various porting approaches considered and given the constraints of the GENE code and its development model, justify the decisions made, and describe the path taken in porting GENE to GPUs. We introduce a novel library called gtensor that was developed along the way to support the process. Performance results are presented for the ported code, which in a single node of the Summit supercomputer achieves a speed-up of almost 15× compared to running on central processing unit (CPU) only. Typical GPU kernels are memory-bound, achieving about 90% of peak. Our analysis shows that there is still room for improvement if we can refactor/fuse kernels to achieve higher arithmetic intensity. We also performed a weak parallel scalability study, which shows that the code runs well on a massively parallel system, but communication costs start becoming a significant bottleneck.

Germaschewski, K. (ORCID:0000000284956354)↗

DOE OSTI2023

Focus enhancement in long schlieren imaging systems using corrector lenses

Long schlieren imaging systems, where the parallel light test section is longer than the focal length of the focusing schlieren optics, have a limited region in the test section in which any occluding object, such as a wind tunnel model, is in focus in the schlieren image. Corrector lenses are introduced here to alter the location in the test section where image focus is achieved. Corrector lenses with focal lengths varying from −1000 to −100mm were studied. Lens-type inline and z -type mirror schlieren systems were experimentally tested with multiple collecting optic focal lengths to characterize the changes in focal position. An automated image processing method was used to determine the plane of best focus from image sequences. The introduction of the corrector lens was observed to move the location of best focus within the schlieren system test section while also causing a decrease in the focal sharpness of the images and altering the magnification. The thin lens equation was found to provide a good estimate of the focal location change in the schlieren imaging systems with the addition of the corrector lens.

Torres, Sivana M.↗