Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parallel, scaling”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,513 records · Page 84

Efficient Simulation of Nested Hollow Sphere Intersections: for Dynamically Nested Compartmental Models in Cell Biology

In the particle-based simulation of cell-biological systems in continuous space, a key performance bottleneck is the computation of all possible intersections between particles. These typically rely for collision detection on solid sphere approaches. The behavior of cell biological systems is influenced by dynamic hierarchical nesting, such as the forming of, the transport within, and the merging of vesicles. Existing collision detection algorithms are found not to be designed for these types of spatial cell-biological models, because nearly all existing high performance parallel algorithms are focusing on solid sphere interactions. The known algorithms for solid sphere intersections return more intersections than actually occur with nested hollow spheres. Here we define a new problem of computing the intersections among arbitrarily nested hollow spheres of possibly different sizes, thicknesses, positions, and nesting levels. We describe a new algorithm designed to solve this nested hollow sphere intersection problem and implement it for parallel execution on graphical processing units (GPUs). We present first results about the runtime performance and scaling to hundreds of thousands of spheres, and compare the performance with that from a leading solid object intersection package also running on GPUs.

Koester, Till↗

A New Model for Simulating the Imbibition of a Wetting-Phase Fluid in a Matrix-Fracture Dual Connectivity System

The imbibition experiment is an effective approach for measuring petrophysical properties of porous media, with many such experiments performed over the past decade. Quite some empirical, analytical, and numerical models have been developed to simulate spontaneous imbibition of the wetting phase fluid into porous media, but limitations still exist. In previous studies, the imbibition process has been considered to give a piston-like displacement or the porous medium modeled as multiply-sized pores linked with bonds; both approaches fail to yield comprehensive results due to their neglect of the presence of irregular fractures or nonuniform flow paths through the matrix. By building a numerical model for simulating laboratory-scale experimental data, we performed imbibition tests on several fractured Barnett Shale samples having fractures either parallel ( P ) or transverse ( T ) to the bedding plane and used MATLAB to build a new numerical model by combining the imbibition process in fractures and the matrix using concepts from percolation theory. The experimental data show that the rocks with P -direction fractures have a more steady increase of imbibition rates than the case of T -direction one. As the shale matrix with low pore connectivity hampers the upward water movement, the imbibition rate of shales with T -direction fractures will decrease suddenly after the bottom layer in contact with water is saturated during the initial period. This wetting phase movement (WPM) model can simulate 3D porous media with 2D fractures. The rate of imbibition by fractured porous media is associated with physical parameters such as porosity and fracture distribution (e.g., the number and angle of fractures). Using Monte Carlo methods, we examined fracture parameters and predicted elapsed time and cumulative water imbibition, for the Barnett Shale samples. The results show that the rate of imbibed water mass is sensitive to the number of fractures directly connected to water source, and the connectivity between two neighboring grid cells is a key parameter for the wetting-front progression. The findings of this study can help to better understand the imbibition process with multiple influencing processes and factors in fractured-matrix rocks. Although the experiments, data simulation, and prediction results are based only on Barnett Shale samples, the model is readily applicable to imbibition tests of other fractured rocks to show the spatial and temporal behavior during a dynamic imbibition process that are not easily captured experimentally.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

BDEM (Discrete-element-simulator for high-solids granular flows) [SWR-22-72]

BDEM is a discrete element method based simulation tool developed specifically for modeling high-solids granular flows that include polydispersity, heat-transfer, moving boundaries and chemistry. Our solver provides facilities for simulating spherical/non-spherical particles with modified contact and friction models in complex dynamic geometries defined using level-sets or triangulated files. The solver is developed on top of NREL's open-source performance portable library, AMReX, providing parallel execution capabilities on current and upcoming high-performance-computing (HPC) architectures. Simulations at the scale of several millions to billion particles have been performed using this software on large scale computing resources. This software can be applied to non-reacting solids dominant flows in silos, hoppers and screw conveyors as well as in high temperature reacting systems such as screw kilns and auger reactors.

Sitaraman, Hariswaran↗

Transmission Level High Temperature Superconducting Fault Current Limiter

The primary objective of this project was to demonstrate the feasibility and reliability of utilizing high-temperature superconducting (HTS) materials in a Transmission Level Superconducting Fault Current Limiter (SFCL) application. During the project, the type of high-temperature superconducting material used evolved from 1 st generation (1G) BSCCO-2212 melt cast bulk high-temperature superconductors to 2 nd generation (2G) YBCO-based high-temperature superconducting tape. The SFCL employed SuperPower's “Matrix” technology, that offers modular features to enable scale up to transmission voltage levels. The SFCL consists of individual modules that contain elements and parallel inductors that assist in carrying the current during the fault. A number of these modules are arranged in an m x n array to form the current-limiting matrix.

24 POWER TRANSMISSION AND DISTRIBUTION↗

VTK-m User's Guide (V.1.6)

High-performance computing relies on ever finer threading. Advances in processor technology include ever greater numbers of cores, hyperthreading, accelerators with integrated blocks of cores, and special vectorized instructions, all of which require more software parallelism to achieve peak performance. Traditional visualization solutions cannot support this extreme level of concurrency. Extreme scale systems require a new programming model and a fundamental change in how we design algorithms. To address these issues we created VTK-m: the visualization toolkit for multi-/many-core architectures.

97 MATHEMATICS AND COMPUTING↗

Initial Investigation of Coupled Electron-Photon Transport with SCEPTRE and RAPTURE (Rev.1.1)

The SCEPTRE1 code models coupled photon and electron transport in material media using discrete ordinates methods. The code can use different solvers in 1D and 3D in parallel, promising users the ability to run problems that are significant both in physics and computational scale. One capability that is perhaps unique at this time in the NNSA complex is SCEPTRE’s coupled photon– electron transport physics in a discrete ordinates approach. For example, incident x–rays can generate a significant electron population, whose transport can be simulated within the same code. In this context, fully–coupled means that photons can produce electrons and electrons can produce photons; uncoupled or no–coupling means photons do not produce electrons. Partial–coupling, an intermediate option in which photons can produce electrons but electrons do not produce photons, is not considered in the present work. The MCNP code can treat this physics with a Monte Carlo approach. MCNP should be viewed as complementary to SCEPTRE in both computational method (Monte Carlo versus discrete ordinates) as well as data libraries. SCEPTRE and MCNP should provide important checks on each other, especially from complementary modeling frameworks of a S n (discrete ordinates) mesh based method versus Monte Carlo particle based method. In order to learn more about SCEPTRE, and how it might inform engineering work at the Laboratory, we used it to carry out a set of initial studies. This was a series of 1D simulations of photon beams hitting Aluminum slabs. Our studies mainly used SCEPTRE directly, and made little use of the closely associated RAPTURE code (more on this below). The goals of these studies were first, to familiarize ourselves with operating the code, and second, to begin to assess the importance of coupled electron–photon transport. To support these studies, we began to develop a set of scripts to initialize inputs, run tools, process outputs, and plot results. An initial version of these scripts has been committed to the Lightning workflow repository. This memo relates the results of those studies.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Polarized fusion, its Implications and plans for Direct Measurements in a Tokamak

Our energy-hungry world is burning. A long-term solution, possibly the only ultimate one, that is just approaching the horizon after decades of struggle, is fusion. Recent developments allow us to apply techniques from spin physics to advance the viability of this critical option. The cross section for the primary fusion fuel in a tokamak reactor, D+T /to sigma + n, would be increased by a factor of 1.5 if the fuels were spin polarized parallel to the local field. Simulations predict further non-linear power gains in large-scale machines such as ITER, due to increased alpha heating. These are significant enhancements that could lower the requirements needed to reach ignition and could be used to extend useful reactor life by compensating for neutron degradation of critical components. The potential realization of such benefits rests on the survival of spin polarization for periods comparable to the energy containment time. Interest in polarized fuel options had an initial peak of activity in the 1980s, where calculations predicted that polarizations could in fact survive a plasma environment. However, concerns were raised regarding the cumulative impacts of fuel recycling from the reactor walls. In addition, the technical challenges of preparing and handling polarized materials prevented any direct tests. Over the last several decades, this situation has changed dramatically. Detailed simulations of the ITER plasma have projected negligible wall recycling in a high power reactor. In addition, a combination of advances in three areas - polarized material technologies developed for nuclear and particle physics as well as for medical imaging, polymer pellets developed for Inertial Con nement, and cryogenic injection guns developed for delivering fuel into the core of tokamaks - have matured to the point where a direct in situ measurement is possible. A Jefferson Lab - DIII-D/General Atomics - University of Virginia collaboration is developing designs for a proof-of-principle polarization survival experiment using the isospin mirror reaction, D +3 He /to sigma + p, at the DIII-D tokamak in San Diego.

Sandorfi, Andrew↗

On Simulating the Formation of Structured, Crystalline Systems via Non-classical Pathways

Observations in crystal growth and assembly from recent in situ methods suggest alternative, non-classical crystallization pathways play an important role in the determination of the micro- and meso- structures in crystalline systems. These processes display parallels that cross-cut multiple disciplines investigating crystallization across four orders of magnitude in size scales and widely differing environments, hinting that alternative crystal growth pathways may be a fundamental scheme in natural crystal formation. Using a system of short-range attractive microbeads, we demonstrate that the addition of a small concentration of sub-species incommensurate with the lattice spacing of the dominant species results in a stark change in crystal size and morphology. These changes are attributed to the presence of fleeting, amorphous-like configurations of beads that ultimately change the melting and growth dynamics in preferred directions. From these real-time observations, we hypothesize the amorphous mineral precursors present in biological mineralized tissues undergo similar non-classical crystallization processes resulting in the complex structures found in biomineralization.

36 MATERIALS SCIENCE↗

RAYLEIGH QUOTIENT ITERATION IN 3D, DETERMINISTIC NEUTRON TRANSPORT

Today’s “grand challenge” neutron transport problems require 3-D meshes with billions of cells, hundreds of energy groups, and accurate quadratures and scattering expansions. Leadership-class computers provide platforms on which high-fidelity fluxes can be calculated. However, appropriate methods are needed that can use these machines effectively. Such methods must be able to to use hundreds of thousands of cores and have good convergence properties. Rayleigh quotient iteration (RQI) is an eigenvalue solver that has been added to the SN code Denovo to address convergence. Rayleigh quotient iteration is an optimal shifted inverse iteration method that should converge in fewer iterations than the more common power method and other shifted inverse iteration methods for many problems of interest. Denovo’s RQI uses a new multigroup Krylov solver for the fixed source solutions inside every iteration that allows parallelization in energy in addition to space and angle. This Krylov solver has been shown to scale successfully to 200,000 cores: for example one test problem scaled from 69,120 cores to 190,080 cores with 98% efficiency. This paper shows that RQI works for some small problems. However, the Krylov method upon which it relies does not always converge because RQI creates ill-conditioned systems. This result leads to the conclusion that preconditioning is needed to allow this method to be applicable to a wider variety of problems.

Slaybaugh, R. N.↗

Deconvolute individual genomes from metagenome sequences through short read clustering

Metagenome assembly from short next-generation sequencing data is a challenging process due to its large scale and computational complexity. Clustering short reads by species before assembly offers a unique opportunity for parallel downstream assembly of genomes with individualized optimization. However, current read clustering methods suffer either false negative (under-clustering) or false positive (over-clustering) problems. Here we extended our previous read clustering software, SpaRC, by exploiting statistics derived from multiple samples in a dataset to reduce the under-clustering problem. Using synthetic and real-world datasets we demonstrated that this method has the potential to cluster almost all of the short reads from genomes with sufficient sequencing coverage. The improved read clustering in turn leads to improved downstream genome assembly quality.

59 BASIC BIOLOGICAL SCIENCES↗

Rayleigh Quotient Iteration in 3D, Deterministic Neutron Transport

Today's "grand challenge" neutron transport problems require 3-D meshes with billions of cells, hundreds of energy groups, and accurate quadratures and scattering expansions. Leadership-class computers provide platforms on which high-fidelity fluxes can be calculated. However, appropriate methods are needed that can use these machines effectively. Such methods must be able to use hundreds of thousands of cores and have good convergence properties. Rayleigh quotient iteration (RQI) is an eigenvalue solver that has been added to the Sn code Denovo to address convergence. Rayleigh quotient iteration is an optimal shifted inverse iteration method that should converge in fewer iterations than the more common power method and other shifted inverse iteration methods for many problems of interest. Denovo's RQI uses a new multigroup Krylov solver for the fixed source solutions inside every iteration that allows parallelization in energy in addition to space and angle. This Krylov solver has been shown to scale successfully to 200,000 cores: for example one test problem scaled from 69,120 cores to 190,080 cores with 98% efficiency. This paper shows that RQI works for some small problems. However, the Krylov method upon which it relies does not always converge because RQI creates ill-conditioned systems. This result leads to the conclusion that preconditioning is needed to allow this method to be applicable to a wider variety of problems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Network Offoaded Hierarchical Collectives Using ConnectX-2's CORE-Direct Capabilities

As the scale of High Performance Computing (HPC) systems continues to increase, demanding that we extract even more parallelism from applications, the need to move communication management away from the Central Processing Unit (CPU) becomes even greater. Moving this management to the network, frees up CPU cycles for computation, making it possible to overlap computation and communication. In this paper we continue to investigate how to best use the new CORE-Direct support added in the ConnectX-2 Host Channel Adapter (HCA) for creating high performance, asynchronous collective operations that are managed by the HCA. Specifically we consider the network topology, creating a two-level communication hierarchy, reducing the MPI Barrier completion time by 45%, from 26.59 microseconds, when not considering network topology, to 14.72 microseconds, with the CPU based collective barrier operation completing in 19.04 microseconds. The nonblocking barrier algorithm has similar performance, with about 50% of that time available for computation.

99 GENERAL AND MISCELLANEOUS↗

Advanced Control of Next Generation Offshore Wind Turbines

Advanced turbine controls and structural dampers have the potential to significantly reduce the cost of energy (CoE) for offshore wind turbines. Progress made in these two areas on a Department of Energy (DoE) funded program is reported. A lidar-assisted control strategy, with objective to reduce component loads and increase energy capture, is developed and implemented. The controller has been tested in both simulations and on a 3MW utility-scale prototype. The controller results indicate a significant reduction in the tower fatigue loads. In a parallel effort, potential of a passive and semi-active tuned-mass damper (TMD) is evaluated to mitigate fatigue and extreme loads. Simulation results with passive and semi-active TMD indicate significant load reduction for tower and substructure for both fixed-bottom and floating wind turbines. Finally, levelized cost of energy modeling process to account for benefits of advanced controls is discussed.

structural dampers. cost of energy, lidar-assisted↗

PoPLAR: Portal for Petascale Lifescience Applications and Research

Background: We are focusing specifically on fast data analysis and retrieval in bioinformatics that will have a direct impact on the quality of human health and the environment. The exponential growth of data generated in biology research, from small atoms to big ecosystems, necessitates an increasingly large computational component to perform analyses. Novel DNA sequencing technologies and complementary high-throughput approaches–such as proteomics, genomics, metabolomics, and meta-genomics–drive data-intensive bioinformatics. While individual research centers or universities could once provide for these applications, this is no longer the case. Today, only specialized national centers can deliver the level of computing resources required to meet the challenges posed by rapid data growth and the resulting computational demand. Consequently, we are developing massively parallel applications to analyze the growing flood of biological data and contribute to the rapid discovery of novel knowledge. Methods: The efforts of previous National Science Foundation (NSF) projects provided for the generation of parallel modules for widely used bioinformatics applications on the Kraken supercomputer. We have profiled and optimized the code of some of the scientific community’s most widely used desktop and small-cluster-based applications, including BLAST from the National Center for Biotechnology Information (NCBI), HMMER, and MUSCLE; scaled them to tens of thousands of cores on high-performance computing (HPC) architectures; made them robust and portable to next-generation architectures; and incorporated these parallel applications in science gateways with a web-based portal. Results: This paper will discuss the various developmental stages, challenges, and solutions involved in taking bioinformatics applications from the desktop to petascale with a front-end portal for very-large-scale data analysis in the life sciences. Conclusions: This research will help to bridge the gap between the rate of data generation and the speed at which scientists can study this data. The ability to rapidly analyze data at such a large scale is having a significant, direct impact on science achieved by collaborators who are currently using these tools on supercomputers.

59 BASIC BIOLOGICAL SCIENCES↗

SDI CFD MODELING ANALYSIS

The Savannah River Remediation (SRR) Organization requested that Savannah River National Laboratory (SRNL) develop a Computational Fluid Dynamics (CFD) method to mix and blend the miscible contents of the blend tanks to ensure the contents are properly blended before they are transferred from the blend tank; such as, Tank 50H, to the Salt Waste Processing Facility (SWPF) feed tank. The work described here consists of two modeling areas. They are the mixing modeling analysis during miscible liquid blending operation, and the flow pattern analysis during transfer operation of the blended liquid. The transient CFD governing equations consisting of three momentum equations, one mass balance, two turbulence transport equations for kinetic energy and dissipation rate, and one species transport were solved by an iterative technique until the species concentrations of tank fluid were in equilibrium. The steady-state flow solutions for the entire tank fluid were used for flow pattern analysis, for velocity scaling analysis, and the initial conditions for transient blending calculations. A series of the modeling calculations were performed to estimate the blending times for various jet flow conditions, and to investigate the impact of the cooling coils on the blending time of the tank contents. The modeling results were benchmarked against the pilot scale test results. All of the flow and mixing models were performed with the nozzles installed at the mid-elevation, and parallel to the tank wall. From the CFD modeling calculations, the main results are summarized as follows: (1) The benchmark analyses for the CFD flow velocity and blending models demonstrate their consistency with Engineering Development Laboratory (EDL) and literature test results in terms of local velocity measurements and experimental observations. Thus, an application of the established criterion to SRS full scale tank will provide a better, physically-based estimate of the required mixing time, and elevation of transfer pump for minimum sludge disturbance. (2) An empirical equation for a tank with no cooling coils agrees reasonably with the current modeling results for the dual jet. (3) From the sensitivity study of the cooling coils, it was found that the tank mixing time for the coiled tank was about two times longer than that of the tank fluid with no coils under the 1/10th scale, while the coiled tank required only 50% longer than the one without coils under the full scale Tank 50H. In addition, the time difference is reduced when the pumping U{sub o}d{sub o} value is increased for a given tank. (4) The blending time for T-shape dual jet pump is about 20% longer than that of 15{sup o} upward V-shape pump under the 1/10th pilot-scale tank, while the time difference between the two pumps is about 12% for the full-scale Tank 50H. These results are consistent with the literature information. (5) A transfer pump with a solid-plate suction screen operating at 130 gpm can be located 9.5 inches above settled sludge for 2 in screen height in a 85 ft waste tank without disturbing any sludge. Detailed results are summarized in Table 13. Final pump performance calculations were made by using the established CW pump design, and operating conditions to satisfy the two requirements of minimum sludge disturbance, and adequate blending of tank contents. The final calculation results show that the blending times for the coiled and uncoiled tanks coupled with the CW pump design are 159 and 83 minutes, respectively. All the results are provided in Table 16.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Towards scaling community detection on distributed-memory heterogeneous systems

Distributed multi-GPU systems pose significant challenges and opportunities for efficient execution of parallel applications. Graph algorithms are generally characterized by irregular memory accesses, low computation to communication ratios, and load balancing problems that are especially hard to address on multi-GPU systems. Graph community detection is an important problem in the emerging domain of graph analytics with numerous applications. In this paper, we present our ongoing work on distributed-memory multi-GPU implementation for graph community detection. Our work parallelizes the widely used (albeit serial) Louvain method on distributed multi-GPU platforms. Supported by an extensive set of experiments on a multi-GPU enabled supercomputer (OLCF Summit) and a single compute node (Nvidia DGX-2®), we demonstrate competitive performance to existing distributed-memory CPU-based implementation, and up to 6.5 better results than Nvidia RAPIDS® CUGRAPH. To the best of our knowledge, this work represents the first effort for community detection on distributed multi-GPU systems. Our approach and related findings can be extended to numerous other iterative graph algorithms on multi-GPU systems.

97 MATHEMATICS AND COMPUTING↗

GraphReduce: Processing Large-Scale Graphs on Accelerator-Based Systems

Recent work on real-world graph analytics has sought to leverage the massive amount of parallelism offered by GPU devices, but challenges remain due to the inherent irregularity of graph algorithms and limitations in GPU-resident memory for storing large graphs. We present GraphReduce, a highly efficient and scalable GPU-based framework that operates on graphs that exceed the device’s internal memory capacity. GraphReduce adopts a combination of edge- and vertex-centric implementations of the Gather-Apply-Scatter programming model and operates on multiple asynchronous GPU streams to fully exploit the high degrees of parallelism in GPUs with efficient graph data movement between the host and device.

Architecture optimization, reuse, performance, ene↗

FOX: A Fault-Oblivious Extreme-Scale Execution Environment Boston University Final Report Project Number: DE-SC0005365

Exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today's machines. Systems software for exascale machines must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massive data analysis in a highly unreliable hardware environment with billions of threads of execution. The FOX project explored systems software and runtime support for a new approach to the data and work distribution for fault oblivious application execution. Our major OS work at Boston University focused on developing a new light-weight operating systems model that provides an appropriate context for both multi-core and multi-node application development. This work is discussed in section 1. Early on in the FOX project BU developed infrastructure for prototyping dynamic HPC environments in which the sets of nodes that an application is run on can be dynamically grown or shrunk. This work was an extension of the Kittyhawk project and is discussed in section 2. Section 3 documents the publications and software repositories that we have produced. To put our work in context of the complete FOX project contribution we include in section 4 an extended version of a paper that documents the complete work of the FOX team.

97 MATHEMATICS AND COMPUTING↗