Search NASA⌕ Search

SEARCH · Search NASA

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.

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

At least 523 records · Page 29

Exploiting New Features of COMSOL Version 4 on Conjugate Heat Transfer Problems

Users of COMSOL Multiphysics at version 3.5a and earlier have enjoyedmany features that have provided not only a good user experience atthe GUI interface, but also the capability to solve many classes ofproblems in a consistent manner with the physics being simulated. Withthe new release version 4.0 and later (4+) of COMSOL, the user isprovided a dramatic new interface from which to interact, and many newfeatures ``under the hood'' for solving problems more efficiently and with evengreater accuracy and consistency than before. This paper will exploreseveral of these new version 4+ features for the conjugate heattransfer class of problems. Our environment is challenging in that wedemand high-quality solutions for nuclear-reactor systems and themodels tend to become large and difficult to solve. Areasinvestigated include turbulence modeling, distributed parallelprocessing, solver scaling, and opengl graphics issues in a Linuxcomputing environment.

99 GENERAL AND MISCELLANEOUS↗

Improving Parallel I/O Performance with Data Layout Awareness

Parallel applications can benefit greatly from massive computational capability, but their performance suffers from large latency of I/O accesses. The poor I/O performance has been attributed as a critical cause of the low sustained performance of parallel computing systems. In this study, we propose a data layout-aware optimization strategy to promote a better integration of the parallel I/O middleware and parallel file systems, two major components of the current parallel I/O systems, and to improve the data access performance. We explore the layout-aware optimization in both independent I/O and collective I/O, two primary forms of I/O in parallel applications. We illustrate that the layout-aware I/O optimization could improve the performance of current parallel I/O strategy effectively. The experimental results verify that the proposed strategy could improve parallel I/O performance by nearly 40% on average. The proposed layout-aware parallel I/O has a promising potential in improving the I/O performance of parallel systems.

99 GENERAL AND MISCELLANEOUS↗

Optimizing HPC Fault-Tolerant Environment: An Analytical Approach

The increasingly large ensemble size of modern High-Performance Computing (HPC) systems has drastically increased the possibility of failures. Performance under failures and its optimization become timely important issues facing the HPC community. In this study, we propose an analytical model to predict the application performance. The model characterizes the impact of coordinated checkpointing and system failures on application performance, considering all the factors including workload, the number of nodes, failure arrival rate, recovery cost, and checkpointing interval and overhead. Based on the model, we gauge three parameters, the number of compute nodes, checkpointing interval, and the number of spare nodes to conduct a comprehensive study of performance optimization under failures. Performance scalability under failures is also studied to explore the performance improvement space for different parameters. Experimental results from both synthetic and actual system failure logs confirm that the proposed model and optimization methodologies are effective and feasible.

99 GENERAL AND MISCELLANEOUS↗

Experiences from the Roadrunner petascale hybrid systems

The combination of flexible microprocessors (AMD Opterons) with high-performing accelerators (IBM PowerXCell 8i) resulted in the extremely powerful Roadrunner system. Many challenges in both hardware and software were overcome to achieve its goals. In this talk we detail some of the experiences in achieving performance on the Roadrunner system. In particular we examine several implementations of the kernel application, Sweep3D, using a work-queue approach, a more portable Thread-building-blocks approach, and an MPI on the accelerator approach.

97 MATHEMATICS AND COMPUTING↗

Porting LAMMPS to GPUs.

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. LAMMPS has potentials for soft materials (biomolecules, polymers) and solid-state materials (metals, semiconductors) and coarse-grained or mesoscopic systems. It can be used to model atoms or, more generically, as a parallel particle simulator at the atomic, meso, or continuum scale. LAMMPS runs on single processors or in parallel using message-passing techniques and a spatial-decomposition of the simulation domain. The code is designed to be easy to modify or extend with new functionality.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Aggregation of Real-Time System Monitoring Data for Analyzing Large-Scale Parallel and Distributed Computing Environments

We present a monitoring system for large-scale parallel and distributed computing environments that allows to trade-off accuracy in a tunable fashion to gain scalability without compromising fidelity. The approach relies on classifying each gathered monitoring metric based on individual needs and on aggregating messages containing classes of individual monitoring metrics using a tree-based overlay network. The MRNet-based prototype is able to significantly reduce the amount of gathered and stored monitoring data, e.g., by a factor of ~56 in comparison to the Ganglia distributed monitoring system. A simple scaling study reveals, however, that further efforts are needed in reducing the amount of data to monitor future-generation extreme-scale systems with up to 1,000,000 nodes. The implemented solution did not had a measurable performance impact as the 32-node test system did not produce enough monitoring data to interfere with running applications.

97 MATHEMATICS AND COMPUTING↗

PFLOTRAN-E4D: A parallel open source PFLOTRAN module for simulating time-lapse electrical resistivity data

Time-lapse electrical resistivity tomography (ERT) is finding increased application for remotely monitoring processes occurring in the near subsurface in three-dimensions (i.e. 4D monitoring). However, there are few codes capable of simulating the evolution of subsurface resistivity and corresponding tomographic measurements arising from a particular process, particularly in parallel and with an open source license. Herein we describe and demonstrate an electrical resistivity tomography module for the PFLOTRAN subsurface simulation code, named PFLOTRAN-E4D. The PFLOTRAN-E4D module operates in parallel using a dedicated set of compute cores in a master-slave configuration. At each time step, the master processes receives subsurface states from PFLOTRAN, converts those states to bulk electrical conductivity, and instructs the slave processes to simulate a tomographic data set. The resulting multi-physics simulation capability enables accurate feasibility studies for ERT imaging, the identification of the ERT signatures that are unique to a given process, and facilitates the joint inversion of ERT data with hydrogeological data for subsurface characterization. PFLOTRAN-E4D is demonstrated herein using a field study of stage-driven groundwater/river water interaction ERT monitoring along the Columbia River, Washington, USA. Results demonstrate the complex nature of changes subsurface electrical conductivity, in both the saturated and unsaturated zones, arising from water table changes and from river water intrusion into the aquifer. The results also demonstrate the sensitivity of surface based ERT measurements to those changes over time. PFLOTRAN-E4D is available with the PFLOTRAN development version with an open-source license at https://bitbucket.org/pflotran/pflotran-dev .

Environmental Molecular Sciences Laboratory↗

SCIP: a single-cell image processor toolbox

Abstract Summary Each cell is a phenotypically unique individual that is influenced by internal and external processes, operating in parallel. To characterize the dynamics of cellular processes one needs to observe many individual cells from multiple points of view and over time, so as to identify commonalities and variability. With this aim, we engineered a software, ‘SCIP’, to analyze multi-modal, multi-process, time-lapse microscopy morphological and functional images. SCIP is capable of automatic and/or manually corrected segmentation of cells and lineages, automatic alignment of different microscopy channels, as well as detect, count and characterize fluorescent spots (such as RNA tagged by MS2-GFP), nucleoids, Z rings, Min system, inclusion bodies, undefined structures, etc. The results can be exported into *mat files and all results can be jointly analyzed, to allow studying not only each feature and process individually, but also find potential relationships. While we exemplify its use on Escherichia coli, many of its functionalities are expected to be of use in analyzing other prokaryotes and eukaryotic cells as well. We expect SCIP to facilitate the finding of relationships between cellular processes, from small-scale (e.g. gene expression) to large-scale (e.g. cell division), in single cells and cell lineages. Availability and implementation http://www.ca3-uninova.org/project_scip Supplementary information Supplementary data are available at Bioinformatics online.

Martins, Leonardo (ORCID:0000000333512910)↗

An evaluation of parallel optimization for OpenSolaris Network Stack

Computing is now shifting towards multiprocessing. The fundamental goal of multiprocessing is improved performance through the introduction of additional hardware threads or cores (referred to as 'cores' for simplicity). Modern network stacks can exploit parallel cores to allow either message-based parallelism or connection-based parallelism as a means to enhance performance. OpenSolaris has redesigned and parallelized to better utilize additional cores. Three special technologies, named Softring Set, Soft ring and Squeue are introduced in OpenSolaris for stack parallelization. In this paper, we study the OpenSolaris packet receiving process and its core parallelism optimization techniques. Experiment results show that these techniques allow OpenSolaris to achieve better network I/O performance in multiprocessing environments; however, network stack parallelization has also brought extra overheads for system. An effective and efficient network I/O optimization in multiprocessing environments is required to cross all levers of the network stack from network interface to application.

99 GENERAL AND MISCELLANEOUS↗

Savannah River Site HB-Line Plutonium Oxide Production Process Simulation Model - 17458

The AFS II/Plutonium Oxide Production process is in its initial operational phase at the Savannah River Site's (SRS) HB-Line. The process is new for the facility where it is being performed, but the facility itself has been in use on and off for over 50 years. Beginning this process inside the facility has resulted in multiple process delays, due to both equipment issues and process restrictions. In order to better understand the process and to identify ways to improve facility performance, Savannah River Nuclear Solutions (SRNS), in conjuncture with Newport News Shipbuilding (NNS), developed the HB-Line Process Simulation Model. This tool completely replicates the operations that comprise the HB-Line process and simulates all of the constraints associated with the process. The model realistically accounts for the number of personnel required for a process step, the time required for a process step to occur, rules related to the parallel operation of process steps, and realistic equipment and operational delay data. The result is a tool that allows SRNS to test different scenarios for improving the process throughput, while realistically accounting for potential process delays and restrictions. The tool is currently in use and has allowed SRNS to present to their customer, the National Nuclear Security Administration (NNSA), estimated production capabilities over wide-ranging timetables and assumptions. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Modeling Cooperative Threads to Project GPU Performance for Adaptive Parallelism

Most accelerators, such as graphics processing units (GPUs) and vector processors, are particularly suitable for accelerating massively parallel workloads. On the other hand, conventional workloads are developed for multi-core parallelism, which often scale to only a few dozen OpenMP threads. When hardware threads significantly outnumber the degree of parallelism in the outer loop, programmers are challenged with efficient hardware utilization. A common solution is to further exploit the parallelism hidden deep in the code structure. Such parallelism is less structured: parallel and sequential loops may be imperfectly nested within each other, neigh boring inner loops may exhibit different concurrency patterns (e.g. Reduction vs. Forall), yet have to be parallelized in the same parallel section. Many input-dependent transformations have to be explored. A programmer often employs a larger group of hardware threads to cooperatively walk through a smaller outer loop partition and adaptively exploit any encountered parallelism. This process is time-consuming and error-prone, yet the risk of gaining little or no performance remains high for such workloads. To reduce risk and guide implementation, we propose a technique to model workloads with limited parallelism that can automatically explore and evaluate transformations involving cooperative threads. Eventually, our framework projects the best achievable performance and the most promising transformations without implementing GPU code or using physical hardware. We envision our technique to be integrated into future compilers or optimization frameworks for autotuning.

Meng, Jiayuan↗

Enhanced Sustainability in Treatment of Contaminated Metals for Clearance and Recycling - 20290

Cyclife Sweden AB has, for more than 30 years, provided metal treatment services to the domestic and international nuclear industry with the aim of creating value through metal clearance and recycling. These operations are to a large extent based on the concept that the materials, after pre-treatment, including decontamination, will be melted for clearance. During the melting process, some nuclides separate from the metal while the remaining radioactivity becomes fully homogenized in the metal bath and the resulting ingots, along with the samples taken before casting At a time when activities to fight Climate Challenge are in focus, any savings in energy consumption, in addition to the positive environmental effect of recycling metals back to industry, is more than welcome. If the clearance of certain metallic items can be achieved safely, without using melting, it is the environmentally preferred option provided it carries a reasonable cost. It is even better if an object can go through a decontamination and clearance process prior to re-use inside or outside the nuclear sector. Cyclife Sweden is currently investing in a direct clearance process, to be operated in parallel with the melting process. This new process is expected to be fully operational in the late summer of 2020 and includes pre-treatment, decontamination and heavily shielded clearance measurement installations. The treatment will also allow clearance measurements of larger objects without the need for segmentation, along with allowing objects composed of different materials, like electric motors can be accepted for treatment. This paper gives an overview of the circular economy aspects in a nuclear back-end context, the Cyclife approach to further implement a circular economy approach in the processes, Material Acceptance Criteria for treatment, the facility set-up for the new process and how the melting route and the direct route can be combined in an efficient industrial scale process. To put the new capabilities into perspective, the two different treatment and clearance approaches, i.e. direct clearance and melting, are to be compared. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Ultra-scale Visualization Climate Data Analysis Tools (UV-CDAT)

This report summarizes work carried out by the Ultra-scale Visualization Climate Data Analysis Tools (UV-CDAT) Team for the period of January 1, 2011 through June 30, 2011. It discusses highlights, overall progress, period goals, and collaborations and lists papers and presentations. To learn more about our project, please visit our UV-CDAT website (URL: http://uv-cdat.org). This report will be forwarded to the program manager for the Department of Energy (DOE) Office of Biological and Environmental Research (BER), national and international collaborators and stakeholders, and to researchers working on a wide range of other climate model, reanalysis, and observation evaluation activities. The UV-CDAT executive committee consists of Dean N. Williams of Lawrence Livermore National Laboratory (LLNL); Dave Bader and Galen Shipman of Oak Ridge National Laboratory (ORNL); Phil Jones and James Ahrens of Los Alamos National Laboratory (LANL), Claudio Silva of Polytechnic Institute of New York University (NYU-Poly); and Berk Geveci of Kitware, Inc. The UV-CDAT team consists of researchers and scientists with diverse domain knowledge whose home institutions also include the National Aeronautics and Space Administration (NASA) and the University of Utah. All work is accomplished under DOE open-source guidelines and in close collaboration with the project's stakeholders, domain researchers, and scientists. Working directly with BER climate science analysis projects, this consortium will develop and deploy data and computational resources useful to a wide variety of stakeholders, including scientists, policymakers, and the general public. Members of this consortium already collaborate with other institutions and universities in researching data discovery, management, visualization, workflow analysis, and provenance. The UV-CDAT team will address the following high-level visualization requirements: (1) Alternative parallel streaming statistics and analysis pipelines - Data parallelism, Task parallelism, Visualization parallelism; (2) Optimized parallel input/output (I/O); (3) Remote interactive execution; (4) Advanced intercomparison visualization; (5) Data provenance processing and capture; and (6) Interfaces for scientists - Workflow data analysis and visualization construction tools, and Visualization interfaces.

54 ENVIRONMENTAL SCIENCES↗

Computational Particle Dynamic Simulations on Multicore Processors (CPDMu) Final Report Phase I

Statement of Problem - Department of Energy has many legacy codes for simulation of computational particle dynamics and computational fluid dynamics applications that are designed to run on sequential processors and are not easily parallelized. Emerging high-performance computing architectures employ massively parallel multicore architectures (e.g., graphics processing units) to increase throughput. Parallelization of legacy simulation codes is a high priority, to achieve compatibility, efficiency, accuracy, and extensibility. General Statement of Solution - A legacy simulation application designed for implementation on mainly-sequential processors has been represented as a graph G. Mathematical transformations, applied to G, produce a graph representation {und G} for a high-performance architecture. Key computational and data movement kernels of the application were analyzed/optimized for parallel execution using the mapping G {yields} {und G}, which can be performed semi-automatically. This approach is widely applicable to many types of high-performance computing systems, such as graphics processing units or clusters comprised of nodes that contain one or more such units. Phase I Accomplishments - Phase I research decomposed/profiled computational particle dynamics simulation code for rocket fuel combustion into low and high computational cost regions (respectively, mainly sequential and mainly parallel kernels), with analysis of space and time complexity. Using the research team's expertise in algorithm-to-architecture mappings, the high-cost kernels were transformed, parallelized, and implemented on Nvidia Fermi GPUs. Measured speedups (GPU with respect to single-core CPU) were approximately 20-32X for realistic model parameters, without final optimization. Error analysis showed no loss of computational accuracy. Commercial Applications and Other Benefits - The proposed research will constitute a breakthrough in solution of problems related to efficient parallel computation of particle and fluid dynamics simulations. These problems occur throughout DOE, military and commercial sectors: the potential payoff is high. We plan to license or sell the solution to contractors for military and domestic applications such as disaster simulation (aerodynamic and hydrodynamic), Government agencies (hydrological and environmental simulations), and medical applications (e.g., in tomographic image reconstruction). Keywords - High-performance Computing, Graphic Processing Unit, Fluid/Particle Simulation. Summary for Members of Congress - Department of Energy has many simulation codes that must compute faster, to be effective. The Phase I research parallelized particle/fluid simulations for rocket combustion, for high-performance computing systems.

97 MATHEMATICS AND COMPUTING↗

Cloud object store for checkpoints of high performance computing applications using decoupling middleware

Cloud object storage is enabled for checkpoints of high performance computing applications using a middleware process. A plurality of files, such as checkpoint files, generated by a plurality of processes in a parallel computing system are stored by obtaining said plurality of files from said parallel computing system; converting said plurality of files to objects using a log structured file system middleware process; and providing said objects for storage in a cloud object storage system. The plurality of processes may run, for example, on a plurality of compute nodes. The log structured file system middleware process may be embodied, for example, as a Parallel Log-Structured File System (PLFS). The log structured file system middleware process optionally executes on a burst buffer node.

97 MATHEMATICS AND COMPUTING↗