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 1,261 records · Page 70

Development of Thin Film Thermocouples on Ceramic Materials for Advanced Propulsion System Applications

Thin film thermocouples have been developed for use on metal parts in jet engines to 1000 c. However, advanced propulsion systems are being developed that will use ceramic materials and reach higher temperatures. The purpose of this work is to develop thin film thermocouples for use on ceramic materials. The new thin film thermocouples are Pt13Rh/Pt fabricated by the sputtering process. Lead wires are attached using the parallel-gap welding process. The ceramic materials tested are silicon nitride, silicon carbide, aluminum oxide, and mullite. Both steady state and thermal cycling furnace tests were performed in the temperature range to 1500 C. High-heating-rate tests were performed in an arc lamp heat-flux-calibration facility. The fabrication of the thin film thermocouples is described. The thin film thermocouple output was compared to a reference wire thermocouple. Drift of the thin film thermocouples was determined, and causes of drift are discussed. The results of high heating rate tests up to 2500 C/sec are presented. The stability of the ceramic materials is examined. It is concluded that Pt13Rh/Pt thin film thermocouples are capable of meeting lifetime goals of 50 hours or more up to temperature of 1500 C depending on the stability of the particular ceramic substrate.

Holanda, R.↗

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↗

Electronic Packaging Techniques

A characteristic of aerospace system design is that equipment size and weight must always be kept to a minimum, even in small components such as electronic packages. The dictates of spacecraft design have spawned a number of high-density packaging techniques, among them methods of connecting circuits in printed wiring boards by processes called stitchbond welding and parallel gap welding. These processes help designers compress more components into less space; they also afford weight savings and lower production costs.

Source record↗

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↗

Multidisciplinary Optimization Methods for Aircraft Preliminary Design

This paper describes a research program aimed at improved methods for multidisciplinary design and optimization of large-scale aeronautical systems. The research involves new approaches to system decomposition, interdisciplinary communication, and methods of exploiting coarse-grained parallelism for analysis and optimization. A new architecture, that involves a tight coupling between optimization and analysis, is intended to improve efficiency while simplifying the structure of multidisciplinary, computation-intensive design problems involving many analysis disciplines and perhaps hundreds of design variables. Work in two areas is described here: system decomposition using compatibility constraints to simplify the analysis structure and take advantage of coarse-grained parallelism; and collaborative optimization, a decomposition of the optimization process to permit parallel design and to simplify interdisciplinary communication requirements.

Kroo, Ilan↗

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↗

Evaluating In-Clique and Topological Parallelism Strategies for Junction Tree-Based Bayesian Inference Algorithm on the Cray XMT

Long viewed as a strong statistical inference technique, Bayesian networks have emerged to be an important class of applications for high-performance computing. We have applied an architecture-conscious approach to parallelizing the Lauritzen-Spiegelhalter Junction Tree algorithm for exact inferencing in Bayesian networks. In optimizing the Junction Tree algorithm, we have implemented both in-clique and topological parallelism strategies to best leverage the fine-grained synchronization and massive-scale multithreading of the Cray XMT architecture. Two topological techniques were developed to parallelize the evidence propagation process through the Bayesian network. One technique involves performing intelligent scheduling of junction tree nodes based on its topology and relative size. The second technique involves decomposing the junction tree into a much finer tree-like representation to offer much more opportunities for parallelism. We evaluate these optimizations on five different Bayesian networks and report our findings and observations. Another important contribution of this paper is to demonstrate the application of massive-scale multithreading for load balancing and use of implicit parallelism-based compiler optimizations in designing scalable inferencing algorithms.

99 GENERAL AND MISCELLANEOUS↗

Cloud object store for archive storage of high performance computing data using decoupling middleware

Cloud object storage is enabled for archived data, such as checkpoints and results, of high performance computing applications using a middleware process. A plurality of archived files, such as checkpoint files and results, generated by a plurality of processes in a parallel computing system are stored by obtaining the plurality of archived files from the parallel computing system; converting the plurality of archived files to objects using a log structured file system middleware process; and providing the 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↗

Collective Prefetching for Parallel I/O Systems

Data prefetching can be beneficial for improving parallel I/O system performance, but the amount of benefit depends on how efficiently and swiftly prefetches can be done. In this study, we propose a new prefetching strategy, called collective prefetching. The idea is to exploit the correlation among I/O accesses of multiple processes of a parallel application and carry out prefetches collectively, instead of the traditional strategy of carrying out prefetches by each process individually. The rationale behind this new collective prefetching strategy is that the concurrent processes of the same parallel application have strong correlation with respect to their I/O requests. We present the idea, initial design and implementation of the new collective prefetching strategy in this study. The preliminary experimental results show that this new collective prefetching strategy holds promise for improving parallel I/O performance.

Chen, Yong↗

Parallelization of a Parabolized Navier-Stokes Solver with a Design Optimizer

The design of future supersonic aircraft, such as the High Speed Civil Transport (HSCT), will rely heavily on computational methods for aircraft design and the prediction of the complex aerodynamics encountered in flight. Parabolized Navier-Stokes (PNS) equation flow solvers are recognized as efficient and accurate computational tools for the solution of supersonic and hypersonic flow-fields, while design optimizers have the potential to be valuable tools within the overall design process. Presently, however, the execution of the flow solver in conjunction with a design optimizer presents a computationally intensive and formidable problem. To meet the challenges and increasing demand for multidisciplinary numerical tools which are faster, more robust and provide greater functionality, alternative strategies are explored to increase computational throughput by coupling a design optimizer and flow solver in a parallel processing environment. To address this problem the parallel processing of a PNS flow solver with a nonlinear constraint design optimizer is investigated as an alternative computational method.

Pallis, J. M.↗

Methods and apparatuses for information analysis on shared and distributed computing systems

Apparatuses and computer-implemented methods for analyzing, on shared and distributed computing systems, information comprising one or more documents are disclosed according to some aspects. In one embodiment, information analysis can comprise distributing one or more distinct sets of documents among each of a plurality of processes, wherein each process performs operations on a distinct set of documents substantially in parallel with other processes. Operations by each process can further comprise computing term statistics for terms contained in each distinct set of documents, thereby generating a local set of term statistics for each distinct set of documents. Still further, operations by each process can comprise contributing the local sets of term statistics to a global set of term statistics, and participating in generating a major term set from an assigned portion of a global vocabulary.

97 MATHEMATICS AND COMPUTING↗

Application of high-performance computing to numerical simulation of human movement

We have examined the feasibility of using massively-parallel and vector-processing supercomputers to solve large-scale optimization problems for human movement. Specifically, we compared the computational expense of determining the optimal controls for the single support phase of gait using a conventional serial machine (SGI Iris 4D25), a MIMD parallel machine (Intel iPSC/860), and a parallel-vector-processing machine (Cray Y-MP 8/864). With the human body modeled as a 14 degree-of-freedom linkage actuated by 46 musculotendinous units, computation of the optimal controls for gait could take up to 3 months of CPU time on the Iris. Both the Cray and the Intel are able to reduce this time to practical levels. The optimal solution for gait can be found with about 77 hours of CPU on the Cray and with about 88 hours of CPU on the Intel. Although the overall speeds of the Cray and the Intel were found to be similar, the unique capabilities of each machine are better suited to different portions of the computational algorithm used. The Intel was best suited to computing the derivatives of the performance criterion and the constraints whereas the Cray was best suited to parameter optimization of the controls. These results suggest that the ideal computer architecture for solving very large-scale optimal control problems is a hybrid system in which a vector-processing machine is integrated into the communication network of a MIMD parallel machine.

NASA Discipline Musculoskeletal↗

Large-Scale Numerical Simulations of Human Motion

This paper examines the feasibility of using massively-parallel and vector-processing supercomputers to solve large-scale optimal control problems for human movement. Specifically, we compare the computational expense of determining the optimal controls for the single support phase of walking using a conventional serial machine (a Silicon Graphics Personal Iris 4D25 workstation), a MIMD parallel machine (an Intel iPSC/860 comprising 128 processors), and a parallel-vector-processing machine (a Cray Y-MP 8/864). With the human body modeled as a 14 degree-of-freedom linkage actuated by 46 musculotendinous units, computation of the optimal controls for walking could take up to 3 months of CPU time on the Iris. Both the Cray Y-MP and the Intel iPSC/860 are able to reduce this time to practical levels. The optimal control solution for walking can be found with about 77 hours of CPU time on the Cray, and with about 88 hours of CPU time on the Intel. Although the overall speeds of the Cray and the Intel were found to be similar, the unique capabilities of each machine are best suited to different parts of the optimal control algorithm used. The Intel performed best in the calculation of the derivatives of the performance criterion and the constraints. In contrast, the Cray performed best during parameter optimization of the controls. These results suggest that the ideal computer architecture for solving very large-scale optimal control problems is a hybrid system in which a vector-processing machine is integrated into the communication network of a MIMD parallel machine.

Anderson, Frank C.↗

Metaplastic and energy-efficient biocompatible graphene artificial synaptic transistors for enhanced accuracy neuromorphic computing

CMOS-based computing systems that employ the von Neumann architecture are relatively limited when it comes to parallel data storage and processing. In contrast, the human brain is a living computational signal processing unit that operates with extreme parallelism and energy efficiency. Although numerous neuromorphic electronic devices have emerged in the last decade, most of them are rigid or contain materials that are toxic to biological systems. In this work, we report on biocompatible bilayer graphene-based artificial synaptic transistors (BLAST) capable of mimicking synaptic behavior. The BLAST devices leverage a dry ion-selective membrane, enabling long-term potentiation, with ~50 aJ/µm 2 switching energy efficiency, at least an order of magnitude lower than previous reports on two-dimensional material-based artificial synapses. The devices show unique metaplasticity, a useful feature for generalizable deep neural networks, and we demonstrate that metaplastic BLASTs outperform ideal linear synapses in classic image classification tasks. With switching energy well below the 1 fJ energy estimated per biological synapse, the proposed devices are powerful candidates for bio-interfaced online learning, bridging the gap between artificial and biological neural networks.

97 MATHEMATICS AND COMPUTING↗

Niche and neutral processes both shape community structure in parallelized, aerobic, single carbon-source enrichments

We present DNA sequence data in FASTA-formatted files from aerobic environmental microcosms inoculated with a sole carbon source. DNA sequences are of 16S rRNA genes present in DNA extracted from each microcosm along with the environmental samples (soil, water) used to inoculate them. These samples were sequenced using the Illumina MiSeq platform at the Environmental Sample Preparation and Sequencing Facility at Argonne National Laboratory. This data is compatible with standard microbiome analysis pipelines (e.g., QIIME, mothur, etc.).

Flynn, Theodore M.↗