Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network partition”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Solubilities of nitrogen and noble gases in basalt melt

Nitrogen and noble gases are important tracers in geochemistry and chosmochemistry. Compared to noble gases, however, physicochemical properties of nitrogen, such as solubility in melt or melt/silicate partition, are not well known. Solubility of nitrogen in basalt melt depends on redox condition of the atmosphere. For example, solubility of nitrogen in E chondrite melt under reducing conditions is as high as 2 mol percent at 1500 C, suggesting that nitrogen is chemically dissolved in silicate melts, i.e., being dissolved as free anions or replacing oxygen sites in silicate network. However, the solubility and the dissolution mechanism of nitrogen under oxidizing conditions are not well investigated. To obtain nitrogen solubility in silicate melts under various redox conditions and to understand its mechanism, we are conducting experiments by using (15)N(15)N-labeled nitrogen gas. This makes it easy to distinguish dissolved nitrogen from later contamination of atmospheric nitrogen, and hence enables us to measure the nitrogen solubility accurately. As a preliminary experiment, we have measured solubility of nitrogen in basalt melt under the atmospheric oxygen pressure.

Miyazaki, A.↗
NASA NTRS1990

Method of up-front load balancing for local memory parallel processors

In a parallel processing computer system with multiple processing units and shared memory, a method is disclosed for uniformly balancing the aggregate computational load in, and utilizing minimal memory by, a network having identical computations to be executed at each connection therein. Read-only and read-write memory are subdivided into a plurality of process sets, which function like artificial processing units. Said plurality of process sets is iteratively merged and reduced to the number of processing units without exceeding the balance load. Said merger is based upon the value of a partition threshold, which is a measure of the memory utilization. The turnaround time and memory savings of the instant method are functions of the number of processing units available and the number of partitions into which the memory is subdivided. Typical results of the preferred embodiment yielded memory savings of from sixty to seventy five percent.

Baffes, Paul Thomas↗
NASA NTRS1994

Methodologies and systems for heterogeneous concurrent computing

Heterogeneous concurrent computing is gaining increasing acceptance as an alternative or complementary paradigm to multiprocessor-based parallel processing as well as to conventional supercomputing. While algorithmic and programming aspects of heterogeneous concurrent computing are similar to their parallel processing counterparts, system issues, partitioning and scheduling, and performance aspects are significantly different. In this paper, we discuss critical design and implementation issues in heterogeneous concurrent computing, and describe techniques for enhancing its effectiveness. In particular, we highlight the system level infrastructures that are required, aspects of parallel algorithm development that most affect performance, system capabilities and limitations, and tools and methodologies for effective computing in heterogeneous networked environments. We also present recent developments and experiences in the context of the PVM system and comment on ongoing and future work.

Sunderam, V. S.↗
NASA NTRS2013

Impact of Surface Roughness and Soil Texture on Mineral Dust Emission Fluxes Modeling

Dust production models (DPM) used to estimate vertical fluxes of mineral dust aerosols over arid regions need accurate data on soil and surface properties. The Laboratoire Inter-Universitaire des Systemes Atmospheriques (LISA) data set was developed for Northern Africa, the Middle East, and East Asia. This regional data set was built through dedicated field campaigns and include, among others, the aerodynamic roughness length, the smooth roughness length of the erodible fraction of the surface, and the dry (undisturbed) soil size distribution. Recently, satellite-derived roughness length and high-resolution soil texture data sets at the global scale have emerged and provide the opportunity for the use of advanced schemes in global models. This paper analyzes the behavior of the ERS satellite-derived global roughness length and the State Soil Geographic data base-Food and Agriculture Organization of the United Nations (STATSGO-FAO) soil texture data set (based on wet techniques) using an advanced DPM in comparison to the LISA data set over Northern Africa and the Middle East. We explore the sensitivity of the drag partition scheme (a critical component of the DPM) and of the dust vertical fluxes (intensity and spatial patterns) to the roughness length and soil texture data sets. We also compare the use of the drag partition scheme to a widely used preferential source approach in global models. Idealized experiments with prescribed wind speeds show that the ERS and STATSGO-FAO data sets provide realistic spatial patterns of dust emission and friction velocity thresholds in the region. Finally, we evaluate a dust transport model for the period of March to July 2011 with observed aerosol optical depths from Aerosol Robotic Network sites. Results show that ERS and STATSGO-FAO provide realistic simulations in the region.

textures↗
NASA NTRS1990

Advanced systems engineering and network planning support

The objective of this task was to take a fresh look at the NASA Space Network Control (SNC) element for the Advanced Tracking and Data Relay Satellite System (ATDRSS) such that it can be made more efficient and responsive to the user by introducing new concepts and technologies appropriate for the 1997 timeframe. In particular, it was desired to investigate the technologies and concepts employed in similar systems that may be applicable to the SNC. The recommendations resulting from this study include resource partitioning, on-line access to subsets of the SN schedule, fluid scheduling, increased use of demand access on the MA service, automating Inter-System Control functions using monitor by exception, increase automation for distributed data management and distributed work management, viewing SN operational control in terms of the OSI Management framework, and the introduction of automated interface management.

Walters, David H.↗
NASA NTRS1994

Optimizing tertiary storage organization and access for spatio-temporal datasets

We address in this paper data management techniques for efficiently retrieving requested subsets of large datasets stored on mass storage devices. This problem represents a major bottleneck that can negate the benefits of fast networks, because the time to access a subset from a large dataset stored on a mass storage system is much greater that the time to transmit that subset over a network. This paper focuses on very large spatial and temporal datasets generated by simulation programs in the area of climate modeling, but the techniques developed can be applied to other applications that deal with large multidimensional datasets. The main requirement we have addressed is the efficient access of subsets of information contained within much larger datasets, for the purpose of analysis and interactive visualization. We have developed data partitioning techniques that partition datasets into 'clusters' based on analysis of data access patterns and storage device characteristics. The goal is to minimize the number of clusters read from mass storage systems when subsets are requested. We emphasize in this paper proposed enhancements to current storage server protocols to permit control over physical placement of data on storage devices. We also discuss in some detail the aspects of the interface between the application programs and the mass storage system, as well as a workbench to help scientists to design the best reorganization of a dataset for anticipated access patterns.

Chen, Ling Tony↗
NASA NTRS1994

Spacecraft On-Board Information Extraction Computer (SOBIEC)

The Jet Propulsion Laboratory is the Technical Monitor on an SBIR Program issued for Irvine Sensors Corporation to develop a highly compact, dual use massively parallel processing node known as SOBIEC. SOBIEC couples 3D memory stacking technology provided by nCUBE. The node contains sufficient network Input/Output to implement up to an order-13 binary hypercube. The benefit of this network, is that it scales linearly as more processors are added, and it is a superset of other commonly used interconnect topologies such as: meshes, rings, toroids, and trees. In this manner, a distributed processing network can be easily devised and supported. The SOBIEC node has sufficient memory for most multi-computer applications, and also supports external memory expansion and DMA interfaces. The SOBIEC node is supported by a mature set of software development tools from nCUBE. The nCUBE operating system (OS) provides configuration and operational support for up to 8000 SOBIEC processors in an order-13 binary hypercube or any subset or partition(s) thereof. The OS is UNIX (USL SVR4) compatible, with C, C++, and FORTRAN compilers readily available. A stand-alone development system is also available to support SOBIEC test and integration.

Eisenman, David↗
NASA NTRS2008

'Electrically-Hot' Convection and Tropical Cyclone Development in the Eastern Atlantic

The depth and intensity of convective-scale "hot" towers in intensifying tropical disturbances has been hypothesized to play a role in tropical cyclogenesis via dynamic and thermodynamic feedbacks on the larger meso-to-synoptic scale circulation. In this investigation we investigate the role that widespread and/or intense lightning-producing convection (i.e., "electrically-hot towers") resident in African Easterly Waves (AEW) may play in tropical cyclogenesis over the eastern Atlantic Ocean. NCEP reanalysis data for the months of July to November for the years 2004, 2006, and 2007 are analyzed for the domain of 5 N - 15 N and 500W - 300 E. Specifically, NCEP data for individual AEWs are partitioned into northerly, southerly, trough, and ridge phases using the 700 hPa meridional winds. Subsequently, information from National Hurricane Center storm reports were divided up into developing and non-developing waves (i.e. tropical cyclogenesis). Finally, composites were created of developing and non-developing waves using the NCEP variables, but with the inclusion of lightning flash count and infrared brightness temperature information. The Zeus and World Wide Lightning Location Network lightning data were used for the lightning information, and the IR brightness temperature data was extracted from the NASA global-merged infrared brightness temperature dataset.

Leppert, Kenneth, II↗
NASA NTRS2000

The Urban Fabric of the City as Its Affects Thermal Energy Responses Derived from Remote Sensing Data

The physical geography of the city affects numerous aspects of its interlinked biophysical, social, and land-atmosphere characteristics - those attributes that come together to form the total urban environment. One approach to studying the multitude of interactions that occur as a result of urbanization is to view the city from a systems ecology perspective, where energy and material cycle into and out of the urban milieu. Thus, the urban ecosystem is synergistic in linking land, air, water, and living organisms in a vast network of interrelated physical, human, and biological process. Given the number and the shear complexity of the exchanges and, ultimately, their effects, that occur within the urban environment, we are focusing our research on looking at how the morphology or urban fabric of the city, drives thermal energy exchanges across the urban landscape. The study of thermal energy attributes for different cities provides insight into how thermal fluxes and characteristics are partitioned across the city landscape in response to each city's morphology. We are using thermal infrared remote sensing data obtained at a high spatial resolution from aircraft, along with satellite data, to identify and quantify thermal energy characteristics for 4 U.S. cities: Atlanta, GA, Baton Rouge, LA, Salt Lake City, UT, and Sacramento, CA. Analysis of how thermal energy is spatially distributed across the urban landscapes for these cities provides a unique perspective for understanding how the differing morphology of cities forces land-atmosphere exchanges, such as the urban heat island effect, as well as related meteorological and air quality interactions. Keyword: urban ecosystems, remote sensing, urban heat island

Quattrochi, Dale A.↗
NASA NTRS2004

[PVFS 2000: An operational parallel file system for Beowulf]

The approach has been to develop Parallel Virtual File System version 2 (PVFS2) , retaining the basic philosophy of the original file system but completely rewriting the code. It shows the architecture of the server and client components. BMI - BMI is the network abstraction layer. It is designed with a common driver and modules for each protocol supported. The interface is non-blocking, and provides mechanisms for optimizations including pinning user buffers. Currently TCP/IP and GM(Myrinet) modules have been implemented. Trove -Trove is the storage abstraction layer. It provides for storing both data spaces and name/value pairs. Trove can also be implemented using different underlying storage mechanisms including native files, raw disk partitions, SQL and other databases. The current implementation uses native files for data spaces and Berkeley db for name/value pairs.

Ligon, Walt↗
NASA NTRS1994

Galileo mission planning for Low Gain Antenna based operations

The Galileo mission operations concept is undergoing substantial redesign, necessitated by the deployment failure of the High Gain Antenna, while the spacecraft is on its way to Jupiter. The new design applies state-of-the-art technology and processes to increase the telemetry rate available through the Low Gain Antenna and to increase the information density of the telemetry. This paper describes the mission planning process being developed as part of this redesign. Principal topics include a brief description of the new mission concept and anticipated science return (these have been covered more extensively in earlier papers), identification of key drivers on the mission planning process, a description of the process and its implementation schedule, a discussion of the application of automated mission planning tool to the process, and a status report on mission planning work to date. Galileo enhancements include extensive reprogramming of on-board computers and substantial hard ware and software upgrades for the Deep Space Network (DSN). The principal mode of operation will be onboard recording of science data followed by extended playback periods. A variety of techniques will be used to compress and edit the data both before recording and during playback. A highly-compressed real-time science data stream will also be important. The telemetry rate will be increased using advanced coding techniques and advanced receivers. Galileo mission planning for orbital operations now involves partitioning of several scarce resources. Particularly difficult are division of the telemetry among the many users (eleven instruments, radio science, engineering monitoring, and navigation) and allocation of space on the tape recorder at each of the ten satellite encounters. The planning process is complicated by uncertainty in forecast performance of the DSN modifications and the non-deterministic nature of the new data compression schemes. Key mission planning steps include quantifying resource or capabilities to be allocated, prioritizing science observations and estimating resource needs for each, working inter-and intra-orbit trades of these resources among the Project elements, and planning real-time science activity. The first major mission planning activity, a high level, orbit-by-orbit allocation of resources among science objectives, has already been completed; and results are illustrated in the paper. To make efficient use of limited resources, Galileo mission planning will rely on automated mission planning tools capable of dealing with interactions among time-varying downlink capability, real-time science and engineering data transmission, and playback of recorded data. A new generic mission planning tool is being adapted for this purpose.

Gershman, R.↗
NASA NTRS1994

On k-ary n-cubes: Theory and applications

Many parallel processing networks can be viewed as graphs called k-ary n-cubes, whose special cases include rings, hypercubes and toruses. In this paper, combinatorial properties of k-ary n-cubes are explored. In particular, the problem of characterizing the subgraph of a given number of nodes with the maximum edge count is studied. These theoretical results are then used to compute a lower bounding function in branch-and-bound partitioning algorithms and to establish the optimality of some irregular partitions.

Mao, Weizhen↗
NASA NTRS2001

A Latency-Tolerant Partitioner for Distributed Computing on the Information Power Grid

NASA's Information Power Grid (IPG) is an infrastructure designed to harness the power of graphically distributed computers, databases, and human expertise, in order to solve large-scale realistic computational problems. This type of a meta-computing environment is necessary to present a unified virtual machine to application developers that hides the intricacies of a highly heterogeneous environment and yet maintains adequate security. In this paper, we present a novel partitioning scheme. called MinEX, that dynamically balances processor workloads while minimizing data movement and runtime communication, for applications that are executed in a parallel distributed fashion on the IPG. We also analyze the conditions that are required for the IPG to be an effective tool for such distributed computations. Our results show that MinEX is a viable load balancer provided the nodes of the IPG are connected by a high-speed asynchronous interconnection network.

Das, Sajal K.↗
NASA NTRS1993

On-line upgrade of program modules using AdaPT

One purpose of our research is the investigation of the effectiveness and expressiveness of AdaPT, a set of language extensions to Ada 83, for distributed systems. As a part of that effort, we are now investigating the subject of replacing, e.g. upgrading, software modules while the software system remains in operation. The AdaPT language extensions provide a good basis for this investigation for several reasons: they include the concept of specific, self-contained program modules which can be manipulated; support for program configuration is included in the language; and although the discussion will be in terms of the AdaPT language, the AdaPT to Ada 83 conversion methodology being developed as another part of this project will provide a basis for the application of our findings to Ada 83 and Ada 9X systems. The purpose of this investigation is to explore the basic mechanisms of the replacement process. With this purpose in mind, we will avoid including issues whose presence would obscure these basic mechanisms by introducing additional, unrelated concerns. Thus, while replacement in the presence of real-time deadlines, heterogeneous systems, and unreliable networks is certainly a topic of interest, we will first gain an understanding of the basic processes in the absence of such concerns. The extension of the replacement process to more complex situations can be made later. A previous report established an overview of the module replacement problem, a taxonomy of the various aspects of the replacement process, and a solution to one case in the replacement taxonomy. This report provides solutions to additional cases in the replacement process taxonomy: replacement of partitions with state and replacement of nodes. The solutions presented here establish the basic principles for module replacement. Extension of these solutions to other more complicated cases in the replacement taxonomy is direct, though requiring substantial work beyond the available funding.

Waldrop, Raymond S.↗
NASA NTRS2014

Using SpF to Achieve Petascale for Legacy Pseudospectral Applications

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community. We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. Highlevel abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely inprocessor. The granularity of domain decomposition provided by SpF is only constrained by the datalocality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures. In this presentation, we will describe our experience in porting legacy pseudospectral models, MoSST and DYNAMO, to use SpF as well as present preliminary performance results provided by the improved scalability.

DYNAMO↗
NASA NTRS2001

Global Modeling of Tropospheric Chemistry with Assimilated Meteorology: Model Description and Evaluation

We present a first description and evaluation of GEOS-CHEM, a global three-dimensional (3-D) model of tropospheric chemistry driven by assimilated meteorological observations from the Goddard Earth Observing System (GEOS) of the NASA Data Assimilation Office (DAO). The model is applied to a 1-year simulation of tropospheric ozone-NOx-hydrocarbon chemistry for 1994, and is evaluated with observations both for 1994 and for other years. It reproduces usually to within 10 ppb the concentrations of ozone observed from the worldwide ozonesonde data network. It simulates correctly the seasonal phases and amplitudes of ozone concentrations for different regions and altitudes, but tends to underestimate the seasonal amplitude at northern midlatitudes. Observed concentrations of NO and peroxyacetylnitrate (PAN) observed in aircraft campaigns are generally reproduced to within a factor of 2 and often much better. Concentrations of HNO3 in the remote troposphere are overestimated typically by a factor of 2-3, a common problem in global models that may reflect a combination of insufficient precipitation scavenging and gas-aerosol partitioning not resolved by the model. The model yields an atmospheric lifetime of methylchloroform (proxy for global OH) of 5.1 years, as compared to a best estimate from observations of 5.5 plus or minus 0.8 years, and simulates H2O2 concentrations observed from aircraft with significant regional disagreements but no global bias. The OH concentrations are approximately 20% higher than in our previous global 3-D model which included an UV-absorbing aerosol. Concentrations of CO tend to be underestimated by the model, often by 10-30 ppb, which could reflect a combination of excessive OH (a 20% decrease in model OH could be accommodated by the methylchloroform constraint) and an underestimate of CO sources (particularly biogenic). The model underestimates observed acetone concentrations over the South Pacific in fall by a factor of 3; a missing source from the ocean may be implicated.

Bey, Isabelle↗
NASA NTRS2013

SpF: Enabling Petascale Performance for Pseudospectral Dynamo Models

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community.We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. High-level abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely in-processor. The granularity of domain-decomposition provided by SpF is only constrained by the data-locality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures.In this presentation, we will describe the basic architecture of SpF as well as preliminary performance data and experience with adapting legacy dynamo codes. We will conclude with a discussion of planned extensions to SpF that will provide pseudospectral applications with additional flexibility with regard to time integration, linear solvers, and discretization in the radial direction.

Pseudospectral (PS)↗
NASA NTRS1994

Remote Objects Message Exchange (ROME)

The performance of a single program running on a single processor is limited by the character of the processor. Moreover, the cost and difficulty of developing and sustaining programs tend to increase as their size and complexity increase. Clearly there ought to be some advantage in partitioning powerful application software in relatively small and simple components that can run in parallel on multiple processors; the software should run faster and it should be cheaper and easier to deploy. Remote Objects Message Exchange (ROME) is an attempt to provide a single relatively simple, universally available abstraction for data communication among C++ objects. It aims to enable the C++ application developer to specify objects' interactions with other objects wholly in terms of the application domain, without concern for details of interprocess communication. Every ROME-compliant object is conceptually a network peer of every other, as if each one were (for example) a separate UNIX process.

processors application software data communication↗