Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scientific application”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Dynamic file-access characteristics of a production parallel scientific workload

Multiprocessors have permitted astounding increases in computational performance, but many cannot meet the intense I/O requirements of some scientific applications. An important component of any solution to this I/O bottleneck is a parallel file system that can provide high-bandwidth access to tremendous amounts of data in parallel to hundreds or thousands of processors. Most successful systems are based on a solid understanding of the expected workload, but thus far there have been no comprehensive workload characterizations of multiprocessor file systems. This paper presents the results of a three week tracing study in which all file-related activity on a massively parallel computer was recorded. Our instrumentation differs from previous efforts in that it collects information about every I/O request and about the mix of jobs running in a production environment. We also present the results of a trace-driven caching simulation and recommendations for designers of multiprocessor file systems.

Kotz, David↗
NASA NTRS1994

Precise GPS orbits for geodesy

The Global Positioning System (GPS) has become, in recent years, the main space-based system for surveying and navigation in many military, commercial, cadastral, mapping, and scientific applications. Better receivers, interferometric techniques (DGPS), and advances in post-processing methods have made possible to position fixed or moving receivers with sub-decimeter accuracies in a global reference frame. Improved methods for obtaining the orbits of the GPS satellites have played a major role in these achievements; this paper gives a personal view of the main developments in GPS orbit determination.

Colombo, Oscar L.↗
NASA NTRS1995

Graphite-Fiber Heat Radiators

Heat radiators of proposed type feature thermally conductive fibers protruding from metallic surfaces to provide increased heat-dissipation surface areas. Free of leaks and more reliable than radiators incorporating heat pipes. Also lightweight and relatively inexpensive. Radial graphite fibers carry heat away from spherical shell and radiate heat into space. Radiators prove useful on Earth in special industrial and scientific applications involving dissipation of heat in vacuum or in relatively still air.

Phillips, Wayne M.↗
NASA NTRS1995

File-access characteristics of parallel scientific workloads

Phenomenal improvements in the computational performance of multiprocessors have not been matched by comparable gains in I/O system performance. This imbalance has resulted in I/O becoming a significant bottleneck for many scientific applications. One key to overcoming this bottleneck is improving the performance of parallel file systems. The design of a high-performance parallel file system requires a comprehensive understanding of the expected workload. Unfortunately, until recently, no general workload studies of parallel file systems have been conducted. The goal of the CHARISMA project was to remedy this problem by characterizing the behavior of several production workloads, on different machines, at the level of individual reads and writes. The first set of results from the CHARISMA project describe the workloads observed on an Intel iPSC/860 and a Thinking Machines CM-5. This paper is intended to compare and contrast these two workloads for an understanding of their essential similarities and differences, isolating common trends and platform-dependent variances. Using this comparison, we are able to gain more insight into the general principles that should guide parallel file-system design.

Nieuwejaar, Nils↗
NASA NTRS1995

Characterizing parallel file-access patterns on a large-scale multiprocessor

High-performance parallel file systems are needed to satisfy tremendous I/O requirements of parallel scientific applications. The design of such high-performance parallel file systems depends on a comprehensive understanding of the expected workload, but so far there have been very few usage studies of multiprocessor file systems. This paper is part of the CHARISMA project, which intends to fill this void by measuring real file-system workloads on various production parallel machines. In particular, we present results from the CM-5 at the National Center for Supercomputing Applications. Our results are unique because we collect information about nearly every individual I/O request from the mix of jobs running on the machine. Analysis of the traces leads to various recommendations for parallel file-system design.

Purakayastha, A.↗
NASA NTRS1996

Role of the BIPM in UTC Dissemination to the Real Time User

The generation and dissemination of International Atomic Time (TAI), and Coordinated Universal Time (UTC) are explicitly mentioned in the list of principal tasks of the Bureau International des Poids et Mesures (BIPM), that appears in the Compes Rendus of the the 18e Conference Generales des Poids et Measures, in 1987. These time scales are used as the ultimate reference in the most demanding scientific applications and must, therefore, be of the best metrological quality in terms of reliability, long term stability, and conformity of the scale interval with the second, the unit of time of the International System of Units. To meet these requirements, it is necessary that the readings of the atomic clocks, spread all over the world, that are used as basic timing data for TAI and UTC generation, must be combined in the most efficient way possible. In particular, to take full advantage of the quality of each contributing clock calls for observation of its performance over a sufficiently long time. At present, the computation period treats data in blocks covering two months. TAI and UTC are thus deferred-time scales that cannot be immediately available to real-time users. The BIPM can, nevertheless be of help to real-time users. The predictability of UTC is a fundamental attribute of the scale for institutions responsible for the dissemination of real-time time scales. It allows them to improve their local representations of UTC and, thus, implement a more thorough steering of the time scales diffused in real-time. With a view to improving the predicatbility of UTC, the BIPM examines in detail timing techniques and basic theories in order to propose alternative solutions for timing algorithms. This, coupled with a recent improvement of timing data, makes UTC more stable and thus, more predictable. At a more practical level, effort is being devoted to putting in place automatic procedures for reducing the time needed for data collection and treatment: monthly results are already available ten days earlier than before.

Quinn, T. J.↗
NASA NTRS1995

Ensuring correct rollback recovery in distributed shared memory systems

Distributed shared memory (DSM) implemented on a cluster of workstations is an increasingly attractive platform for executing parallel scientific applications. Checkpointing and rollback techniques can be used in such a system to allow the computation to progress in spite of the temporary failure of one or more processing nodes. This paper presents the design of an independent checkpointing method for DSM that takes advantage of DSM's specific properties to reduce error-free and rollback overhead. The scheme reduces the dependencies that need to be considered for correct rollback to those resulting from transfers of pages. Furthermore, in-transit messages can be recovered without the use of logging. We extend the scheme to a DSM implementation using lazy release consistency, where the frequency of dependencies is further reduced.

Janssens, Bob↗
NASA NTRS1996

Performance of the Galley Parallel File System

As the input/output (I/O) needs of parallel scientific applications increase, file systems for multiprocessors are being designed to provide applications with parallel access to multiple disks. Many parallel file systems present applications with a conventional Unix-like interface that allows the application to access multiple disks transparently. This interface conceals the parallism within the file system, which increases the ease of programmability, but makes it difficult or impossible for sophisticated programmers and libraries to use knowledge about their I/O needs to exploit that parallelism. Furthermore, most current parallel file systems are optimized for a different workload than they are being asked to support. We introduce Galley, a new parallel file system that is intended to efficiently support realistic parallel workloads. Initial experiments, reported in this paper, indicate that Galley is capable of providing high-performance 1/O to applications the applications that rely on them. In Section 3 we describe that access data in patterns that have been observed to be common.

Nieuwejaar, Nils↗
NASA NTRS1996

The Galley Parallel File System

As the I/O needs of parallel scientific applications increase, file systems for multiprocessors are being designed to provide applications with parallel access to multiple disks. Many parallel file systems present applications with a conventional Unix-like interface that allows the application to access multiple disks transparently. The interface conceals the parallelism within the file system, which increases the ease of programmability, but makes it difficult or impossible for sophisticated programmers and libraries to use knowledge about their I/O needs to exploit that parallelism. Furthermore, most current parallel file systems are optimized for a different workload than they are being asked to support. We introduce Galley, a new parallel file system that is intended to efficiently support realistic parallel workloads. We discuss Galley's file structure and application interface, as well as an application that has been implemented using that interface.

Nieuwejaar, Nils↗
NASA NTRS1997

An X-Ray Analysis Database of Photoionization Cross Sections Including Variable Ionization

Results of research efforts in the following areas are discussed: review of the major theoretical and experimental data of subshell photoionization cross sections and ionization edges of atomic ions to assess the accuracy of the data, and to compile the most reliable of these data in our own database; detailed atomic physics calculations to complement the database for all ions of 17 cosmically abundant elements; reconciling the data from various sources and our own calculations; and fitting cross sections with functional approximations and incorporating these functions into a compact computer code.Also, efforts included adapting an ionization equilibrium code, tabulating results, and incorporating them into the overall program and testing the code (both ionization equilibrium and opacity codes) with existing observational data. The background and scientific applications of this work are discussed. Atomic physics cross section models and calculations are described. Calculation results are compared with available experimental data and other theoretical data. The functional approximations used for fitting cross sections are outlined and applications of the database are discussed.

Wang, Ping↗
NASA NTRS1997

Parallel supercomputing with commodity components

We have implemented a parallel computer architecture based entirely upon commodity personal computer components. Using 16 Intel Pentium Pro microprocessors and switched fast ethernet as a communication fabric, we have obtained sustained performance on scientific applications in excess of one Gigaflop. During one production astrophysics treecode simulation, we performed 1.2 x 10(sup 15) floating point operations (1.2 Petaflops) over a three week period, with one phase of that simulation running continuously for two weeks without interruption. We report on a variety of disk, memory and network benchmarks. We also present results from the NAS parallel benchmark suite, which indicate that this architecture is competitive with current commercial architectures. In addition, we describe some software written to support efficient message passing, as well as a Linux device driver interface to the Pentium hardware performance monitoring registers.

Performance↗
NASA NTRS1996

Preliminary Work in Obtaining Site-Directed Mutants of Hen Egg White Lysozyme

Protein crystal growth studies are recognized as a critical endeavor in the field of molecular biotechnology. The scientific applications of this field include the understanding of how enzymes function and the accumulation of accurate information of atomic structures, a key factor in the process of rational drug design. NASA has committed substantial investment and resources to the field of protein crystal growth and has conducted many microgravity protein crystal growth experiments aboard shuttle flights. Crystals grown in space tend to be larger, denser and have a more perfect habit and geometry. These improved properties gained in the microgravity environment of space result largely from the reduction of solutal convection, and the elimination of sedimentation at the growing crystal surface. Shuttle experiments have yielded many large, high quality crystals that are suitable for high resolution X-ray diffraction analysis. Examples of biologically important macromolecules which have been successfully crystallized during shuttle missions include: lysozyme, isocitrate lyase, gamma-interferon, insulin, human serum albumin and canavalin. Numerous other examples are also available. In addition to obtaining high quality crystals, investigators are also interested in learning the mechanisms by which the growth events take place. Crystallization experiments indicate that for the enzyme HEWL, measured growth rates do not follow mathematical models for 2D nucleation and dislocation-led growth of tetragonal protein crystals. As has been suggested by the laboratory of Marc L. Pusey, a possible explanation for the disagreement between observation and data is that HEWL tetraconal crystals form by aggregated units of lysozyme in supersaturated solutions. Surface measurement data was shown to fit very well with a model using an octamer unit cell as the growth unit. According to this model, the aggregation pathway and subsequent crystal growth is described by: monomer < ------ > dimer < ------- > tetramer < ------ > octamer < ------ > higher order. It is believed that multimer aggregation of lysozyme occurs by interaction at specific binding sites on the surface of the protein crystals. If the presence of discrete binding sites and the aggregation hypothesis is true, then it follows that the alteration of the binding site(s) should have significant effect on the measurements obtained during growth experiments. Site-directed mutagenesis allows the specific alteration of proteins by replacement, deletion or addition of specific amino acid residues. This report outlines the approach for this strategy and the progress made thus far toward that end.

Holmes, Leonard D.↗
NASA NTRS1998

Precision Spectroscopy, Diode Lasers, and Optical Frequency Measurement Technology

This compilation is a selected set of reprints from the Optical Frequency Measurement Group of the Time and Frequency Division of the National Institute of Standards and Technology, and consists of work published between 1987 and 1997. The two main programs represented here are (1) development of tunable diode-laser technology for scientific applications and precision measurements, and (2) research toward the goal of realizing optical-frequency measurements and synthesis. The papers are organized chronologically in five, somewhat arbitrarily chosen categories: Diode Laser Technology, Tunable Laser Systems, Laser Spectroscopy, Optical Synthesis and Extended Wavelength Coverage, and Multi-Photon Interactions and Optical Coherences.

DIODE LASERS↗
NASA NTRS2000

QuikSCAT Mission

The QuikSCAT Mission of the National Aeronautics and Space Administration (NASA) is planned for launch in Spring 1999, reducing the data gap in ocean-wind vector created by the loss of the NASA Scatterometer (NSCAT) on the Japanese Advanced Earth Observing Satellite (ADEOS) spacecraft. The NSCAT instrument ceased functioning when ADEOS failed on June 30, 1997. The follow-on scatterometer for monitoring ocean winds, called SeaWinds, is scheduled for launch on the Japanese ADEOS-II spacecraft in 2000. The Jet Propulsion Laboratory (JPL) has met the challenge to develop and integrate the instrument, ground system, and launch vehicle in less than a year. QuikSCAT will use pencil-beam-antennas in a conical-scan design which is more compact than the fixed fan-beam design of NSCAT. The antenna will radiate ku-band microwaves at 40 and 46 incident angle and measure the backscatter power across a continuous 1800 km swath. QuikSCAT is capable of providing wind-speed and wind-direction at 25 km resolution over 92 percent of the Earth's ice-free oceans every day, under both clear and cloudy conditions. Standard data products will be delivered to science users within 14-days, and fast data products will be available to operational users within two hours of data acquisition. QuikSCAT will be managed by JPL for the NASA's Office of Earth Science Enterprise. It will be launched from Vandenberg Air Force Base, aboard a Titan II vehicle. The satellite core-systems was built by Ball Aerospace Systems Division, Boulder, CO. The operation of QuikSCAT is expected to overlap with ERS-2 and SeaWinds. Spaceborne scatterometers have demonstrated a broad spectrum of scientific applications, including weather systems, wind-driven ocean circulation, land vegetation, polar ice morphology and dynamics, and Ocean-atmosphere-ice interaction.

Liu, W. Timothy↗
NASA NTRS2001

Enhancing the Remote Variable Operations in NPSS/CCDK

Many scientific applications in aerodynamics and solid mechanics are written in Fortran. Refitting these legacy Fortran codes with distributed objects can increase the code reusability. The remote variable scheme provided in NPSS/CCDK helps programmers easily migrate the Fortran codes towards a client-server platform. This scheme gives the client the capability of accessing the variables at the server site. In this paper, we review and enhance the remote variable scheme by using the operator overloading features in C++. The enhancement enables NPSS programmers to use remote variables in much the same way as traditional variables. The remote variable scheme adopts the lazy update approach and the prefetch method. The design strategies and implementation techniques are described in details. Preliminary performance evaluation shows that communication overhead can be greatly reduced.

Sang, Janche↗
NASA NTRS2001

Discovering Communicable Scientific Knowledge from Spatio-Temporal Data

This paper describes how we used regression rules to improve upon a result previously published in the Earth science literature. In such a scientific application of machine learning, it is crucially important for the learned models to be understandable and communicable. We recount how we selected a learning algorithm to maximize communicability, and then describe two visualization techniques that we developed to aid in understanding the model by exploiting the spatial nature of the data. We also report how evaluating the learned models across time let us discover an error in the data.

Schwabacher, Mark↗
NASA NTRS1994

High Performance Computing at NASA

The speaker will give an overview of high performance computing in the U.S. in general and within NASA in particular, including a description of the recently signed NASA-IBM cooperative agreement. The latest performance figures of various parallel systems on the NAS Parallel Benchmarks will be presented. The speaker was one of the authors of the NAS (National Aerospace Standards) Parallel Benchmarks, which are now widely cited in the industry as a measure of sustained performance on realistic high-end scientific applications. It will be shown that significant progress has been made by the highly parallel supercomputer industry during the past year or so, with several new systems, based on high-performance RISC processors, that now deliver superior performance per dollar compared to conventional supercomputers. Various pitfalls in reporting performance will be discussed. The speaker will then conclude by assessing the general state of the high performance computing field.

Bailey, David H.↗
NASA NTRS1994

Performance and the NAS Parallel Benchmarks

This talk will describe the NAS (National Aerospace Standards) Parallel Benchmarks, which are now widely cited in the high performance computing field as a measure of sustained performance on realistic scientific applications. The latest performance results will be included. It will be shown that significant progress has been made by several systems during the past year or so, with sustained performance on a par with the best conventional systems, and with performance per dollar significantly exceeding the conventional systems. This talk will also describe many of the pitfalls of performance reporting, and will give advice on how to avoid such pitfalls. The overall state of the field of high performance computing will also be discussed.

Bailey, David H.↗