Search NASA⌕ Search

SEARCH · Search NASA

Results for “Supercomputing”

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
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

The engine design engine. A clustered computer platform for the aerodynamic inverse design and analysis of a full engine

An application for parallel computation on a combined cluster of powerful workstations and supercomputers was developed. A Parallel Virtual Machine (PVM) is used as message passage language on a macro-tasking parallelization of the Aerodynamic Inverse Design and Analysis for a Full Engine computer code. The heterogeneous nature of the cluster is perfectly handled by the controlling host machine. Communication is established via Ethernet with the TCP/IP protocol over an open network. A reasonable overhead is imposed for internode communication, rendering an efficient utilization of the engaged processors. Perhaps one of the most interesting features of the system is its versatile nature, that permits the usage of the computational resources available that are experiencing less use at a given point in time.

Sanz, J.↗
NASA NTRS1992

Current state and future direction of computer systems at NASA Langley Research Center

Computer systems have advanced at a rate unmatched by any other area of technology. As performance has dramatically increased there has been an equally dramatic reduction in cost. This constant cost performance improvement has precipitated the pervasiveness of computer systems into virtually all areas of technology. This improvement is due primarily to advances in microelectronics. Most people are now convinced that the new generation of supercomputers will be built using a large number (possibly thousands) of high performance microprocessors. Although the spectacular improvements in computer systems have come about because of these hardware advances, there has also been a steady improvement in software techniques. In an effort to understand how these hardware and software advances will effect research at NASA LaRC, the Computer Systems Technical Committee drafted this white paper to examine the current state and possible future directions of computer systems at the Center. This paper discusses selected important areas of computer systems including real-time systems, embedded systems, high performance computing, distributed computing networks, data acquisition systems, artificial intelligence, and visualization.

Rogers, James L.↗
NASA NTRS1992

Meso-beta scale numerical simulation studies of terrain-induced jet streak mass/momentum perturbations

Work performed during the report period is summarized. The first numerical experiment which was performed on the North Carolina Supercomputer Center's CRAY-YMP machine during the second half of FY92 involved a 36 hour simulation of the CCOPE case study. This first coarse-mesh simulation employed the GMASS model with a 178 x 108 x 32 matrix of grid points spaced approximately 24 km apart. The initial data was comprised of the global 2.5 x 2.5 degree analyses as well as all available North American rawinsonde data valid at 0000 UTC 11 July 1981. Highly-smoothed LFM-derived terrain data were utilized so as to determine the mesoscale response of the three-dimensional atmosphere to weak terrain forcing prior to including the observed highly complex terrain of the northern Rocky Mountain region. It was felt that the model should be run with a spectrum of terrain geometries, ranging from observed complex terrain to no terrain at all, to determine how crucial the terrain was in forcing the mesoscale phenomena. Both convection and stratiform (stable) precipitation were not allowed in this simulation so that their relative importance could be determined by inclusion in forth-coming simulations. A full suite of planetary boundary layer forcing was allowed in the simulation, including surface sensible and latent heat fluxes employing the Blakadar PBL formulation. The details of this simulation, which in many ways could be considered the control simulation, including the important synoptic-scale, meso-alpha scale, and meso-beta scale circulations is described. These results are compared to the observations diagnosed by Koch and his colleagues as well as hypotheses set forth in the project proposal for terrain-influences upon the jet stream and their role in the generation of mesoscale wave phenomenon. The fundamental goal of the analyses being the discrimination among background geostrophic adjustment, terrain influences, and shearing instability in the initiation and maintainance of mesoscale internal wave phenomena. Based upon these findings, FY93 plans are discussed. A review of linear theory and theoretical modeling of a geostrophic zonal wind anomaly is included.

Lin, Yuh-Lang↗
NASA NTRS1989

Distributed Finite Element Analysis Using a Transputer Network

The principal objective of this research effort was to demonstrate the extraordinarily cost effective acceleration of finite element structural analysis problems using a transputer-based parallel processing network. This objective was accomplished in the form of a commercially viable parallel processing workstation. The workstation is a desktop size, low-maintenance computing unit capable of supercomputer performance yet costs two orders of magnitude less. To achieve the principal research objective, a transputer based structural analysis workstation termed XPFEM was implemented with linear static structural analysis capabilities resembling commercially available NASTRAN. Finite element model files, generated using the on-line preprocessing module or external preprocessing packages, are downloaded to a network of 32 transputers for accelerated solution. The system currently executes at about one third Cray X-MP24 speed but additional acceleration appears likely. For the NASA selected demonstration problem of a Space Shuttle main engine turbine blade model with about 1500 nodes and 4500 independent degrees of freedom, the Cray X-MP24 required 23.9 seconds to obtain a solution while the transputer network, operated from an IBM PC-AT compatible host computer, required 71.7 seconds. Consequently, the $80,000 transputer network demonstrated a cost-performance ratio about 60 times better than the $15,000,000 Cray X-MP24 system.

Watson, James↗
NASA NTRS1992

Open systems storage platforms

The building blocks for an open storage system includes a system platform, a selection of storage devices and interfaces, system software, and storage applications CONVEX storage systems are based on the DS Series Data Server systems. These systems are a variant of the C3200 supercomputer with expanded I/O capabilities. These systems support a variety of medium and high speed interfaces to networks and peripherals. System software is provided in the form of ConvexOS, a POSIX compliant derivative of 4.3BSD UNIX. Storage applications include products such as UNITREE and EMASS. With the DS Series of storage systems, Convex has developed a set of products which provide open system solutions for storage management applications. The systems are highly modular, assembled from off the shelf components with industry standard interfaces. The C Series system architecture provides a stable base, with the performance and reliability of a general purpose platform. This combination of a proven system architecture with a variety of choices in peripherals and application software allows wide flexibility in configurations, and delivers the benefits of open systems to the mass storage world.

Collins, Kirby↗
NASA NTRS1989

Dynamics of planetary atmospheres

The overall goal is to illuminate the mechanisms that control weather and climate on the Earth and other planets. Each planet presents its own puzzling behavior - the stability of jets and vortices in Jupiter's otherwise turbulent atmosphere, the superrotation of the Venus atmosphere, the interplay of dust, polar volatiles, and climate change in Mars, the supersonic meteorology of Io, and the counterintuitive equator-to-pole temperature gradients on the outer planets. The data sets are generally those obtained from spacecraft - cloud-tracked winds, radiometrically inferred temperatures, and the results of in situ observations where appropriate. The approach includes both data analysis and modeling, ranging from analytic modeling to time-dependent numerical modeling of atmospheric dynamics. The latter approach involves the use of supercomputers such as the San Diego Cray. Progress is generally made when a model with a small number of free parameters either fits a data set that has a large number of independent observations or applies to several planets at once.

Ingersoll, Andrew P.↗
NASA NTRS1993

Jet Engine hot parts IR Analysis Procedure (J-EIRP)

A thermal radiation analysis method called Jet Engine IR Analysis Procedure (J-EIRP) was developed to evaluate jet engine cavity hot parts source radiation. The objectives behind J-EIRP were to achieve the greatest accuracy in model representation and solution, while minimizing computer resources and computational time. The computer programs that comprise J-EIRP were selected on the basis of their performance, accuracy, and flexibility to solve both simple and complex problems. These programs were intended for use on a personal computer, but include the ability to solve large problems on a mainframe or supercomputer. J-EIRP also provides the user with a tool for developing thermal design experience and engineering judgment through analysis experimentation, while using minimal computer resources. A sample jet engine cavity analysis demonstrates the procedure and capabilities within J-EIRP, and is compared to a simplified method for approximating cavity radiation. The goal is to introduce the terminology and solution process used in J-EIRP and to provide insight into the radiation heat transfer principles used in this procedure.

Baumeister, Joseph F.↗
NASA NTRS1993

Applications of wavelet-based compression to multidimensional Earth science data

A data compression algorithm involving vector quantization (VQ) and the discrete wavelet transform (DWT) is applied to two different types of multidimensional digital earth-science data. The algorithms (WVQ) is optimized for each particular application through an optimization procedure that assigns VQ parameters to the wavelet transform subbands subject to constraints on compression ratio and encoding complexity. Preliminary results of compressing global ocean model data generated on a Thinking Machines CM-200 supercomputer are presented. The WVQ scheme is used in both a predictive and nonpredictive mode. Parameters generated by the optimization algorithm are reported, as are signal-to-noise (SNR) measurements of actual quantized data. The problem of extrapolating hydrodynamic variables across the continental landmasses in order to compute the DWT on a rectangular grid is discussed. Results are also presented for compressing Landsat TM 7-band data using the WVQ scheme. The formulation of the optimization problem is presented along with SNR measurements of actual quantized data. Postprocessing applications are considered in which the seven spectral bands are clustered into 256 clusters using a k-means algorithm and analyzed using the Los Alamos multispectral data analysis program, SPECTRUM, both before and after being compressed using the WVQ program.

Bradley, Jonathan N.↗
NASA NTRS1993

A Novel Method for Characterization of Superconductors: Physical Measurements and Modeling of Thin Films

A method for characterization of granular superconducting thin films has been developed which encompasses both the morphological state of the sample and its fabrication process parameters. The broad scope of this technique is due to the synergism between experimental measurements and their interpretation using numerical simulation. Two novel technologies form the substance of this system: the magnetically modulated resistance method for characterizing superconductors; and a powerful new computer peripheral, the Parallel Information Processor card, which provides enhanced computing capability for PC computers. This enhancement allows PC computers to operate at speeds approaching that of supercomputers. This makes atomic scale simulations possible on low cost machines. The present development of this system involves the integration of these two technologies using mesoscale simulations of thin film growth. A future stage of development will incorporate atomic scale modeling.

Kim, B. F.↗
NASA NTRS1992

A distributed analysis and visualization system for model and observational data

The objective of this proposal is to develop an integrated and distributed analysis and display software system which can be applied to all areas of the Earth System Science to study numerical model and earth observational data from storm to global scale. This system will be designed to be easy to use, portable, flexible and easily extensible and to adhere to current and emerging standards whenever possible. It will provide an environment for visualization of the massive amounts of data generated from satellites and other observational field measurements and from model simulations during or after their execution. Two- and three-dimensional animation will also be provided. This system will be based on a widely used software package from NASA called GEMPAK and prototype software for three dimensional interactive displays built at NCSA. The underlying foundation of the system will be a set of software libraries which can be distributed across a UNIX based supercomputer and workstations.

Wilhelmson, Robert↗
NASA NTRS1991

Information technologies for astrophysics circa 2001

It is easy to extrapolate current trends to see where technologies relating to information systems in astrophysics and other disciplines will be by the end of the decade. These technologies include miniaturization, multiprocessing, software technology, networking, databases, graphics, pattern computation, and interdisciplinary studies. It is less easy to see what limits our current paradigms place on our thinking about technologies that will allow us to understand the laws governing very large systems about which we have large data sets. Three limiting paradigms are as follows: saving all the bits collected by instruments or generated by supercomputers; obtaining technology for information compression, storage, and retrieval off the shelf; and the linear model of innovation. We must extend these paradigms to meet our goals for information technology at the end of the decade.

Denning, Peter J.↗
NASA NTRS1993

Hypersonic panel flutter in a rarefied atmosphere

Panel flutter is a form of dynamic aeroelastic instability resulting from the interaction between motion of an aircraft structural panel and the aerodynamic loads exerted on that panel by air flowing past one of the faces. It differs from lifting surface flutter in the sense that it is not usually catastrophic, the panel's motion being limited by nonlinear membrane stresses produced by the transverse displacement. Above some critical airflow condition, the linear instability grows to a limit cycle . The present investigation studies panel flutter in an aerodynamic regime known as 'free molecule flow', wherein intermolecular collisions can be neglected and loads are caused by interactions between individual molecules and the bounding surface. After collision with the panel, molecules may be reflected specularly or reemitted in diffuse fashion. Two parameters characterize this process: the 'momentum accommodation coefficient', which is the fraction of the specularly reflected molecules; and the ratio between the panel temperature and that of the free airstream. This model is relevant to the case of hypersonic flight vehicles traveling at very high altitudes and especially for panels oriented parallel to the airstream or in the vehicle's lee. Under these conditions the aerodynamic shear stress turns out to be considerably larger than the surface pressures, and shear effects must be included in the model. This is accomplished by means of distributed longitudinal and bending loads. The former can cause the panel to buckle. In the example of a simply-supported panel, it turns out that the second mode of free vibration tends to dominate the flutter solution, which is carried out by a Galerkin analysis. Several parametric studies are presented. They include the effects of (1) temperature ratio; (2) momentum accommodation coefficient; (3) spring parameters, which are associated with how the panel is connected to adjacent structures; (4) a parameter which relates compressive end load to its value which would cause classical column buckling; (5) a parameter proportional to the pressure differential between the front and back faces; and (6) initial curvature. The research is completed by an investigation into the possibility of accounting for molecular collisions, which proves to be infeasible given the speeds of current mainframe supercomputers.

Resende, Hugo B.↗
NASA NTRS1992

Some recent applications of Navier-Stokes codes to rotorcraft

Many operational limitations of helicopters and other rotary-wing aircraft are due to nonlinear aerodynamic phenomena incuding unsteady, three-dimensional transonic and separated flow near the surfaces and highly vortical flow in the wakes of rotating blades. Modern computational fluid dynamics (CFD) technology offers new tools to study and simulate these complex flows. However, existing Euler and Navier-Stokes codes have to be modified significantly for rotorcraft applications, and the enormous computational requirements presently limit their use in routine design applications. Nevertheless, the Euler/Navier-Stokes technology is progressing in anticipation of future supercomputers that will enable meaningful calculations to be made for complete rotorcraft configurations.

Mccroskey, W. J.↗
NASA NTRS1993

Technology for national asset storage systems

An industry-led collaborative project, called the National Storage Laboratory, was organized to investigate technology for storage systems that will be the future repositories for our national information assets. Industry participants are IBM Federal Systems Company, Ampex Recording Systems Corporation, General Atomics DISCOS Division, IBM ADSTAR, Maximum Strategy Corporation, Network Systems Corporation, and Zitel Corporation. Industry members of the collaborative project are funding their own participation. Lawrence Livermore National Laboratory through its National Energy Research Supercomputer Center (NERSC) will participate in the project as the operational site and the provider of applications. The expected result is an evaluation of a high performance storage architecture assembled from commercially available hardware and software, with some software enhancements to meet the project's goals. It is anticipated that the integrated testbed system will represent a significant advance in the technology for distributed storage systems capable of handling gigabyte class files at gigabit-per-second data rates. The National Storage Laboratory was officially launched on 27 May 1992.

Coyne, Robert A.↗
NASA NTRS1993

Grand challenges in mass storage: A systems integrators perspective

Within today's much ballyhooed supercomputing environment, with its CFLOPS of CPU power, and Gigabit networks, there exists a major roadblock to computing success; that of Mass Storage. The solution to this mass storage problem is considered to be one of the 'Grand Challenges' facing the computer industry today, as well as long into the future. It has become obvious to us, as well as many others in the industry, that there is no clear single solution in sight. The Systems Integrator today is faced with a myriad of quandaries in approaching this challenge. He must first be innovative in approach, second choose hardware solutions that are volumetric efficient; high in signal bandwidth; available from multiple sources; competitively priced, and have forward growth extendibility. In addition he must also comply with a variety of mandated, and often conflicting software standards (GOSIP, POSIX, IEEE, MSRM 4.0, and others), and finally he must deliver a systems solution with the 'most bang for the buck' in terms of cost vs. performance factors. These quandaries challenge the Systems Integrator to 'push the envelope' in terms of his or her ingenuity and innovation on an almost daily basis. This dynamic is explored further, and an attempt to acquaint the audience with rational approaches to this 'Grand Challenge' is made.

Lee, Richard R.↗
NASA NTRS1993

The modern high rate digital cassette recorder

The magnetic tape recorder has played an essential role in the capture and storage of instrumentation data for more than thirty years. During this time, data recording technology has steadily progressed to meet user demands for more channels, wider bandwidths, and longer recording durations. When acquisition and processing moved from analog to digital techniques, so recorder design followed suit. Milestones marking the evolution of the data recorder through these various stages - multi-track analog, high density longitudinal digital, and more recently rotary digital - have often represented important breakthroughs in the handling of ever-greater quantities of data. Throughout this period there has been a very clear line of demarcation between data storage methods in the 'instrumentation world' on the one hand and the 'computer peripheral world' on the other. This is despite the fact that instrumentation data, whether analog or digital at the point of acquisition, is now likely to be processed on a digital computer at some stage. Regardless of whether the processing device is a small personal computer, a workstation, or the largest supercomputer, system integrators have traditionally been faced with the same basic problem - how to interface what is essentially a manually controlled, continuously running device (the tape recorder) into the fast start/stop computer environment without resorting to an excessive amount of complex custom interfacing and performance compromise. The increasing availability of affordable high power processing equipment throughout the scientific world is forcing recorder manufacturers to make their latest and perhaps most important breakthrough - the computer-friendly data recorder. The operating characteristics of such recorders are discussed and the resultant impact on both data acquisition and data analysis elements of system configuration are considered.

Clemow, Martin↗
NASA NTRS1993

Mass optical storage-tape (MOST)

In today's large mainframe and supercomputer environment there exists a continuous demand for increased performance in digital storage systems. The user need for near-line storage capacity is currently doubling every four years. In addition to higher capacity, a desire exists for higher data transfer rates, and longer term database archivability, at lower, and lower cost. Each component of this quartet of demands appears to be insatiable. Magnetic tape technology presently dominates the digital mass storage markets, but the continuous growth of requirements is drawing attention to the limitations of the technology as an archival mass storage medium. The lowest cost option currently available for long term data storage is to use magnetic tape, although it is not well suited to meeting the need for many tens of years of reliable storage. Today, the majority of magnetic tape mass storage systems are based on the IBM 3480/3490 (or compatible) tape drives. These drives offer only moderate transfer rates and relatively small increments of storage, both of which create a logistics problem due to the large numbers of cartridges necessary in a typical system and the time taken to transfer data. Both higher cartridge capacity and data transfer rates are available in some helical scan magnetic tape systems; however, these command a substantially higher price, exacerbating the cost problem, and are not compatible with most installed systems or tape databases.

Oakley, William S.↗
NASA NTRS1993

Measurements over distributed high performance computing and storage systems

Requirements are carefully described in descriptions of systems to be acquired but often there is no requirement to provide measurements and performance monitoring to ensure that requirements are met over the long term after acceptance. A set of measurements for various UNIX-based systems will be available at the 1992 Goddard Conference on Mass Storage Systems and Technologies. The authors invite others to contribute to the set of measurements. The framework for presenting the measurements of supercomputers, workstations, file servers, mass storage systems, and the networks that interconnect them are given. Production control and database systems are also included. Though other applications and third party software systems are not addressed, it is important to measure them as well. The capability to integrate measurements from all these components from different vendors, and from the third party software systems was recognized and there are efforts to standardize a framework to do this. The measurement activity falls into the domain of management standards. Standards work is ongoing for Open Systems Interconnection (OSI) systems management; AT&T, Digital, and Hewlett-Packard are developing management systems based on this architecture even though it is not finished. Another effort is in the UNIX International Performance Management Working Group. In addition, there are the Open Systems Foundation's Distributed Management Environment and the Object Management Group. A paper comparing the OSI systems management model and the Object Management Group model has been written. The IBM world has had a capability for measurement for various IBM systems since the 1970's and different vendors were able to develop tools for analyzing and viewing these measurements. Since IBM was the only vendor, the user groups were able to lobby IBM for the kinds of measurements needed. In the UNIX world of multiple vendors, a common set of measurements will not be as easy to get.

Williams, Elizabeth↗