SEARCH · Engineering Papers

Results for “High performance Computing”

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.

SourceResearch connectionFrom yearThrough year

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

At least 829 records · Page 46

All sources NASA NTRS DOE OSTI

NASA NTRS1992

Automatic data partitioning on distributed memory multicomputers

Distributed-memory parallel computers are increasingly being used to provide high levels of performance for scientific applications. Unfortunately, such machines are not very easy to program. A number of research efforts seek to alleviate this problem by developing compilers that take over the task of generating communication. The communication overheads and the extent of parallelism exploited in the resulting target program are determined largely by the manner in which data is partitioned across different processors of the machine. Most of the compilers provide no assistance to the programmer in the crucial task of determining a good data partitioning scheme. A novel approach is presented, the constraints-based approach, to the problem of automatic data partitioning for numeric programs. In this approach, the compiler identifies some desirable requirements on the distribution of various arrays being referenced in each statement, based on performance considerations. These desirable requirements are referred to as constraints. For each constraint, the compiler determines a quality measure that captures its importance with respect to the performance of the program. The quality measure is obtained through static performance estimation, without actually generating the target data-parallel program with explicit communication. Each data distribution decision is taken by combining all the relevant constraints. The compiler attempts to resolve any conflicts between constraints such that the overall execution time of the parallel program is minimized. This approach has been implemented as part of a compiler called Paradigm, that accepts Fortran 77 programs, and specifies the partitioning scheme to be used for each array in the program. We have obtained results on some programs taken from the Linpack and Eispack libraries, and the Perfect Benchmarks. These results are quite promising, and demonstrate the feasibility of automatic data partitioning for a significant class of scientific application programs with regular computations.

Gupta, Manish↗

NASA NTRS1984

High accuracy pointing for earth observation experiments

An evaluation of mission requirements for postulated earth observation orbital payload experiments has indicated that high accuracy pointing and stabilization must be provided for adequate performance. A computer simulation has been conducted to determine the capabilities of an auxiliary pointing system which employs a combination of conventional gimbals and magnetic bearing actuators. This Annular Suspension and Pointing System (ASPS) is found to be a viable means of providing the high slew rates associated with landmark tracking from low orbit, while simultaneously achieving the high degree pointing and stabilization dictated by science payload requirements.

Keckler, C. R.↗

NASA NTRS2011

Accelerated Adaptive MGS Phase Retrieval

The Modified Gerchberg-Saxton (MGS) algorithm is an image-based wavefront-sensing method that can turn any science instrument focal plane into a wavefront sensor. MGS characterizes optical systems by estimating the wavefront errors in the exit pupil using only intensity images of a star or other point source of light. This innovative implementation of MGS significantly accelerates the MGS phase retrieval algorithm by using stream-processing hardware on conventional graphics cards. Stream processing is a relatively new, yet powerful, paradigm to allow parallel processing of certain applications that apply single instructions to multiple data (SIMD). These stream processors are designed specifically to support large-scale parallel computing on a single graphics chip. Computationally intensive algorithms, such as the Fast Fourier Transform (FFT), are particularly well suited for this computing environment. This high-speed version of MGS exploits commercially available hardware to accomplish the same objective in a fraction of the original time. The exploit involves performing matrix calculations in nVidia graphic cards. The graphical processor unit (GPU) is hardware that is specialized for computationally intensive, highly parallel computation. From the software perspective, a parallel programming model is used, called CUDA, to transparently scale multicore parallelism in hardware. This technology gives computationally intensive applications access to the processing power of the nVidia GPUs through a C/C++ programming interface. The AAMGS (Accelerated Adaptive MGS) software takes advantage of these advanced technologies, to accelerate the optical phase error characterization. With a single PC that contains four nVidia GTX-280 graphic cards, the new implementation can process four images simultaneously to produce a JWST (James Webb Space Telescope) wavefront measurement 60 times faster than the previous code.

Lam, Raymond K.↗

NASA NTRSDate not supplied

Recommended DSMC Collision Model Parameters for Planetary Entry

Hybrid simulation frameworks combining Computational Fluid Dynamics (CFD) and Direct Simulation Monte Carlo (DSMC) are frequently employed to efficiently perform high-fidelity simulations of environments consisting of both continuum and rarified flow. DSMC is a stochastic, particle-based method which solves the fundamental Boltzmann equation and is therefore necessary for high-Knudsen flow where continuum-based assumptions governing CFD break down. However, the DSMC methodology is generally computationally inefficient to model the continuum regime. In a CFD/DSMC hybrid approach, obtaining an accurate, high-fidelity solution hinges on the consistent treatment of transport properties and the thermo-chemical models employed within the two solvers. In principle, in regions where CFD and DSMC are both employed, the same gas mixture under the same conditions should have the same properties, regardless of simulation type. Observed differences should be due to non-equilibrium processes, rather than differences in physical models. The goal of this work is to provide a comprehensive DSMC transport database encompassing the vast majority of known gas species encountered during Earth or other planetary atmospheric entry. This goal is largely possible due to recently performed ab initio quantum chemistry calculations. Combined with other high-fidelity data, the planned database will consist of collision integral data for over 200 neutral and ionized species and over 20000 binary collisions. From these collision integrals, Nelder-Mead optimization is used to compute collision-specific Variable Soft Sphere (VSS) collision model parameters, fitted from 300 K to 20000 K. Initial comparisons of transport properties of relevant equilibrium gas mixtures show great agreement between CFD and DSMC-derived results. The completed database can be readily applied to model binary collisions of any gas mixture containing the included species over the specified temperature range, making it a valuable tool for future planetary probe modeling efforts. An example is shown below in Fig. 1. Equilibrium mixture transport properties for a 35-species mixture composed originally of 10% air and 90% pyrolysis species of a carbon-phenolic ablator material [4] are computed using both fitted VSS Parameters and the original CFD collision integral values. Deviations in computed properties between the two approaches are less than 5% for the entire temperature range.

M. R. Gosma↗

NASA NTRS1980

ASPS performance with large payloads onboard the Shuttle Orbiter

A high fidelity digital computer simulation was used to establish the viability of the Annular Suspension and Pointing System (ASPS) for satisfying the pointing and stability requirements of facility class payloads, such as the Solar Optical Telescope, when subjected to the Orbiter disturbance environment. The ASPS and its payload were subjected to disturbances resulting from crew motions in the Orbiter aft flight deck and VRCS thruster firings. Worst case pointing errors of 0.005 arc seconds were experienced under the disturbance environment simulated; this is well within the 0.08 arc seconds requirement specified by the payload.

Keckler, C. R.↗

NASA NTRS2008

Application of the CloudSat and NEXRAD Radars Toward Improvements in High Resolution Operational Forecasts

As computational power increases, operational forecast models are performing simulations with higher spatial resolution allowing for the transition from sub-grid scale cloud parameterizations to an explicit forecast of cloud characteristics and precipitation through the use of single- or multi-moment bulk water microphysics schemes. investments in space-borne and terrestrial remote sensing have developed the NASA CloudSat Cloud Profiling Radar and the NOAA National Weather Service NEXRAD system, each providing observations related to the bulk properties of clouds and precipitation through measurements of reflectivity. CloudSat and NEXRAD system radars observed light to moderate snowfall in association with a cold-season, midlatitude cyclone traversing the Central United States in February 2007. These systems are responsible for widespread cloud cover and various types of precipitation, are of economic consequence, and pose a challenge to operational forecasters. This event is simulated with the Weather Research and Forecast (WRF) Model, utilizing the NASA Goddard Cumulus Ensemble microphysics scheme. Comparisons are made between WRF-simulated and observed reflectivity available from the CloudSat and NEXRAD systems. The application of CloudSat reflectivity is made possible through the QuickBeam radiative transfer model, with cautious application applied in light of single scattering characteristics and spherical target assumptions. Significant differences are noted within modeled and observed cloud profiles, based upon simulated reflectivity, and modifications to the single-moment scheme are tested through a supplemental WRF forecast that incorporates a temperature dependent snow crystal size distribution.

Molthan, A. L.↗

NASA NTRSDate not supplied

Computational Approaches for Li-O2 Battery Design

Threshold energy densities for general aviation electric aircraft are 400 Wh/kg with more ambitious air vehicles having significantly higher requirements. Li-O2 batteries, with the highest theoretical capacity, are one of the few “beyond Li-ion” chemistries that might satisfy the extraordinary specific capacity as well as specific power requirements of electric aircraft. However, side reactions at interfaces, in particular at the cathode, over the charge-discharge cycles result in very short cycle-life and dramatic reduction of capacity. Addressing these issues, in addition to others, are crucial for realizing practical, high performance Li-O2 batteries. In this talk, we discuss atomistic computational work to understand and mitigate some of the issues, including those at interfaces, that affect the Li-O2 electrochemistry. To start, we discuss the deposition mechanisms, both surface and solution based, of Li2O2 and their dependence on external potential. Next, we explore molten salt electrolytes as a stable alternative to organic electrolytes and approaches taken to develop new practical molten salt eutectic mixtures. Finally, we address the issue of reactive carbon-cathodes and possible cathode-candidates that were identified throughput high-throughput computations.

Li-Air battery↗

NASA NTRS2002

A Grid Infrastructure for Supporting Space-based Science Operations

Emerging technologies for computational grid infrastructures have the potential for revolutionizing the way computers are used in all aspects of our lives. Computational grids are currently being implemented to provide a large-scale, dynamic, and secure research and engineering environments based on standards and next-generation reusable software, enabling greater science and engineering productivity through shared resources and distributed computing for less cost than traditional architectures. Combined with the emerging technologies of high-performance networks, grids provide researchers, scientists and engineers the first real opportunity for an effective distributed collaborative environment with access to resources such as computational and storage systems, instruments, and software tools and services for the most computationally challenging applications.

Bradford, Robert N.↗

NASA NTRS1972

New technology in turbine aerodynamics.

Cursory review of some recent work that has been done in turbine aerodynamic research. Topics discussed include the aerodynamic effect of turbine coolant, high work-factor (ratio of stage work to square of blade speed) turbines, and computer methods for turbine design and performance prediction. Experimental cooled-turbine aerodynamics programs using two-dimensional cascades, full annular cascades, and cold rotating turbine stage tests are discussed with some typical results presented. Analytically predicted results for cooled blade performance are compared to experimental results. The problems and some of the current programs associated with the use of very high work factors for fan-drive turbines of high-bypass-ratio engines are discussed. Computer programs have been developed for turbine design-point performance, off-design performance, supersonic blade profile design, and the calculation of channel velocities for subsonic and transonic flowfields. The use of these programs for the design and analysis of axial and radial turbines is discussed.

Glassman, A. J.↗

NASA NTRS1988

Semi-automatic process partitioning for parallel computation

On current multiprocessor architectures one must carefully distribute data in memory in order to achieve high performance. Process partitioning is the operation of rewriting an algorithm as a collection of tasks, each operating primarily on its own portion of the data, to carry out the computation in parallel. A semi-automatic approach to process partitioning is considered in which the compiler, guided by advice from the user, automatically transforms programs into such an interacting task system. This approach is illustrated with a picture processing example written in BLAZE, which is transformed into a task system maximizing locality of memory reference.

Koelbel, Charles↗

NASA NTRS1995

High temperature superconductors applications in telecommunications

The purpose of this paper is twofold: (1) to discuss high temperature superconductors with specific reference to their employment in telecommunications applications; and (2) to discuss a few of the limitations of the normally employed two-fluid model. While the debate on the actual usage of high temperature superconductors in the design of electronic and telecommunications devices - obvious advantages versus practical difficulties - needs to be settled in the near future, it is of great interest to investigate the parameters and the assumptions that will be employed in such designs. This paper deals with the issue of providing the microwave design engineer with performance data for such superconducting waveguides. The values of conductivity and surface resistance, which are the primary determining factors of a waveguide performance, are computed based on the two-fluid model. A comparison between two models - a theoretical one in terms of microscopic parameters (termed Model A) and an experimental fit in terms of macroscopic parameters (termed Model B) - shows the limitations and the resulting ambiguities of the two-fluid model at high frequencies and at temperatures close to the transition temperature. The validity of the two-fluid model is then discussed. Our preliminary results show that the electrical transport description in the normal and superconducting phases as they are formulated in the two-fluid model needs to be modified to incorporate the new and special features of high temperature superconductors. Parameters describing the waveguide performance - conductivity, surface resistance and attenuation constant - will be computed. Potential applications in communications networks and large scale integrated circuits will be discussed. Some of the ongoing work will be reported. In particular, a brief proposal is made to investigate of the effects of electromagnetic interference and the concomitant notion of electromagnetic compatibility (EMI/EMC) of high T(sub c) superconductors.

Kumar, A. Anil↗

NASA NTRS1974

Research on development of equations for performance trajectory computation

A computer program for computing the performance trajectory of spacecraft was developed. An analytical study of a minimum fuel flight for high speed aircraft was conducted. The computer program to compute a minimum time reentry into the atmosphere for an Apollo-type capsule is presented. A technical summary of the minimum fuel problem is provided.

Harmon, G. R.↗

NASA NTRS1994

Re-engineering Nascom's network management architecture

The development of Nascom systems for ground communications began in 1958 with Project Vanguard. The low-speed systems (rates less than 9.6 Kbs) were developed following existing standards; but, there were no comparable standards for high-speed systems. As a result, these systems were developed using custom protocols and custom hardware. Technology has made enormous strides since the ground support systems were implemented. Standards for computer equipment, software, and high-speed communications exist and the performance of current workstations exceeds that of the mainframes used in the development of the ground systems. Nascom is in the process of upgrading its ground support systems and providing additional services. The Message Switching System (MSS), Communications Address Processor (CAP), and Multiplexer/Demultiplexer (MDM) Automated Control System (MACS) are all examples of Nascom systems developed using standards such as, X-windows, Motif, and Simple Network Management Protocol (SNMP). Also, the Earth Observing System (EOS) Communications (Ecom) project is stressing standards as an integral part of its network. The move towards standards has produced a reduction in development, maintenance, and interoperability costs, while providing operational quality improvement. The Facility and Resource Manager (FARM) project has been established to integrate the Nascom networks and systems into a common network management architecture. The maximization of standards and implementation of computer automation in the architecture will lead to continued cost reductions and increased operational efficiency. The first step has been to derive overall Nascom requirements and identify the functionality common to all the current management systems. The identification of these common functions will enable the reuse of processes in the management architecture and promote increased use of automation throughout the Nascom network. The MSS, CAP, MACS, and Ecom projects have indicated the potential value of commercial-off-the-shelf (COTS) and standards through reduced cost and high quality. The FARM will allow the application of the lessons learned from these projects to all future Nascom systems.

Drake, Brian C.↗

NASA NTRS1994

An Aerodynamic Analysis of a Mixed Flow Turbine

The aerodynamic performance of a high-work Mixed Flow Turbine (MFT) is computed and compared with experimental data. A three dimensional (3-D) viscous analysis is applied to the single stage MFT geometry with a relatively long upstream transition duct. Predicted vane surface static pressures and circumferentially averaged spanwise quantities at stator and rotor exits agree favorably with data. Compared to the results of axisymmetric flow analysis from design intent, the 3-D computation agrees much better especially in the endwall regions where throughflow prediction fails to assess the loss mechanism properly. Potential sources of performance loss such as tip leakage and secondary flows are also properly captured by the analysis.

Kim, Chan M.↗

NASA NTRS1974

High-tip-speed fiber composite compressor blades: Vibration and strength analysis

An analytical procedure is described which couples composite mechanics computer codes with NASTRAN. This procedure was used to perform a detailed analysis of a high-tip-speed fiber composite compressor fan blade. The results indicate that the various vibration modes of this blade are highly coupled. Mechanical load ply stresses are well below the corresponding room temperature strengths. Lamination residual stresses are likely to cause transply cracks and interply delamination. Transply cracks and relaxation of root fixity decrease the vibrational frequencies whereas centrifugal stiffening increases them. Comparisons of results for various parameters are presented in tabular and graphical form.

Chamis, C. C.↗

NASA NTRS1974

High-tip-speed fiber composite compressor blades - Vibration and strength analyses

Chamis, C. C.↗

NASA NTRS1998

Design and Performance Analysis of a Massively Parallel Atmospheric General Circulation Model

In the 1990's computer manufacturers are increasingly turning to the development of parallel processor machines to meet the high performance needs of their customers. Simultaneously, atmospheric scientists study weather and climate phenomena ranging from hurricanes to El Nino to global warming that require increasingly fine resolution models. Here, implementation of a parallel atmospheric general circulation model (GCM) which exploits the power of massively parallel machines is described. Using the horizontal data domain decomposition methodology, this FORTRAN 90 model is able to integrate a 0.6 deg. longitude by 0.5 deg. latitude problem at a rate of 19 Gigaflops on 512 processors of a Cray T3E 600; corresponding to 280 seconds of wall-clock time per simulated model day. At this resolution, the model has 64 times as many degrees of freedom and performs 400 times as many floating point operations per simulated day as the model it replaces.

Schaffer, Daniel S.↗

NASA NTRS1978

Technology advances and market forces: Their impact on high performance architectures

Reasonable projections into future supercomputer architectures and technology require an analysis of the computer industry market environment, the current capabilities and trends within the component industry, and the research activities on computer architecture in the industrial and academic communities. Management, programmer, architect, and user must cooperate to increase the efficiency of supercomputer development efforts. Care must be taken to match the funding, compiler, architecture and application with greater attention to testability, maintainability, reliability, and usability than supercomputer development programs of the past.

Best, D. R.↗