Search NASA⌕ Search

SEARCH · Search NASA

Results for “high performance computing systems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,027 records · Page 57

X-ray astronomy instrumentation studies

Preliminary designs were made for a multiplane, multiwire position sensitive proportional counter for X-ray use. Anode spacing was 2 mm and cathode spacing 1 mm. Assistance was provided in setting up and operating two multiwire proportional counters, one with 5 mm anode spacing, and the other with 2 mm spacing. Argon-based counter gases were used for preliminary work in assembling a working experimental system to measure xenon fluorescence yields. The design and specification of a high purity gas filling system capable of supplying mixtures of xenon and other gases to proportional counters was also performed. The system is mounted on a cart, is fully operational, and is flexible enough to be easily used as a pumping station for other clean applications. When needed, assistance was given to put into operation various computer-related pieces of equipment.

Gregory, J. C.↗

A flight test maneuver autopilot for a highly manueverable aircraft

A flight test maneuver autopilot (FTMAP) is currently being flown to increase the quality and quantity of the data obtained in the flight testing of the highly maneuverable aircraft technology (HiMAT) remotely piloted research vehicle (RPRV). The FTMAP resides in a ground-based digital computer and was designed to perform certain prescribed maneuvers precisely, while maintaining critical flight parameters within close tolerances. The FTMAP operates as a non-flight-critical outer loop controller and augments the vehicle primary flight control system. The inputs to the FTMAP consist of telemetry-downlinked aircraft sensor data. During FTMAP operation, the FTMAP computer replaces normal pilot inputs to the aircraft stick and throttle positions. The FTMAP maneuvers include straight-and-level flight, level accelerations and decelerations, pushover pullups, and windup turns. The pushover pullups can be executed holding throttle or Mach number fixed. The windup turns can be commanded by either normal acceleration or angle of attack. The operational procedures, control mode configuration, and initial simulation results are discussed.

Roncoli, R. B.↗

An approximation technique for computing optimal fixed-order controllers for infinite-dimensional systems

The finite-dimensional approximation of the infinite-dimensional Bernstein/Hyland optimal projection theory is investigated analytically. The approach yields fixed-finite-order controllers which are optimal with respect to high-order approximating finite-dimensional plant models. The technique is illustrated by computing a sequence of first-order controllers for a one-dimensional SISO parabolic (heat/diffusion) system using a spline-based Ritz-Galerkin finite-element approximation. The numerical studies indicate convergence of the feedback gains with less than 2-percent performance degradation over full-order LQG controllers.

Bernstein, Dennis S.↗

NASA's supercomputing experience

A brief overview of NASA's recent experience in supercomputing is presented from two perspectives: early systems development and advanced supercomputing applications. NASA's role in supercomputing systems development is illustrated by discussion of activities carried out by the Numerical Aerodynamical Simulation Program. Current capabilities in advanced technology applications are illustrated with examples in turbulence physics, aerodynamics, aerothermodynamics, chemistry, and structural mechanics. Capabilities in science applications are illustrated by examples in astrophysics and atmospheric modeling. Future directions and NASA's new High Performance Computing Program are briefly discussed.

Bailey, F. Ron↗

Directions in parallel programming: HPF, shared virtual memory and object parallelism in pC++

Fortran and C++ are the dominant programming languages used in scientific computation. Consequently, extensions to these languages are the most popular for programming massively parallel computers. We discuss two such approaches to parallel Fortran and one approach to C++. The High Performance Fortran Forum has designed HPF with the intent of supporting data parallelism on Fortran 90 applications. HPF works by asking the user to help the compiler distribute and align the data structures with the distributed memory modules in the system. Fortran-S takes a different approach in which the data distribution is managed by the operating system and the user provides annotations to indicate parallel control regions. In the case of C++, we look at pC++ which is based on a concurrent aggregate parallel model.

Bodin, Francois↗

Flight test of takeoff performance monitoring system

The Takeoff Performance Monitoring System (TOPMS) is a computer software and hardware graphics system that visually displays current runway position, acceleration performance, engine status, and other situation advisory information to aid pilots in their decision to continue or to abort a takeoff. The system was developed at the Langley Research Center using the fixed-base Transport Systems Research Vehicle (TSRV) simulator. (The TSRV is a highly modified Boeing 737-100 research airplane.) Several versions of the TOPMS displays were evaluated on the TSRV B-737 simulator by more than 40 research, United States Air Force, airline and industry and pilots who rated the system satisfactory and recommended further development and testing. In this study, the TOPMS was flight tested on the TSRV. A total of 55 takeoff and 30 abort situations were investigated at 5 airfields. TOPMS displays were observed on the navigation display screen in the TSRV research flight deck during various nominal and off-nominal situations, including normal takeoffs; reduced-throttle takeoffs; induced-acceleration deficiencies; simulated-engine failures; and several gross-weight, runway-geometry, runway-surface, and ambient conditions. All tests were performed on dry runways. The TOPMS software executed accurately during the flight tests and the displays correctly depicted the various test conditions. Evaluation pilots found the displays easy to monitor and understand. The algorithm provides pretakeoff predictions of the nominal distances that are needed to accelerate the airplane to takeoff speed and to brake it to a stop; these predictions agreed reasonably well with corresponding values measured during several fully executed and aborted takeoffs. The TOPMS is operational and has been retained on the TSRV for general use and demonstration.

Middleton, David B.↗

Reusable, Extensible High-Level Data-Distribution Concept

A framework for high-level specification of data distributions in data-parallel application programs has been conceived. [As used here, distributions signifies means to express locality (more specifically, locations of specified pieces of data) in a computing system composed of many processor and memory components connected by a network.] Inasmuch as distributions exert a great effect on the performances of application programs, it is important that a distribution strategy be flexible, so that distributions can be adapted to the requirements of those programs. At the same time, for the sake of productivity in programming and execution, it is desirable that users be shielded from such error-prone, tedious details as those of communication and synchronization. As desired, the present framework enables a user to refine a distribution type and adjust it to optimize the performance of an application program and conceals, from the user, the low-level details of communication and synchronization. The framework provides for a reusable, extensible, data-distribution design, denoted the design pattern, that is independent of a concrete implementation. The design pattern abstracts over coding patterns that have been found to be commonly encountered in both manually and automatically generated distributed parallel programs. The following description of the present framework is necessarily oversimplified to fit within the space available for this article. Distributions are among the elements of a conceptual data-distribution machinery, some of the other elements being denoted domains, index sets, and data collections (see figure). Associated with each domain is one index set and one distribution. A distribution class interface (where "class" is used in the object-oriented-programming sense) includes operations that enable specification of the mapping of an index to a unit of locality. Thus, "Map(Index)" specifies a unit, while "LocalLayout(Index)" specifies the local address within that unit. The distribution class can be extended to enable specification of commonly used distributions or novel user-defined distributions. A data collection can be defined over a domain. The term "data collection" in this context signifies, more specifically, an abstraction of mappings from index sets to variables. Since the index set is distributed, the addresses of the variables are also distributed.

James, Mark↗

Bayesian Software Health Management for Aircraft Guidance, Navigation, and Control

Modern aircraft, both piloted fly-by-wire commercial aircraft as well as UAVs, more and more depend on highly complex safety critical software systems with many sensors and computer-controlled actuators. Despite careful design and V&V of the software, severe incidents have happened due to malfunctioning software. In this paper, we discuss the use of Bayesian networks (BNs) to monitor the health of the on-board software and sensor system, and to perform advanced on-board diagnostic reasoning. We will focus on the approach to develop reliable and robust health models for the combined software and sensor systems.

Schumann, Johann↗

Advanced modulation technology development for earth station demodulator applications. Coded modulation system development

A jointly optimized coded modulation system is described which was designed, built, and tested by COMSAT Laboratories for NASA LeRC which provides a bandwidth efficiency of 2 bits/s/Hz at an information rate of 160 Mbit/s. A high speed rate 8/9 encoder with a Viterbi decoder and an Octal PSK modem are used to achieve this. The BER performance is approximately 1 dB from the theoretically calculated value for this system at a BER of 5 E-7 under nominal conditions. The system operates in burst mode for downlink applications and tests have demonstrated very little degradation in performance with frequency and level offset. Unique word miss rate measurements were conducted which demonstrate reliable acquisition at low values of Eb/No. Codec self tests have verified the performance of this subsystem in a stand alone mode. The codec is capable of operation at a 200 Mbit/s information rate as demonstrated using a codec test set which introduces noise digitally. The measured performance is within 0.2 dB of the computer simulated predictions. A gate array implementation of the most time critical element of the high speed Viterbi decoder was completed. This gate array add-compare-select chip significantly reduces the power consumption and improves the manufacturability of the decoder. This chip has general application in the implementation of high speed Viterbi decoders.

Miller, Susan P.↗

Development of Multi-Physics Dynamics Models for High-Frequency Large-Amplitude Structural Response Simulation

An analytic approach is demonstrated to reveal potential pyroshock-driven dynamic effects causing power losses in the Thermo-Electric (TE) module bars of the Mars Science Laboratory (MSL) Multi-Mission Radioisotope Thermoelectric Generator (MMRTG). This study utilizes high-fidelity finite element analysis with SIERRA/PRESTO codes to estimate wave propagation effects due to large-amplitude suddenly-applied pyro shock loads in the MMRTG. A high fidelity model of the TE module bar was created with approximately 30 million degrees-of-freedom (DOF). First, a quasi-static preload was applied on top of the TE module bar, then transient tri-axial acceleration inputs were simultaneously applied on the preloaded module. The applied input acceleration signals were measured during MMRTG shock qualification tests performed at the Jet Propulsion Laboratory. An explicit finite element solver in the SIERRA/PRESTO computational environment, along with a 3000 processor parallel super -computing framework at NASA AMES, was used for the simulation. The simulation results were investigated both qualitatively and quantitatively. The predicted shock wave propagation results provide detailed structural responses throughout the TE module bar, and key insights into the dynamic response (i.e., loads, displacements, accelerations) of critical internal spring/piston compression systems, TE materials, and internal component interfaces in the MMRTG TE module bar. They also provide confidence on the viability of this high-fidelity modeling scheme to accurately predict shock wave propagation patterns within complex structures. This analytic approach is envisioned for modeling shock sensitive hardware susceptible to intense shock environments positioned near shock separation devices in modern space vehicles and systems.

Shock Waves↗

Comparative Study of Active Flow Control Strategies for Lift Enhancement of a Simplified High-Lift Configuration

Numerical simulations have been performed for a simplified high-lift (SHL) version of the Common Research Model (CRM) configuration, where the Fowler flaps of the conventional high-lift (CRM-HL) configuration are replaced by a set of simple hinged flaps. These hinged flaps are equipped with integrated modular active flow control (AFC) cartridges on the suction surface, and the resulting geometry is known as the CRM-SHL-AFC configuration. The main objective is to make use of AFC devices on the CRM-SHL-AFC configuration to recover the aerodynamic performance (lift) of the CRM-HL configuration. In the current paper, a Lattice Boltzmann method-based computational fluid dynamics (CFD) code, known as PowerFLOWQ® is used to simulate the entire flow field associated with the CRM-SHL-AFC configuration equipped with several different types of AFC devices. The transonic version of the PowerFLOWQ® code that has been validated for high speed flows is used to accurately simulate the flow field generated by the high-momentum actuators required to mitigate reversed flow regions on the suction surfaces of the main wing and the flap. The numerical solutions predict the expected trends in aerodynamic forces as the actuation levels are increased. More efficient AFC systems and actuator arrangements emerged based on the parametric studies performed prior to a Fall 2018 wind tunnel test. Preliminary comparisons of the numerical solutions for lift and surface pressures are presented here with the experimental data, demonstrating the usefulness of CFD for predicting the flow field and lift characteristics of AFC-enabled high-lift configurations.

Vatsa, Veer N.↗

The cascade high productivity language

This paper describes the design of Chapel, the Cascade High Productivity Language, which is being developed in the DARPA-funded HPCS project Cascade led by Cray Inc. Chapel pushes the state-of-the-art in languages for HEC system programming by focusing on productivity, in particular by combining the goal of highest possible object code performance with that of programmability offered by a high-level user interface.

high productivity languages↗

Advanced microfabrication technologies for microspacecraft

Advanced microfabrication technologies offer the prospect of reducing the weight and size of spacecraft through the use of lighter and stronger materials in conjunction with new mechanical/structural design concepts and design optimization methods. At the same time, electronic components have been scaled down while increasing functional utility. A two-fold benefit is derived for space applications through the use of less expensive components and the lower launch costs associated with lighter components. GE-CRD is actively pursuing research in these key technologies for a wide range of applications including satellites. These key technologies will be reviewed and an update on GE progress will be given. The need to reduce weight and lower cost, while maintaining product quality and reliability are primary drivers in the design of satellites, in general, and microsatellites in particular. For the structural subsystem, these requirements pose a complex design problem unless new mechanical design concepts and computer-aided design optimization methods are employed. Several new concepts, such as battery packs doubling as panel reinforcements and fuel tanks as integral structural members, need to utilized. In addition, new viscoelastic material damping concepts for spacecraft components provide for lighter weight/lower cost designs, while satisfying the structural dynamics requirements. High density interconnect (HDI) technology permits the use of bare IC's on a ceramic substrate with 90 percent active area utilization. A copper/polyimide multilayer structure is the backbone of the technology, which has demonstrated a size/weight reduction of greater than 10x compared to printed circuit board with performance up to the GHz level. HDI modules have exceptional mechanical robustness as evidenced by survival of 180 kg rapid acceleration tests. Microelectromechanical systems (MEMS) are redefining sensors and actuators by miniaturization through micromachining techniques. Sharing many fabrication steps with HDI, we have developed a new technique for surface micromachining of copper/polyimide structures using computer-aided laser patterning.

Ghezzo, M.↗

High Performance Access to Archival Data Stored in HDF4 and HDF5 on Cloud Object Stores Without Reformatting the Files

Cloud computing offers numerous advantages for users of extensive Earth science data collections. These benefits encompass direct online access to data files and granules from any location, scalable access supporting parallel computing workflows, and flexible computing tools enabling innovative experimentation with processing techniques. However, older archival file formats designed for distinct computing systems hinder efficient access to decade-long time-series data when compared to data stored in modern cloud-optimized formats like Web Object Stores (WOS), exemplified by Amazon Web Services’ Simple Storage Service (S3). We describe DMR++ (Dataset Metadata Response plus plus), a technology facilitating efficient access to HDF5 (Hierarchical Data Format, version 5) and HDF4 files stored on WOS systems without requiring data reformatting. DMR++ achieves performance comparable to technologies like Zarr while preserving the original file structure, a substantial benefit considering the vast quantity of archival files held by organizations such as NASA. Moreover, DMR++ typically outperforms cloud-optimized versions of HDF5. Essentially an XML (Extensible Markup Language) document usually stored alongside the described data, DMR++ can also be generated on-the-fly but is generally created during data staging to the WOS. Archival files that use HDF4/5 often store large arrays of numerical data. The data in these files is often compressed, typically reducing their size by a factor of four or more. To achieve efficient access to portions of those arrays, they are 'chunked' into smaller sub-arrays, each individually compressed. The chunk size is a compromise, where spinning disks can efficiently access data in smaller chunks while S3 favors larger chunks. A simple optimization of aggregating smaller chunks that are stored adjacently, transferring them in a single access and then individually decompressing them will improve performance. NASA data pose an additional challenge: special Application Programmer Interface (API) libraries are often needed to compute some variables. These libraries are incompatible with WOS environments. Our solution involves storing computed values in the DMR++ document or a companion file, making them accessible like other variables and eliminating the need for specialized APIs. We outline specific optimizations for both satellite grid and swath data stored in HDF4-EOS2 (Earth Observing System).

James Gallagher↗

Optical system of the visual imaging subsystem on the Viking Orbiter spacecraft

The development of the optical system for the Viking Orbiter spacecraft is presented. Each spacecraft consisted of an orbiter and a lander, and the orbiter provided support during the lander descent, landing and operation on the Martian surface, and prior to separation the orbiter provided science data for site selection and certification. To support these objectives each orbiter carried twin camera systems with identical 475 mm f/3.5 telescopes. The development of the Visual Imaging Subsystem which used all spherical catadioptric cassegrains with all elements fabricated from pure fused silica and Mangin primary mirrors is described. Computer aided design optimization and the ray aberration analysis of the final design are presented. The Viking telescopes had high theoretical and measured performance and obtained many high quality images of the Martian surface.

Larks, L.↗

When worlds collide - Jetted vapor plumes and the moon's origin

It is proposed that a collision between a Mars-sized planetesimal and the protoearth explains both the anomalously large angular momentum of the earth-moon system and the similarity between the moon's bulk composition and the earth's mantle. An approximate calculation was performed to obtain information on the highest speed, most highly shocked ejecta and the ejection pattern, speed, angles of launch, etc. as a function of the impact parameter and the ratio of the sizes of the colliding protoplanets. Computation results are in agreement with the megaimpact hypothesis.

Melosh, H. J.↗

Finite-dimensional approximation for optimal fixed-order compensation of distributed parameter systems

In controlling distributed parameter systems it is often desirable to obtain low-order, finite-dimensional controllers in order to minimize real-time computational requirements. Standard approaches to this problem employ model/controller reduction techniques in conjunction with LQG theory. In this paper we consider the finite-dimensional approximation of the infinite-dimensional Bernstein/Hyland optimal projection theory. This approach yields fixed-finite-order controllers which are optimal with respect to high-order, approximating, finite-dimensional plant models. The technique is illustrated by computing a sequence of first-order controllers for one-dimensional, single-input/single-output, parabolic (heat/diffusion) and hereditary systems using spline-based, Ritz-Galerkin, finite element approximation. Numerical studies indicate convergence of the feedback gains with less than 2 percent performance degradation over full-order LQG controllers for the parabolic system and 10 percent degradation for the hereditary system.

Bernstein, Dennis S.↗

Reliable communication in the presence of failures

The design and correctness of a communication facility for a distributed computer system are reported on. The facility provides support for fault-tolerant process groups in the form of a family of reliable multicast protocols that can be used in both local- and wide-area networks. These protocols attain high levels of concurrency, while respecting application-specific delivery ordering constraints, and have varying cost and performance that depend on the degree of ordering desired. In particular, a protocol that enforces causal delivery orderings is introduced and shown to be a valuable alternative to conventional asynchronous communication protocols. The facility also ensures that the processes belonging to a fault-tolerant process group will observe consistant orderings of events affecting the group as a whole, including process failures, recoveries, migration, and dynamic changes to group properties like member rankings. A review of several uses for the protocols is the ISIS system, which supports fault-tolerant resilient objects and bulletin boards, illustrates the significant simplification of higher level algorithms made possible by our approach.

Birman, Kenneth P.↗