Search NASA⌕ Search

SEARCH · Search NASA

Results for “computer system performance”

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 1,477 records · Page 82

The Viking parachute qualification test technique.

The parachute system for NASA's Viking '75 Mars lander was flight qualified in four high-altitude flight tests at the White Sands Missile range (WSMR). A balloon system lifted a full-scale simulated Viking spacecraft to an altitude where a varying number of rocket motors were used to propel the high drag, lifting test vehicle to test conditions which would simulate the range of entry conditions expected at Mars. A ground-commanded cold gas pointing system located on the balloon system provided powered vehicle azimuth control to insure that the flight trajectory remained within the WSMR boundaries. A unique ground-based computer-radar system was employed to monitor inflight performance of the powered vehicle and insure that command ignition of the parachute mortar occurred at the required test conditions of Mach number and dynamic pressure. Performance data were obtained from cameras, telemetry, and radar.

Raper, J. L.↗

Optical Signal Processing: Poisson Image Restoration and Shearing Interferometry

Optical signal processing can be performed in either digital or analog systems. Digital computers and coherent optical systems are discussed as they are used in optical signal processing. Topics include: image restoration; phase-object visualization; image contrast reversal; optical computation; image multiplexing; and fabrication of spatial filters. Digital optical data processing deals with restoration of images degraded by signal-dependent noise. When the input data of an image restoration system are the numbers of photoelectrons received from various areas of a photosensitive surface, the data are Poisson distributed with mean values proportional to the illuminance of the incoherently radiating object and background light. Optical signal processing using coherent optical systems is also discussed. Following a brief review of the pertinent details of Ronchi's diffraction grating interferometer, moire effect, carrier-frequency photography, and achromatic holography, two new shearing interferometers based on them are presented. Both interferometers can produce variable shear.

Hong, Yie-Ming↗

Simulation Of The Internal-Combustion Engine

Program adapts to available information about particular engine. Mathematical model of internal-combustion engine constructed and implemented as computer program suitable for use on large digital computer systems. ZMOTTO program calculates Otto-cycle performance parameters as well as working-fluid compositions and properties throughout cycle for number of consecutive cycles and for variety of input parameters. Written in standard FORTRAN IV.

Zeleznik, Frank J.↗

Benchmarking hypercube hardware and software

It was long a truism in computer systems design that balanced systems achieve the best performance. Message passing parallel processors are no different. To quantify the balance of a hypercube design, an experimental methodology was developed and the associated suite of benchmarks was applied to several existing hypercubes. The benchmark suite includes tests of both processor speed in the absence of internode communication and message transmission speed as a function of communication patterns.

Grunwald, Dirk C.↗

Information processing in the primate visual system - An integrated systems perspective

The primate visual system contains dozens of distinct areas in the cerebral cortex and several major subcortical structures. These subdivisions are extensively interconnected in a distributed hierarchical network that contains several intertwined processing streams. A number of strategies are used for efficient information processing within this hierarchy. These include linear and nonlinear filtering, passage through information bottlenecks, and coordinated use of multiple types of information. In addition, dynamic regulation of information flow within and between visual areas may provide the computational flexibility needed for the visual system to perform a broad spectrum of tasks accurately and at high resolution.

Van Essen, David C.↗

Knowledge From Pictures (KFP)

The old maxim goes: 'A picture is worth a thousand words'. The objective of the research reported in this paper is to demonstrate this idea as it relates to the knowledge acquisition process and the automated development of an expert system's rule base. A prototype tool, the Knowledge From Pictures (KFP) tool, has been developed which configures an expert system's rule base by an automated analysis of and reasoning about a 'picture', i.e., a graphical representation of some target system to be supported by the diagnostic capabilities of the expert system under development. This rule base, when refined, could then be used by the expert system for target system monitoring and fault analysis in an operational setting. Most people, when faced with the problem of understanding the behavior of a complicated system, resort to the use of some picture or graphical representation of the system as an aid in thinking about it. This depiction provides a means of helping the individual to visualize the bahavior and dynamics of the system under study. An analysis of the picture augmented with the individual's background information, allows the problem solver to codify knowledge about the system. This knowledge can, in turn, be used to develop computer programs to automatically monitor the system's performance. The approach taken is this research was to mimic this knowledge acquisition paradigm. A prototype tool was developed which provides the user: (1) a mechanism for graphically representing sample system-configurations appropriate for the domain, and (2) a linguistic device for annotating the graphical representation with the behaviors and mutual influences of the components depicted in the graphic. The KFP tool, reasoning from the graphical depiction along with user-supplied annotations of component behaviors and inter-component influences, generates a rule base that could be used in automating the fault detection, isolation, and repair of the system.

Truszkowski, Walt↗

Autonomous control

KSC has been developing the Knowledge-Based Autonomous Test Engineer (KATE), which is a tool for performing automated monitoring, diagnosis, and control of electromechanical devices. KATE employs artificial intelligence computing techniques to perform these functions. The KATE system consists of a generic shell and a knowledge base. The KATE shell is the portion of the system which performs the monitoring, diagnosis, and control functions. It is generic in the sense that it is application independent. This means that the monitoring activity, for instance, will be performed with the same algorithms regardless of the particular physical device being used. The knowledge base is the portion of the system which contains specific functional and behavorial information about the physical device KATE is working with. Work is nearing completion on a project at KSC to interface a Texas Instruments Explorer running a LISP version of KATE with a Generic Checkout System (GCS) test-bed to control a physical simulation of a shuttle tanking system (humorously called the Red Wagon because of its color and mobility). The Autonomous Control System (ACS) project supplements and extends the KATE/GCS project by adding three other major activities. The activities include: porting KATE from the Texas Instruments Explorer machine to an Intel 80386-based UNIX workstation in the LISP language; rewriting KATE as necessary to run on the same 80386 workstation but in the Ada language; and investigating software and techniques to translate ANSI Standard Common LISP to Mil Standard Ada. Primary goals of this task are as follows: (1) establish the advantages of using expert systems to provide intelligent autonomous software for Space Station Freedom applications; (2) determine the feasibility of using Ada as the run-time environment for model-based expert systems; (3) provide insight into the advantages and disadvantagesof using LISP or Ada in the run-time environment for expert systems; and (4) compare the performance of the 80386 processor to a symbolic processor as a delivery vehicle for expert systems.

Brown, Barbara↗

Cooperative GN&C development in a rapid prototyping environment

The Navigation, Control and Aeronautics Division (NCAD) at NASA-JSC is exploring ways of producing Guidance, Navigation and Control (GN&C) flight software faster, better, and cheaper. To achieve these goals NCAD established two hardware/software facilities that take an avionics design project from initial inception through high fidelity real-time hardware-in-the-loop testing. Commercially available software products are used to develop the GN&C algorithms in block diagram form and then automatically generate source code from these diagrams. A high fidelity real-time hardware-in-the-loop laboratory provides users with the capability to analyze mass memory usage within the targeted flight computer, verify hardware interfaces, conduct system level verification, performance, acceptance testing, as well as mission verification using reconfigurable and mission unique data. To evaluate these concepts and tools, NCAD embarked on a project to build a real-time 6 DOF simulation of the Soyuz Assured Crew Return Vehicle flight software. To date, a productivity increase of 185 percent has been seen over traditional NASA methods for developing flight software.

Bordano, Aldo↗

Activities of the Research Institute for Advanced Computer Science

The Research Institute for Advanced Computer Science (RIACS) was established by the Universities Space Research Association (USRA) at the NASA Ames Research Center (ARC) on June 6, 1983. RIACS is privately operated by USRA, a consortium of universities with research programs in the aerospace sciences, under contract with NASA. The primary mission of RIACS is to provide research and expertise in computer science and scientific computing to support the scientific missions of NASA ARC. The research carried out at RIACS must change its emphasis from year to year in response to NASA ARC's changing needs and technological opportunities. Research at RIACS is currently being done in the following areas: (1) parallel computing; (2) advanced methods for scientific computing; (3) high performance networks; and (4) learning systems. RIACS technical reports are usually preprints of manuscripts that have been submitted to research journals or conference proceedings. A list of these reports for the period January 1, 1994 through December 31, 1994 is in the Reports and Abstracts section of this report.

Oliger, Joseph↗

Development of software for the MSFC solar vector magnetograph

The Marshall Space Flight Center Solar Vector Magnetograph is a special purpose telescope used to measure the vector magnetic field in active areas on the surface of the sun. This instrument measures the linear and circular polarization intensities (the Stokes vectors Q, U and V) produced by the Zeeman effect on a specific spectral line due to the solar magnetic field from which the longitudinal and transverse components of the magnetic field may be determined. Beginning in 1990 as a Summer Faculty Fellow in project JOVE and continuing under NASA Grant NAG8-1042, the author has been developing computer software to perform these computations, first using a DEC MicroVAX system equipped with a high speed array processor, and more recently using a DEC AXP/OSF system. This summer's work is a continuation of this development.

Kineke, Jack↗

Comparison of 250 MHz R10K Origin 2000 and 400 MHz Origin 2000 Using NAS Parallel Benchmarks

This report describes results of benchmark tests on Steger, a 250 MHz Origin 2000 system with R10K processors, currently installed at the NASA Ames National Advanced Supercomputing (NAS) facility. For comparison purposes, the tests were also run on Lomax, a 400 MHz Origin 2000 with R12K processors. The BT, LU, and SP application benchmarks in the NAS Parallel Benchmark Suite and the kernel benchmark FT were chosen to measure system performance. Having been written to measure performance on Computational Fluid Dynamics applications, these benchmarks are assumed appropriate to represent the NAS workload. Since the NAS runs both message passing (MPI) and shared-memory, compiler directive type codes, both MPI and OpenMP versions of the benchmarks were used. The MPI versions used were the latest official release of the NAS Parallel Benchmarks, version 2.3. The OpenMP versions used were PBN3b2, a beta version that is in the process of being released. NPB 2.3 and PBN3b2 are technically different benchmarks, and NPB results are not directly comparable to PBN results.

Turney, Raymond D.↗

Inlet Performance Analysis Code Developed

The design characteristics of an inlet very much depend on whether the inlet is to be flown at subsonic, supersonic, or hypersonic speed. Whichever the case, the primary function of an inlet is to deliver free-stream air to the engine face at the highest stagnation pressure possible and with the lowest possible variation in both stagnation pressure and temperature. At high speeds, this is achieved by a system of oblique and/or normal shock waves, and possibly some isentropic compression. For both subsonic and supersonic flight, current design practice indicates that the inlet should deliver the air to the engine face at approximately Mach 0.45. As a result, even for flight in the high subsonic regime, the inlet must retard (or diffuse) the air substantially. Second, the design of an inlet is influenced largely by the compromise between high performance and low weight. This compromise involves tradeoffs between the mission requirements, flight trajectory, airframe aerodynamics, engine performance, and weight-all of which, in turn, influence each other. Therefore, to study the effects of some of these influential factors, the Propulsion System Analysis Office of the NASA Lewis Research Center developed the Inlet Performance Analysis Code (IPAC). This code uses oblique shock and Prandtl-Meyer expansion theory to predict inlet performance. It can be used to predict performance for a given inlet geometric design such as pitot, axisymmetric, and two-dimensional. IPAC also can be used to design preliminary inlet systems and to make subsequent performance analyses. It computes the total pressure, the recovery, the airflow, and the drag coefficients. The pressure recovery includes losses associated with normal and oblique shocks, internal and external friction, the sharp lip, and diffuser components. Flow rate includes captured, engine, spillage, bleed, and bypass flows. The aerodynamic drag calculation includes drags associated with spillage, cowl lip suction, wave, bleed, and bypass.

Jules, Kenol↗

Intrinsic evolution of controllable oscillators in FPTA-2

Simple one- and two-bit controllable oscillators were intrinsically evolved using only four cells of Field Programmable Transistor Array (FPTA-2). These oscillators can produce different oscillations for different setting of control signals. Therefore, they could be used, in principle, to compose complex networks of oscillators that could exhibit rich dynamical behavior in order to perform a computation or to model a desired system.

evolvable hardware↗

Color Choice is Everything - Impacts Color makes to the Lighting Environment

When contracts are let out to design multiple systems in a vehicle, it is a challenge to maintain integration between system leads. Designers on niche systems, like lighting and control panel design, often get caught up in the challenge of designing the light source or visual interface and fail to include time in their schedule to work with system architects on how their lighting system will be integrated. Additionally, behavioral scientists, industrial designers, and materials engineers get caught up with the materials and look of the system, but often fail to consider how the selection of their materials could affect the certification or performance of electronic devices like lighting systems. Additionally, computer modeling of the system architecture often assumes a perfect environment without the clutter of actual human use (dirt, stowage, crowding). As a result, lighting systems, and backlit displays run the risk of being overdesigned or under designed. Engineers making the assumption that because they have no input or there is no requirement on work surface reflectance, make the assumption that they can t count on good material choices and thus may install more lighting than is necessary. While having more lights may seem better, for a vehicle that is trying to conserve power, more lights may not be a good option. On the other hand, designers who made the opposite assumption and designed a lighting system that only produced just enough light, often wind up with a system that did conserve power, but didn t produce enough light. These situations are exasperated when the system starts to be used and the models are not perfect anymore. The lack of coordination and iterative design not only can impact lighting levels within an environment, but also can affect color perception. This is because, if materials do not represent a gradation of white or black, the material unevenly absorbs and reflects light at different wavelengths of the visual spectrum. The lighting designer may have built a light that meets light spectra requirements, but the eventual light reaching the human user may not be the spectra of light architects intended, if materials near the light source change the spectrum just by how much color is absorbed or reflected. With the recent findings concerning Circadian rhythm, where the spectra of light is extremely important for addressing crew sleep and wake cycles, system architects should pay considerable attention on the impact material choices have in changing the light spectrum in an environment. This presentation will show examples of how material choices impact the resulting illuminance, color spectrum, and power usage of an illuminated space. Its goal is to encourage system designers and planners to use more care in development of requirements and the verification of systems intended for the human visual interface.

Clark, Toni A.↗

CLEERS Aftertreatment Modeling and Analysis

CLEERS is an R&D focus project of the Diesel Cross-Cut Team. The overall objective is to promote the development of improved computational tools for simulating realistic full-system performance of lean-burn engines and the associated emissions control systems. Three fundamental research projects are sponsored at PNNL through CLEERS: DPF, SCR, and LNT. Resources are shared between the three efforts in order to actively respond to current industrial needs. This report documents recent results obtained during FY14.

Environmental Molecular Sciences Laboratory↗

Review of Enabling Technologies to Facilitate Secure Compute Customization

High performance computing environments are often used for a wide variety of workloads ranging from simulation, data transformation and analysis, and complex workflows to name just a few. These systems may process data for a variety of users, often requiring strong separation between job allocations. There are many challenges to establishing these secure enclaves within the shared infrastructure of high-performance computing (HPC) environments. The isolation mechanisms in the system software are the basic building blocks for enabling secure compute enclaves. There are a variety of approaches and the focus of this report is to review the different virtualization technologies that facilitate the creation of secure compute enclaves. The report reviews current operating system (OS) protection mechanisms and modern virtualization technologies to better understand the performance/isolation properties. We also examine the feasibility of running ``virtualized'' computing resources as non-privileged users, and providing controlled administrative permissions for standard users running within a virtualized context. Our examination includes technologies such as Linux containers (LXC [32], Docker [15]) and full virtualization (KVM [26], Xen [5]). We categorize these different approaches to virtualization into two broad groups: OS-level virtualization and system-level virtualization. The OS-level virtualization uses containers to allow a single OS kernel to be partitioned to create Virtual Environments (VE), e.g., LXC. The resources within the host's kernel are only virtualized in the sense of separate namespaces. In contrast, system-level virtualization uses hypervisors to manage multiple OS kernels and virtualize the physical resources (hardware) to create Virtual Machines (VM), e.g., Xen, KVM. This terminology of VE and VM, detailed in Section 2, is used throughout the report to distinguish between the two different approaches to providing virtualized execution environments. As part of our technology review we analyzed several current virtualization solutions to assess their vulnerabilities. This included a review of common vulnerabilities and exposures (CVEs) for Xen, KVM, LXC and Docker to gauge their susceptibility to different attacks. The complete details are provided in Section 5 on page 33. Based on this review we concluded that system-level virtualization solutions have many more vulnerabilities than OS level virtualization solutions. As such, security mechanisms like sVirt (Section 3.3) should be considered when using system-level virtualization solutions in order to protect the host against exploits. The majority of vulnerabilities related to KVM, LXC, and Docker are in specific regions of the system. Therefore, future "zero day attacks" are likely to be in the same regions, which suggests that protecting these areas can simplify the protection of the host and maintain the isolation between users. The evaluations of virtualization technologies done thus far are discussed in Section 4. This includes experiments with 'user' namespaces in VEs, which provides the ability to isolate user privileges and allow a user to run with different UIDs within the container while mapping them to non-privileged UIDs in the host. We have identified Linux namespaces as a promising mechanism to isolate shared resources, while maintaining good performance. In Section 4.1 we describe our tests with LXC as a non-root user and leveraging namespaces to control UID/GID mappings and support controlled sharing of parallel file-systems. We highlight several of these namespace capabilities in Section 6.2.3. The other evaluations that were performed during this initial phase of work provide baseline performance data for comparing VEs and VMs to purely native execution. In Section 4.2 we performed tests using the High-Performance Computing Conjugate Gradient (HPCCG) benchmark to establish baseline performance for a scientific application when run on the Native (host) machine in contrast with execution under Docker and KVM. Our tests verified prior studies showing roughly 2-4% overheads in application execution time & MFlops when running in hypervisor-base environments (VMs) as compared to near native performance with VEs. For more details, see Figures 4.5 (page 28), 4.6 (page 28), and 4.7 (page 29). Additionally, in Section 4.3 we include network measurements for TCP bandwidth performance over the 10GigE interface in our testbed. The Native and Docker based tests achieved >= ~9Gbits/sec, while the KVM configuration only achieved 2.5Gbits/sec (Table 4.6 on page 32). This may be a configuration issue with our KVM installation, and is a point for further testing as we refine the network settings in the testbed. The initial network tests were done using a bridged networking configuration. The report outline is as follows: - Section 1 introduces the report and clarifies the scope of the proj...

Aderholdt, Ferrol↗

Transient multivariable sensor evaluation

A method and system for performing transient multivariable sensor evaluation. The method and system includes a computer system for identifying a model form, providing training measurement data, generating a basis vector, monitoring system data from sensor, loading the system data in a non-transient memory, performing an estimation to provide desired data and comparing the system data to the desired data and outputting an alarm for a defective sensor.

47 OTHER INSTRUMENTATION↗