Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 433 records · Page 24

Exploring the use of I/O nodes for computation in a MIMD multiprocessor

As parallel systems move into the production scientific-computing world, the emphasis will be on cost-effective solutions that provide high throughput for a mix of applications. Cost effective solutions demand that a system make effective use of all of its resources. Many MIMD multiprocessors today, however, distinguish between 'compute' and 'I/O' nodes, the latter having attached disks and being dedicated to running the file-system server. This static division of responsibilities simplifies system management but does not necessarily lead to the best performance in workloads that need a different balance of computation and I/O. Of course, computational processes sharing a node with a file-system service may receive less CPU time, network bandwidth, and memory bandwidth than they would on a computation-only node. In this paper we begin to examine this issue experimentally. We found that high performance I/O does not necessarily require substantial CPU time, leaving plenty of time for application computation. There were some complex file-system requests, however, which left little CPU time available to the application. (The impact on network and memory bandwidth still needs to be determined.) For applications (or users) that cannot tolerate an occasional interruption, we recommend that they continue to use only compute nodes. For tolerant applications needing more cycles than those provided by the compute nodes, we recommend that they take full advantage of both compute and I/O nodes for computation, and that operating systems should make this possible.

Kotz, David↗

Performance Monitoring of Distributed Data Processing Systems

Test and checkout systems are essential components in ensuring safety and reliability of aircraft and related systems for space missions. A variety of systems, developed over several years, are in use at the NASA/KSC. Many of these systems are configured as distributed data processing systems with the functionality spread over several multiprocessor nodes interconnected through networks. To be cost-effective, a system should take the least amount of resource and perform a given testing task in the least amount of time. There are two aspects of performance evaluation: monitoring and benchmarking. While monitoring is valuable to system administrators in operating and maintaining, benchmarking is important in designing and upgrading computer-based systems. These two aspects of performance evaluation are the foci of this project. This paper first discusses various issues related to software, hardware, and hybrid performance monitoring as applicable to distributed systems, and specifically to the TCMS (Test Control and Monitoring System). Next, a comparison of several probing instructions are made to show that the hybrid monitoring technique developed by the NIST (National Institutes for Standards and Technology) is the least intrusive and takes only one-fourth of the time taken by software monitoring probes. In the rest of the paper, issues related to benchmarking a distributed system have been discussed and finally a prescription for developing a micro-benchmark for the TCMS has been provided.

Ojha, Anand K.↗

Thruster Limitation Consideration for Formation Flight Control

Physical constraints of any real system can have a drastic effect on its performance. Some of the more recognized constraints are actuator and sensor saturation and bandwidth, power consumption, sampling rate (sensor and control-loop) and computation limits. These constraints can degrade system s performance, such as settling time, overshoot, rising time, and stability margins. In order to address these issues, researchers have investigated the use of robust and nonlinear controllers that can incorporate uncertainty and constraints into a controller design. For instance, uncertainties can be addressed in the synthesis model used in such algorithms as H(sub infinity), or mu. There is a significant amount of literature addressing this type of problem. However, there is one constraint that has not often been considered; that is, actuator authority resolution. In this work, thruster resolution and controller schemes to compensate for this effect are investigated for position and attitude control of a Low Earth Orbit formation flight system. In many academic problems, actuators are assumed to have infinite resolution. In real system applications, such as formation flight systems, the system actuators will not have infinite resolution. High-precision formation flying requires the relative position and the relative attitude to be controlled on the order of millimeters and arc-seconds, respectively. Therefore, the minimum force resolution is a significant concern in this application. Without the sufficient actuator resolution, the system may be unable to attain the required pointing and position precision control. Furthermore, fuel may be wasted due to high-frequency chattering phenomena when attempting to provide a fine control with inadequate actuators. To address this issue, a Sliding Mode Controller is developed along with the boundary Layer Control to provide the best control resolution constraints. A Genetic algorithm is used to optimize the controller parameters according to the states error and fuel consumption criterion. The tradeoffs and effects of the minimum force limitation on performance are studied and compared to the case without the limitation. Furthermore, two methods are proposed to reduce chattering and improve precision.

Yunjun Xu↗

DSS-13 26-meter antenna upgraded radiometer system

The Deep Space Station (DSS)-13 26-m antenna radiometer system was upgraded with an IBM-compatible computer-controlled configuration with improved supporting hardware and software. Software was generated to analyze results and correct for antenna mispointing, tropospheric loss, and other observing errors. This total power radiometer configuration provides a prototype for the new DSS-13 34-m antenna. The radiometer system is described in terms of the theory, instrumentation hardware, computer configuration, and operational features and performance. The system is used to obtain antenna efficiency and pointing model data and is useful for radio source calibrations required for radio astronomy. Some recent results are given.

Stelzried, C. T.↗

Equation solvers for distributed-memory computers

A large number of scientific and engineering problems require the rapid solution of large systems of simultaneous equations. The performance of parallel computers in this area now dwarfs traditional vector computers by nearly an order of magnitude. This talk describes the major issues involved in parallel equation solvers with particular emphasis on the Intel Paragon, IBM SP-1 and SP-2 processors.

Storaasli, Olaf O.↗

Response of gravity level fluctuations on the Gravity Probe-B spacecraft propellant system

Time-dependent computations have been performed to investigate the dynamical behaviors of fluid under a microgravity environment. A computer algorithm is introduced which can be used to simulate the fluid behavior in that environment, in particular the excitation of sloshing waves due to different gravity environments and rotation speeds. A suggestion on the proper handling and managing of cryogenic fluid propellant to be used in the Gravity Probe-B spacecraft propulsion is made.

Hung, R. J.↗

Spacecraft attitude determination using a second-order nonlinear filter

The stringent attitude determination accuracy and faster slew maneuver requirements demanded by present-day spacecraft control systems motivate the development of recursive nonlinear filters for attitude estimation. This paper presents the second-order filter development for the estimation of attitude quaternion using three-axis gyro and star tracker measurement data. Performance comparisons have been made by computer simulation of system models and filter mechanization. It is shown that the second-order filter consistently performs better than the extended Kalman filter when the performance index of the root sum square estimation error of the quaternion vector is compared. The second-order filter identifies the gyro drift rates faster than the extended Kalman filter. The uniqueness of this algorithm is the online generation of the time-varying process and measurement noise covariance matrices, derived as a function or the process and measurement nonlinearity, respectively.

Vathsal, S.↗

Application-Controlled Parallel Asynchronous Input/Output Utility

A software utility tool has been designed to alleviate file system I/O performance bottlenecks to which many high-end computing (HEC) applications fall prey because of the relatively large volume of data generated for a given amount of computational work. In an effort to reduce computing resource waste, and to improve sustained performance of these HEC applications, a lightweight software utility has been designed to circumvent bandwidth limitations of typical HEC file systems by exploiting the faster inter-processor bandwidth to move output data from compute nodes to designated I/O nodes as quickly as possible, thereby minimizing the I/O wait time. This utility has successfully demonstrated a significant performance improvement within a major NASA weather application.

Clune, Thomas↗

A system to geometrically rectify and map airborne scanner imagery and to estimate ground area

A system of computer programs were developed which performs geometric rectification and line-by-line mapping of airborne multispectral scanner data to ground coordinates and estimates ground area. The system requires aircraft attitude and positional information furnished by ancillary aircraft equipment, as well as ground control points. The geometric correction and mapping procedure locates the scan lines, or the pixels on each line, in terms of map grid coordinates. The area estimation procedure gives ground area for each pixel or for a predesignated parcel specified in map grid coordinates. The results of exercising the system with simulated data showed the uncorrected video and corrected imagery and produced area estimates accurate to better than 99.7%.

Spencer, M. M.↗

ISIS and META projects

The ISIS project has developed a new methodology, virtual synchony, for writing robust distributed software. High performance multicast, large scale applications, and wide area networks are the focus of interest. Several interesting applications that exploit the strengths of ISIS, including an NFS-compatible replicated file system, are being developed. The META project is distributed control in a soft real-time environment incorporating feedback. This domain encompasses examples as diverse as monitoring inventory and consumption on a factory floor, and performing load-balancing on a distributed computing system. One of the first uses of META is for distributed application management: the tasks of configuring a distributed program, dynamically adapting to failures, and monitoring its performance. Recent progress and current plans are reported.

Birman, Kenneth↗

A computer simulation of Skylab dynamics and attitude control for performance verification and operational support

A simulation of the Skylab attitude and pointing control system (APCS) is outlined and discussed. Implementation is via a large hybrid computer and includes those factors affecting system momentum management, propellant consumption, and overall vehicle performance. The important features of the flight system are discussed; the mathematical models necessary for this treatment are outlined; and the decisions involved in implementation are discussed. A brief summary of the goals and capabilities of this tool is also included.

Buchanan, H.↗

HEC Applications on Columbia Project

NASA's Columbia system consists of a cluster of twenty 512 processor SGI Altix systems. Each of these systems is 3 TFLOP/s in peak performance - approximately the same as the entire compute capability at NAS just one year ago. Each 512p system is a single system image machine with one Linunx O5, one high performance file system, and one globally shared memory. The NAS Terascale Applications Group (TAG) is chartered to assist in scaling NASA's mission critical codes to at least 512p in order to significantly improve emergency response during flight operations, as well as provide significant improvements in the codes. and rate of scientific discovery across the scientifc disciplines within NASA's Missions. Recent accomplishments are 4x improvements to codes in the ocean modeling community, 10x performance improvements in a number of computational fluid dynamics codes used in aero-vehicle design, and 5x improvements in a number of space science codes dealing in extreme physics. The TAG group will continue its scaling work to 2048p and beyond (10240 cpus) as the Columbia system becomes fully operational and the upgrades to the SGI NUMAlink memory fabric are in place. The NUMlink uprades dramatically improve system scalability for a single application. These upgrades will allow a number of codes to execute faster at higher fidelity than ever before on any other system, thus increasing the rate of scientific discovery even further

Taft, Jim↗

Performability evaluation of the SIFT computer

Performability modeling and evaluation techniques are applied to the SIFT computer as it might operate in the computational evironment of an air transport mission. User-visible performance of the total system (SIFT plus its environment) is modeled as a random variable taking values in a set of levels of accomplishment. These levels are defined in terms of four attributes of total system behavior: safety, no change in mission profile, no operational penalties, and no economic process whose states describe the internal structure of SIFT as well as relavant conditions of the environment. Base model state trajectories are related to accomplishment levels via a capability function which is formulated in terms of a 3-level model hierarchy. Performability evaluation algorithms are then applied to determine the performability of the total system for various choices of computer and environment parameter values. Numerical results of those evaluations are presented and, in conclusion, some implications of this effort are discussed.

Meyer, J. F.↗

Stellar Photometry Software

We describe the Stellar Photometry Software (SPS), which combines in a single program procedures for locating stars, computing a mean stellar point-spread function (PSF), and performing aperture and/or multiple PSF-fitting photometry, along with related bookkeeping functions. The software can be run either interactively or in batch mode on computers using the UNIX operating system. The performance of SPS is compared to that of the photometry programs DoPHOT and IRAF/DAOPHOT, using both real and simulated CCD observations. A direct comparison of the instrumental magnitudes shows that all three programs produce comparable results.

Janes, Kenneth A.↗

Modeling Improvements and Users Manual for Axial-flow Turbine Off-design Computer Code AXOD

An axial-flow turbine off-design performance computer code used for preliminary studies of gas turbine systems was modified and calibrated based on the experimental performance of large aircraft-type turbines. The flow- and loss-model modifications and calibrations are presented in this report. Comparisons are made between computed performances and experimental data for seven turbines over wide ranges of speed and pressure ratio. This report also serves as the users manual for the revised code, which is named AXOD.

Glassman, Arthur J.↗