SEARCH · Search NASA

Results for “Parallel connection”

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 343 records · Page 19

All sources NASA NTRS DOE OSTI

NASA NTRS1989

A computational fluid dynamics algorithm on a massively parallel computer

The implementation and performance of a finite-difference algorithm for the compressible Navier-Stokes equations in two or three dimensions on the Connection Machine are described. This machine is a single-instruction multiple-data machine with up to 65536 physical processors. The implicit portion of the algorithm is of particular interest. Running times and megadrop rates are given for two- and three-dimensional problems. Included are comparisons with the standard codes on a Cray X-MP/48.

Jespersen, Dennis C.↗

NASA NTRS1992

Network issues for large mass storage requirements

File Servers and Supercomputing environments need high performance networks to balance the I/O requirements seen in today's demanding computing scenarios. UltraNet is one solution which permits both high aggregate transfer rates and high task-to-task transfer rates as demonstrated in actual tests. UltraNet provides this capability as both a Server-to-Server and Server-to-Client access network giving the supercomputing center the following advantages highest performance Transport Level connections (to 40 MBytes/sec effective rates); matches the throughput of the emerging high performance disk technologies, such as RAID, parallel head transfer devices and software striping; supports standard network and file system applications using SOCKET's based application program interface such as FTP, rcp, rdump, etc.; supports access to the Network File System (NFS) and LARGE aggregate bandwidth for large NFS usage; provides access to a distributed, hierarchical data server capability using DISCOS UniTree product; supports file server solutions available from multiple vendors, including Cray, Convex, Alliant, FPS, IBM, and others.

Perdue, James↗

NASA NTRS1995

NAS Experiences of Porting CM Fortran Codes to HPF on IBM SP2 and SGI Power Challenge

Current Connection Machine (CM) Fortran codes developed for the CM-2 and the CM-5 represent an important class of parallel applications. Several users have employed CM Fortran codes in production mode on the CM-2 and the CM-5 for the last five to six years, constituting a heavy investment in terms of cost and time. With Thinking Machines Corporation's decision to withdraw from the hardware business and with the decommissioning of many CM-2 and CM-5 machines, the best way to protect the substantial investment in CM Fortran codes is to port the codes to High Performance Fortran (HPF) on highly parallel systems. HPF is very similar to CM Fortran and thus represents a natural transition. Conversion issues involved in porting CM Fortran codes on the CM-5 to HPF are presented. In particular, the differences between data distribution directives and the CM Fortran Utility Routines Library, as well as the equivalent functionality in the HPF Library are discussed. Several CM Fortran codes (Cannon algorithm for matrix-matrix multiplication, Linear solver Ax=b, 1-D convolution for 2-D datasets, Laplace's Equation solver, and Direct Simulation Monte Carlo (DSMC) codes have been ported to Subset HPF on the IBM SP2 and the SGI Power Challenge. Speedup ratios versus number of processors for the Linear solver and DSMC code are presented.

Saini, Subhash↗

NASA NTRS2001

Latency Hiding in Dynamic Partitioning and Load Balancing of Grid Computing Applications

The Information Power Grid (IPG) concept developed by NASA is aimed to provide a metacomputing platform for large-scale distributed computations, by hiding the intricacies of highly heterogeneous environment and yet maintaining adequate security. In this paper, we propose a latency-tolerant partitioning scheme that dynamically balances processor workloads on the.IPG, and minimizes data movement and runtime communication. By simulating an unsteady adaptive mesh application on a wide area network, we study the performance of our load balancer under the Globus environment. The number of IPG nodes, the number of processors per node, and the interconnected speeds are parameterized to derive conditions under which the IPG would be suitable for parallel distributed processing of such applications. Experimental results demonstrate that effective solution are achieved when the IPG nodes are connected by a high-speed asynchronous interconnection network.

Das, Sajal K.↗

NASA NTRS2009

Small Deflection Energy Analyzer for Energy and Angular Distributions

The development of the Small Deflection Energy Analyzer (SDEA) charged-particle spectrometer for energy and angle distributions responds to a longstanding need to measure the wind velocity vector in Earth s thermosphere, and to obtain the ion-drift vector in the ionosphere. The air and ions above 120 km are endowed with bulk velocities and temperatures just like air near the ground, but with separate spatial and temporal variations. It is important to understand these not only for study of the physics and chemistry of the Sun-Earth connection, but also for spacecraft orbit predictions, and communications through the ionosphere. The SDEA consists of a pair of parallel conducting plates separated by a small distance, with an entrance slit on one end, and an exit slit on the other. A voltage applied to these plates develops an electric field between the plates, and this field deflects ions passing through it. If an ion has too little energy, it will strike one of the plates. If it has too much, it will strike the back wall. An ion with the amount of energy being searched for will have its trajectory bent just enough to exit the back slit. The SDEA units are compact, rectangular, and operate with low voltages. The units can be built up into small arrays. These arrays could be used either to widen the field of view or to sharpen an existing one. This approach can also be used to obtain angular distributions in two planes simultaneously, thus cutting down the ion source power requirements in half. This geometry has enabled a new mass-spectrometer concept that can provide miniaturized mass spectrometers for use in industrial plants, air-pollution monitoring, and noxious-gas detection.

Herrero, Federico A.↗

NASA NTRS2013

Operation of Direct Drive Systems: Experiments in Peak Power Tracking and Multi-Thruster Control

Direct-drive power and propulsion systems have the potential to significantly reduce the mass of high-power solar electric propulsion spacecraft, among other advantages. Recent experimental direct-drive work has significantly mitigated or retired the technical risks associated with single-thruster operation, so attention is now moving toward systems-level areas of interest. One of those areas is the use of a Hall thruster system as a peak power tracker to fully use the available power from a solar array. A simple and elegant control based on the incremental conductance method, enhanced by combining it with the unique properties of Hall thruster systems, is derived here and it is shown to track peak solar array power very well. Another area of interest is multi-thruster operation and control. Dualthruster operation was investigated in a parallel electrical configuration, with both thrusters operating from discharge power provided by a single solar array. Startup and shutdown sequences are discussed, and it is shown that multi-thruster operation and control is as simple as for a single thruster. Some system architectures require operation of multiple cathodes while they are electrically connected together. Four different methods to control the discharge current emitted by individual cathodes in this configuration are investigated, with cathode flow rate control appearing to be advantageous. Dual-parallel thruster operation with equal cathode current sharing at total powers up to 10 kW is presented.

solar electric propulsion (SEP) vehicles↗

NASA NTRS1982

Clutchless multiple drive source for output shaft

A first shaft is connected to a source of rotational power and has a gear fixedly mounted on the shaft. A second gear is fixedly mounted on a gear shaft that is parallel to the first shaft. A third gear, also fixedly mounted on gear shaft, meshes with a fourth gear fixedly mounted on the output shaft. The first input shaft and output shaft are rotatably mounted through a housing that is itself rotatable with respect to a support. Both shafts are coaxial and in end-to-end relationship. A second input shaft is connected to a second source of rotational power. A fifth gear, fixedly mounted on second input shaft, meshes with a sixth gear, which is fixedly mounted on rotatable housing and in coaxial relationship with first input shaft. In operation, the first drive source and gear train provide rotational power in a first direction to drive the output shaft in a given direction of rotation. The second source of rotational power may be operated either to decrease the rate of rotation imparted to the output shaft by the first source of rotational power, or to increase that rate of rotation, depending on which direction the housing is rotated by the second source of rotational power.

Webster, L. D.↗

NASA NTRS2013

Stress-Dependent Voltage Offsets From Polymer Insulators Used in Rock Mechanics and Material Testing

Dielectric insulators are used in a variety of laboratory settings when performing experiments in rock mechanics, petrology, and electromagnetic studies of rocks in the fields of geophysics,material science, and civil engineering. These components may be used to electrically isolate geological samples from the experimental equipment, to perform a mechanical compliance function between brittle samples and the loading equipment, to match ultrasonic transducers, or perform other functions. In manyexperimental configurations the insulators bear the full brunt of force applied to the sample but do not need to withstand high voltages, therefore the insulators are often thin sheets of mechanically tough polymers. From an instrument perspective, transduction from various types of mechanical perturbation has beenqualitatively compared for a number of polymers [1, 2] and these error sources are readily apparent duringhigh-impedance measurements if not mitigated. However even when following best practices, a force dependent voltage signal still remains and its behavior is explored in this presentation. In this experimenttwo thin sheets (0.25 mm) of high-density polyethylene (HDPE) were set up in a stack, held alternatelybetween three aluminum bars; this stack was placed on the platen of a 60T capacity hydraulic testingmachine. The surface area, A, over which the force is applied to the PE sheets in this sandwich is roughly 40 square cm, each sheet forming a parallel-plate capacitor having roughly 320 pF [3], assuming therelative dielectric permittivity of PE is approximately 2.3. The outer two aluminum bars were connected to the LO input ofthe electrometer and the central aluminum bar was connected to the HI input of a Keithley model 617 electrometer. Once the stack is mechanically well-seated with no air gaps, the voltage offset is observed tobe a linear function of the baseline voltage for a given change in applied force. For a periodically appliedforce of 66.7 kN the voltage offsets were measured as a function of initial voltage, and these data were fitwith a linear function that was constrained to pass through the origin. The best fit solution had a correlation coefficient of R=0.85 and a slope of approximately -0.0228 volts/volt. The voltage offset when normalizedis demonstrated to be constant -2.28% for both positive and negative polarities over nearly 3 orders ofbaseline voltage magnitude. From this, the voltage-force coefficient is derived to be -0.34 ppm/N. Thiscorrelates well to a first-order parallel plate capacitor model that assumes constant area, and smalldeformation such that the polymer may be mechanically modeled by a spring that obeys Hookes law. Thissimple model predicts that the coefficient of proportionality is a function of Youngs modulus E= 0.8 GPaand surface area of the insulator, theoretically -1EA= -0.31 ppm/N. The outcome of this work is animproved insulator made from ultra-high molecular weight (UHMW) polyethylene and other approachestoward the minimization of and compensation for these experimental artifacts.

Electromagnetic Studies of Rocks↗

NASA NTRS1980

A note on sound radiation into a uniformly flowing fluid

Sound radiation generated by mechanical or vibratory source arrangements and, in some instances of planar or piston types, encompasses all magnitudes of the wavelength or frequency as well as disposition of the observation site. The comparative increase in average total radiated power from infinitesimally small or point sources of periodic strength, on passing from rest to steady rectilinear motion, depends only on Mach number in the noncompact case; and a formally analogous rise in output is linked, to the presence of a steady parallel flow past a rigid plane wall in which a compact circular piston executes normal oscillations. The perspective of effects connected with such a background is flow is widened by regard for an elongated or strip piston, which prototype permits a straightforward and general analysis.

Levine, H.↗

NASA NTRS1985

Beam forming network

The network, which is connected to a layer of 134 feed elements that transmit and receive microwaves, consists of a pair of circuit boards parallel to the feed element layer. One of the two boards has 87 dividers that each divide a signal to be transmitted into seven portions, and the other board has 134 combiners that each collect seven transmit signal portions and deliver the sum to one of the feed elements. A similar arrangement is used to handle received signals. The large number of interconnections are made by printed circuit conductors radiating from each of the numerous dividers and combiners, and by providing interconnection pins that interconnect the ends of pairs of conductors lying on the two boards. The printed circuit conductors extend in undulating paths that provide maximum separation of conductors to minimize crosstalk.

Cramer, P. W., Jr.↗

NASA NTRS1988

Fast Fourier Transform algorithm design and tradeoffs

The Fast Fourier Transform (FFT) is a mainstay of certain numerical techniques for solving fluid dynamics problems. The Connection Machine CM-2 is the target for an investigation into the design of multidimensional Single Instruction Stream/Multiple Data (SIMD) parallel FFT algorithms for high performance. Critical algorithm design issues are discussed, necessary machine performance measurements are identified and made, and the performance of the developed FFT programs are measured. Fast Fourier Transform programs are compared to the currently best Cray-2 FFT program.

Kamin, Ray A., III↗

NASA NTRS1989

Local area network with fault-checking, priorities, and redundant backup

This invention is a redundant error detecting and correcting local area networked computer system having a plurality of nodes each including a network connector board within the node for connecting to an interfacing transceiver operably attached to a network cable. There is a first network cable disposed along a path to interconnect the nodes. The first network cable includes a plurality of first interfacing transceivers attached thereto. A second network cable is disposed in parallel with the first cable and, in like manner, includes a plurality of second interfacing transceivers attached thereto. There are a plurality of three position switches each having a signal input, three outputs for individual selective connection to the input, and a control input for receiving signals designating which of the outputs is to be connected to the signal input. Each of the switches includes means for designating a response address for responding to addressed signals appearing at the control input and each of the switches further has its signal input connected to a respective one of the input/output lines from the nodes. Also, one of the three outputs is connected to a repective one of the plurality of first interfacing transceivers. There is master switch control means having an output connected to the control inputs of the plurality of three position switches and an input for receiving directive signals for outputting addressed switch position signals to the three position switches as well as monitor and control computer means having a pair of network connector boards therein connected to respective ones of one of the first interfacing transceivers and one of the second interfacing transceivers and an output connected to the input of the master switch means for monitoring the status of the networked computer system by sending messages to the nodes and receiving and verifying messages therefrom and for sending control signals to the master switch to cause the master switch to cause respective ones of the nodes to use a desired one of the first and second cables for transmitting and receiving messages and for disconnecting desired ones of the nodes from both cables.

Morales, Sergio↗

NASA NTRS1993

Parallel integer sorting with medium and fine-scale parallelism

Two new parallel integer sorting algorithms, queue-sort and barrel-sort, are presented and analyzed in detail. These algorithms do not have optimal parallel complexity, yet they show very good performance in practice. Queue-sort designed for fine-scale parallel architectures which allow the queueing of multiple messages to the same destination. Barrel-sort is designed for medium-scale parallel architectures with a high message passing overhead. The performance results from the implementation of queue-sort on a Connection Machine CM-2 and barrel-sort on a 128 processor iPSC/860 are given. The two implementations are found to be comparable in performance but not as good as a fully vectorized bucket sort on the Cray YMP.

Dagum, Leonardo↗

NASA NTRS1999

Atomic Oxygen Lamp Cleaning Facility Fabricated and Tested

NASA Lewis Research Center's Atomic Oxygen Lamp Cleaning Facility was designed to produce an atomic oxygen plasma within a metal halide lamp to remove carbon-based contamination. It is believed that these contaminants contribute to the high failure rate realized during the production of these lamps. The facility is designed to evacuate a metal halide lamp and produce a radio frequency generated atomic oxygen plasma within it. Oxygen gas, with a purity of 0.9999 percent and in the pressure range of 150 to 250 mtorr, is used in the lamp for plasma generation while the lamp is being cleaned. After cleaning is complete, the lamp can be backfilled with 0.9999-percent pure nitrogen and torch sealed. The facility comprises various vacuum components connected to a radiation-shielded box that encloses the bulb during operation. Radiofrequency power is applied to the two parallel plates of a capacitor, which are on either side of the lamp. The vacuum pump used, a Leybold Trivac Type D4B, has a pumping speed of 4-m3/hr, has an ultimate pressure of <8x10-4, and is specially adapted for pure oxygen service. The electronic power supply, matching network, and controller (500-W, 13.56-MHz) used to supply the radiofrequency power were purchased from RF Power Products Inc. Initial test results revealed that this facility could remove the carbon-based contamination from within bulbs.

Sechkar, Edward A.↗

NASA NTRS2007

Loop Heat Pipe Operation with Thermoelectric Converters and Coupling Blocks

This paper presents theoretical and experimental studies on using thermoelectric converters (TECs) and coupling blocks to control the operating temperature of a miniature loop heat pipes (MLHP). The MLHP has two parallel evaporators and two parallel condensers, and each evaporator has its own integral compensation chamber (CC). A TEC is attached to each CC, and connected to the evaporator via a copper thermal strap. The TEC can provide both heating and cooling to the CC, therefore extending the LHP operating temperature over a larger range of the evaporator heat load. A bi-polar power supply is used for the TEC operation. The bipolar power supply automatically changes the direction of the current to the TEC, depending on whether the CC requires heating or cooling, to maintain the CC temperature at the desired set point. The TEC can also enhance the startup success by maintaining a constant CC temperature during the start-up transient. Several aluminum coupling blocks are installed between the vapor line and liquid line. The coupling blocks serve as a heat exchanger which preheats the cold returning liquid so as to reduce the amount of liquid subcooling, and hence the power required to maintain the CC at the desired set point temperature. This paper focuses on the savings of the CC control heater power afforded by the TECs when compared to traditional electric heaters. Tests were conducted by varying the evaporator power, the condenser sink temperature, the CC set point temperature, the number of coupling blocks, and the thermal conductance of the thermal strap. Test results show that the TECs are able to control the CC temperature within k0.5K under all test conditions, and the required TEC heater power is only a fraction of the required electric heater power.

Ku, Jentung↗

NASA NTRS1989

NETRA: A parallel architecture for integrated vision systems. 1: Architecture and organization

Computer vision is regarded as one of the most complex and computationally intensive problems. An integrated vision system (IVS) is considered to be a system that uses vision algorithms from all levels of processing for a high level application (such as object recognition). A model of computation is presented for parallel processing for an IVS. Using the model, desired features and capabilities of a parallel architecture suitable for IVSs are derived. Then a multiprocessor architecture (called NETRA) is presented. This architecture is highly flexible without the use of complex interconnection schemes. The topology of NETRA is recursively defined and hence is easily scalable from small to large systems. Homogeneity of NETRA permits fault tolerance and graceful degradation under faults. It is a recursively defined tree-type hierarchical architecture where each of the leaf nodes consists of a cluster of processors connected with a programmable crossbar with selective broadcast capability to provide for desired flexibility. A qualitative evaluation of NETRA is presented. Then general schemes are described to map parallel algorithms onto NETRA. Algorithms are classified according to their communication requirements for parallel processing. An extensive analysis of inter-cluster communication strategies in NETRA is presented, and parameters affecting performance of parallel algorithms when mapped on NETRA are discussed. Finally, a methodology to evaluate performance of algorithms on NETRA is described.

Choudhary, Alok N.↗

NASA NTRS1991

A parallel vectorized implementation of triple excitations in CCSD(T) - Application to the binding energies of the AlH3, AlH2F, AlHF2 and AlF3 dimers

An efficient method for various noniterative estimates of connected triple excitations in coupled-cluster theory is outlined and related to a similar expression occurring in Moller-Plesset perturbation theory. The method is highly vectorized and capable of utilizing multiple processors on a shared-memory machine, leading to computational rates in excess of one billion floating-point operations per second on four processors of a CRAY Y-MP. Using the new procedure, the binding energies of the D(2h) diborane-type dimers of AlH3, AlH2F, AlHF2, and AlF3 have been determined to be 32, 40, 20, and 47 kcal/mol, respectively. For Al2F6, the correlation procedure includes 232 molecular orbitals and over 1.5 x 10 to the 6th single and double coupled-cluster amplitudes, effectively accounting for over 2 x 10 to the 9th connected triple excitations.

Rendell, Alistair P.↗

NASA NTRS1996

Effect of Variable Gravity on Evaporation of Binary Fluids in a Capillary Pore Evaporator

The research project focuses on experimental investigation of the capillary-pumped evaporative heat transfer phenomenon. The objective is to examine whether the heat transfer and stability of a heated meniscus in a capillary pore can be enhanced by adding trace amounts of a non-volatile solute to a solvent and to understand the changes that occur. The experimental setup consists of a single pore evaporator connected to a reservoir which supplies liquid to the evaporator. In addition to the experiments of capillary-pumped evaporation, a parallel experimental study has been conducted to systematically investigate the effects of gravity as well as the effects of bulk composition on the heat transfer characteristics of evaporating binary thin films near the contact line region along an inclined heated surface. To investigate the buoyancy effects on evaporation along an inclined heated surface, the angle of inclination from a horizontal plane was varied fro 15 C to 90 C. An optimum concentration between 0.5% and 1% decane in pentane/decane solutions has been demonstrated at different angles of inclination. Improved heat transfer was found for the geometry with the smallest angle of inclination of 15 degrees. In addition, flow visualization has revealed that at low inclination angles effective heat transfer takes place primarily due to an extension of the thin film near the contact line. At these low inclination angles, the optimum concentration is associated with enhanced wetting characteristics and reduced thermocapillary stresses along the interface.

Girgis, Morris M.↗