Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel implementation”

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 721 records · Page 40

Parallel PAB3D: Experiences with a Prototype in MPI

PAB3D is a three-dimensional Navier Stokes solver that has gained acceptance in the research and industrial communities. It takes as computational domain, a set disjoint blocks covering the physical domain. This is the first report on the implementation of PAB3D using the Message Passing Interface (MPI), a standard for parallel processing. We discuss briefly the characteristics of tile code and define a prototype for testing. The principal data structure used for communication is derived from preprocessing "patching". We describe a simple interface (COMMSYS) for MPI communication, and some general techniques likely to be encountered when working on problems of this nature. Last, we identify levels of improvement from the current version and outline future work.

Guerinoni, Fabio↗

Parallel computing strategies for block multigrid implicit solution of the Euler equations

A multigrid diagonal implicit algorithm has been developed to solve the three-dimensional Euler equations of inviscid compressible flow on block-structured grids. An improved method of advancing the multigrid cycle has been examined with respect to convergence rates, accuracy, and efficiency. In this method, the multigrid cycle is advanced independently in each of the blocks, and the information exchange between the blocks is done using buffer arrays, allowing for the asynchronous updating of interface boundary conditions. This updating scheme is used to eliminate the convergence problems found in a previous implementation of the algorithm while retaining its potential for efficient parallel execution. Results are computed for transonic flows past wings and include pressure distributions to verify the accuracy of the scheme and convergence histories to demonstrate the efficiency of the method. Efficiencies that were obtained using a modest number of processors in parallel are also presented and discussed.

Yadlin, Yoram↗

Address tracing of parallel systems via TRAPEDS

Trace-driven simulation is an important aid in performance analysis of computer systems. Capturing address traces to use in these simulations, however, is a difficult problem for parallel processor architectures. A technique termed TRAPEDS modifies executable code (at the assembly language level) to dynamically collect the address trace from executing code. TRAPEDS has recently been implemented on both a hypercube multicomputer and a shared-memory multiprocessor. Particular attention is focused on strategies for efficiently and accurately collecting traces from both classes of parallel machines. The iPSC/2 hypercube multicomputer implementation traces both user and system code, and performs simulation on-the-fly to avoid large storage costs. Strategies are detailed for mitigating address trace distortion when collecting operating system traces. The Encore Multimax multiprocessor implementation uses a timer-based approach to reflect the interleaving of the processor traces and stores the traces to disc. Time and space overhead results are presented for both TRAPEDS implementations. Experimental cache simulation results derived from iPSC/2 address traces are presented to illustrate the importance of tracing operating system references.

Stunkel, Craig B.↗

An Optimized Multicolor Point-Implicit Solver for Unstructured Grid Applications on Graphics Processing Units

In the field of computational fluid dynamics, the Navier-Stokes equations are often solved using an unstructuredgrid approach to accommodate geometric complexity. Implicit solution methodologies for such spatial discretizations generally require frequent solution of large tightly-coupled systems of block-sparse linear equations. The multicolor point-implicit solver used in the current work typically requires a significant fraction of the overall application run time. In this work, an efficient implementation of the solver for graphics processing units is proposed. Several factors present unique challenges to achieving an efficient implementation in this environment. These include the variable amount of parallelism available in different kernel calls, indirect memory access patterns, low arithmetic intensity, and the requirement to support variable block sizes. In this work, the solver is reformulated to use standard sparse and dense Basic Linear Algebra Subprograms (BLAS) functions. However, numerical experiments show that the performance of the BLAS functions available in existing CUDA libraries is suboptimal for matrices representative of those encountered in actual simulations. Instead, optimized versions of these functions are developed. Depending on block size, the new implementations show performance gains of up to 7x over the existing CUDA library functions.

Zubair, Mohammad↗

Commercialization of materials processing in space

The primary motivation of the Materials Processing in Space program is the scientific and commercial utilization of the effects of the unique environments of space on material processes. The reduction or elimination of the pervasive influences of gravity on Earth-based process mechanisms affords opportunities for understanding and improving ground-based processing or producing select materials in space which, typically, would be of low volume, high value commercial interest. Additionally, the unlimited, if not 'hard' vacuum of space affords equally interesting influences on material processes. To evolve the commercialization of Materials Processing in Space, the program seeks to establish and demonstrate the scientific/technological precepts for analyzing and using the space environment and, in parallel, to establish the legal and management mechanisms to implement commercial ventures.

Zoller, L. K.↗

Advanced digital SAR processing study

A highly programmable, land based, real time synthetic aperture radar (SAR) processor requiring a processed pixel rate of 2.75 MHz or more in a four look system was designed. Variations in range and azimuth compression, number of looks, range swath, range migration and SR mode were specified. Alternative range and azimuth processing algorithms were examined in conjunction with projected integrated circuit, digital architecture, and software technologies. The advaced digital SAR processor (ADSP) employs an FFT convolver algorithm for both range and azimuth processing in a parallel architecture configuration. Algorithm performace comparisons, design system design, implementation tradeoffs and the results of a supporting survey of integrated circuit and digital architecture technologies are reported. Cost tradeoffs and projections with alternate implementation plans are presented.

Martinson, L. W.↗

Algorithms and programming tools for image processing on the MPP, introduction

The programming tools and parallel algorithms created for the Massively Parallel Processor (MPP) located at the NASA Goddard Space Center are discussed. A user-friendly environment for high level language parallel algorithm development was developed. The issues involved in implementing certain algorithms on the MPP were researched. The expected results were compared with the actual results.

Source record↗

Spectral element methods: Algorithms and architectures

Spectral element methods are high-order weighted residual techniques for partial differential equations that combine the geometric flexibility of finite element methods with the rapid convergence of spectral techniques. Spectral element methods are described for the simulation of incompressible fluid flows, with special emphasis on implementation of spectral element techniques on medium-grained parallel processors. Two parallel architectures are considered: the first, a commercially available message-passing hypercube system; the second, a developmental reconfigurable architecture based on Geometry-Defining Processors. High parallel efficiency is obtained in hypercube spectral element computations, indicating that load balancing and communication issues can be successfully addressed by a high-order technique/medium-grained processor algorithm-architecture coupling.

Fischer, Paul↗

Spectral element methods - Algorithms and architectures

Spectral element methods are high-order weighted residual techniques for partial differential equations that combine the geometric flexibility of finite element methods with the rapid convergence of spectral techniques. Spectral element methods are described for the simulation of incompressible fluid flows, with special emphasis on implementation of spectral element techniques on medium-grained parallel processors. Two parallel architectures are considered; the first, a commercially available message-passing hypercube system; the second, a developmental reconfigurable architecture based on Geometry-Defining Processors. High parallel efficiency is obtained in hypercube spectral element computations, indicating that load balancing and communication issues can be successfully addressed by a high-order technique/medium-grained processor algorithm-architecture coupling.

Fischer, Paul↗

Periodic Application of Concurrent Error Detection in Processor Array Architectures

Processor arrays can provide an attractive architecture for some applications. Featuring modularity, regular interconnection and high parallelism, such arrays are well-suited for VLSI/WSI implementations, and applications with high computational requirements, such as real-time signal processing. Preserving the integrity of results can be of paramount importance for certain applications. In these cases, fault tolerance should be used to ensure reliable delivery of a system's service. One aspect of fault tolerance is the detection of errors caused by faults. Concurrent error detection (CED) techniques offer the advantage that transient and intermittent faults may be detected with greater probability than with off-line diagnostic tests. Applying time-redundant CED techniques can reduce hardware redundancy costs. However, most time-redundant CED techniques degrade a system's performance.

Chen, Paul Peichuan↗

Learning and optimization with cascaded VLSI neural network building-block chips

To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

Duong, T.↗

An MPI-IO Interface to HPSS

This paper describes an implementation of the proposed MPI-IO standard for parallel I/O. Our system uses third-party transfer to move data over an external network between the processors where it is used and the I/O devices where it resides. Data travels directly from source to destination, without the need for shuffling it among processors or funneling it through a central node. Our distributed server model lets multiple compute nodes share the burden of coordinating data transfers. The system is built on the High Performance Storage System (HPSS), and a prototype version runs on a Meiko CS-2 parallel computer.

Parallel Processing↗

Analysis and Modeling of a Two-Phase Jet Pump of a Flow Boiling Test Facility for Aerospace Applications

Jet pumps are devices capable of pumping fluids to a higher pressure employing a nozzle/diffuser/mixing chamber combination. A primary fluid is usually allowed to pass through a converging-diverging nozzle where it can accelerate to supersonic speeds at the nozzle exit. The relatively high kinetic energy that the primary fluid possesses at the nozzle exit is accompanied by a low pressure region in order to satisfy Bernoulli's equation. The low pressure region downstream of the nozzle exit permits a secondary fluid to be entrained into and mixed with the primary fluid in a mixing chamber located downstream of the nozzle. Several combinations may exist in terms of the nature of the primary and secondary fluids in so far as whether they are single or two-phase fluids. Depending on this, the jet pump may be classified as gas/gas, gas/liquid, liquid/liquid, two-phase/liquid, or similar combinations. The mixing chamber serves to create a homogeneous single-phase or two-phase mixture which enters a diffuser where the high kinetic energy of the fluid is converted into pressure energy. If the fluid mixture entering the diffuser is in the supersonic flow regime, a normal shock wave usually develops inside the diffuser. If the fluid mixture is one that can easily change phase, a condensation shock would normally develop. Because of the overall rise in pressure in the diffuser as well as the additional rise in pressure across the shock layer, condensation becomes more likely. Associated with the pressure rise across the shock is a velocity reduction from the supersonic to the subsonic range. If the two-phase flow entering the diffuser is predominantly gaseous with liquid droplets suspended in it, it will transform into a predominantly liquid flow containing gaseous bubbles (bubbly flow) somewhere in the diffuser. While past researchers have been able to model the two-phase flow jet pump using the one-dimensional assumption with no shock waves and no phase change, there is no research known to the authors apart from that of Anand (1992) which accounted for condensation shocks. One of the objectives of this research effort is to develop a comprehensive model in which the effects of phase slip and inter-phase heat transfer as well as the wall friction and shock waves are accounted for. While this modeling effort is predominantly analytical in nature and is primarily intended to provide a parametric understanding of the jet pump performance under different operating scenarios, another parallel effort employing a commercial CFD code is also implemented. The latter effort is primarily intended to model an axisymmetric counterpart of the problem in question. The viability of using the CFD code to model a two-phase flow jet pump will be assessed by attempting to recreate some of the existing performance data of similar jet pumps. The code will eventually be used to generate the jet pump performance characteristics of several scenarios involving jet pump geometries as well as flow regimes in order to be able to determine an optimum design which would be suitable for a two-phase flow boiling test facility at NASA-Marshall. Because of the extensive nature of the analytical model developed, the following section will only provide very brief highlights of it, while leaving the details to a more complete report submitted to the NASA colleague. This report will also contain some of the simulation results obtained using the CFD code.

Sherif, S. A.↗

Multidisciplinary High-Fidelity Analysis and Optimization of Aerospace Vehicles: Formulation - Part 1

An objective of the High Performance Computing and Communication Program at the NASA Langley Research Center is to demonstrate multidisciplinary shape and sizing optimization of a complete aerospace vehicle configuration by using high-fidelity, finite element structural analysis and computational fluid dynamics aerodynamic analysis in a distributed, heterogeneous computing environment that includes high performance parallel computing. A software system has been designed and implemented to integrate a set of existing discipline analysis codes, some of them computationally intensive, into a distributed computational environment for the design of a highspeed civil transport configuration. The paper describes the engineering aspects of formulating the optimization by integrating these analysis codes and associated interface codes into the system. The discipline codes are integrated by using the Java programming language and a Common Object Request Broker Architecture (CORBA) compliant software product. A companion paper presents currently available results.

Walsh, J. L.↗

Reduction of Sample Rotation in Electrostatic Levitation

In many containerless processing systems, control of sample rotation is an important issue. Sample rotation is even more important for microgravity containerless processing systems, where the centrifugal acceleration can approach 1 g for even a small rotation rate. Prior work on rotation control by Rhim focused on driving the sample rotation at a controlled rate for droplet dynamics experiments and measurement of electrical conductivity. His technique allows controlled, fast rotation, but for many microgravity experiments the goal is zero rotation. To minimize sample rotation, two approaches are apparent: first, to identify and balance or eliminate the driving forces for undesired sample rotation, or second, implement a feedback-based rotation control loop in parallel with the position control loop. In this work, we have taken the first approach. To minimize sample rotation, the simplest approach is to identify and balance or eliminate the driving forces for undesired sample rotation. Our experiments show that the dominant driving force for rotation of machined Zr spheres in the MSFC ESL is photon pressure from the heating laser. Experimental results showing the correlation between heating power and torque are compared to theoretical predictions, and a strategy for minimizing the torque due to photon pressure is presented.

Hyers, R. W↗

Optical Processing of Speckle Images with Bacteriorhodopsin for Pattern Recognition

Logarithmic processing of images with multiplicative noise characteristics can be utilized to transform the image into one with an additive noise distribution. This simplifies subsequent image processing steps for applications such as image restoration or correlation for pattern recognition. One particularly common form of multiplicative noise is speckle, for which the logarithmic operation not only produces additive noise, but also makes it of constant variance (signal-independent). We examine the optical transmission properties of some bacteriorhodopsin films here and find them well suited to implement such a pointwise logarithmic transformation optically in a parallel fashion. We present experimental results of the optical conversion of speckle images into transformed images with additive, signal-independent noise statistics using the real-time photochromic properties of bacteriorhodopsin. We provide an example of improved correlation performance in terms of correlation peak signal-to-noise for such a transformed speckle image.

Downie, John D.↗

Multidisciplinary High-Fidelity Analysis and Optimization of Aerospace Vehicles: Preliminary Results - Part 2

An objective of the High Performance Computing and Communication Program at the NASA Langley Research Center is to demonstrate multidisciplinary shape and sizing optimization of a complete aerospace vehicle configuration by using high-fidelity finite-element structural analysis and computational fluid dynamics aerodynamic analysis in a distributed, heterogeneous computing environment that includes high performance parallel computing. A software system has been designed and implemented to integrate a set of existing discipline analysis codes, some of them computationally intensive, into a distributed computational environment for the design of a high-speed civil transport configuration. The paper describes both the preliminary results from implementing and validating the multidisciplinary analysis and the results from an aerodynamic optimization. The discipline codes are integrated by using the Java programming language and a Common Object Request Broker Architecture compliant software product. A companion paper describes the formulation of the multidisciplinary analysis and optimization system.

Walsh, J. L.↗

NbN A/D Conversion of IR Focal Plane Sensor Signal at 10 K

We are implementing a 12 bit SFQ counting ADC with parallel-to-serial readout using our established 10 K NbN capability. This circuit provides a key element of the analog signal processor (ASP) used in large infrared focal plane arrays. The circuit processes the signal data stream from a Si:As BIB detector array. A 10 mega samples per second (MSPS) pixel data stream flows from the chip at a 120 megabit bit rate in a format that is compatible with other superconductive time dependent processor (TDP) circuits being developed. We will discuss our planned ASP demonstration, the circuit design, and test results.

conversion↗