SEARCH · Engineering Papers
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.
The impact of gigabit networking with Myrinet 2000 hardware and MPICH-GM software on a 2-way SMP Beowulf-class cluster for parallel unstructured adaptive mesh refinement using the PYRAMID library is described.
Currently, message passing (MP) and shared address space (SAS) are the two leading parallel programming paradigms. MP has been standardized with MPI, and is the more common and mature approach; however, code development can be extremely difficult, especially for irregularly structured computations. SAS offers substantial ease of programming, but may suffer from performance limitations due to poor spatial locality and high protocol overhead. In this paper, we compare the performance of and the programming effort required for six applications under both programming models on a 32-processor PC-SMP cluster, a platform that is becoming increasingly attractive for high-end scientific computing. Our application suite consists of codes that typically do not exhibit scalable performance under shared-memory programming due to their high communication-to-computation ratios and/or complex communication patterns. Results indicate that SAS can achieve about half the parallel efficiency of MPI for most of our applications, while being competitive for the others. A hybrid MPI+SAS strategy shows only a small performance advantage over pure MPI in some cases. Finally, improved implementations of two MPI collective operations on PC-SMP clusters are presented.
The current compute environment that most researchers are using for the calculation of 3D unsteady Computational Fluid Dynamic (CFD) results is a super-computer class machine. The Massively Parallel Processors (MPP's) such as the 160 node IBM SP2 at NAS and clusters of workstations acting as a single MPP (like NAS's SGI Power-Challenge array and the J90 cluster) provide the required computation bandwidth for CFD calculations of transient problems. If we follow the traditional computational analysis steps for CFD (and we wish to construct an interactive visualizer) we need to be aware of the following: (1) Disk space requirements. A single snap-shot must contain at least the values (primitive variables) stored at the appropriate locations within the mesh. For most simple 3D Euler solvers that means 5 floating point words. Navier-Stokes solutions with turbulence models may contain 7 state-variables. (2) Disk speed vs. Computational speeds. The time required to read the complete solution of a saved time frame from disk is now longer than the compute time for a set number of iterations from an explicit solver. Depending, on the hardware and solver an iteration of an implicit code may also take less time than reading the solution from disk. If one examines the performance improvements in the last decade or two, it is easy to see that depending on disk performance (vs. CPU improvement) may not be the best method for enhancing interactivity. (3) Cluster and Parallel Machine I/O problems. Disk access time is much worse within current parallel machines and cluster of workstations that are acting in concert to solve a single problem. In this case we are not trying to read the volume of data, but are running the solver and the solver outputs the solution. These traditional network interfaces must be used for the file system. (4) Numerics of particle traces. Most visualization tools can work upon a single snap shot of the data but some visualization tools for transient problems require dealing with time.
The increasing reliability of parallel systems and clusters of computers has resulted in these systems becoming more attractive for true production workloads. Today, the primary obstacle to production use of clusters of computers is the lack of a functional and robust Job Management System for parallel applications. This document provides a checklist of NAS requirements for job queuing and scheduling in order to make most efficient use of parallel systems and clusters for parallel applications. Future requirements are also identified to assist software vendors with design planning.
The recent proliferation of high performance work stations and the increased reliability of parallel systems have illustrated the need for robust job management systems to support parallel applications. To address this issue, the national Aerodynamic Simulation (NAS) supercomputer facility compiled a requirements checklist for job queuing/scheduling software. Next, NAS began an evaluation of the leading job management system (JMS) software packages against the checklist. This report describes the three-phase evaluation process, and presents the results of Phase 1: Capabilities versus Requirements. We show that JMS support for running parallel applications on clusters of workstations and parallel systems is still insufficient, even in the leading JMS's. However, by ranking each JMS evaluated against the requirements, we provide data that will be useful to other sites in selecting a JMS.
The recent proliferation of high performance workstations and the increased reliability of parallel systems have illustrated the need for robust job management systems to support parallel applications. To address this issue, NAS compiled a requirements checklist for job queuing/scheduling software. Next, NAS evaluated the leading job management system (JMS) software packages against the checklist. A year has now elapsed since the first comparison was published, and NAS has repeated the evaluation. This report describes this second evaluation, and presents the results of Phase 1: Capabilities versus Requirements. We show that JMS support for running parallel applications on clusters of workstations and parallel systems is still lacking, however, definite progress has been made by the vendors to correct the deficiencies. This report is supplemented by a WWW interface to the data collected, to aid other sites in extracting the evaluation information on specific requirements of interest.
We present the supernova (SN) sample and Type-Ia SN (SN Ia) rates from the Cluster Lensing And Supernova survey with Hubble (CLASH). Using the Advanced Camera for Surveys and the Wide Field Camera 3 on the Hubble Space Telescope (HST), we have imaged 25 galaxy-cluster fields and parallel fields of non-cluster galaxies. We report a sample of 27 SNe discovered in the parallel fields. Of these SNe, approximately 13 are classified as SN Ia candidates, including four SN Ia candidates at redshifts z greater than 1.2.We measure volumetric SN Ia rates to redshift 1.8 and add the first upper limit on the SN Ia rate in the range z greater than 1.8 and less than 2.4. The results are consistent with the rates measured by the HST/ GOODS and Subaru Deep Field SN surveys.We model these results together with previous measurements at z less than 1 from the literature. The best-fitting SN Ia delay-time distribution (DTD; the distribution of times that elapse between a short burst of star formation and subsequent SN Ia explosions) is a power law with an index of 1.00 (+0.06(0.09))/(-0.06(0.10)) (statistical) (+0.12/−0.08) (systematic), where the statistical uncertainty is a result of the 68% and 95% (in parentheses) statistical uncertainties reported for the various SN Ia rates (from this work and from the literature), and the systematic uncertainty reflects the range of possible cosmic star-formation histories. We also test DTD models produced by an assortment of published binary population synthesis (BPS) simulations. The shapes of all BPS double-degenerate DTDs are consistent with the volumetric SN Ia measurements, when the DTD models are scaled up by factors of 3-9. In contrast, all BPS single-degenerate DTDs are ruled out by the measurements at greater than 99% significance level.
Computational Fluid Dynamics (CFD) calculations require a great deal of computing power for completing the detailed computations involved. In an effort shorten the time it takes to complete such calculations they are implemented on a parallel computer. In the case of a parallel computer some sort of message passing structure must be used to communicate between the computers because, unlike a single machine, each computer in a parallel computing cluster does not have access to all the data or run all the parts of the total program. Thus, message passing is used to divide up the data and send instructions to each machine. The nature of my work this summer involves programming the "message passing" aspect of the parallel computer. I am working on modifying an existing program, which was written with OpenMP, and does not use a multi-machine parallel computing structure, to work with Message Passing Interface (MPI) routines. The actual code is being written in the FORTRAN 90 programming language. My goal is to write a parameterized message passing structure that could be used for a variety of individual applications and implement it on Silicon Graphics Incorporated s (SGI) IRIX operating system. With this new parameterized structure engineers would be able to speed up computations for a wide variety of purposes without having to use larger and more expensive computing equipment from another division or another NASA center.
The developed methodology is aimed at improving the efficiency of executing block-structured algorithms on parallel, distributed, heterogeneous computers. The basic approach of these algorithms is to divide the flow domain into many sub- domains called blocks, and solve the governing equations over these blocks. Dynamic load balancing problem is defined as the efficient distribution of the blocks among the available processors over a period of several hours of computations. In environments with computers of different architecture, operating systems, CPU speed, memory size, load, and network speed, balancing the loads and managing the communication between processors becomes crucial. Load balancing software tools for mutually dependent parallel processes have been created to efficiently utilize an advanced computation environment and algorithms. These tools are dynamic in nature because of the chances in the computer environment during execution time. More recently, these tools were extended to a second operating system: NT. In this paper, the problems associated with this application will be discussed. Also, the developed algorithms were combined with the load sharing capability of LSF to efficiently utilize workstation clusters for parallel computing. Finally, results will be presented on running a NASA based code ADPAC to demonstrate the developed tools for dynamic load balancing.
The spatially constrained clustering (SCC) iterative parallel region-growing technique is applied to image analysis. The SCC algorithm is implemented on the massively parallel processor at NASA Goddard. Most previous region-growing approaches have the drawback that the segmentation produced depends on the order in which portions of the image are processed. The ideal solution to this problem (merging only the single most similar pair of spatially adjacent regions in the image in each iteration) becomes impractical except for very small images, even on a massively parallel computer. The SCC algorithm overcomes these problems by performing, in parallel, the best merge within each of a set of local, possibly overlapping, subimages. A region-splitting stage is also incorporated into the algorithm, but experiments show that region splitting generally does not improve segmentation results. The SCC algorithm has been tested on various imagery data, and test results for a Landsat TM image are summarized.
This report outlines the detailed simulation of Aircraft Turbofan Engine. The objectives were to develop a detailed flow model of a full turbofan engine that runs on parallel workstation clusters overnight and to develop an integrated system of codes for combustor design and analysis to enable significant reduction in design time and cost. The model will initially simulate the 3-D flow in the primary flow path including the flow and chemistry in the combustor, and ultimately result in a multidisciplinary model of the engine. The overnight 3-D simulation capability of the primary flow path in a complete engine will enable significant reduction in the design and development time of gas turbine engines. In addition, the NPSS (Numerical Propulsion System Simulation) multidisciplinary integration and analysis are discussed.
The NASA HPCC Program, together with other agencies participating in the Federal HPCC Program, intends to advance technologies to enable the execution of grand challenge applications at sustained rates up to TeraFLOPS. During 1995-6 NASA undertook two major systems software efforts to improve the state of high performance support software and tools. The first of these activities was a replanning of support software and tools activities internal to the Agency. In replanning the software activities emphasis was placed on Meeting the needs of Grand Challenge Uses Few projects Near term useful results. The revised NASA plan calls for support software and tools activities in four areas: Application Creation Process Support Application Usage/Operations Support Advanced Support Software and Tools Concepts Metrics Based Monitoring and Management The second major activity undertaken was participation in a multiagency Task Force resulting from the Second Pasadena Workshop on System Software and Tools. The task force developed the Guidelines for Writing System Software and Tools Requirements for Parallel and Clustered Computers.
The interrelationships of major clades within the Arthropoda remain one of the most contentious issues in systematics, which has traditionally been the domain of morphologists. A growing body of DNA sequences and other types of molecular data has revitalized study of arthropod phylogeny and has inspired new considerations of character evolution. Novel hypotheses such as a crustacean-hexapod affinity were based on analyses of single or few genes and limited taxon sampling, but have received recent support from mitochondrial gene order, and eye and brain ultrastructure and neurogenesis. Here we assess relationships within Arthropoda based on a synthesis of all well sampled molecular loci together with a comprehensive data set of morphological, developmental, ultrastructural and gene-order characters. The molecular data include sequences of three nuclear ribosomal genes, three nuclear protein-coding genes, and two mitochondrial genes (one protein coding, one ribosomal). We devised new optimization procedures and constructed a parallel computer cluster with 256 central processing units to analyse molecular data on a scale not previously possible. The optimal 'total evidence' cladogram supports the crustacean-hexapod clade, recognizes pycnogonids as sister to other euarthropods, and indicates monophyly of Myriapoda and Mandibulata.
The slides review computational requirements for nozzle exhaust flow and noise calculations and the current numerical method, validation of prefactored compact scheme on CAA benchmark problems, a curvilinear grid performance test of gust response of a Joukowski airfoil, airfoil surface RMS pressure distribution and far field noise radiation results for Joukowski airfoil in a vortical gust, boundary distance study for Joukowski airfoil problem, and performance of ICOMP parallel Macintosh cluster.
This paper discusses work done by JPL's Parallel Applications Technologies Group in helping scientists access and visualize very large data sets through the use of multiple computing resources, such as parallel supercomputers, clusters, and grids.
This paper discusses work done by JPL 's Parallel Applications Technologies Group in helping scientists access and visualize very large data sets through the use of multiple computing resources, such as parallel supercomputers, clusters, and grids These tools do one or more of the following tasks visualize local data sets for local users, visualize local data sets for remote users, and access and visualize remote data sets The tools are used for various types of data, including remotely sensed image data, digital elevation models, astronomical surveys, etc The paper attempts to pull some common elements out of these tools that may be useful for others who have to work with similarly large data sets.
The Terminal Area Simulation System (TASS) is a three-dimensional, time-dependent, large eddy simulation model that has been developed for studies of wake vortex and weather hazards to aviation, along with other atmospheric turbulence, and cloud-scale weather phenomenology. This document describes the source code for TASS version 10.0 and provides users with needed documentation to run the model. The source code is programed in Fortran language and is formulated to take advantage of vector and efficient multi-processor scaling for execution on massively-parallel supercomputer clusters. The code contains different initialization modules allowing the study of aircraft wake vortex interaction with the atmosphere and ground, atmospheric turbulence, atmospheric boundary layers, precipitating convective clouds, hail storms, gust fronts, microburst windshear, supercell and mesoscale convective systems, tornadic storms, and ring vortices. The model is able to operate in either two- or three-dimensions with equations numerically formulated on a Cartesian grid. The primary output from the TASS is time-dependent domain fields generated by the prognostic equations and diagnosed variables. This document will enable a user to understand the general logic of TASS, and will show how to configure and initialize the model domain. Also described are the formats of the input and output files, as well as the parameters that control the input and output.
Despite great advancements in the parallelization of numerical simulation codes over the last 20 years, it is still common to perform grid generation in serial. Generating large scale grids in serial often requires using special "grid generation" compute machines that can have more than ten times the memory of average machines. While some parallel mesh generation techniques have been proposed, generating very large meshes for LES or aeroacoustic simulations is still a challenging problem. An automated method for the parallel generation of very large scale off-body hierarchical meshes is presented here. This work enables large scale parallel generation of off-body meshes by using a novel combination of parallel grid generation techniques and a hybrid "top down" and "bottom up" oct-tree method. Meshes are generated using hardware commonly found in parallel compute clusters. The capability to generate very large meshes is demonstrated by the generation of off-body meshes surrounding complex aerospace geometries. Results are shown including a one billion cell mesh generated around a Predator Unmanned Aerial Vehicle geometry, which was generated on 64 processors in under 45 minutes.