Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel systems”

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 1,261 records · Page 70

Data flow modeling techniques

There have been a number of simulation packages developed for the purpose of designing, testing and validating computer systems, digital systems and software systems. Complex analytical tools based on Markov and semi-Markov processes have been designed to estimate the reliability and performance of simulated systems. Petri nets have received wide acceptance for modeling complex and highly parallel computers. In this research data flow models for computer systems are investigated. Data flow models can be used to simulate both software and hardware in a uniform manner. Data flow simulation techniques provide the computer systems designer with a CAD environment which enables highly parallel complex systems to be defined, evaluated at all levels and finally implemented in either hardware or software. Inherent in data flow concept is the hierarchical handling of complex systems. In this paper we will describe how data flow can be used to model computer system.

Kavi, K. M.↗

Partitioning problems in parallel, pipelined, and distributed computing

The problem of optimally assigning the modules of a parallel program over the processors of a multiple-computer system is addressed. A sum-bottleneck path algorithm is developed that permits the efficient solution of many variants of this problem under some constraints on the structure of the partitions. In particular, the following problems are solved optimally for a single-host, multiple-satellite system: partitioning multiple chain-structured parallel programs, multiple arbitrarily structured serial programs, and single-tree structured parallel programs. In addition, the problem of partitioning chain-structured parallel programs across chain-connected systems is solved under certain constraints. All solutions for parallel programs are equally applicable to pipelined programs. These results extend prior research in this area by explicitly taking concurrency into account and permit the efficient utilization of multiple-computer architectures for a wide range of problems of practical interest.

Bokhari, Shahid H.↗

Portable and Transparent Message Compression in MPI Libraries to Improve the Performance and Scalability of Parallel Applications

The goal of this project has been to develop a lossless compression algorithm for message-passing libraries that can accelerate HPC systems by reducing the communication time. Because both compression and decompression have to be performed in software in real time, the algorithm has to be extremely fast while still delivering a good compression ratio. During the first half of this project, they designed a new compression algorithm called FPC for scientific double-precision data, made the source code available on the web, and published two papers describing its operation, the first in the proceedings of the Data Compression Conference and the second in the IEEE Transactions on Computers. At comparable average compression ratios, this algorithm compresses and decompresses 10 to 100 times faster than BZIP2, DFCM, FSD, GZIP, and PLMI on the three architectures tested. With prediction tables that fit into the CPU's L1 data acache, FPC delivers a guaranteed throughput of six gigabits per second on a 1.6 GHz Itanium 2 system. The C source code and documentation of FPC are posted on-line and have already been downloaded hundreds of times. To evaluate FPC, they gathered 13 real-world scientific datasets from around the globe, including satellite data, crash-simulation data, and messages from HPC systems. Based on the large number of requests they received, they also made these datasets available to the community (with permission of the original sources). While FPC represents a great step forward, it soon became clear that its throughput was too slow for the emerging 10 gigabits per second networks. Hence, no speedup can be gained by including this algorithm in an MPI library. They therefore changed the aim of the second half of the project. Instead of implementing FPC in an MPI library, they refocused their efforts to develop a parallel compression algorithm to further boost the throughput. After all, all modern high-end microprocessors contain multiple CPUs on a single die and will undoubtedly contain even larger numbers of CPUs in the future. Hence, a compute node in a parallel system is likely to have multiple processors per interconnection link. Thus, they investigated how to best exploit multiple CPUs to compress and decompress data for a single link, i.e., they developed a parallel version of the FPC algorithm called pFPC. On a 4-core 3 GHz Xeon system, pFPC exceeds 10 gigabits per second both in compression and decompression throughput while still reaching a compression ratio of 18%, which is reasonable for their double-precision floating-point datasets. At half this throughput, it achieves a 41% compression ratio. Moreover, the algorithm scales well to four cores and promises even higher throughputs on larger machines. Additional results and a description of the pFPC algorithm have recently been published in the proceedings of the Data Compression Conference. The C source code of pFPC is also publicly available.

97 MATHEMATICS AND COMPUTING↗

Experimental Study of an Easily Controlled Ultra-High-Resolution Pixel-Matched Parallel-Hole Collimator with a Small Cadmium Zinc Telluride Pixelated Gamma Camera System

The aim of this study was to develop an easily controlled, ultra-high-resolution, tungsten parallel-hole collimator based on a small pixelated gamma camera system. A small cadmium zinc telluride (CZT) pixelated semiconductor detector (eValuator-2500 detector [eV product, Saxonburg, PA]) was evaluated. This detector is composed of an array of 51.2 × 0.8 × 3-mm{sup 3} individual CZT crystal elements. The ultra-high-resolution, pixel-matched, parallel-hole collimators consisted of six layers, with the same between the hole and pixel size. The basic characteristics of the imaging system, such as sensitivity and spatial resolution, was measured using a {sup 57}Co point source. The measured averages of sensitivity and spatial resolution varied depending on the septal heights of the ultra-high-resolution parallel-hole collimator and source-to-collimator distances. When the 30-mm septal height was at 1-cm source-to-collimator distance, the spatial resolution was approximately 0.85 mm. Using 5-mm septal height, over 0.3 cps/kBq sensitivity was achieved. One advantage of our system is the use of stacked collimators that can select the best combination of system sensitivity and spatial resolution. Our results demonstrated that the developed CZT–pixelated gamma camera system using an ultra-high-resolution parallel-hole collimator of various collimator geometric designs has potential as an effective instrument.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Exploring Machine Learning Techniques For Dynamic Modeling on Future Exascale Systems

Future exascale systems must be optimized for both power and performance at scale in order to achieve DOE’s goal of a sustained petaflop within 20 Megawatts by 2022 [1]. Massive parallelism of the future systems combined with complex memory hierarchies will form a barrier to efficient application and architecture design. These challenges are exacerbated with emerging complex architectures such as GPGPUs and Intel Xeon Phi as parallelism increases orders of magnitude and system power consumption can easily triple or quadruple. Therefore, we need techniques that can reduce the search space for optimization, isolate power-performance bottlenecks, identify root causes for software/hardware inefficiency, and effectively direct runtime scheduling.

Song, Shuaiwen↗

Efficient Use of Distributed Systems for Scientific Applications

Distributed computing has been regarded as the future of high performance computing. Nationwide high speed networks such as vBNS are becoming widely available to interconnect high-speed computers, virtual environments, scientific instruments and large data sets. One of the major issues to be addressed with distributed systems is the development of computational tools that facilitate the efficient execution of parallel applications on such systems. These tools must exploit the heterogeneous resources (networks and compute nodes) in distributed systems. This paper presents a tool, called PART, which addresses this issue for mesh partitioning. PART takes advantage of the following heterogeneous system features: (1) processor speed; (2) number of processors; (3) local network performance; and (4) wide area network performance. Further, different finite element applications under consideration may have different computational complexities, different communication patterns, and different element types, which also must be taken into consideration when partitioning. PART uses parallel simulated annealing to partition the domain, taking into consideration network and processor heterogeneity. The results of using PART for an explicit finite element application executing on two IBM SPs (located at Argonne National Laboratory and the San Diego Supercomputer Center) indicate an increase in efficiency by up to 36% as compared to METIS, a widely used mesh partitioning tool. The input to METIS was modified to take into consideration heterogeneous processor performance; METIS does not take into consideration heterogeneous networks. The execution times for these applications were reduced by up to 30% as compared to METIS. These results are given in Figure 1 for four irregular meshes with number of elements ranging from 30,269 elements for the Barth5 mesh to 11,451 elements for the Barth4 mesh. Future work with PART entails using the tool with an integrated application requiring distributed systems. In particular this application, illustrated in the document entails an integration of finite element and fluid dynamic simulations to address the cooling of turbine blades of a gas turbine engine design. It is not uncommon to encounter high-temperature, film-cooled turbine airfoils with 1,000,000s of degrees of freedom. This results because of the complexity of the various components of the airfoils, requiring fine-grain meshing for accuracy. Additional information is contained in the original.

Taylor, Valerie↗

Thought Leaders during Crises in Massive Social Networks

The vast amount of social media data that can be gathered from the internet coupled with workflows that utilize both commodity systems and massively parallel supercomputers, such as the Cray XMT, open new vistas for research to support health, defense, and national security. Computer technology now enables the analysis of graph structures containing more than 4 billion vertices joined by 34 billion edges along with metrics and massively parallel algorithms that exhibit near-linear scalability according to number of processors. The challenge lies in making this massive data and analysis comprehensible to an analyst and end-users that require actionable knowledge to carry out their duties. Simply stated, we have developed language and content agnostic techniques to reduce large graphs built from vast media corpora into forms people can understand. Specifically, our tools and metrics act as a survey tool to identify thought leaders' -- those members that lead or reflect the thoughts and opinions of an online community, independent of the source language.

97 MATHEMATICS AND COMPUTING↗

Grafted nickel-promoter catalysts for dry reforming of methane identified through high-throughput experimentation

High-throughput synthesis of a series of monometallic and bimetallic catalysts (45 bimetallic and 50 monometallic samples) consisting of nickel and one of nine different metal promoters (B, Co, Cu, Fe, Mg, Mn, Sn, V and Zn) supported on one of six different metal oxides alumina, ceria, magnesia, silica and titania) is carried out via organometallic grafting using a robotic platform. The catalysts are evaluated for their activity and selectivity for the dry reforming of methane at a feed ratio of CH 4 :CO 2 of 1 at 650–800 °C in a parallel flow reactor system. The type of oxide support prevails over the type of additive for both catalyst activity and stability. On Al 2 O 3 and MgO, Fe was found to be the best promoter; on SiO 2 , Cu is the best promoter at 700 °C and higher, while on TiO 2 , Mn is found to enhance the conversion at 800 °C. On CeO 2 , all additives except Fe have beneficial effects. Twenty-five catalysts show > 90% methane conversion with ten catalysts showing > 95% conversion at 800 °C with the H 2 :CO ratios ranging from 0.8 to 1.2. Amongst the ten highest performers, NiFe/Al 2 O 3 and NiFe/MgO are more active than Ni/Al 2 O 3 and Ni/MgO, respectively and were stable over a period of 25 h at 800 °C. Characterization on the as-prepared samples reveals highly dispersed phase, while after reduction in H 2 , highly dispersed and reduced nickel particles up to 10 nm are formed. The particles do not increase in size under dry reforming reaction conditions at 800 °C. An increased hydrogen consumption observed during H 2 -TPR of the nickel particles is positively correlated with methane conversion for Al 2 O 3 -based catalysts. The resistance to deactivation by coking and variation in coke structure are investigated by spectroscopic and microscopic methods to identify the relationship between metal promoters, alloy formation, and type of surface carbon deposits. Carbon whiskers were observed on the ten selected spent samples and are preferentially deposited on Ni rather than on the promoters. Carbon nanotube formation and metal particle removal from support were not observed to cause deactivation while amorphous carbon formation was clearly linked to catalyst deactivation, as amorphous carbon could encapsulate nickel, either on the support or at the end of the carbon nanotube. Furthermore, the organometallic grafting technique is an efficient and suitable technique for synthesizing highly dispersed and homogeneous phases which lead to high conversion and high durability for dry reforming of methane.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Electromechanical memcapacitor model offering biologically plausible spiking.

In this article, we introduce a new nanoscale electromechanical device - a leaky memcapacitor - and show that it may be useful for the hardware implementation of spiking neurons. The leaky memcapacitor is a movableplate capacitor that becomes quite conductive when the plates come close to each other. The equivalent circuit of the leaky memcapacitor involves a memcapacitive and memristive system connected in parallel. In the leaky memcapacitor, resistance and capacitance depend on the same internal state variable, which is the displacement of the movable plate. We have performed a comprehensive analysis showing that several types of spiking observed in biological neurons can be implemented with the leaky memcapacitor. Significant attention is paid to the dynamic properties of the model. As in leaky memcapacitors the capacitive, leaking resistive, and reset functionalities are implemented naturally within the same device structure, their use will simplify the creation of spiking neural networks.

Zhang, Zixi↗

Scaling of NO{sub x} emissions from a laboratory-scale mild combustion furnace

A systematic experimental campaign has been carried out to investigate the scaling of NO{sub x} emissions from a moderate or intense low-oxygen dilution (MILD) combustion furnace operating with a parallel jet burner system in which the reactants and the exhaust ports are all mounted on the same wall. Its maximum capacity was 20 kW from the fuel and 3.3 kW from air preheat, with a turndown ratio of 1:3. The burner system was configured to achieve high dilution of the incoming reactants. A comprehensive data set comprising 191 global measurements of temperature and exhaust gas emissions is presented, together with temperature contours on the furnace centerline plane. It was found that, although heat extraction, air preheat, excess air, firing rate, dilution, and fuel type all affect global NO{sub x} emissions, they do not control NO{sub x} scaling. The combined effects of these global parameters can be ultimately characterized by a furnace temperature and a global residence time. A temperature-time scaling approach, previously reported for open jet diffusion flames, proved to be a useful tool for comparison of NO{sub x} emissions from highly diluted furnace environments regardless of the furnace/burner geometries. Regression-based predictions found the characteristic temperature to correlate with 85% of the data with an accuracy of only {+-}50%. The leading-order approach also showed that the jet exit Froude number is of limited value for NO{sub x} scaling in the MILD regime. Because of the weak dependence on temperature observed in the data and the moderate magnitude of the measured temperatures, it is deduced that the prompt-NO and/or N{sub 2}O-intermediate pathways are of significance comparable to that of the thermal-NO pathway. The analysis also suggests that NO{sub x} formation is controlled neither by kinetics nor by mixing, and hence the conditions inside this furnace approach or span the range in which Damkoehler numbers are of order unity, Da=O(1). (author)

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A high-order discontinuous Galerkin method with unstructured space–time meshes for two-dimensional compressible flows on domains with large deformations

We introduce a high-order accurate space-time discontinuous Galerkin method for solving two-dimensional compressible flow problems on fully unstructured space-time meshes. The discretization is based on a nodal formulation, with appropriate numerical fluxes for the first and the second-order terms, respectively. The scheme is implicit, and we solve the resulting non-linear systems using a parallel Newton-Krylov solver. The meshes are produced by a mesh moving technique with element connectivity updates, and the corresponding space-time elements are produced directly based on these local operations. To obtain globally conforming tetrahedral meshes, we first derive the required conditions on a prism boundary mesh to allow for a valid local triangulation. Next, we present an efficient algorithm for finding a global mesh that satisfies these conditions. We additionally show how to add and remove mesh nodes, again using local constructs for the space-time mesh. Our approach is demonstrated on a number of test problems, showing the high-order accuracy for model problems, and the ability to solve flow problems on domains with complex large deformations.

97 MATHEMATICS AND COMPUTING↗

Numerical approach of the quantum circuit theory

In this paper we develop a numerical method based on the quantum circuit theory to approach the coherent electronic transport in a network of quantum dots connected with arbitrary topology. The algorithm was employed in a circuit formed by quantum dots connected each other in a shape of a linear chain (associations in series), and of a ring (associations in series, and in parallel). For both systems we compute two current observables: conductance and shot noise power. We find an excellent agreement between our numerical results and the ones found in the literature. Moreover, we analyze the algorithm efficiency for a chain of quantum dots, where the mean processing time exhibits a linear dependence with the number of quantum dots in the array.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Translational research in the MPICH project

The MPICH project is an example of translational research in computer science before that term was well known or even coined. The project began in 1992 as an effort to develop a portable, high-performance implementation of the emerging Message-Passing Interface (MPI) Standard. It has enabled the widespread adoption of MPI as a way to write scalable parallel applications on systems of all sizes including upcoming exascale supercomputers. In this paper, we describe how the translational research process was used in MPICH, how that led to its success, the challenges encountered and lessons learned, and how the process could be applied to other similar projects.

97 MATHEMATICS AND COMPUTING↗

Towards Simulations of Outer Membrane Proteins in Lipopolysaccharide Membranes

Biomolecular simulation derived properties of LPS membranes that impact the structural and internal dynamics of transmembrane proteins are shown to exhibit good agreement with available experimental data within the time scale simulated, chosen force field and simulation conditions. The molecular model used offers an accurate representation of the LPS layer, including the high asymmetry and low fluidity characteristics of outer membranes. This contribution describes the data intensive analysis of the large molecular time trajectories generated for these systems using massively parallel computing resources.

59 BASIC BIOLOGICAL SCIENCES↗

New cosmic rays experiments in the underground laboratory of IFIN-HH from Slanic Prahova, Romania

Since 2006 a modern laboratory has been developed by IFIN-HH in the underground of Slanic Prahova salt ore. This work presents a short review of previous scientific activities performed in the underground laboratory, in parallel with some plans for the future. A mobile detector for cosmic muon flux measurements has been set up at IFIN-HH, Romania. The device is used to measure the muon flux on different locations at the surface and underground and it consists of two detection layers, each one including four large scintillator plates. A new rotatable detector for measurements of the directional variation of the muon flux has been designed and it is presently under preliminary tests. Built from four layers of sensitive material and using for collecting the signals and directing them to the micro PMTs a new technique, through optical fibers instead wave length shifters, it allows an easy discrimination of the moun flux on the arrival directions of muons. Combining the possibility to rotate and the directionality properties, the underground muon detector is acting like a muon tomography device, being able to scan, using cosmic muons, the rock material above the detector. In parallel new detection system based on SiPM will be also installed in the following weeks. It should be composed by four layers, each layer consisting in 4 scintillator plates what we consider in the following as a module of detection. For this purpose, first two scintillator layers, with the optical fibers positioned on perpendicular directions are put in coincidence with other two layers, 1 m distance from the first two, with similar optical fiber arrangement, thus allowing reconstructing muon trajectory. It is intended also to design and construct an experimental device for the investigation of such radio antennas and the behavior of the signal in rock salt at the Slanic salt mine in Romania. Another method to detect high energy neutrinos is based on the detection of secondary particles resulting from the interaction with the salt massive. We intent to design and construct a 3D array in the underground of Slanic Prahova salt ore.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

ALIGNMENTS OF GROUP GALAXIES WITH NEIGHBORING GROUPS

Using a sample of galaxy groups found in the Sloan Digital Sky Survey Data Release 4, we measure the following four types of alignment signals: (1) the alignment between the distributions of the satellites of each group relative to the direction of the nearest neighbor group (NNG); (2) the alignment between the major axis direction of the central galaxy of the host group (HG) and the direction of the NNG; (3) the alignment between the major axes of the central galaxies of the HG and the NNG; and (4) the alignment between the major axes of the satellites of the HG and the direction of the NNG. We find strong signal of alignment between the satellite distribution and the orientation of central galaxy relative to the direction of the NNG, even when the NNG is located beyond 3r {sub vir} of the host group. The major axis of the central galaxy of the HG is aligned with the direction of the NNG. The alignment signals are more prominent for groups that are more massive and with early-type central galaxies. We also find that there is a preference for the two major axes of the central galaxies of the HG and NNG to be parallel for the system with both early central galaxies, however, not for the systems with both late-type central galaxies. For the orientation of satellite galaxies, we do not find any significant alignment signals relative to the direction of the NNG. From these four types of alignment measurements, we conclude that the large-scale environment traced by the nearby group affects primarily the shape of the host dark matter halo, and hence also affects the distribution of satellite galaxies and the orientation of central galaxies. In addition, the NNG directly affects the distribution of the satellite galaxies by inducing asymmetric alignment signals, and the NNG at very small separation may also contribute a second-order impact on the orientation of the central galaxy in the HG.

79 ASTRONOMY AND ASTROPHYSICS↗

RADIO POLARIZATION OBSERVATIONS OF G319.9-0.7: A BOW-SHOCK NEBULA WITH AN AZIMUTHAL MAGNETIC FIELD POWERED BY PULSAR J1509-5850

We report radio polarization observations of G319.9-0.7 (MSC 319.9-0.7) at 3 and 6 cm obtained with the Australia Telescope Compact Array. The source shows a highly elongated morphology with the energetic pulsar J1509-5850 located at the tip. We found a flat radio spectrum of index alpha = -0.26 +- 0.04 and a high degree of linear polarization. These results confirm G319.9-0.7 as a bow-shock pulsar wind nebula. The polarization maps suggest a helical magnetic field trailing the pulsar, with the symmetry axis parallel to the system's inferred direction of motion. This is the first time such a field geometry has been seen in a bow-shock nebula, and it may be the result of an alignment between the pulsar spin axis and its space velocity. Compared to other bow-shock examples, G319.9-0.7 exhibits very different properties in the field structure and surface brightness distribution, illustrating the large diversity of the population.

79 ASTRONOMY AND ASTROPHYSICS↗

Casimir effect of massive vector fields

We study the Casimir effect due to a massive vector field in a system of two parallel plates made of real materials, in an arbitrary magnetodielectric background. The plane waves satisfying the Proca equations are classified into transverse modes and longitudinal modes which have different dispersion relations. Transverse modes are further divided into type I and type II corresponding to TE and TM modes in the massless case. For general magnetodielectric media, we argue that the correct boundary conditions are the continuities of H{sub ||}, {phi}, A, and {partial_derivative}{sub x}A{sub x}, where x is the direction normal to the plates. Although there are type I transverse modes that satisfy all the boundary conditions, it is impossible to find type II transverse modes or longitudinal modes that satisfy all the boundary conditions. To circumvent this problem, type II transverse modes and longitudinal modes have to be considered together. We call the contribution to the Casimir energy from type I transverse modes TE contribution, and the contribution from the superposition of type II transverse modes and longitudinal modes TM contribution. Their massless limits give, respectively, the TE and TM contributions to the Casimir energy of a massless vector field. The limit where the plates become perfectly conducting is discussed in detail. For the special case where the background has a unity refractive index, it is shown that the TM contribution to the Casimir energy can be written as a sum of contributions from two different types of modes, corresponding to type II discrete modes and type III continuum modes discussed by Barton and Dombey [G. Barton and N. Dombey, Ann. Phys. (N.Y.) 162, 231 (1985).]. For general background, this splitting does not work. The limit where both plates become infinitely permeable and the limit where one plate becomes perfectly conducting and one plate becomes infinitely permeable are also investigated.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗