Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed parallelization”

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 163 records · Page 9

Evaluation of the Intel iWarp parallel processor for space flight applications

The potential of a DARPA-sponsored advanced processor, the Intel iWarp, for use in future SSF Data Management Systems (DMS) upgrades is evaluated through integration into the Ames DMS testbed and applications testing. The iWarp is a distributed, parallel computing system well suited for high performance computing applications such as matrix operations and image processing. The system architecture is modular, supports systolic and message-based computation, and is capable of providing massive computational power in a low-cost, low-power package. As a consequence, the iWarp offers significant potential for advanced space-based computing. This research seeks to determine the iWarp's suitability as a processing device for space missions. In particular, the project focuses on evaluating the ease of integrating the iWarp into the SSF DMS baseline architecture and the iWarp's ability to support computationally stressing applications representative of SSF tasks.

Hine, Butler P., III↗

Ion beams and the ion/ion acoustic instability upstream from the earth's bow shock

This paper considers the generation of enhanced ion acoustic fluctuations by field-aligned ion beams upstream from the earth's bow shock. Steep slopes in the beam distribution parallel and possibly strongly oblique to the magnetic field are correlated with bursts of ion acoustic noise in the upstream region. Linear theory shows that it is the slope of the beam distribution at oblique angles to the magnetic field that determines the growth rate of the ion/ion acoustic instability. Because of instrumentation limitations, it is suggested but not confirmed that enhanced ion acoustic fluctuations in the upstream region and in the presence of field-aligned beams are driven by such steep-sided distributions.

Fuselier, S. A.↗

An Asynchronous Task-based Fan-Both Sparse Cholesky Solver

Systems of linear equations arise at the heart of many scientific and engineering applications. Many of these linear systems are sparse; i.e., most of the elements in the coefficient matrix are zero. Direct methods based on matrix factorizations are sometimes needed to ensure accurate solutions. For example, accurate solution of sparse linear systems is needed in shift-invert Lanczos to compute interior eigenvalues. The performance and resource usage of sparse matrix factorizations are critical to time-to-solution and maximum problem size solvable on a given platform. In many applications, the coefficient matrices are symmetric, and exploiting symmetry will reduce both the amount of work and storage cost required for factorization. When the factorization is performed on large-scale distributed memory platforms, communication cost is critical to the performance of the algorithm. At the same time, network topologies have become increasingly complex, so that modern platforms exhibit a high level of performance variability. This makes scheduling of computations an intricate and performance-critical task. In this paper, we investigate the use of an asynchronous task paradigm, one-sided communication and dynamic scheduling in implementing sparse Cholesky factorization (symPACK) on large-scale distributed memory platforms. Our solver symPACK relies on efficient and flexible communication primitives provided by the UPC++ library. Performance evaluation shows good scalability and that symPACK outperforms state-of-the-art parallel distributed memory factorization packages, validating our approach on practical cases.

Jacquelin, Mathias↗

An analytic formula for the relativistic incoherent Thomson backscattering spectrum for a drifting bi-Maxwellian plasma

An analytic formula has been derived for the relativistic incoherent Thomson backscattering spectrum for a drifting anisotropic plasma when the scattering vector is parallel to the drifting direction. The shape of the scattering spectrum is insensitive to the electron temperature perpendicular to the scattering vector, but its amplitude may be modulated. As a result, while the measured temperature correctly represents the electron distribution parallel to the scattering vector, the electron density may be underestimated when the perpendicular temperature is higher than the parallel temperature. Since the scattering spectrum in shorter wavelengths is greatly enhanced by the existence of drift, the diagnostics might be used to measure local electron current density in fusion plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Array distribution in data-parallel programs

We consider distribution at compile time of the array data in a distributed-memory implementation of a data-parallel program written in a language like Fortran 90. We allow dynamic redistribution of data and define a heuristic algorithmic framework that chooses distribution parameters to minimize an estimate of program completion time. We represent the program as an alignment-distribution graph. We propose a divide-and-conquer algorithm for distribution that initially assigns a common distribution to each node of the graph and successively refines this assignment, taking computation, realignment, and redistribution costs into account. We explain how to estimate the effect of distribution on computation cost and how to choose a candidate set of distributions. We present the results of an implementation of our algorithms on several test problems.

Chatterjee, Siddhartha↗

Massive parallelism in the future of science

Massive parallelism appears in three domains of action of concern to scientists, where it produces collective action that is not possible from any individual agent's behavior. In the domain of data parallelism, computers comprising very large numbers of processing agents, one for each data item in the result will be designed. These agents collectively can solve problems thousands of times faster than current supercomputers. In the domain of distributed parallelism, computations comprising large numbers of resource attached to the world network will be designed. The network will support computations far beyond the power of any one machine. In the domain of people parallelism collaborations among large groups of scientists around the world who participate in projects that endure well past the sojourns of individuals within them will be designed. Computing and telecommunications technology will support the large, long projects that will characterize big science by the turn of the century. Scientists must become masters in these three domains during the coming decade.

Denning, Peter J.↗

Flow of GE90 Turbofan Engine Simulated

The objective of this task was to create and validate a three-dimensional model of the GE90 turbofan engine (General Electric) using the APNASA (average passage) flow code. This was a joint effort between GE Aircraft Engines and the NASA Lewis Research Center. The goal was to perform an aerodynamic analysis of the engine primary flow path, in under 24 hours of CPU time, on a parallel distributed workstation system. Enhancements were made to the APNASA Navier-Stokes code to make it faster and more robust and to allow for the analysis of more arbitrary geometry. The resulting simulation exploited the use of parallel computations by using two levels of parallelism, with extremely high efficiency.The primary flow path of the GE90 turbofan consists of a nacelle and inlet, 49 blade rows of turbomachinery, and an exhaust nozzle. Secondary flows entering and exiting the primary flow path-such as bleed, purge, and cooling flows-were modeled macroscopically as source terms to accurately simulate the engine. The information on these source terms came from detailed descriptions of the cooling flow and from thermodynamic cycle system simulations. These provided boundary condition data to the three-dimensional analysis. A simplified combustor was used to feed boundary conditions to the turbomachinery. Flow simulations of the fan, high-pressure compressor, and high- and low-pressure turbines were completed with the APNASA code.

Veres, Joseph P.↗

Plasma heating at collisionless shocks due to the kinetic cross-field streaming instability

Heating at collisionless shocks due to the kinetic cross-field streaming instability, which is the finite beta (ratio of plasma to magnetic pressure) extension of the modified two stream instability, is studied. Heating rates are derived from quasi-linear theory and compared with results from particle simulations to show that electron heating relative to ion heating and heating parallel to the magnetic field relative to perpendicular heating for both the electrons and ions increase with beta. The simulations suggest that electron dynamics determine the saturation level of the instability, which is manifested by the formation of a flattop electron distribution parallel to the magnetic field. As a result, both the saturation levels of the fluctuations and the heating rates decrease sharply with beta. Applications of these results to plasma heating in simulations of shocks and the earth's bow shock are described.

Winske, D.↗

Parallel/distributed direct method for solving linear systems

A new family of parallel schemes for directly solving linear systems is presented and analyzed. It is shown that these schemes exhibit a near optimal performance and enjoy several important features: (1) For large enough linear systems, the design of the appropriate paralleled algorithm is insensitive to the number of processors as its performance grows monotonically with them; (2) It is especially good for large matrices, with dimensions large relative to the number of processors in the system; (3) It can be used in both distributed parallel computing environments and tightly coupled parallel computing systems; and (4) This set of algorithms can be mapped onto any parallel architecture without any major programming difficulties or algorithmical changes.

Lin, Avi↗

PRAIS: Distributed, real-time knowledge-based systems made easy

This paper discusses an architecture for real-time, distributed (parallel) knowledge-based systems called the Parallel Real-time Artificial Intelligence System (PRAIS). PRAIS strives for transparently parallelizing production (rule-based) systems, even when under real-time constraints. PRAIS accomplishes these goals by incorporating a dynamic task scheduler, operating system extensions for fact handling, and message-passing among multiple copies of CLIPS executing on a virtual blackboard. This distributed knowledge-based system tool uses the portability of CLIPS and common message-passing protocols to operate over a heterogeneous network of processors.

Goldstein, David G.↗

Rexsss Performance Analysis: Domain Decomposition Algorithm Implementations for Resilient Numerical Partial Differential Equation Solvers

The future of extreme-scale computing is expected to magnify the influence of soft faults as a source of inaccuracy or failure in solutions obtained from distributed parallel computations. The development of resilient computational tools represents an essential recourse for understanding the best methods for absorbing the impacts of soft faults without sacrificing solution accuracy. The Rexsss (Resilient Extreme Scale Scientific Simulations) project pursues the development of fault resilient algorithms for solving partial differential equations (PDEs) on distributed systems. Performance analyses of current algorithm implementations assist in the identification of runtime inefficiencies.

97 MATHEMATICS AND COMPUTING↗

Changes in the distribution of plastids and endoplasmic reticulum during cellular differentiation in root caps of Zea mays

In calyptrogen cells of Zea mays, proplastids are distributed randomly throughout the cell, and the endoplasmic reticulum (ER) is distributed parallel to the cell walls. The differentiation of calyptrogen cells into columella statocytes is characterized by the following sequential events: (1) formation of ER complexes at the distal and proximal ends of the cell, (2) differentiation of proplastids into amyloplasts, (3) sedimentation of amyloplasts onto the distal ER complex, (4) breakdown of the distal ER complex and sedimentation of amyloplasts to the bottom of the cell, and (5) formation of sheets of ER parallel to the longitudinal cell walls. Columella statocytes located in the centre of the cap each possess 4530 +/- 780 micrometers2 of ER surface area, an increase of 670 per cent over that of calyptrogen cells. The differentiation of peripheral cells correlates positively with (1) the ER becoming arranged in concentric sheets, (2) amyloplasts and ER becoming randomly distributed, and (3) a 280 per cent increase in ER surface area over that of columella statocytes. These results are discussed relative to graviperception and mucilage secretion, which are functions of columella and peripheral cells, respectively.

NASA Discipline Number 40-10↗

A Fast Parallel Algorithm for Selected Inversion of Structured Sparse Matrices with Application to 2D Electronic Structure Calculations

We present an efficient parallel algorithm and its implementation for computing the diagonal of $H^-1$ where $H$ is a 2D Kohn-Sham Hamiltonian discretized on a rectangular domain using a standard second order finite difference scheme. This type of calculation can be used to obtain an accurate approximation to the diagonal of a Fermi-Dirac function of $H$ through a recently developed pole-expansion technique \cite{LinLuYingE2009}. The diagonal elements are needed in electronic structure calculations for quantum mechanical systems \citeHohenbergKohn1964, KohnSham 1965,DreizlerGross1990. We show how elimination tree is used to organize the parallel computation and how synchronization overhead is reduced by passing data level by level along this tree using the technique of local buffers and relative indices. We analyze the performance of our implementation by examining its load balance and communication overhead. We show that our implementation exhibits an excellent weak scaling on a large-scale high performance distributed parallel machine. When compared with standard approach for evaluating the diagonal a Fermi-Dirac function of a Kohn-Sham Hamiltonian associated a 2D electron quantum dot, the new pole-expansion technique that uses our algorithm to compute the diagonal of $(H-z_i I)^-1$ for a small number of poles $z_i$ is much faster, especially when the quantum dot contains many electrons.

74 ATOMIC AND MOLECULAR PHYSICS↗

Proven and Robust Ground Support Systems - GSFC Success and Lessons Learned

Over the past fifteen years, Goddard Space Flight Center has developed several successful science missions in-house: the Wilkinson Microwave Anisotropy Probe (WMAP), the Imager for Magnetopause-to-Aurora Global Exploration (IMAGE), the Earth Observing 1 (EO-1) [1], and the Space Technology 5 (ST-5)[2] missions, several Small Explorers, and several balloon missions. Currently in development are the Solar Dynamics Observatory (SDO) [3] and the Lunar Reconnaissance Orbiter (LRO)[4]. What is not well known is that these missions have been supported during spacecraft and/or instrument integration and test, flight software development, and mission operations by two in house satellite Telemetry and Command (T & C) Systems, the Integrated Test and Operations System (ITOS) and the Advanced Spacecraft Integration and System Test (ASIST). The advantages of an in-house satellite Telemetry and Command system are primarily in the flexibility of management and maintenance - the developers are considered a part of the mission team, get involved early in the development process of the spacecraft and mission operations-control center, and provide on-site, on-call support that goes beyond Help Desk and simple software fixes. On the other hand, care must be taken to ensure that the system remains generic enough for cost effective re-use from one mission to the next. The software is designed such that many features are user-configurable. Where user-configurable options were impractical, features were designed so as to be easy for the development team to modify. Adding support for a new ground message header, for example, is a one-day effort because of the software framework on which that code rests. This paper will discuss the many features of the Goddard satellite Telemetry and Command systems that have contributed to the success of the missions listed above. These features include flexible user interfaces, distributed parallel commanding and telemetry decommutation, a procedure language, the interfaces and tools needed for a high degree of automation, and instantly accessible archives of spacecraft telemetry. It will discuss some of the problems overcome during development, including secure commanding over networks or the Internet, constellation support for the three satellites that comprise the ST-5 mission, and geographically distributed telemetry end users.

Pfarr, Barbara↗

A search for parallel electric fields by observing secondary electrons and photoelectrons in the low-altitude auroral zone

Model calculations are performed demonstrating the effect of weak parallel electric fields on the differential spectra of the low-energy electrons observed in the inverted-V electron precipitation events in the topside ionosphere. A comparison of the altitude dependence of the observed spectra with the model calculations shows that there can be, on average, no more than a 2-V potential drop between the altitudes of 400 and 900 km, corresponding to a distributed parallel dc electric field of less than 4 microV/m under the inverted-V electron precipitation regions. Statistical results are presented on the spectral dependence of secondary electrons on the inverted-V primary beam parameters.

Fung, Shing F.↗

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗

Support for Debugging Automatically Parallelized Programs

This viewgraph presentation provides information on the technical aspects of debugging computer code that has been automatically converted for use in a parallel computing system. Shared memory parallelization and distributed memory parallelization entail separate and distinct challenges for a debugging program. A prototype system has been developed which integrates various tools for the debugging of automatically parallelized programs including the CAPTools Database which provides variable definition information across subroutines as well as array distribution information.

Hood, Robert↗

Incorporating Parallel Computing into the Goddard Earth Observing System Data Assimilation System (GEOS DAS)

Atmospheric data assimilation is a method of combining actual observations with model forecasts to produce a more accurate description of the earth system than the observations or forecast alone can provide. The output of data assimilation, sometimes called the analysis, are regular, gridded datasets of observed and unobserved variables. Analysis plays a key role in numerical weather prediction and is becoming increasingly important for climate research. These applications, and the need for timely validation of scientific enhancements to the data assimilation system pose computational demands that are best met by distributed parallel software. The mission of the NASA Data Assimilation Office (DAO) is to provide datasets for climate research and to support NASA satellite and aircraft missions. The system used to create these datasets is the Goddard Earth Observing System Data Assimilation System (GEOS DAS). The core components of the the GEOS DAS are: the GEOS General Circulation Model (GCM), the Physical-space Statistical Analysis System (PSAS), the Observer, the on-line Quality Control (QC) system, the Coupler (which feeds analysis increments back to the GCM), and an I/O package for processing the large amounts of data the system produces (which will be described in another presentation in this session). The discussion will center on the following issues: the computational complexity for the whole GEOS DAS, assessment of the performance of the individual elements of GEOS DAS, and parallelization strategy for some of the components of the system.

Larson, Jay W.↗