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 1,297 records · Page 72

Preliminary Evaluation of MapReduce for High-Performance Climate Data Analysis

MapReduce is an approach to high-performance analytics that may be useful to data intensive problems in climate research. It offers an analysis paradigm that uses clusters of computers and combines distributed storage of large data sets with parallel computation. We are particularly interested in the potential of MapReduce to speed up basic operations common to a wide range of analyses. In order to evaluate this potential, we are prototyping a series of canonical MapReduce operations over a test suite of observational and climate simulation datasets. Our initial focus has been on averaging operations over arbitrary spatial and temporal extents within Modern Era Retrospective- Analysis for Research and Applications (MERRA) data. Preliminary results suggest this approach can improve efficiencies within data intensive analytic workflows.

Duffy, Daniel Q.↗

pFUnit 3.0 Tutorial Advanced

This tutorial will introduce Fortran developers to unit-testing and test-driven development (TDD) using pFUnit. As with other unit-testing frameworks, pFUnit, simplifies the process of writing, collecting, and executing tests while providing clear diagnostic messages for failing tests. pFUnit specifically targets the development of scientific-technical software written in Fortran and includes customized features such as: assertions for multi-dimensional arrays, distributed (MPI) and thread-based (OpenMP) parallellism, and flexible parameterized tests.These sessions will include numerous examples and hands-on exercises that gradually build in complexity. Attendees are expected to have working knowledge of F90, but familiarity with object-oriented syntax in F2003 and MPI will be of benefit for the more advanced examples. By the end of the tutorial the audience should feel comfortable in applying pFUnit within their own development environment.

Test Driven using pFUnit↗

Coarrars for Parallel Processing

The design of the Coarray feature of Fortran 2008 was guided by answering the question "What is the smallest change required to convert Fortran to a robust and efficient parallel language." Two fundamental issues that any parallel programming model must address are work distribution and data distribution. In order to coordinate work distribution and data distribution, methods for communication and synchronization must be provided. Although originally designed for Fortran, the Coarray paradigm has stimulated development in other languages. X10, Chapel, UPC, Titanium, and class libraries being developed for C++ have the same conceptual framework.

Fortran↗

Hadoop for High-Performance Climate Analytics: Use Cases and Lessons Learned

Scientific data services are a critical aspect of the NASA Center for Climate Simulations mission (NCCS). Hadoop, via MapReduce, provides an approach to high-performance analytics that is proving to be useful to data intensive problems in climate research. It offers an analysis paradigm that uses clusters of computers and combines distributed storage of large data sets with parallel computation. The NCCS is particularly interested in the potential of Hadoop to speed up basic operations common to a wide range of analyses. In order to evaluate this potential, we prototyped a series of canonical MapReduce operations over a test suite of observational and climate simulation datasets. The initial focus was on averaging operations over arbitrary spatial and temporal extents within Modern Era Retrospective- Analysis for Research and Applications (MERRA) data. After preliminary results suggested that this approach improves efficiencies within data intensive analytic workflows, we invested in building a cyber infrastructure resource for developing a new generation of climate data analysis capabilities using Hadoop. This resource is focused on reducing the time spent in the preparation of reanalysis data used in data-model inter-comparison, a long sought goal of the climate community. This paper summarizes the related use cases and lessons learned.

analytics↗

Source of the Bursty Bulk Flow Diffuse Aurora: Electrostatic Cyclotron Harmonic and Whistler Waves in the Coupling of Bursty Bulk Flows to Auroral Precipitation

Electron cyclotron harmonic (ECH) and whistler chorus waves are recognized as the two mechanisms responsible for the resonant wave‐particle interactions necessary to precipitate plasma sheet electrons into the ionosphere, producing the diffuse Aurora. Previous work has demonstrated ECH waves dominate electron scattering at L shells >8, while whistler chorus dominates scattering at L shells L < 8. However, we find from Time History of Events and Macroscale (THEMIS) Interactions during Substorms observations of fast flows at L = 12 that oblique whistler chorus emissions play the dominant role in scattering electrons. Previous works have identified whistler‐mode waves within fast flows that are produced by an electron temperature anisotropy Te,⊥/Te,||> 1, consistent with electron betatron acceleration. Here, however, we find whistler chorus emissions throughout an interval of fast flows where Te,⊥/Te,||< 1. Parallel electron beams account for the enhanced parallel electron temperature and serve as the instability mechanism for the whistler chorus. The parallel electron beams and associated cigar‐shaped distributions are consistent with Fermi acceleration at dipolarizations in fast flows. We demonstrate that the scattering efficiency of the whistler chorus exceeds that of ECH waves, which THEMIS also detects during the fast flows. The obliquity of the whistler waves permits efficient scattering of lower‐energy electrons into the diffuse aurora. We conclude that Fermi acceleration of electrons provides one important free‐energy source for the wave‐particle interactions responsible for coupling plasma sheet electrons into the diffuse aurora during substorm conditions.

Wendel, D. E.↗

Electron Anisotropies in Magnetotail Dipolarization Events

Anisotropic electron distributions can be a major source of free energy for the generation of microinstabilities and waves. Here we investigate specifically anisotropies of the suprathermal electrons associated with dipolarization events in the geomagnetic tail. The investigation is based on an MHD simulation of magnetotail reconnection, flow bursts and dipolarization. This simulation is used to trace test particles in the electromagnetic fields of the MHD simulation and investigate their acceleration and contributions to flux increases. The simulated velocity distributions yield anisotropies which can be dominantly parallel (“cigar”-shaped), perpendicular (“pancake”-shaped) to the magnetic field, or a combination thereof (e.g., “rolling-pin”-shaped), depending on location, relative timing, and energy.

electron anisotropies↗

Performance Characterization of a Hierarchical MPI Implementations on Large-scale Distributed-memory Platforms

The building blocks of emerging Petascale massively parallel processing (MPP) systems are multi-core processors with four or more cores as a single processing element and a customized network interface. The resulting memory and communication hierarchy of these platforms are now exposed to application developers and end users by creating a hierarchical or multi-core aware message-passing (MPI) programming interface and by providing a handful of runtime, tunable parameters that allows mapping and control of MPI tasks and message handling. We characterize performance of MPI communication patterns and present strategies for optimizing applications performance on Cray XT series systems that are composed of contemporary AMD processors and a proprietary network infrastructure. We highlight dependencies in its memory and network subsystems, which could influence production-level applications performance. We demonstrate that MPI micro-benchmarks could mislead an application developer or end user since these benchmarks often do not expose the interplay between memory allocation and usage in the user space, which depends on the number of tasks or cores and workload characteristics. Our studies show performance improvements compared to the default options for our target scientific benchmarks and production-level applications.

99 GENERAL AND MISCELLANEOUS↗

The New MCNP6 Depletion Capability

The first MCNP based inline Monte Carlo depletion capability was officially released from the Radiation Safety Information and Computational Center as MCNPX 2.6.0. Both the MCNP5 and MCNPX codes have historically provided a successful combinatorial geometry based, continuous energy, Monte Carlo radiation transport solution for advanced reactor modeling and simulation. However, due to separate development pathways, useful simulation capabilities were dispersed between both codes and not unified in a single technology. MCNP6, the next evolution in the MCNP suite of codes, now combines the capability of both simulation tools, as well as providing new advanced technology, in a single radiation transport code. We describe here the new capabilities of the MCNP6 depletion code dating from the official RSICC release MCNPX 2.6.0, reported previously, to the now current state of MCNP6. NEA/OECD benchmark results are also reported. The MCNP6 depletion capability enhancements beyond MCNPX 2.6.0 reported here include: (1) new performance enhancing parallel architecture that implements both shared and distributed memory constructs; (2) enhanced memory management that maximizes calculation fidelity; and (3) improved burnup physics for better nuclide prediction. MCNP6 depletion enables complete, relatively easy-to-use depletion calculations in a single Monte Carlo code. The enhancements described here help provide a powerful capability as well as dictate a path forward for future development to improve the usefulness of the technology.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Parallel Climate Analysis Toolkit (ParCAT)

The parallel analysis toolkit (ParCAT) provides parallel statistical processing of large climate model simulation datasets. ParCAT provides parallel point-wise average calculations, frequency distributions, sum/differences of two datasets, and difference-of-average and average-of-difference for two datasets for arbitrary subsets of simulation time. ParCAT is a command-line utility that can be easily integrated in scripts or embedded in other application. ParCAT supports CMIP5 post-processed datasets as well as non-CMIP5 post-processed datasets. ParCAT reads and writes standard netCDF files.

Smith, Brian Edward↗

GeoPhysical Analysis Code

GPAC is a code that integrates open source libraries for element formulations, linear algebra, and I/O with two main LLNL-Written components: (i) a set of standard finite elements physics solvers for rersolving Darcy fluid flow, explicit mechanics, implicit mechanics, and fluid-mediated fracturing, including resolution of contact both implicity and explicity, and (ii) a MPI-based parallelization implementation for use on generic HPC distributed memory architectures. The resultant code can be used alone for linearly elastic problems and problems involving hydraulic fracturing, where the mesh topology is dynamically changed. The key application domain is for low-rate stimulation and fracture control in subsurface reservoirs (e.g., enhanced geothermal sites and unconventional shale gas stimulation). GPAC also has interfaces to call external libraries for, e.g., material models and equations of state; however, LLNL-developed EOS and material models will not be part of the current release.

Source record↗

GeoPhysical Analysis Code

GPAC is a code that integrates open source libraries for element formulations, linear algebra, and I/O with two main LLNL-written components: (i) a set of standard finite, discrete, and discontinuous displacement element physics solvers for resolving Darcy fluid flow, explicit mechanics, implicit mechanics, fault rupture and earthquake nucleation, and fluid-mediated fracturing, including resolution of physcial behaviors both implicity and explicity, and (ii) a MPI-based parallelization implementation for use on generic HPC distributed memory architectures. The resultant code can be used alone for linearly elastic problems; ploblems involving hydraulic fracturing, where the mesh topology is dynamically changed; fault rupture modeling and seismic risk assessment; and general granular materials behavior. The key application domain is for low-rate stimulation and fracture control in subsurface reservoirs (e.g., enhanced geothermal sites and unconventional shale gas stimulation). GPAC also has interfaces to call external libraries for , e.g., material models and equations of state; however, LLNL-developed EOS and material models will not be part of the current release. CPAC's secondary applications include modeling fault evolution for predicting the statistical distribution of earthquake events and to capture granular materials behavior under different load paths.

Source record↗

ecode - Electron Transport Algorithm Testing v. 1.0

ecode is a Monte Carlo code used for testing algorithms related to electron transport. The code can read basic physics parameters, such as energy-dependent stopping powers and screening parameters. The code permits simple planar geometries of slabs or cubes. Parallelization consists of domain replication, with work distributed at the start of the calculation and statistical results gathered at the end of the calculation. Some basic routines (such as input parsing, random number generation, and statistics processing) are shared with the Integrated Tiger Series codes. A variety of algorithms for uncertainty propagation are incorporated based on the stochastic collocation and stochastic Galerkin methods. These permit uncertainty only in the total and angular scattering cross sections. The code contains algorithms for simulating stochastic mixtures of two materials. The physics is approximate, ranging from mono-energetic and isotropic scattering to screened Rutherford angular scattering and Rutherford energy-loss scattering (simple electron transport models). No production of secondary particles is implemented, and no photon physics is implemented.

Franke, Brian C.↗

The new MCNP6 depletion capability

The first MCNP based in-line Monte Carlo depletion capability was officially released from the Radiation Safety Information and Computational Center as MCNPX 2.6.0. Both the MCNP5 and MCNPX codes have historically provided a successful combinatorial geometry based, continuous energy, Monte Carlo radiation transport solution for advanced reactor modeling and simulation. However, due to separate development pathways, useful simulation capabilities were dispersed between both codes and not unified in a single technology. MCNP6, the next evolution in the MCNP suite of codes, now combines the capability of both simulation tools, as well as providing new advanced technology, in a single radiation transport code. We describe here the new capabilities of the MCNP6 depletion code dating from the official RSICC release MCNPX 2.6.0, reported previously, to the now current state of MCNP6. NEA/OECD benchmark results are also reported. The MCNP6 depletion capability enhancements beyond MCNPX 2.6.0 reported here include: (1) new performance enhancing parallel architecture that implements both shared and distributed memory constructs; (2) enhanced memory management that maximizes calculation fidelity; and (3) improved burnup physics for better nuclide prediction. MCNP6 depletion enables complete, relatively easy-to-use depletion calculations in a single Monte Carlo code. The enhancements described here help provide a powerful capability as well as dictate a path forward for future development to improve the usefulness of the technology. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Mapping mesoscale heterogeneity in the plastic deformation of a copper single crystal

The work reported here is part of a 'multiscale characterization' study of heterogeneous deformation patterns in metals. A copper single crystal was oriented for single slip in the (111)[{bar 1}01] slip system and tested to {approx}10% strain in roughly uniaxial compression. The macroscopic strain field was monitored during the test by optical 'image correlation'. The strain field was measured on orthogonal surfaces, one of which (the x-face) was oriented perpendicular to [1{bar 2}1] and contained the [{bar 1}01] direction of the preferred slip system. The macroscopic strain developed in an inhomogeneous pattern of broad, crossed shear bands in the x-face. One, the primary band, lay parallel to (111). The second, the 'conjugate' band, was oriented perpendicular to (111) with an overall ({bar 1}01) habit that contains no common slip plane of the fcc crystal. The mesoscopic deformation pattern was explored with selected area diffraction, using a focused synchrotron radiation polychromatic beam with a resolution of 1-3 {micro}m. Areas within the primary, conjugate and mixed (primary + conjugate) strain regions of the x-face were identified and mapped for their orientation, excess defect density and shear stress. The mesoscopic defect structure was concentrated in broad, somewhat irregular primary bands that lay nominally parallel to (111) in an almost periodic distribution with a period of about 30 {micro}m. These primary bands were dominant even in the region of conjugate strain. There were also broad conjugate defect bands, almost precisely perpendicular to the primary bands, that tended to bridge primary bands and terminate at them. The residual shear stresses were large (ranging to well above 500 MPa) and strongly correlated with the primary shear bands; interband stresses were small. The maximum resolved shear stresses within the primary bands were oriented out of the plane of the bands, and, hence, could not recover the dislocation structure in the bands. The maximum resolved shear stresses in the interband regions lay predominantly in {l_brace}111{r_brace} planes. The results are compared to the mesoscopic defect patterns found in Cu in etch pit studies done some decades ago, which also revealed a mesoscopic dislocation structure made up of orthogonal bands.

36 MATERIALS SCIENCE↗

Distributed computation of graphics primitives on a transputer network

A method is developed for distributing the computation of graphics primitives on a parallel processing network. Off-the-shelf transputer boards are used to perform the graphics transformations and scan-conversion tasks that would normally be assigned to a single transputer based display processor. Each node in the network performs a single graphics primitive computation. Frequently requested tasks can be duplicated on several nodes. The results indicate that the current distribution of commands on the graphics network shows a performance degradation when compared to the graphics display board alone. A change to more computation per node for every communication (perform more complex tasks on each node) may cause the desired increase in throughput.

Ellis, Graham K.↗

Simultaneous Retrieval of Effective Refractive Index and Density from Size Distribution and Light Scattering Data: Weakly-Absorbing Aerosol

We propose here a novel approach for retrieving in parallel the effective density and real refractive index of weakly absorbing aerosol from optical and size distribution measurements. Here we define “weakly absorbing” as aerosol single-scattering albedos that exceed 0.95 at 0.5 um.The required optical measurements are the scattering coefficient and the hemispheric backscatter fraction, obtained in this work from an integrating nephelometer. The required size spectra come from a Scanning Mobility Particle Sizer and an Aerodynamic Particle Sizer. The performance of this approach is first evaluated using a sensitivity study with synthetically generated but measurement-related inputs. The sensitivity study reveals that the proposed approach is robust to random noise; additionally the uncertainties of the retrieval are almost linearly proportional to the measurement errors, and these uncertainties are smaller for the real refractive index than for the effective density. Next, actual measurements are used to evaluate our approach. These measurements include the optical, microphysical, and chemical properties of weakly absorbing aerosol which are representative of a variety of coastal summertime conditions observed during the Two-Column Aerosol Project (TCAP; http://campaign.arm.gov/tcap/). The evaluation includes calculating the root mean square error (RMSE) between the aerosol characteristics retrieved by our approach, and the same quantities calculated using the conventional volume mixing rule for chemical constituents. For dry conditions (defined in this work as relative humidity less than 55%) and sub-micron particles, a very good (RMSE~3%) and reasonable (RMSE~28%) agreement is obtained for the retrieved real refractive index (1.49±0.02) and effective density (1.68±0.21), respectively. Our approach permits discrimination between the retrieved aerosol characteristics of sub-micron and sub-10micron particles. The evaluation results also reveal that the retrieved density and refractive index tend to decrease with an increase of the relative humidity.

density↗

Design & Implementation of MACSio

We are proposing to develop “MACSio” (pronounced “max-ee-oh”), a Multi-purpose, Application-Centric, Scalable I/O proxy application. It is being proposed to fill a long existing void in co-design proxy applications that allow for I/O performance testing and evaluation of tradeoffs in data model interfaces and parallel I/O paradigms for multi-physics, HPC applications. Two key design features of MACSio will set it apart from existing I/O benchmarking tools. The first is the level of abstraction (LOA) at which MACSio is being designed to operate. The second is the degree of flexibility MACSio is being designed to provide in driving an HPC I/O workload through parameterized, user-defined data objects and a variety of parallel I/O paradigms and I/O interfaces. Combined, these features will allow MACSio to closely mimic I/O workloads for a wide variety of real applications and, in particular, multi-physics applications where data object distribution and composition vary dramatically both within and across parallel tasks. These data objects can then be marshaled using one or more I/O interfaces and parallel I/O paradigms, allowing for direct comparisons of software interfaces, parallel I/O paradigms, and filesystem technologies with the same set of customizable data objects.

97 MATHEMATICS AND COMPUTING↗