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 1,333 records · Page 74

Towards scaling community detection on distributed-memory heterogeneous systems

Distributed multi-GPU systems pose significant challenges and opportunities for efficient execution of parallel applications. Graph algorithms are generally characterized by irregular memory accesses, low computation to communication ratios, and load balancing problems that are especially hard to address on multi-GPU systems. Graph community detection is an important problem in the emerging domain of graph analytics with numerous applications. In this paper, we present our ongoing work on distributed-memory multi-GPU implementation for graph community detection. Our work parallelizes the widely used (albeit serial) Louvain method on distributed multi-GPU platforms. Supported by an extensive set of experiments on a multi-GPU enabled supercomputer (OLCF Summit) and a single compute node (Nvidia DGX-2®), we demonstrate competitive performance to existing distributed-memory CPU-based implementation, and up to 6.5 better results than Nvidia RAPIDS® CUGRAPH. To the best of our knowledge, this work represents the first effort for community detection on distributed multi-GPU systems. Our approach and related findings can be extended to numerous other iterative graph algorithms on multi-GPU systems.

97 MATHEMATICS AND COMPUTING↗

Hashing strategies for the Cray XMT.

Two of the most commonly used hashing strategies - linear probing and hashing with chaining - are adapted for efficient execution on a Cray XMT. These strategies are designed to minimize memory contention. Datasets that follow a power law distribution cause significant performance challenges to shared memory parallel hashing implementations. Experimental results show good scalability up to 128 processors on two power law datasets with different data types: integer and string. These implementations can be used in a wide range of applications.

99 GENERAL AND MISCELLANEOUS↗

Sheath energy transmission in a collisional plasma with collisionless sheath

Sheath energy transmission governs the plasma energy exhaust onto a material surface. The ion channel is dominated by convection, but the electron channel has a significant thermal conduction component, which is dominated by the Knudsen layer effect in the presence of an absorbing wall. First-principle kinetic simulations also reveal a robustly supersonic sheath entry flow. The ion sheath energy transmission and the sheath potential are accurately predicted by a sheath model of truncated bi-Maxwellian electron distribution. The electron energy transmission is further enhanced by a parallel heat flux of the perpendicular degrees of freedom.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Distributed non-equilibrium Green’s function algorithms for the simulation of nanoelectronic devices with scattering

Through the non-equilibrium Green’s function (NEGF) formalism, quantum-scale device simulation can be performed with the inclusion of electron-phonon scattering. Yet, the simulation of realistically sized devices under the NEGF formalism typically requires prohibitive amounts of memory and computation time. Two of the most demanding computational problems for NEGF simulation involve mathematical operations with structured matrices called semiseparable matrices. In this work, we present parallel approaches for these computational problems which allow for efficient distribution of both memory and computation based upon the underlying device structure. This is vital when simulating realistically sized devices due to the aforementioned computational burdens. First, we consider determining a distributed compact representation for the retarded Green’s function matrix G R . This compact representation is exact and allows for any entry in the matrix to be generated through the inherent semiseparable structure. The second parallel operation allows for the computation of electron density and current characteristics for the device. Specifically, matrix products between the distributed representation for the semiseparable matrix G R and the self-energy scattering terms in Σ < produce the less-than Green’s function G < . As an illustration of the computational efficiency of our approach, we stably generate the mobility for nanowires with cross-sectional sizes as large as 4.5 nm, assuming an atomistic model with scattering.

47 OTHER INSTRUMENTATION↗

On the approximations of the distribution function of fusion alpha particles

The solution of the drift-kinetic equation for fusion-born alpha particles is derived in the limit of dominant parallel streaming, and it is related to the usual slowing-down distribution function. The typical approximations of the fast tail of fusion-born alpha particles are briefly compared and discussed. In particular, approximating the distribution function of fast-alpha particles with an “equivalent” Maxwellian is inaccurate to describe absorption of radio-frequency waves in the ion-cyclotron range of frequencies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

An efficient massively parallel Euler solver for unstructured grids

A data parallel mesh-vertex upwind finite-volume scheme for solving the Euler equations on triangular unstructured meshes is described. A novel vertex-based partitioning of the problem is introduced which minimizes the computation and communication costs associated with distributing the computation to the processors of a massively parallel computer. Finally, the performance of this unstructured computation on 8K processors of the Connection Machine CM-2 is compared with one processor of a Cray-YMP. The experiments show that 8K processors of the CM-2 achieve approximately 70 percent of the performance of one processor of the Cray-YMP on the unstructured mesh computations described here.

Hammond, Steven W.↗

Evidence for Spiral Magnetic Structures at the Magnetopause: A Case for Multiple Reconnections

We analyze plasma structures within the low latitude boundary layer (LLBL) observed by the lnterball Tail spacecraft under southward interplanetary magnetic field. Ion velocity distributions observed in the LLBL under these conditions fall into three categories: (a) D-shaped distributions, (b) ion velocity distributions consisting of two counterstreaming magnetosheath-type, and (c) distributions with three components where one of them has nearly zero velocity parallel to magnetic field (VlI), while the other two are counter-streaming components. D-shaped ion velocity distributions (a) correspond to magnetosheath plasma injections into reconnected flux tubes, as influenced by spacecraft location relative to the reconnection site. Simultaneous counter-streaming injections (b) suggest multiple reconnections. Three-component ion velocity distributions (c) and theii evolution with decreasing number density in the LLBL are consistent v behavior expected on long spiral flux tube islands at the magnetopaus as has been proposed and found to occur in magnetopause simulatior We interpret these distributions as a natural consequence of the formation of spiral magnetic flux tubes consisting of a mixture of alternating segments originating from the magnetosheath and magnetospheric plasmas. We suggest that multiple reconnections pla! an important role in the formation of the LLBL.

Vaisberg, O. L.↗

SWAMP+: multiple subsequence alignment using associative massive parallelism

A new parallel algorithm SWAMP+ incorporates the Smith-Waterman sequence alignment on an associative parallel model known as ASC. It is a highly sensitive parallel approach that expands traditional pairwise sequence alignment. This is the first parallel algorithm to provide multiple non-overlapping, non-intersecting subsequence alignments with the accuracy of Smith-Waterman. The efficient algorithm provides multiple alignments similar to BLAST while creating a better workflow for the end users. The parallel portions of the code run in O(m+n) time using m processors. When m = n, the algorithmic analysis becomes O(n) with a coefficient of two, yielding a linear speedup. Implementation of the algorithm on the SIMD ClearSpeed CSX620 confirms this theoretical linear speedup with real timings.

99 GENERAL AND MISCELLANEOUS↗

Resonator with a back deformable mirror for the formation of a beam with a given intensity distribution

We present the results of a numerical-analytical study of formation of an output beam with a given intensity distribution for a resonator with a back deformable mirror (DM) and semitransparent spherical front mirror. Using the theory of inverse optical problems in the diffraction approximation, the basic characteristics of a laser resonator with a DM are considered as functions of the reference resonator configuration and the form of the distribution function, describing the given intensity. The laser beam formation in the reference resonator with plane-parallel and concentric configurations is compared. In the investigated resonators, the given intensity distribution is a fundamental mode; the selectivity (determined by the power losses of transverse modes) of the resonator with a DM is comparable with that of the reference resonator. It is shown that the formation of the given intensity distributions (uniform, super-Gaussian, or having several maxima) requires a DM with the amplitude of deformations of the optical surface of the order of {lambda} and the number of control channels from 1 to nearly 10.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Characteristics of reflected and diffuse ions upstream from the earth's bow shock

The distinction between two types of upstream ion populations is made on the basis of pronounced differences in their distribution functions. The reflected ions represent a fast beam with temperatures typically one-million to five-million K and speeds up to five times the solar wind speed. An important feature of the reflected ion distributions is their strong temperature anisotropy, with perpendicular temperature exceeding parallel temperature by a factor of two or three. In contrast, the diffuse ions occupy a much larger region of phase space, both in energy and angle; their distribution function generally has the form of a circular ridge in two dimensions and a spherical shell in three dimensions. Accordingly, their temperature is much larger (not less than about 10-million K) and their bulk speed is typically smaller than the solar wind speed.

Paschmann, G.↗

Spreadsheet Calculation of Jets in Crossflow: Opposed Rows of Slots Slanted at 45 Degrees

The purpose of this study was to extend a baseline empirical model to the case of jets entering the mainstream flow from opposed rows of 45 degrees slanted slots. The results in this report were obtained using a spreadsheet modified from the one posted with NASA/TM--2010-216100. The primary conclusion in this report is that the best mixing configuration for opposed rows of 45 degrees slanted slots at any down stream distance is a parallel staggered configuration where the slots are angled in the same direction on top and bottom walls and one side is shifted by half the orifice spacing. Although distributions from perpendicular slanted slots are similar to those from parallel staggered configurations at some downstream locations, results for perpendicular slots are highly dependent on downstream distance and are no better than parallel staggered slots at locations where they are similar and are worse than parallel ones at other distances.

Holderman, James D.↗

Spreadsheet Calculation of Jets in Crossflow: Opposed Rows of Slots Slanted at 45 Degrees

The purpose of this study was to extend a baseline empirical model to the case of jets entering the mainstream flow from opposed rows of 45 degrees slanted slots. The results in this report were obtained using a spreadsheet modified from the one posted with NASA/TM--2010-216100. The primary conclusion in this report is that the best mixing configuration for opposed rows of 45 degrees slanted slots at any down stream distance is a parallel staggered configuration where the slots are angled in the same direction on top and bottom walls and one side is shifted by half the orifice spacing. Although distributions from perpendicular slanted slots are similar to those from parallel staggered configurations at some downstream locations, results for perpendicular slots are highly dependent on downstream distance and are no better than parallel staggered slots at locations where they are similar and are worse than parallel ones at other distances.

Holderman, James D.↗

A non-destructive method for crack quantification in photovoltaic backsheets under accelerated and real-world exposures

The long-term durability of photovoltaic modules is paramount for the continued growth of the industry. Polymer backsheets are of particular concern since they provide electrical insulation and an environmental barrier. In this paper, 23 freestanding, multilayer backsheets with nine unique material combinations underwent four different weathering exposures under accelerated and real-world conditions. Besides changes in color and gloss, the induced degradation included parallel or mudflat cracks on 11 backsheets, sometimes in combination with delamination or blistering. Similar degradation has been observed in previous studies and is concerning since cracks compromise the mechanical integrity and electrical safety of backsheets. Quantitative parameters are desirable to reliably classify categories of cracks and supply unbiased features for statistical analysis in predictive lifetime models. We developed an analysis technique that utilizes surface profilometry data to quantify the depth, width, area, spacing, and number of cracks. Parameters are automatically extracted from the raw data by an algorithm running on a high performance distributed computing cluster. Our algorithm excelled at characterizing parallel cracks with minimal de-adhesion, and only an estimated 4% of crack detections were false positives. The addition of humidity and temperature variation formed up to three times as many cracks on a photodose basis compared to dry, constant temperature exposures. Cracks in real-world and accelerated exposures propagated to similar depths with equivalent photodoses; however, the number of cracks formed in accelerated exposures was far greater on a photodose basis. Of samples that cracked, the best performing backsheet configuration was polyvinyl fluoride/poly (ethylene-terephthalate)/polyethylene (PVF/PET/PE) while the least durable was PET/PET/ethylene-vinyl acetate. Finally, none of the six PVF/PET/PVF backsheets cracked in any of the exposures.

14 SOLAR ENERGY↗

Hypercluster Parallel Processor

Hypercluster computer system includes multiple digital processors, operation of which coordinated through specialized software. Configurable according to various parallel-computing architectures of shared-memory or distributed-memory class, including scalar computer, vector computer, reduced-instruction-set computer, and complex-instruction-set computer. Designed as flexible, relatively inexpensive system that provides single programming and operating environment within which one can investigate effects of various parallel-computing architectures and combinations on performance in solution of complicated problems like those of three-dimensional flows in turbomachines. Hypercluster software and architectural concepts are in public domain.

Blech, Richard A.↗

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↗

Absorption and emission of extraordinary-mode electromagnetic waves near cyclotron frequency in nonequilibrium plasmas

An investigation is presented of two cases: (1) weakly relativistic electrons with a loss-cone type distribution, and (2) electrons with a drift velocity parallel to the ambient magnetic field. Numerical computations are given for physical parameters close to those in the polar region of the earth magnetosphere and laboratory experiments, with attention to the fast extraordinary-mode radiation whose frequency is near that of the electron cyclotron frequency. The fast extraordinary mode can escape from a strong field region to the weaker field region and may therefore be measured outside the plasma. It is found that the X mode radiation can be amplified by means of a cyclotron maser effect when the electrons have a loss-cone distribution, and it is concluded that, when the electron energy is sufficiently high, the X mode cutoff frequency may be lower than the cyclotron frequency.

Wu, C. S.↗

PARALLEL IMPLEMENTATION OF THE TOPAZ OPACITY CODE: ISSUES IN LOAD-BALANCING

The TOPAZ opacity code explicitly includes configuration term structure in the calculation of bound-bound radiative transitions. This approach involves myriad spectral lines and requires the large computational capabilities of parallel processing computers. It is important, however, to make use of these resources efficiently. For example, an increase in the number of processors should yield a comparable reduction in computational time. This proportional 'speedup' indicates that very large problems can be addressed with massively parallel computers. Opacity codes can readily take advantage of parallel architecture since many intermediate calculations are independent. On the other hand, since the different tasks entail significantly disparate computational effort, load-balancing issues emerge so that parallel efficiency does not occur naturally. Several schemes to distribute the labor among processors are discussed.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗