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 1,135 records · Page 63

Improving Block-level Efficiency with scsi-mq

Current generation solid-state storage devices are exposing a new bottlenecks in the SCSI and block layers of the Linux kernel, where IO throughput is limited by lock contention, inefficient interrupt handling, and poor memory locality. To address these limitations, the Linux kernel block layer underwent a major rewrite with the blk-mq project to move from a single request queue to a multi-queue model. The Linux SCSI subsystem rework to make use of this new model, known as scsi-mq, has been merged into the Linux kernel and work is underway for dm-multipath support in the upcoming Linux 4.0 kernel. These pieces were necessary to make use of the multi-queue block layer in a Lustre parallel filesystem with high availability requirements. We undertook adding support of the 3.18 kernel to Lustre with scsi-mq and dm-multipath patches to evaluate the potential of these efficiency improvements. In this paper we evaluate the block-level performance of scsi-mq with backing storage hardware representative of a HPC-targerted Lustre filesystem. Our findings show that SCSI write request latency is reduced by as much as 13.6%. Additionally, when profiling the CPU usage of our prototype Lustre filesystem, we found that CPU idle time increased by a factor of 7 with Linux 3.18 and blk-mq as compared to a standard 2.6.32 Linux kernel. Our findings demonstrate increased efficiency of the multi-queue block layer even with disk-based caching storage arrays used in existing parallel filesystems.

Cluster Computing↗

Hybrid AI/Cognitive Tactical Behavior Framework for LVC (LDRD Project Final Report)

This Lab-Directed Research and Development (LDRD) sought to develop technology that enhances scenario construction speed, entity behavior robustness, and scalability in Live-Virtual-Constructive (LVC) simulation. We investigated issues in both simulation architecture and behavior modeling. We developed path-planning technology that improves the ability to express intent in the planning task while still permitting an efficient search algorithm. An LVC simulation demonstrated how this enables 'one-click' layout of squad tactical paths, as well as dynamic re-planning for simulated squads and for real and simulated mobile robots. We identified human response latencies that can be exploited in parallel/distributed architectures. We did an experimental study to determine where parallelization would be productive in Umbra-based force-on-force (FOF) simulations. We developed and implemented a data-driven simulation composition approach that solves entity class hierarchy issues and supports assurance of simulation fairness. Finally, we proposed a flexible framework to enable integration of multiple behavior modeling components that model working memory phenomena with different degrees of sophistication.

99 GENERAL AND MISCELLANEOUS↗

Parallel Multivariate Spatio-Temporal Clustering of Large Ecological Datasets on Hybrid Supercomputers

A proliferation of data from vast networks of remote sensing platforms (satellites, unmanned aircraft systems (UAS), airborne etc.), observational facilities (meteorological, eddy covariance etc.), state-of-the-art sensors, and simulation models offer unprecedented opportunities for scientific discovery. Unsupervised classification is a widely applied data mining approach to derive insights from such data. However, classification of very large data sets is a complex computational problem that requires efficient numerical algorithms and implementations on high performance computing (HPC) platforms. Additionally, increasing power, space, cooling and efficiency requirements has led to the deployment of hybrid supercomputing platforms with complex architectures and memory hierarchies like the Titan system at Oak Ridge National Laboratory. The advent of such accelerated computing architectures offers new challenges and opportunities for big data analytics in general and specifically, large scale cluster analysis in our case. Although there is an existing body of work on parallel cluster analysis, those approaches do not fully meet the needs imposed by the nature and size of our large data sets. Moreover, they had scaling limitations and were mostly limited to traditional distributed memory computing platforms. We present a parallel Multivariate Spatio-Temporal Clustering (MSTC) technique based on k-means cluster analysis that can target hybrid supercomputers like Titan. We developed a hybrid MPI, CUDA and OpenACC implementation that can utilize both CPU and GPU resources on computational nodes. We describe performance results on Titan that demonstrate the scalability and efficacy of our approach in processing large ecological data sets.

Sreepathi, Sarat↗

Performance of BLAS 3, FFTs and NAS Parallel Benchmarks on Cray T3D

Recently, a Cray T3D Emulator has been made available on the Cray Y-MP and C90 computers. The Pittsburgh Supercomputer Center has acquired a CRAY T3D system and many other centers like Jet Propulsion Laboratory (JPL) will have it by the end of 1994. The Cray T3D system is the firstphase system in Cray Research, Inc.'s (CRI) three-phase massively parallel processing (MPP) program. This system features a heterogeneous architecture that closely couples DEC's ALPHA microprocessors and CRI's parallel-vector technology, i.e. the Cray Y-MP and Cray C90. The Cray T3D Emulator will give prospective users a valuable experience in developing high performance applications on the MPP system. This emulator runs programs written in CRI's MPP Fortran programming model (data sharing and work sharing) or Parallel Virtual Machine (PVM) programming model. It will help the users to study data layout, data locality, and data reference patterns thereby providing feedback which will enable one to write more efficient parallel codes. An overview of the Cray T3D hardware, software, and three of its available programming models is presented.The Cray Fortran Programming Model comprising (a) Data Sharing, (b) Worksharing and (c) Message Passing, will be discussed with examples. We have also implemented distributed BLAS 3 (matrix-matrix multiplication) in data parallel model (using only CSHIFT); worksharing model using block distribution and collapsed distribution; and message passing model using PVM. We have also implemented 2D and 3D FFTs for radix-2 using PVM. The performance of NAS Parallel 'Benchmarks (NPB) on CRAY T3D will be compared with other highly parallel systems such as CM-5, Paragon, C90 etc.

Saini, Subhash↗

Estimating anisotropic diffusion of neutrons near the boundary of a pebble bed random system

Due to the arrangement of the pebbles in a Pebble Bed Reactor (PBR) core, if a neutron is located close to a boundary wall, its path length probability distribution function in directions of flight parallel to the wall is significantly different than in other directions. Hence, anisotropic diffusion of neutrons near the boundaries arises. We describe an analysis of neutron transport in a simplified 3-D pebble bed random system, in which we investigate the anisotropic diffusion of neutrons born near one of the system's boundary walls. While this simplified system does not model the actual physical process that takes place near the boundaries of a PBR core, the present work paves the road to a formulation that may enable more accurate diffusion simulations of such problems to be performed in the future. Monte Carlo codes have been developed for (i) deriving realizations of the 3-D random system, and (ii) performing 3-D neutron transport inside the heterogeneous model; numerical results are presented for three different choices of parameters. These numerical results are used to assess the accuracy of estimates for the mean-squared displacement of neutrons obtained with the diffusion approximations of the Atomic Mix Model and of the recently introduced [1] Non-Classical Theory with angular-dependent path length distribution. The Non-Classical Theory makes use of a Generalized Linear Boltzmann Equation in which the locations of the scattering centers in the system are correlated and the distance to collision is not exponentially distributed. We show that the results predicted using the Non-Classical Theory successfully model the anisotropic behavior of the neutrons in the random system, and more closely agree with experiment than the results predicted by the Atomic Mix Model. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Mapping robust parallel multigrid algorithms to scalable memory architectures

The convergence rate of standard multigrid algorithms degenerates on problems with stretched grids or anisotropic operators. The usual cure for this is the use of line or plane relaxation. However, multigrid algorithms based on line and plane relaxation have limited and awkward parallelism and are quite difficult to map effectively to highly parallel architectures. Newer multigrid algorithms that overcome anisotropy through the use of multiple coarse grids rather than line relaxation are better suited to massively parallel architectures because they require only simple point-relaxation smoothers. The parallel implementation of a V-cycle multiple semi-coarsened grid (MSG) algorithm or distributed-memory architectures such as the Intel iPSC/860 and Paragon computers is addressed. The MSG algorithms provide two levels of parallelism: parallelism within the relaxation or interpolation on each grid and across the grids on each multigrid level. Both levels of parallelism must be exploited to map these algorithms effectively to parallel architectures. A mapping of an MSG algorithm to distributed-memory architectures that demonstrate how both levels of parallelism can be exploited is described. The results is a robust and effective multigrid algorithm for distributed-memory machines.

Overman, Andrea↗

A Concept for Run-Time Support of the Chapel Language

A document presents a concept for run-time implementation of other concepts embodied in the Chapel programming language. (Now undergoing development, Chapel is intended to become a standard language for parallel computing that would surpass older such languages in both computational performance in the efficiency with which pre-existing code can be reused and new code written.) The aforementioned other concepts are those of distributions, domains, allocations, and access, as defined in a separate document called "A Semantic Framework for Domains and Distributions in Chapel" and linked to a language specification defined in another separate document called "Chapel Specification 0.3." The concept presented in the instant report is recognition that a data domain that was invented for Chapel offers a novel approach to distributing and processing data in a massively parallel environment. The concept is offered as a starting point for development of working descriptions of functions and data structures that would be necessary to implement interfaces to a compiler for transforming the aforementioned other concepts from their representations in Chapel source code to their run-time implementations.

James, Mark↗

FTLADS: Object-Logging Based Fault-Tolerant Big Data Transfer System Using Layout Aware Data Scheduling

The layout-aware data scheduling (LADS) data movement framework optimizes congestion for end-to-end data transfers. During data transfer, LADS can avoid congested storage elements by exploiting the underlying storage layout at each endpoint. This improves the I/O bandwidth and hence the data transfer rate across high-speed networks. However, the absence of fault tolerance (FT) in LADS results in data retransmission overhead and may lead to possible data integrity issues upon faults. In this paper, we propose object-logging FT mechanisms to avoid transmitting the objects that are successfully written into the parallel file system (PFS) at the sink end. Depending on the number of log files created for the whole dataset, we have classified our FT mechanisms into three different categories: file logger, transaction logger, and universal logger. Also, to address the space overhead, we have proposed different methods of populating the log files with the information of the successfully transferred objects. We have evaluated the data transfer performance and recovery time overhead of the proposed object-logging-based FT mechanisms on the LADS data transfer framework. Our experimental results reflect that FT mechanisms exhibit negligible overhead (<; 1%) with respect to the data transfer time. Yet, the fault recovery time is 10% higher than the total data transfer time at any fault point.

97 MATHEMATICS AND COMPUTING↗

High Performance FORTRAN

High performance FORTRAN is a set of extensions for FORTRAN 90 designed to allow specification of data parallel algorithms. The programmer annotates the program with distribution directives to specify the desired layout of data. The underlying programming model provides a global name space and a single thread of control. Explicitly parallel constructs allow the expression of fairly controlled forms of parallelism in particular data parallelism. Thus the code is specified in a high level portable manner with no explicit tasking or communication statements. The goal is to allow architecture specific compilers to generate efficient code for a wide variety of architectures including SIMD, MIMD shared and distributed memory machines.

Mehrotra, Piyush↗

Radial evolution of solar wind thermal electron distributions due to expansion and collisions

ISEE 3 electron observations near 1 AU show that the solar wind thermal electron temperature anisotropy, T(parallel)/T(perpendicular), is typically 1.0 to 1.5, with densest distributions most nearly isotropic, but is sometimes much higher when density is low. For a small observational subset characterized by high density and low bulk speed, T(perpendicular) can exceed T(parallel). Based on these and other observations, a simple model is proposed for radial evolution of thermal electrons in a structureless solar wind under the influence of Coulomb collisions and geometric expansion in a spiral interplanetary magnetic field. The model, which satisfactorily explains the 1 AU observations, shows that the evolution of electron temperature and T(parallel)/T(perpendicular) is controlled by plasma density, flow speed, and initial temperature, with density the most important factor. The model makes predictions for radial distances other than 1 AU and for high solar latitudes.

Phillips, J. L.↗

A parallel algorithm for channel routing on a hypercube

A new parallel simulated annealing algorithm for channel routing on a P processor hypercube is presented. The basic idea used is to partition a set of tracks equally among processors in the hypercube. In parallel, P/2 pairs of processors perform displacements and exchanges of nets between tracks, compute the changes in cost functions, and accept moves using a parallel annealing criteria. Through the use of a unique distributed data structure, it is possible to minimize message traffic and add versatility and efficiency in a parallel routing tool. The algorithm has been implemented and is being tested on some of the popular channel problems from the literature.

Brouwer, Randall↗

EXTENSIVE [C I] MAPPING TOWARD THE ORION-A GIANT MOLECULAR CLOUD

We have carried out wide-field (0.17 deg{sup 2}) and high-angular resolution (21.''3 {approx} 0.04 pc) observations in the [C I] line toward the Orion-A giant molecular cloud with the Atacama Submillimeter Telescope Experiment 10 m telescope in the On-The-Fly mode. The overall features of the [C I] emission are similar to those of the {sup 12}CO (J = 1-0) emission by Shimajiri et al. in 2011; the total intensity ratio of the [C I] to CO emission ranges from 0.05 to 0.2. The optical depth of the [C I] emission is found to be 0.1-0.75, suggesting optically thin emission. The column density of the [C I] emission is estimated to be (1.0-19) Multiplication-Sign 10{sup 17} cm{sup -2}. These results are consistent with the results of the previous [C I] observations with a low-angular resolution of 2.'2. In the nearly edge-on photon-dominated regions (PDRs) and their candidates of the Orion Bar, DLSF, M 43 Shell, and Region D, the distributions of the [C I] emission coincide with those of the {sup 12}CO emission, inconsistent with the prediction by the plane-parallel PDR model. In addition, the [C I] distribution in the Orion A cloud is found to be more similar to those of the {sup 13}CO (J = 1-0), C{sup 18}O (J = 1-0), and H{sup 13}CO{sup +} (J = 1-0) lines than that of the {sup 12}CO (J = 1-0) line, suggesting that the [C I] emission is not limited to the cloud surface, but is tracing the dense, inner parts of the cloud.

79 ASTRONOMY AND ASTROPHYSICS↗

Adaptive domain decomposition for Monte Carlo simulations on parallel processors

A method is described for performing direct simulation Monte Carlo (DSMC) calculations on parallel processors using adaptive domain decomposition to distribute the computational work load. The method has been implemented on a commercially available hypercube and benchmark results are presented which show the performance of the method relative to current supercomputers. The problems studied were simulations of equilibrium conditions in a closed, stationary box, a two-dimensional vortex flow, and the hypersonic, rarefield flow in a two-dimensional channel. For these problems, the parallel DSMC method ran 5 to 13 times faster than on a single processor of a Cray-2. The adaptive decomposition method worked well in uniformly distributing the computational work over an arbitrary number of processors and reduced the average computational time by over a factor of two in certain cases.

Wilmoth, Richard G.↗

Adaptive domain decomposition for Monte Carlo simulations on parallel processors

A method is described for performing direct simulation Monte Carlo (DSMC) calculations on parallel processors using adaptive domain decomposition to distribute the computational work load. The method has been implemented on a commercially available hypercube and benchmark results are presented which show the performance of the method relative to current supercomputers. The problems studied were simulations of equilibrium conditions in a closed, stationary box, a two-dimensional vortex flow, and the hypersonic, rarefied flow in a two-dimensional channel. For these problems, the parallel DSMC method ran 5 to 13 times faster than on a single processor of a Cray-2. The adaptive decomposition method worked well in uniformly distributing the computational work over an arbitrary number of processors and reduced the average computational time by over a factor of two in certain cases.

Wilmoth, Richard G.↗

Using PVM to host CLIPS in distributed environments

It is relatively easy to enhance CLIPS (C Language Integrated Production System) to support multiple expert systems running in a distributed environment with heterogeneous machines. The task is minimized by using the PVM (Parallel Virtual Machine) code from Oak Ridge Labs to provide the distributed utility. PVM is a library of C and FORTRAN subprograms that supports distributive computing on many different UNIX platforms. A PVM deamon is easily installed on each CPU that enters the virtual machine environment. Any user with rsh or rexec access to a machine can use the one PVM deamon to obtain a generous set of distributed facilities. The ready availability of both CLIPS and PVM makes the combination of software particularly attractive for budget conscious experimentation of heterogeneous distributive computing with multiple CLIPS executables. This paper presents a design that is sufficient to provide essential message passing functions in CLIPS and enable the full range of PVM facilities.

Myers, Leonard↗

Photodissociation of (ICN){sub 2} van der Waals dimer using velocity imaging technique

Photodissociation of (ICN){sub 2} dimer from 265 to 270 nm are studied using time-of-flight mass spectrometry combined with velocity imaging technique. Both I{sup +} and I{sub 2}{sup +} ions are found in the mass spectra. The I{sub 2}{sup +} ions result from (1+1) resonant ionization of the neutral I{sub 2} fragment that is produced in the photodissociation of dimer, but not from dissociative ionization of (ICN){sub 2}; i.e., (ICN){sub 2}{sup +}+h{nu}{yields}I{sub 2}{sup +}+2CN. The dissociation channels of I{sub 2}{sup +} leading to I{sup +} are all found with parallel character. The total kinetic energy distributions and anisotropy parameters of the I{sup +} channels produced by (ICN){sub 2} are almost the same as those from a neutral I{sub 2} sample, thereby confirming that the I{sub 2} fragments are obtained in cold state. With the aid of ab initio calculations, a plausible dissociation mechanism is proposed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Electromagnetic simulations of the ASDEX Upgrade ICRF Antenna with the TOPICA code

Accurate and efficient simulation tools are necessary to optimize the ICRF antenna design for a set of operational conditions. The TOPICA code was developed for performance prediction and for the analysis of ICRF antenna systems in the presence of plasma, given realistic antenna geometries. Fully 3D antenna geometries can be adopted in TOPICA, just as in available commercial codes. But while those commercial codes cannot operate with a plasma loading, the TOPICA code correctly accounts for realistic plasma loading conditions, by means of the coupling with 1D FELICE code. This paper presents the evaluation of the electric current distribution on the structure, of the parallel electric field in the region between the straps and the plasma and the computation of sheaths driving RF potentials. Results of TOPICA simulations will help to optimize and re-design the ICRF ASDEX Upgrade antenna in order to reduce tungsten (W) sputtering attributed to the rectified sheath effect during ICRF operation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗