Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed memory”

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 1,117 records · Page 62

Distributed Data-Flow for In-Situ Visualization and Analysis at Petascale

We conducted a feasibility study to research modifications to data-flow architectures to enable data-flow to be distributed across multiple machines automatically. Distributed data-flow is a crucial technology to ensure that tools like the VisIt visualization application can provide in-situ data analysis and post-processing for simulations on peta-scale machines. We modified a version of VisIt to study load-balancing trade-offs between light-weight kernel compute environments and dedicated post-processing cluster nodes. Our research focused on memory overheads for contouring operations, which involves variable amounts of generated geometry on each node and computation of normal vectors for all generated vertices. Each compute node independently decided whether to send data to dedicated post-processing nodes at each stage of pipeline execution, depending on available memory. We instrumented the code to allow user settable available memory amounts to test extremely low-overhead compute environments. We performed initial testing of this prototype distributed streaming framework, but did not have time to perform scaling studies at and beyond 1000 compute-nodes.

97 MATHEMATICS AND COMPUTING↗

A wavelet-MRA-based adaptive semi-Lagrangian method for the relativistic Vlasov-Maxwell system

In this paper we present a new method for the numerical solution of the relativistic Vlasov-Maxwell system on a phase-space grid using an adaptive semi-Lagrangian method. The adaptivity is performed through a wavelet multiresolution analysis, which gives a powerful and natural refinement criterion based on the local measurement of the approximation error and regularity of the distribution function. Therefore, the multiscale expansion of the distribution function allows to get a sparse representation of the data and thus save memory space and CPU time. We apply this numerical scheme to reduced Vlasov-Maxwell systems arising in laser-plasma physics. Interaction of relativistically strong laser pulses with overdense plasma slabs is investigated. These Vlasov simulations revealed a rich variety of phenomena associated with the fast particle dynamics induced by electromagnetic waves as electron trapping, particle acceleration, and electron plasma wavebreaking. However, the wavelet based adaptive method that we developed here, does not yield significant improvements compared to Vlasov solvers on a uniform mesh due to the substantial overhead that the method introduces. Nonetheless they might be a first step towards more efficient adaptive solvers based on different ideas for the grid refinement or on a more efficient implementation. Here the Vlasov simulations are performed in a two-dimensional phase-space where the development of thin filaments, strongly amplified by relativistic effects requires an important increase of the total number of points of the phase-space grid as they get finer as time goes on. The adaptive method could be more useful in cases where these thin filaments that need to be resolved are a very small fraction of the hyper-volume, which arises in higher dimensions because of the surface-to-volume scaling and the essentially one-dimensional structure of the filaments. Moreover, the main way to improve the efficiency of the adaptive method is to increase the local character in phase-space of the numerical scheme, by considering multiscale reconstruction with more compact support and by replacing the semi-Lagrangian method with more local - in space - numerical scheme as compact finite difference schemes, discontinuous-Galerkin method or finite element residual schemes which are well suited for parallel domain decomposition techniques.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Magnetotransport in a 2D system with strong scatterers: Renormalization of Hall coefficient caused by non-Markovian effects

We show that a sharp dependence of the Hall coefficient R on the magnetic field B arises in two-dimensional electron systems with strong scatterers. The phenomenon is due to classical memory effects. We calculate analytically the dependence of R on B for the case of scattering by antidots (modeled by hard disks of radius a), randomly distributed with concentration n{sub 0} << 1/a{sup 2}. We demonstrate that in very weak magnetic fields ({omega}{sub c}{tau}{sub tr} {<=} n{sub 0}a{sup 2}), memory effects lead to a considerable renormalization of the Boltzmann value of the Hall coefficient: {delta}R/R {approx} 1. With increasing magnetic field, the relative correction to R decreases, then changes sign, and saturates at the value {delta}R/R {approx} -n{sub 0}a{sup 2}. We also discuss the effect of the smooth disorder on the dependence of R on B.

36 MATERIALS SCIENCE↗

Analysis of the energy distribution of interface traps related to tunnel oxide degradation using charge pumping techniques for 3D NAND flash applications

Graphical abstract: The degradation tendency extracted by CP technique was almost the same in both the bulk-type and TFT-type cells. - Highlights: • D{sub it} is directly investigated from bulk-type and TFT-type CTF memory. • Charge pumping technique was employed to analyze the D{sub it} information. • To apply the CP technique to monitor the reliability of the 3D NAND flash. - Abstract: The energy distribution and density of interface traps (D{sub it}) are directly investigated from bulk-type and thin-film transistor (TFT)-type charge trap flash memory cells with tunnel oxide degradation, under program/erase (P/E) cycling using a charge pumping (CP) technique, in view of application in a 3-demension stackable NAND flash memory cell. After P/E cycling in bulk-type devices, the interface trap density gradually increased from 1.55 × 10{sup 12} cm{sup −2} eV{sup −1} to 3.66 × 10{sup 13} cm{sup −2} eV{sup −1} due to tunnel oxide damage, which was consistent with the subthreshold swing and transconductance degradation after P/E cycling. Its distribution moved toward shallow energy levels with increasing cycling numbers, which coincided with the decay rate degradation with short-term retention time. The tendency extracted with the CP technique for D{sub it} of the TFT-type cells was similar to those of bulk-type cells.

36 MATERIALS SCIENCE↗

Operator learning for predicting multiscale bubble growth dynamics

We report simulating and predicting multiscale problems that couple multiple physics and dynamics across many orders of spatiotemporal scales is a great challenge that has not been investigated systematically by deep neural networks (DNNs). Herein, we develop a framework based on operator regression, the so-called deep operator network (DeepONet), with the long-term objective to simplify multiscale modeling by avoiding the fragile and time-consuming “hand-shaking” interface algorithms for stitching together heterogeneous descriptions of multiscale phenomena. To this end, as a first step, we investigate if a DeepONet can learn the dynamics of different scale regimes, one at the deterministic macroscale and the other at the stochastic microscale regime with inherent thermal fluctuations. Specifically, we test the effectiveness and accuracy of the DeepONet in predicting multirate bubble growth dynamics, which is described by a Rayleigh–Plesset (R–P) equation at the macroscale and modeled as a stochastic nucleation and cavitation process at the microscale by dissipative particle dynamics (DPD). First, we generate data using the R–P equation for multirate bubble growth dynamics caused by randomly time-varying liquid pressures drawn from Gaussian random fields (GRFs). Our results show that properly trained DeepONets can accurately predict the macroscale bubble growth dynamics and can outperform long short-term memory networks. We also demonstrate that the DeepONet can extrapolate accurately outside the input distribution using only very few new measurements. Subsequently, we train the DeepONet with DPD data corresponding to stochastic bubble growth dynamics. Although the DPD data are noisy and we only collect sparse data points on the trajectories, the trained DeepONet model is able to predict accurately the mean bubble dynamics for time-varying GRF pressures. Taken together, our findings demonstrate that DeepONets can be employed to unify the macroscale and microscale models of the multirate bubble growth problem, hence providing new insight into the role of operator regression via DNNs in tackling realistic multiscale problems and in simplifying modeling with heterogeneous descriptions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Multi-Level Load Balancing with an Integrated Runtime Approach

The recent trend of increasing numbers of cores per chip has resulted in vast amounts of on-node parallelism. These high core counts result in hardware variability that introduces imbalance. Applications are also becoming more complex, re-sulting in dynamic load imbalance. Load imbalance of any kind can result in loss of performance and system utilization. We address the challenge of handling both transient and persistent load imbalances while maintaining locality with low overhead. In this paper, we propose an integrated runtime system that combines the Charm++ distributed programming model with concurrent tasks to mitigate load imbalances within and across shared memory address spaces. It utilizes a periodic assignment of work to cores based on load measurement, in combination with user created tasks to handle load imbalance. We integrate OpenMP with Charm++ to enable creation of potential tasks via OpenMP's parallel loop construct. This is also available to MPI applications through the Adaptive MPI implementation. We demonstrate the benefits of our work on three applications. We show improvements of Lassen by 29.6% on Cori and 46.5% on Theta. We also demonstrate the benefits on a Charm++ application, ChaNGa by 25.7% on Theta, as well as an MPI proxy application, Kripke, using Adaptive MPI.

Bak, Seonmyeong↗

Short-Term Forecasting of Thermostatic and Residential Loads Using Long Short-Term Memory Recurrent Neural Networks

Internet of Things (IoT) devices in smart grids enable intelligent energy management for grid managers and personalized energy services for consumers. Investigating a smart grid with IoT devices requires a simulation framework with IoT devices modeling. However, there lack comprehensive study on the modeling of IoT devices in smart grids. This paper investigates the IoT device modeling of a thermostatic load and implements the recurrent neural networks model for short-term load forecasting in this IoT-based thermostatic load. The recurrent neural network structure is leveraged to build a load forecasting model on temporal correlation. The temporal recurrent neural network layers including long short-term memory cells are employed to learn the data from both the simulation platform and New South Wales residential datasets. The simulation results are provided for demonstration.

electric load forecasting↗

A model for the distributed storage and processing of large arrays

A conceptual model for parallel computations on large arrays is developed. The model provides a set of language concepts appropriate for processing arrays which are generally too large to fit in the primary memories of a multiprocessor system. The semantic model is used to represent arrays on a concurrent architecture in such a way that the performance realities inherent in the distributed storage and processing can be adequately represented. An implementation of the large array concept as an Ada package is also described.

Mehrota, P.↗

Preliminary study on applying the method of characteristics to pebble-bed HTR - 18637

Neutron transport in high temperature pebble-bed gas-cooled reactor, which is a promising generation IV reactor candidate with cylindrical core, graphite moderator and spherical TRISO coated particles fuel, is of great interest. However, the stochastic method namely Monte Carlo faces with tremendous simulation of particles and the conventional two-step method featured by homogenization only can give the scalar flux. In this paper, method of characteristics is trying to be applied to pebble bed reactor because of its advantages in arbitrary geometry and the ability to obtain solution in neutronically large domains. Some challenges occur when it comes to HTR. First, the amount of calculation and the memory requirement are huge due to the large quantities of spherical fuel and stochastic distribution of pebbles. Second, the arrangement of characteristics and ray tracing process is more complex comparing to LWR with cuboid geometry because the stochastic distribution of the spherical assemblies and the longer neutron mean free path in pebble bed HTR. Third, the treatment of the multiscale sphere fuel need be detail studied to determine the subdivision of flat source region. At present, preliminary research on this subject is undergoing. This paper is concentrated on the modeling of the pebble-bed reactor core by constructive solid geometry (CSG) which allows complex spatial models to be built using boolean operations, characteristics arrangement and the treatment of boundary condition. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

UPC++: A High-Performance Communication Framework for Asynchronous Computation

© 2019 IEEE UPC++ is a C++ library that supports high-performance computation via an asynchronous communication framework. This paper describes a new incarnation that differs substantially from its predecessor, and we discuss the reasons for our design decisions. We present new design features, including future-based asynchrony management, distributed objects, and generalized Remote Procedure Call (RPC). We show microbenchmark performance results demonstrating that one-sided Remote Memory Access (RMA) in UPC++ is competitive with MPI-3 RMA; on a Cray XC40 UPC++ delivers up to a 25% improvement in the latency of blocking RMA put, and up to a 33% bandwidth improvement in an RMA throughput test. We showcase the benefits of UPC++ with irregular applications through a pair of application motifs, a distributed hash table and a sparse solver component. Our distributed hash table in UPC++ delivers near-linear weak scaling up to 34816 cores of a Cray XC40. Our UPC++ implementation of the sparse solver component shows robust strong scaling up to 2048 cores, where it outperforms variants communicating using MPI by up to 3.1x. UPC++ encourages the use of aggressive asynchrony in low-overhead RMA and RPC, improving programmer productivity and delivering high performance in irregular applications.

Bachan, John↗

Long-distance entanglement distribution with single-photon sources

We present an efficient architecture for quantum repeaters based on single-photon sources in combination with quantum memories for photons. Errors inherent to previous repeater protocols using photon-pair sources are eliminated, leading to a significant gain in efficiency. The requirements on the single-photon sources and on the photon detectors are within reach of current technology.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Switching current reduction in magnetoresistive random access memories

We present an approach for minimizing the critical current for the magnetization switching in magnetic tunnel junctions by optimizing the spatial distribution of the current density. We show that such a minimization is possible because critical current is determined by the condition of making one of the magnetization eigenstates grow in time. The excitation of the eigenstates is enhanced when the spatial distributions of the eigenstates and current density overlap. Critical current can be viewed as a functional of the current density spatial distribution and it can be minimized by optimizing this distribution. Such an optimization results in a major reduction of the critical current and increase of the switching efficiency, viz. the ratio between the energy barrier and critical current. The minimized critical current increases approximately linearly with the magnetic tunnel junction size, which is much slower than critical current for the case of a uniform current density. The optimized efficiency can be approximately a constant with respect to the magnetic tunnel junction size, which is much higher than the efficiency for the uniform current density. Additional optimization can be achieved by spatially modulating the material parameters, e.g., the saturation magnetization. The presented approach and obtained scaling of the critical current and efficiency offers opportunities for the magnetic tunnel junction optimization.

36 MATERIALS SCIENCE↗

Mapping Dense LU Factorization on Multicore Supercomputer Nodes

Dense LU factorization is a prominent benchmark used to rank the performance of supercomputers. Many implementations use block-cyclic distributions of matrix blocks onto a two-dimensional process grid. The process grid dimensions drive a trade-off between communication and computation and are architecture- and implementation-sensitive. The critical panel factorization steps can be made less communication-bound by overlapping asynchronous collectives for pivoting with the computation of rank-k updates. By shifting the computation-communication trade-off, a modified block-cyclic distribution can beneficially exploit more available parallelism on the critical path, and reduce panel factorization's memory hierarchy contention on now-ubiquitous multicore architectures. During active panel factorization, rank-1 updates stream through memory with minimal reuse. In a column-major process grid, the performance of this access pattern degrades as too many streaming processors contend for access to memory. A block-cyclic mapping in the row-major order does not encounter this problem, but consequently sacrifices node and network locality in the critical pivoting steps. We introduce 'striding' to vary between the two extremes of row- and column-major process grids. The maximum available parallelism in the critical path work (active panel factorization, triangular solves, and subsequent broadcasts) is bounded by the length or width of the process grid. Increasing one dimension of the process grid decreases the number of distinct processes and nodes in the other dimension. To increase the harnessed parallelism in both dimensions, we start with a tall process grid. We then apply periodic 'rotation' to this grid to restore exploited parallelism along the row to previous levels. As a test-bed for further mapping experiments, we describe a dense LU implementation that allows a block distribution to be defined as a general function of block to processor. Other mappings can be tested wit...

Computer Science↗

Variational data augmentation for a learning-based granular predictive model of power outages

As the trend in climate change continues, extreme weather events are expected to occur with increasing frequency and severity and pose a significant threat to the electric power infrastructure. Regardless of the efforts a utility puts towards hardening the grid, storm-induced damage to the utility assets such as cables and distributed energy resources (DERs) that are particularly vulnerable to such events is unavoidable. Access to a highly granular, in space and time, outage forecasting tool with long lead times (i.e., days ahead) will enhance the efficiency of service restoration efforts. Here, in this study, we propose to develop and implement a multi-model framework as an operational tool based on a granular and multi-day outage forecasting model using operational numerical weather prediction model forecasts and detailed component outage information. An innovative two-layered recurrent neural network, i.e., a long-short-term-memory (LSTM)-based variational autoencoder (VAE) framework and a sliding window are used to address the uneven distribution of different types of weather events and make better use of the time-series data. Case studies are performed to demonstrate the performance of the new framework.

54 ENVIRONMENTAL SCIENCES↗

Diversity waves in collapse-driven population dynamics

Populations of species in ecosystems are often constrained by availability of resources within their environment. In effect this means that a growth of one population, needs to be balanced by comparable reduction in populations of others. In neutral models of biodiversity all populations are assumed to change incrementally due to stochastic births and deaths of individuals. Here we propose and model another redistribution mechanism driven by abrupt and severe collapses of the entire population of a single species freeing up resources for the remaining ones. This mechanism may be relevant e.g. for communities of bacteria, with strain-specific collapses caused e.g. by invading bacteriophages, or for other ecosystems where infectious diseases play an important role. The emergent dynamics of our system is cyclic ‘‘diversity waves’’ triggered by collapses of globally dominating populations. The population diversity peaks at the beginning of each wave and exponentially decreases afterwards. Species abundances are characterized by a bimodal time-aggregated distribution with the lower peak formed by populations of recently collapsed or newly introduced species while the upper peak - species that has not yet collapsed in the current wave. In most waves both upper and lower peaks are composed of several smaller peaks. This self-organized hierarchical peak structure has a long-term memory transmitted across several waves. It gives rise to a scale-free tail of the time-aggregated population distribution with a universal exponent of 1.7. We show that diversity wave dynamics is robust with respect to variations in the rules of our model such as diffusion between multiple environments, species-specific growth and extinction rates, and bet-hedging strategies.

59 BASIC BIOLOGICAL SCIENCES↗

Concept for a distributed processor computer

Future generation computer utilizes cell of single metal oxide semiconductor wafer containing general purpose processor section and small memory of approximately 512 words of 16 bits each. Cells are organized into groups and groups interconnected to form computer.

Bogue, P. N.↗

A scheme for supporting distributed data structures on multicomputers

A data migration mechanism is proposed that allows an explicit and controlled mapping of data to memory. While read or write copies of each data element can be assigned to any processor's memory, longer term storage of each data element is assigned to a specific location in the memory of a particular processor. The proposed integration of a data migration scheme with a compiler is able to eliminate the migration of unneeded data that can occur in multiprocessor paging or caching. The overhead of adjudicating multiple concurrent writes to the same page or cache line is also eliminated. Data is presented that suggests that the scheme may be a pratical method for efficiently supporting data migration.

Hiranandani, Seema↗