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 901 records · Page 50

Programming Strategies for Irregular Algorithms on the Emu Chick

The Emu Chick prototype implements migratory memory-side processing in a novel hardware system. Rather than transferring large amounts of data across the system interconnect, the Emu Chick moves lightweight thread contexts to near-memory cores before the beginning of each remote memory read. Previous work has characterized the performance of the Chick prototype in terms of memory bandwidth and programming differences from more typical, non-migratory platforms, but there has not yet been an analysis of algorithms on this system. This work evaluates irregular algorithms that could benefit from the lightweight, memory-side processing of the Chick and demonstrates techniques and optimization strategies for achieving performance in sparse matrix-vector multiply operation (SpMV), breadth-first search (BFS), and graph alignment across up to eight distributed nodes encompassing 64 nodelets in the Chick system. We also define and justify relative metrics to compare prototype FPGA-based hardware with established ASIC architectures. The Chick currently supports up to 68x scaling for graph alignment, 80 MTEPS for BFS on balanced graphs, and 50% of measured STREAM bandwidth for SpMV.

Hein, Eric↗

Registration and fusion of large-scale melt pool temperature and morphology monitoring data demonstrated for surface topography prediction in LPBF

In-situ monitoring technologies for laser powder bed fusion (LPBF) additive manufacturing often face one key challenge, extracting the ultrafast melt pool (MP) signatures for understanding the localized part properties. Further, the spatial information of each monitored MP signature is essential for correlating the MP – part property. This spatial information is often unavailable especially from commercial LPBF printers. Many MP monitoring methods have been reported and utilized. However, very few of these have the MP’s spatial information. To overcome this challenge, in this work we report a method for spatially registering the key MP signatures (MP intensity, temperature, and area) to the monitored print parts. The MP signatures are obtained from our coaxial high-speed single-camera based two-wavelength imaging pyrometry (STWIP) system and the MP spatial information is obtained from an off-axis camera system. A machine learning aided image analysis method is employed to retrieve the spatial distribution of MPs within the corresponding part’s coordinates system. Then, the MP signature maps (MPSMs) are reconstructed by mapping the STWIP measured MP signatures to the registered MP coordinates. Further, a long short-term memory (LSTM) neural network is developed for estimating the layer surface topography from the registered MPSMs. The obtained results indicate that the layer surface topography can be more accurately estimated by using MP temperature signature rather than MP intensity and/or area signatures as in common practice. Finally, our developed methods for MP monitoring, registration, and MP-surface topography prediction offer advanced capabilities for the online detection of process anomalies and part defects.

36 MATERIALS SCIENCE↗

Optimizing checkpoint data placement with guaranteed burst buffer endurance in large-scale hierarchical storage systems

Non-volatile devices, such as SSDs, will be an integral part of the deepening storage hierarchy on large-scale HPC systems. These devices can be on the compute nodes as part of a distributed burst buffer service or they can be external. Wherever they are located in the hierarchy, one critical design issue is the SSD endurance under the write-heavy workloads, such as the checkpoint I/O for scientific applications. For these environments, it is widely assumed that checkpoint operations can occur once every 60 min and for each checkpoint step as much as half of the system memory can be written out. Unfortunately, for large-scale HPC applications, the burst buffer SSDs can be worn out much more quickly given the extensive amount of data written at every checkpoint step. One possible solution is to control the amount of data written by reducing the checkpoint frequency. However, a direct effect caused by reduced checkpoint frequency is the increased vulnerability window of system failures and therefore potentially wasted computation time, especially for large-scale compute jobs.

Computer Science↗

Structural signature and transition dynamics of Sb 2 Te 3 melt upon fast cooling

Crystalline Sb 2 Te 3 is widely studied due to its important applications in memory materials and topological insulators. The liquid and amorphous structures of this compound as well as the dynamics upon quenching, however, are yet to be fully understood. In this paper, we have systematically studied the dynamical properties and local structure of Sb 2 Te 3 at different temperatures using ab initio molecular dynamics simulations. The calculated structure factors agree well with the experimental results. The atomic number density and mean-squared displacement as a function of temperature clearly indicate three states as the temperature decreases, namely, melt, undercooled liquid and glass state, respectively. By analyzing the chemical environments and bond-angle distribution functions, we demonstrate that the most probable short-range motifs in the Sb 2 Te 3 system are defective octahedrons, and they are connected with each other via four-fold rings. Finally, this interesting structural feature may be responsible for the high fragility and easy phase transition upon glass forming that is applied in memory devices.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Quantum key distribution over probabilistic quantum repeaters

A feasible route toward implementing long-distance quantum key distribution (QKD) systems relies on probabilistic schemes for entanglement distribution and swapping as proposed in the work of Duan, Lukin, Cirac, and Zoller (DLCZ) [Nature (London) 414, 413 (2001)]. Here, we calculate the conditional throughput and fidelity of entanglement for DLCZ quantum repeaters by accounting for the DLCZ self-purification property in the presence of multiple excitations in the ensemble memories as well as loss and other sources of inefficiency in the channel and measurement modules. We then use our results to find the generation rate of secure key bits for QKD systems that rely on DLCZ quantum repeaters. We compare the key generation rate per logical memory employed in the two cases with and without a repeater node. We find the crossover distance beyond which the repeater system outperforms the nonrepeater one. That provides us with the optimum internode distancing in quantum repeater systems. We also find the optimal excitation probability at which the QKD rate peaks. Such an optimum probability, in most regimes of interest, is insensitive to the total distance.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

NSTX-U advances in real-time deterministic PCIe-based internode communication

Distributing control mechanisms across modern commercial off the shelf (COTS) GNU/Linux systems often introduces difficult to mitigate non-deterministic behavior. Existing methods to address this problem involve non-real-time technologies such as Remote Direct Memory Access (RDMA) over Infiniband or custom Ethernet solutions, such as RDMA over Converged Ethernet (RoCE) or userspace Ethernet drivers, that trade determinism for ease of use or lower cost. The National Spherical Torus Experiment Upgrade (NSTX-U) is pursuing a new design that allows direct communication between heterogeneous systems with scalable, microsecond latency with 1 μs of jitter on that latency, outside of the constant transmission delay at the physical layer. The future design of the NSTX-U Real-time Communication System will utilize direct PCIe-to-PCIe communication with kernel support tuned for low overhead, allowing two (or more, through a switch) real-time (RT) systems to communicate and share resources as one larger entity. As a result, this greatly increases the processing capability of the primary Plasma Control System (PCS), turning previously insurmountable computational challenges into a more manageable divide and conquer parallel task.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Frog: Asynchronous Graph Processing on GPU with Hybrid Coloring Model

GPUs have been increasingly used to accelerate graph processing for complicated computational problems regarding graph theory. Many parallel graph algorithms adopt the asynchronous computing model to accelerate the iterative convergence. Unfortunately, the consistent asynchronous computing requires locking or atomic operations, leading to significant penalties/overheads when implemented on GPUs. As such, coloring algorithm is adopted to separate the vertices with potential updating conflicts, guaranteeing the consistency/correctness of the parallel processing. Common coloring algorithms, however, may suffer from low parallelism because of a large number of colors generally required for processing a large-scale graph with billions of vertices. We propose a light-weight asynchronous processing framework called Frog with a preprocessing/hybrid coloring model. The fundamental idea is based on Pareto principle (or 80-20 rule) about coloring algorithms as we observed through masses of realworld graph coloring cases. We find that a majority of vertices (about 80%) are colored with only a few colors, such that they can be read and updated in a very high degree of parallelism without violating the sequential consistency. Accordingly, our solution separates the processing of the vertices based on the distribution of colors. In this work, we mainly answer three questions: (1) how to partition the vertices in a sparse graph with maximized parallelism, (2) how to process large-scale graphs that cannot fit into GPU memory, and (3) how to reduce the overhead of data transfers on PCIe while processing each partition. Here, we conduct experiments on real-world data (Amazon, DBLP, YouTube, RoadNet-CA, WikiTalk and Twitter) to evaluate our approach and make comparisons with well-known non-preprocessed (such as Totem, Medusa, MapGraph and Gunrock) and preprocessed (Cusha) approaches, by testing four classical algorithms (BFS, PageRank, SSSP and CC). On all the tested applications and datasets, Frog is able to significantly outperform existing GPU-based graph processing systems except Gunrock and MapGraph. MapGraph gets better performance than Frog when running BFS on RoadNet-CA. The comparison between Gunrock and Frog is inconclusive. Frog can outperform Gunrock more than 1.04X when running PageRank and SSSP, while the advantage of Frog is not obvious when running BFS and CC on some datasets especially for RoadNet-CA.

97 MATHEMATICS AND COMPUTING↗

GridLAB-D/SG

GridLAB-D is a new power system simulation tool that provides valuable information to users who design and operate electric power transmission and distribution systems, and to utilities that wish to take advantage of the latest smart grid technology. This special release of GridLAB-D was developed to study the proposed Smart Grid technology that is used by Battelle Memorial Institute in the AEP gridSMART demonstration project in Northeast Columbus, Ohio.

Chassin, DavidP.↗

Machine Learning for Memory Reduction in the Implicit Monte Carlo Simulations of Thermal Radiative Transfer [Slides]

Project Goal: Use parametric Machine Learning methods in order to reduce memory requirements at checkpointing & restarting in the IMC simulations of Thermal Radiative Transfer using: Expectation Maximization and Weighted Gaussian Mixture Model-based approach for `particle-data compression', introduced in Plasma Physics to model Maxwellian particle distributions by Luis Chacon and Guangye Chen; Expectation Maximization with Weighted Hyper-Erlang Model in order to compress isotropic IMC particle data in the frequency domain; and Expectation Maximization and von Mises-Fisher Mixture Model for compression of anisotropic IMC particle data in the angular domain (work-in-progress).

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Plasma enhanced multistate storage capability of single ZnO nanowire based memory

Multiple-state storage (MSS) is common for resistive random access memory, but the effects of plasma treatment on the MSS and the switching properties have been scarcely investigated. We have demonstrated a stable four-state storage capability of single zinc oxide nanowire (ZnO NW) treated by argon plasma. The electrical switching is attributed to the electron trapping and detrapping from the oxygen vacancies (V{sub o}s). The MSS relates to the electrical-thermal induced distribution of the V{sub o}s which determines electron transport behavior to show different resistance states. Additionally, programming (set and reset) voltages decrease with plasma treatment due to the thickness modulation of the interface barrier.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Carbon doping in GeTe drives differences in local structure and properties

Advances in low-power, energy-efficient information storage and computing require understanding and controlling the atomic and nanoscale structures of functional materials, such as phase-change materials. Phase-change memory technology enables nonvolatile, low-power memory in devices by storing information through reversible changes in a phase-change material's atomic structure (i.e., transformations between amorphous and crystalline phases) that have corresponding changes in properties, including electronic resistivity and optical reflectivity. Here, we apply complementary X-ray absorption spectroscopy and X-ray pair distribution function analyses to experimentally identify the local- and medium-range atomic structure differences of GeTe and C-doped GeTe thin films. Upon controlled heating, composition- and temperature-dependent atomic structure evolution in GeTe and C-doped GeTe films shows differences in bonding behavior and local structure that directly influence crystallization onset temperature. We find that the introduction of C interrupts Ge–Ge bonds in amorphous GeTe, altering the as-deposited structure to be more similar to the distorted rocksalt structure of crystalline α–GeTe. The change alters the response of the amorphous atomic structure to heating and also lowers the crystallization onset temperature, from 230 °C in GeTe to 220 °C in the C-doped film. The combined insights from both X-ray techniques provide understanding of structural transformations that enables the development and optimization of next-generation memory and computing materials.

36 MATERIALS SCIENCE↗

Estimation of stochastic volatility with long memory for index prices of FTSE Bursa Malaysia KLCI

In recent years, modeling in long memory properties or fractionally integrated processes in stochastic volatility has been applied in the financial time series. A time series with structural breaks can generate a strong persistence in the autocorrelation function, which is an observed behaviour of a long memory process. This paper considers the structural break of data in order to determine true long memory time series data. Unlike usual short memory models for log volatility, the fractional Ornstein-Uhlenbeck process is neither a Markovian process nor can it be easily transformed into a Markovian process. This makes the likelihood evaluation and parameter estimation for the long memory stochastic volatility (LMSV) model challenging tasks. The drift and volatility parameters of the fractional Ornstein-Unlenbeck model are estimated separately using the least square estimator (lse) and quadratic generalized variations (qgv) method respectively. Finally, the empirical distribution of unobserved volatility is estimated using the particle filtering with sequential important sampling-resampling (SIR) method. The mean square error (MSE) between the estimated and empirical volatility indicates that the performance of the model towards the index prices of FTSE Bursa Malaysia KLCI is fairly well.

97 MATHEMATICS AND COMPUTING↗

DNTTD (Distributed Non-Negative Tensor Train Decomposition)

The era of exascale computing opens new venues for innovations and discoveries in many scientific, engineering, and commercial fields. However, with the exa flops also come the extra-large high-dimensional data generated by high performance computing. High-dimensional data is presented as multidimensional arrays, aka tensors. The presence of latent (not directly observable) structures in the tensor allows a unique representation and compression of the data by classical tensor factorization techniques. However, the classical tensor methods are not always stable or they can be exponential in their memory requirements, which makes them not suitable for high-dimensional tensors. Tensor train (TT) is a state-of-the-art tensor network introduced for factorization of high-dimensional tensors. TT transforms the initial high-dimensional tensor in a network of three-dimensional tensors that requires only a linear storage. Many real-world data, such as, density, temperature, population, probability, etc., are non-negative and for an easy interpretation, the algorithms preserving non-negativity are preferred. Here, we introduce a distributed non-negative tensor-train and demonstrate its scalability and the compression on synthetic and real world big datasets.

Bhattarai, Manish↗

OpenSHMEM Sets and Groups: An Approach to Worksharing and Memory Management

Collective operations in the OpenSHMEM programming model are defined over an active set, which is a grouping of Processing Elements (PEs) based on a triple of information including the starting PE, a log2 stride, and the size of the active set. In addition to the active set, collectives require Users to allocate and initialize synchronization (i.e., pSync) and scratchpad (i.e., pWrk) buffers for use by the collective operations. While active sets and the user-defined buffers were previously useful based on hardware and algorithmic considerations, future systems and applications require us to re-evaluate these concepts. In this paper, we propose Sets and Groups as abstractions to create persistent, flexible groupings of PEs (i.e., Sets) and couple these groups of PEs with memory spaces (i.e., Groups), which remove the allocation and initialization burden from the User. To evaluate Sets and Groups, we perform multiple micro-benchmarks to determine the overhead of these abstractions and demonstrate their utility by implementing a distributed All-Pairs Shortest Path (APSP) application, which we evaluate using multiple synthetic and real-world graphs.

Aderholdt, William↗

Outcomes and Prognostic Variables in Adenoid Cystic Carcinoma of the Head and Neck: A Recent Experience

Purpose: To analyze the recent experience of patients with adenoid cystic carcinoma treated with radiation therapy at Memorial Sloan-Kettering Cancer Center. Methods and Materials: From 1990 to 2004, a total of 59 patients with a diagnosis of primary adenoid cystic carcinoma of the head and neck received radiation therapy at our institution. The subsite distribution was oral cavity, 28% (n = 17); paranasal sinuses, 22% (n = 13); parotid, 14% (n = 8); submandibular, 14% (n = 8); oropharynx, 10% (n = 6); sublingual, 3% (n = 2); nasopharynx, 3% (n = 2); and other, 5% (n = 3). T Stage distribution was T1, 34% (n = 20); T2, 19% (n = 11); T3, 14% (n = 8); and T4, 34% (n = 20). Twenty-nine percent of patients (n = 17) were treated with intensity-modulated radiation therapy; 25% (n =15), with three-dimensional conformal therapy, and the remainder, with conventional techniques. Ninety percent (n = 53) of patients received treatment including the base of skull. Results: Median follow-up for surviving patients was 5.9 years. Five-year and 10-year rates of local control and distant metastases-free survival were 91%/81% and 81%/49%, respectively. Five-year and 10-year rates of disease-free and overall survival were 76%/40% and 87%/65%, respectively. On univariate analysis, stage T4 (p = 0.004) and gross/clinical nerve involvement (p = 0.002) were associated with decreased progression free survival, whereas stage T4 and lymph node involvement were associated with decreased overall survival (p = 0.046 and p < 0.001, respectively). Conclusions: Radiation therapy in combination with surgery produces excellent rates of local control, although distant metastases account for a high proportion of failures. Routine treatment to the base of skull reduces the significance of histologic perineural invasion, but major nerve involvement remains an adverse prognostic factor.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Retention modeling for ultra-thin density of Cu-based conductive bridge random access memory (CBRAM)

We investigate the effect of Cu concentration On-state resistance retention characteristics of W/Cu/Ti/HfO{sub 2}/Pt memory cell. The development of RRAM device for application depends on the understanding of the failure mechanism and the key parameters for device optimization. In this study, we develop analytical expression for cations (Cu{sup +}) diffusion model using Gaussian distribution for detailed analysis of data retention time at high temperature. It is found that the improvement of data retention time depends not only on the conductive filament (CF) size but also on Cu atoms concentration density in the CF. Based on the simulation result, better data retention time is observed for electron wave function associated with Cu{sup +} overlap and an extended state formation. This can be verified by analytical calculation of Cu atom defects inside the filament, based on Cu{sup +} diffusion model. The importance of Cu diffusion for the device reliability and the corresponding local temperature of the filament were analyzed by COMSOL Multiphysics simulation.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

MICADO: Parallel implementation of a 2D-1D iterative algorithm for the 3D neutron transport problem in prismatic geometries

The large increase in computing power over the past few years now makes it possible to consider developing 3D full-core heterogeneous deterministic neutron transport solvers for reference calculations. Among all approaches presented in the literature, the method first introduced in [1] seems very promising. It consists in iterating over resolutions of 2D and ID MOC problems by taking advantage of prismatic geometries without introducing approximations of a low order operator such as diffusion. However, before developing a solver with all industrial options at EDF, several points needed to be clarified. In this work, we first prove the convergence of this iterative process, under some assumptions. We then present our high-performance, parallel implementation of this algorithm in the MICADO solver. Benchmarking the solver against the Takeda case shows that the 2D-1D coupling algorithm does not seem to affect the spatial convergence order of the MOC solver. As for performance issues, our study shows that even though the data distribution is suited to the 2D solver part, the efficiency of the ID part is sufficient to ensure a good parallel efficiency of the global algorithm. After this study, the main remaining difficulty implementation-wise is about the memory requirement of a vector used for initialization. An efficient acceleration operator will also need to be developed. (authors)

97 MATHEMATICS AND COMPUTING↗

Improved characteristics of amorphous indium-gallium-zinc-oxide-based resistive random access memory using hydrogen post-annealing

The authors report an improvement in resistive switching (RS) characteristics of amorphous indium-gallium-zinc-oxide (a-IGZO)-based resistive random access memory devices using hydrogen post-annealing. Because this a-IGZO thin film has oxygen off-stoichiometry in the form of deficient and excessive oxygen sites, the film properties can be improved by introducing hydrogen atoms through the annealing process. After hydrogen post-annealing, the device exhibited a stable bipolar RS, low-voltage set and reset operation, long retention (>10{sup 5 }s), good endurance (>10{sup 6} cycles), and a narrow distribution in each current state. The effect of hydrogen post-annealing is also investigated by analyzing the sample surface using X-ray photon spectroscopy and atomic force microscopy.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗