Publications

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

High-performance computing (HPC) systems enable scientists to numerically model complex phenomena in many important physical systems. The next major milestone in the development of HPC systems is the construction of the rst supercomputer capable executing more than an exa op, 10¹⁸ oating point operations per second. On systems of this scale, failures will occur much more frequently than on current systems. As a result, resilience is a key obstacle to building next-generation extremescale systems. Coordinated checkpointing is currently the most widely-used mechanism for handling failures on HPC systems. Although coordinated checkpointing remains e ective on current systems, increasing the scale of today's systems to build next-generation systems will increase the cost of fault tolerance as more and more time is taken away from the application to protect against or recover from failure. Rollback avoidance techniques seek to mitigate the cost of checkpoint/restart by allowing an application to continue its execution rather than rolling back to an earlier checkpoint when failures occur. These techniqes include failure prediction and preventive migration, replicated computation, fault-tolerant algorithms, and softwarebased memory fault correction. In this thesis, we examine how rollback avoidance techniques can be used to address failures on extreme-scale systems. Using a combination of analytic modeling and simulation, we evaluate the potential impact of rollback avoidance on these systems. We then present a novel rollback avoidance technique that exploits similarities in application memory. Finally, we examine the feasibility of using this technique to protect against memory faults in kernel memory.

Two fundamental approximations in macroscale solid-mechanics modeling are (1) the assumption of scale separation in homogenization theory and (2) the use of a macroscopic plasticity material model that represents, in a mean sense, the multitude of inelastic processes occurring at the microscale. With the goal of quantifying the errors induced by these approximations on engineering quantities of interest, we perform a set of direct numerical simulations (DNS) in which polycrystalline microstructures are embedded throughout a macroscale structure. The largest simulations model over 50,000 grains. The microstructure is idealized using a randomly close-packed Voronoi tessellation in which each polyhedral Voronoi cell represents a grain. An face centered cubic crystal-plasticity model is used to model the mechanical response of each grain. The overall grain structure is equiaxed, and each grain is randomly oriented with no overall texture. The detailed results from the DNS simulations are compared to results obtained from conventional macroscale simulations that use homogeneous isotropic plasticity models. The macroscale plasticity models are calibrated using a representative volume element of the idealized microstructure. Ultimately, we envision that DNS modeling will be used to gain new insights into the mechanics of material deformation and failure.

Persistent neurogenesis in the dentate gyrus produces immature neurons with high intrinsic excitability and low levels of inhibition that are predicted to be more broadly responsive to afferent activity than mature neurons. Mounting evidence suggests that these immature neurons are necessary for generating distinct neural representations of similar contexts, but it is unclear how broadly responsive neurons help distinguish between similar patterns of afferent activity. Here we show that stimulation of the entorhinal cortex in mouse brain slices paradoxically generates spiking of mature neurons in the absence of immature neuron spiking. Immature neurons with high intrinsic excitability fail to spike due to insufficient excitatory drive that results from low innervation rather than silent synapses or low release probability. Our results suggest that low synaptic connectivity prevents immature neurons from responding broadly to cortical activity, potentially enabling excitable immature neurons to contribute to sparse and orthogonal dentate representations.

Grain boundary engineered materials are of immense interest for their resistance to hydrogen embrittlement. This work builds on the work undertaken in Part I on the thermodynamic stability and structure of misoriented grain boundaries vicinal to the Σ3 (111) <11¯0> (coherent-twin) boundary to examine hydrogen segregation to those boundaries. The segregation of hydrogen reflects the asymmetry of the boundary structure with the sense of rotation of the grains about the coherent-twin boundary, and the temperature-dependent structural transition present in one sense of misorientation. This work also finds that the presence of hydrogen affects a change in structure of the boundaries with increasing concentration. The structural change effects only one sense of misorientation and results in the reduction in length of the emitted stacking faults. Moreover, the structural change results in the generation of occupied sites populated by more strongly bound hydrogen. The improved understanding of misoriented twin grain boundary structure and the effect on hydrogen segregation resulting from this work is relevant to higher length-scale models. To that end, we examine commonly used metrics such as free volume and atomic stress at the boundary. In conclusion, free volume is found not to be useful as a surrogate for predicting the degree of hydrogen segregation, whereas the volumetric virial stress reliably predicts the locations of hydrogen segregation and exclusion at concentrations below saturation or the point where structural changes are induced by increasing hydrogen concentration.

This paper evaluates the performance of multiphysics coupling algorithms applied to a light water nuclear reactor core simulation. The simulation couples the k-eigenvalue form of the neutron transport equation with heat conduction and subchannel flow equations. We compare Picard iteration (block Gauss-Seidel) to Anderson acceleration and multiple variants of preconditioned Jacobian-free Newton-Krylov (JFNK). The performance of the methods are evaluated over a range of energy group structures and core power levels. A novel physics-based approximation to a Jacobian-vector product has been developed to mitigate the impact of expensive on-line cross section processing steps. Numerical simulations demonstrating the efficiency of JFNK and Anderson acceleration relative to standard Picard iteration are performed on a 3D model of a nuclear fuel assembly. Both criticality (k-eigenvalue) and critical boron search problems are considered.

This article discusses the problem of identifying extreme climate events such as intense storms within large climate data sets. The basic storm detection algorithm is reviewed, which splits the problem into two parts: a spatial search followed by a temporal correlation problem. Two specific implementations of the spatial search algorithm are compared: the commonly used grid point search algorithm is reviewed, and a new algorithm called Stride Search is introduced. The Stride Search algorithm is defined independently of the spatial discretization associated with a particular data set. Results from the two algorithms are compared for the application of tropical cyclone detection, and shown to produce similar results for the same set of storm identification criteria. Differences between the two algorithms arise for some storms due to their different definition of search regions in physical space. The physical space associated with each Stride Search region is constant, regardless of data resolution or latitude, and Stride Search is therefore capable of searching all regions of the globe in the same manner. Stride Search's ability to search high latitudes is demonstrated for the case of polar low detection. Wall clock time required for Stride Search is shown to be smaller than a grid point search of the same data, and the relative speed up associated with Stride Search increases as resolution increases.

Abstract not provided.

The restriction of adult neurogenesis to only a handful of regions of the brain is suggestive of some shared requirement for this dramatic form of structural plasticity. However, a common driver across neurogenic regions has not yet been identified. Computational studies have been invaluable in providing insight into the functional role of new neurons; however, researchers have typically focused on specific scales ranging from abstract neural networks to specific neural systems, most commonly the dentate gyrus area of the hippocampus. These studies have yielded a number of diverse potential functions for new neurons, ranging from an impact on pattern separation to the incorporation of time into episodic memories to enabling the forgetting of old information. This review will summarize these past computational efforts and discuss whether these proposed theoretical functions can be unified into a common rationale for why neurogenesis is required in these unique neural circuits.

In the event of contamination in a water distribution network (WDN), source identification (SI) methods that analyze sensor data can be used to identify the source location(s). Knowledge of the source location and characteristics are important to inform contamination control and cleanup operations. Various SI strategies that have been developed by researchers differ in their underlying assumptions and solution techniques. The following manuscript presents a systematic procedure for testing and evaluating SI methods. The performance of these SI methods is affected by various factors including the size of WDN model, measurement error, modeling error, time and number of contaminant injections, and time and number of measurements. This paper includes test cases that vary these factors and evaluates three SI methods on the basis of accuracy and specificity. The tests are used to review and compare these different SI methods, highlighting their strengths in handling various identification scenarios. These SI methods and a testing framework that includes the test cases and analysis tools presented in this paper have been integrated into EPA's Water Security Toolkit (WST), a suite of software tools to help researchers and others in the water industry evaluate and plan various response strategies in case of a contamination incident. Finally, a set of recommendations are made for users to consider when working with different categories of SI methods.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Our first purpose here is to offer to a general technical and policy audience a perspective on whether the supercomputing community should focus on improving the efficiency of supercomputing systems and their use rather than on building larger and ostensibly more capable systems that are used at low efficiency. After first summarizing our content and defining some necessary terms, we give a concise answer to this question. We then set this in context by characterizing performance of current supercomputing systems on a variety of benchmark problems and actual problems drawn from workloads in the national security, industrial, and scientific context. Along the way we answer some related questions, identify some important technological trends, and offer a perspective on the significance of these trends. Our second purpose is to give a reasonably broad and transparent overview of the related issue space and thereby to better equip the reader to evaluate commentary and controversy concerning supercomputing performance. For example, questions repeatedly arise concerning the Linpack benchmark and its predictive power, so we consider this in moderate depth as an example. We also characterize benchmark and application performance for scientific and engineering use of supercomputers and offer some guidance on how to think about these. Examples here are drawn from traditional scientific computing. Other problem domains, for example, data analytics, have different performance characteristics that are better captured by different benchmark problems or applications, but the story in those domains is similar in character and leads to similar conclusions with regard to the motivating question.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Here, grain boundary-engineered materials are of immense interest for their corrosion resistance, fracture resistance and microstructural stability. This work contributes to a larger goal of understanding both the structure and thermodynamic properties of grain boundaries vicinal (within ±30°) to the Σ3(1 1 1) <1 1¯0> (coherent twin) boundary which is found in grain boundary-engineered materials. The misoriented boundaries vicinal to the twin show structural changes at elevated temperatures. In the case of nickel, this transition temperature is substantially below the melting point and at temperatures commonly reached during processing, making the existence of such boundaries very likely in applications. Thus, the thermodynamic stability of such features is thoroughly investigated in order to predict and fully understand the structure of boundaries vicinal to twins. Low misorientation angle grain boundaries (|θ| ≲ 16°) show distinct ±1/3(1 1 1) disconnections which accommodate misorientation in opposite senses. The two types of disconnection have differing low-temperature structures which show different temperature-dependent behaviours with one type undergoing a structural transition at approximately 600 K. At misorientation angles greater than approximately ±16°, the discrete disconnection nature is lost as the disconnections merge into one another. Free energy calculations demonstrate that these high-angle boundaries, which exhibit a transition from a planar to a faceted structure, are thermodynamically more stable in the faceted configuration.

The electrical conductivity of materials under extremes of temperature and pressure is of crucial importance for a wide variety of phenomena, including planetary modeling, inertial confinement fusion, and pulsed power based dynamic materials experiments. There is a dearth of experimental techniques and data for highly compressed materials, even at known states such as along the principal isentrope and Hugoniot, where many pulsed power experiments occur. We present a method for developing, calibrating, and validating material conductivity models as used in magnetohydrodynamic (MHD) simulations. The difficulty in calibrating a conductivity model is in knowing where the model should be modified. Our method isolates those regions that will have an impact. It also quantitatively prioritizes which regions will have the most beneficial impact. Finally, it tracks the quantitative improvements to the conductivity model during each incremental adjustment. In this paper, we use an experiment on Sandia National Laboratories Z-machine to isentropically launch multiple flyer plates and, with the MHD code ALEGRA and the optimization code DAKOTA, calibrated the conductivity such that we matched an experimental figure of merit to +/-1%.

A minimax estimator has the minimum possible error ("risk") in the worst case. We construct the first minimax estimators for quantum state tomography with relative entropy risk. The minimax risk of nonadaptive tomography scales as O(1/N) - in contrast to that of classical probability estimation, which is O(1/N) - where N is the number of copies of the quantum state used. We trace this deficiency to sampling mismatch: future observations that determine risk may come from a different sample space than the past data that determine the estimate. This makes minimax estimators very biased, and we propose a computationally tractable alternative with similar behavior in the worst case, but superior accuracy on most states.

Abstract not provided.

Geometric partitioning is fast and effective for load-balancing dynamic applications, particularly those requiring geometric locality of data (particle methods, crash simulations). We present, to our knowledge, the first parallel implementation of a multidimensional-jagged geometric partitioner. In contrast to the traditional recursive coordinate bisection algorithm (RCB), which recursively bisects subdomains perpendicular to their longest dimension until the desired number of parts is obtained, our algorithm does recursive multi-section with a given number of parts in each dimension. By computing multiple cut lines concurrently and intelligently deciding when to migrate data while computing the partition, we minimize data movement compared to efficient implementations of recursive bisection. We demonstrate the algorithm's scalability and quality relative to the RCB implementation in Zoltan on both real and synthetic datasets. Our experiments show that the proposed algorithm performs and scales better than RCB in terms of run-time without degrading the load balance. Our implementation partitions 24 billion points into 65,536 parts within a few seconds and exhibits near perfect weak scaling up to 6K cores.

Abstract not provided.

For the purposes of making reliable first-principles predictions of defect energies in semiconductors, it is crucial to distinguish between effective-mass-like defects, which cannot be treated accurately with existing supercell methods, and deep defects, for which density functional theory calculations can yield reliable predictions of defect energy levels. The gallium antisite defect GaAs is often associated with the 78/203 meV shallow double acceptor in Ga-rich gallium arsenide. Within a conceptual framework of level patterns, analyses of structure and spin stabilization can be used within a supercell approach to distinguish localized deep defect states from shallow acceptors such as BAs. This systematic approach determines that the gallium antisite supercell results has signatures inconsistent with an effective mass state and cannot be the 78/203 shallow double acceptor. The properties of the Ga antisite in GaAs are described, total energy calculations that explicitly map onto asymptotic discrete localized bulk states predict that the Ga antisite is a deep double acceptor and has at least one deep donor state.

Abstract not provided.

Abstract not provided.