TOD-Tree: Task-Overlapped Direct Send Tree Image Compositing for Hybrid MPI Parallelism and GPUs
Not provided.
SEARCH · Engineering Papers
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.
Not provided.
the goal of this work was to develop new algorithmic techniques for solving large-scale numerical optimization problems, focusing on problems classes that have proven to be among the most challenging for practitioners: those involving uncertainty and those involving nonconvexity. This research advanced the state-of-the-art in solving mixed integer linear programs containing symmetry, mixed integer nonlinear programs, and stochastic optimization problems. The focus of the work done in the continuation was on Mixed Integer Nonlinear Programs (MINLP)s and Mixed Integer Linear Programs (MILP)s, especially those containing a great deal of symmetry.
The ability to control network dynamics is essential for ensuring desirable functionality of many technological, biological, and social systems. Such systems often consist of a large number of network elements, and controlling large-scale networks remains challenging because the computation and communication requirements increase prohibitively fast with network size. Here, we introduce a notion of network locality that can be exploited to make the control of networks scalable, even when the dynamics are nonlinear. We show that network locality is captured by an information metric and is almost universally observed across real and model networks. In localized networks, the optimal control actions and system responses are both shown to be necessarily concentrated in small neighborhoods induced by the information metric. This allows us to develop localized algorithms for determining network controllability and optimizing the placement of driver nodes. This also allows us to develop a localized algorithm for designing local feedback controllers that approach the performance of the corresponding best global controllers, while incurring a computational cost orders-of-magnitude lower. Here, we validate the locality, performance, and efficiency of the algorithms in Kuramoto oscillator networks, as well as three large empirical networks: synchronization dynamics in the Eastern US power grid, epidemic spreading mediated by the global air-transportation network, and Alzheimer’s disease dynamics in a human brain network. Taken together, our results establish that large networks can be controlled with computation and communication costs comparable to those for small networks.
Purpose: The authors developed a computer algorithm to automatically evaluate images of the American College of Radiology (ACR) mammography accreditation phantom. Methods: The developed algorithm consist of the edge detection of wax insert, nonuniformity correction of background, and correction for magnification and also calculate the cross-correlation coefficient by image matching technique. The algorithm additionally evaluates target shape for fibers, target contrast for speck groups, and target circularity for masses. To obtain an ideal template image without noise and spatial resolution loss, the wax insert containing the embedded test pattern was extracted from the phantom and radiographed. Two template images and ten test phantom images were prepared for this study. The results of evaluation using the algorithm outputs were compared with the averaged results of observer studies by six skilled observers. Results: In comparing the results from the algorithm outputs with the results of observers, the authors found that the computer outputs were well correlated with the evaluations by observers, and they indicate the quality of the phantom image. The correlation coefficients between results of observer studies and two outputs of computer algorithm, i.e., the cross-correlation coefficient by template matching and indices of target shape for fibers, were 0.89 (95% confidence interval, 0.82-0.93; hereinafter the same) and 0.85 (0.76-0.91). The correlation coefficients between observer's results and two outputs: the cross-correlation coefficient and indices of target contrast for speck groups, were 0.83 (0.79-0.86) and 0.85 (0.81-0.88) and between observer's results and two outputs: the cross-correlation coefficient and indices of target circularity for masses, were 0.90 (0.84-0.94) and 0.87 (0.77-0.92). Conclusions: Image evaluation using the ACR phantom is indispensable in quality control of a mammography system. The proposed algorithm is useful for quality control and image evaluation of mammography units.
A (core-collapse) supernova is the final death call of a massive star during which a gigantic amount of a special kind of elementary particles known as neutrinos are released for a brief period of time. An earlier work by the PI and his collaborators has shown that the dense neutrino gas deep inside the supernova can experience "flavor transformation" or "oscillations" in a collective fashion, a macroscopic quantum phenomenon spanning over distances of 100-1000 kilometers. During this process neutrinos of different energies and propagation directions change their identities simultaneously. This phenomenon may be a key to understanding the mechanism of supernova explosion and the origin of many of the chemical elements found on the earth which were produced in the supernovae exploded in the past. The previous understanding of neutrino oscillations in supernovae was based on a stationary 3-dimensional model with 1 spatial dimension and 2 momentum dimensions. In this "neutrino bulb model" neutrinos are emitted from a spherically symmetric surface and they are decoupled from the motion of matter and the production of chemical elements. In order to accurately model the neutrino oscillations in supernovae and determine its physical consequences, sophisticated 7-dimensional (1 temporal dimension + 3 spatial dimensions + 3 momentum dimensions) modelling of neutrino transport must be performed self-consistently together with the hydrodynamic simulation of the flow of energy and matter inside the supernova and with the calculation of the production and destruction of chemical elements through a large nucleosynthesis network. Although it will be long journey to achieve the lofty goal, our project has made important progress in three different fronts towards this goal. In the first front we explored new computing hardware on which the next generation simulation codes may be run. We ported the neutrino bulb code to the platform of Graphics Processing Unit (GPU) and then later developed a new bulb code that can be run on supercomputers equipped with the Intel Xeon CPUs and/or the Xeon Phi coprocessors. In the second front we developed new algorithms that can be used towards computing neutrino oscillations in multi-dimensional models. We have developed a moment expansion method which is approximately 10 times more efficient than the old algorithm. We have also developed numerical codes to solve neutrino oscillations in toy models with two spatial dimensions. In the last front we used analytic methods to study neutrino oscillations in more sophisticated models, e.g. of multiple spatial dimensions and/or with time dependence. By analyzing the neutrino oscillations in toy models with two spacial dimensions we found that the approximate spacial translation symmetry, which is similar to the spherical symmetry in the neutrino bulb model, can be broken spontaneously as neutrino oscillations begin. By analyzing a time-dependent neutrino bulb model we found that certain modes of neutrino oscillations that are suppressed in the stationary model can become active in the time-dependent model. We have also developed theories which give insights to how ordinary matter may affect neutrino oscillations in supernovae and other astrophysical environments.
A team led by NTRCI is working to improve the roll and yaw stability of heavy duty combination trucks through developing stability algorithms, assembling demonstration hardware, and investigating robust wireless communication. Modern electronic stability control (ESC) products automatically slow a vehicle rounding a corner too quickly or apply individual brakes when necessary to improve the steering characteristics of a vehicle. Air brake systems in North America provide no electronic communication between a tractor and semitrailer, limiting the degree to which control systems can be optimized. Prior research has demonstrated stability improvements where dynamic measurements and control commands are communicated between units of a vehicle. Three related activities were undertaken: (1) Develop an algorithm for the optimum yaw and roll control of a combination vehicle. Vehicle state parameters needed to control the vehicle and the proper brake response were determined. An integrated stability control for the tractor and semitrailer requires communication between the two units. Dynamic models were used to assess the algorithm. (2) Implement the ESC algorithm in the laboratory. Hardware components suitable for the harsh environment for measurement, sensor-to-controller communication, and semitrailer-to-tractor communication and brake actuation were specified and assembled as a working system. The goal was to collect the needed vehicle state information, transmit the information to the ESC system, and then actuate the brakes in response to controller commands. (3) Develop a wireless network with the data rate and reliability necessary to communicate dynamic signals for a vehicle stability control system. Adaptive connectivity-aware, multi-hop routing was selected because it can perform in the harsh environment where packet collisions and fading often will exist. The protocol is to give high priority to urgent messages.
What has made the ASR program unique is the amount of information that is available. The suite of recently deployed instruments significantly expands the scope of the program (Mather and Voyles, 2013). The breadth of this information allows us to pose sophisticated process-level questions. Our ASR project, now entering its third year, has been about developing algorithms that use this information in ways that fully exploit the new capacity of the ARM data streams. Using optimal estimation (OE) and Markov Chain Monte Carlo (MCMC) inversion techniques, we have developed methodologies that allow us to use multiple radar frequency Doppler spectra along with lidar and passive constraints where data streams can be added or subtracted efficiently and algorithms can be reformulated for various combinations of hydrometeors by exchanging sets of empirical coefficients. These methodologies have been applied to boundary layer clouds, mixed phase snow cloud systems, and cirrus.
Residential and commercial buildings in China, India, the United States (US), United Kingdom (UK), and Italy consume 39-45% of each nation's primary energy. Building energy models can be used to automatically optimize the return-on-investment for retrofits to improve a building’s energy efficiency. However, with an average of 3,000 building descriptors necessary to accurately simulate a single building, there is a market need to reduce the transaction cost for creating a more robust model for simulating every building in a city and accurately estimate savings prior to capital expenditures.We used two of the world’s fastest supercomputers, assembled unique datasets, and developed innovative algorithms for big data mining to assess different methods to create an accurate building energy model. The team has leveraged a total of eight high performance computing resources and 218 servers to analyze the best methods, metrics, and algorithms for creating an accurate building energy model beyond current industry standards necessary for private-sector financing. The project developed the world’s fastest buildings simulator, has completed over 8 million simulations totaling over 300TB, and mined this data with over 130,000 parallel artificial intelligence algorithms. This was used to quantify accuracy of AI-developed calibration algorithms with results that surpass industry standard guidelines and can identify individual building parameters to between 15% and 32% of their actual value.
The detection of radiological and special nuclear material within the country’s borders is a crucial component of the national security network. Being able to detect small amounts of radiological material at large distances is especially important for search applications. To provide this capability General Electric’s Research Center has developed, as a part of DNDO’s standoff radiation detection system advanced technology demonstration (SORDS-ATD) program, a standoff radiation imaging system (SORIS). This vehicle-based system is capable of detecting weak sources at large distances in relatively short times. To accomplish this, GE has developed a novel coded aperture detector based on commercial components from GE Healthcare. An array of commercial gamma cameras modified to increase the system efficiency and energy range are used as position sensitive detectors. Unlike typical coded aperture systems, however, SORIS employs a non-planar mask and thus does not suffer the typical limitations of partially encoded regions giving it a wide field of view. Source identification is done using both low-statistics anomaly indicators and conventional high-statistics algorithms being developed by Pacific Northwest National Laboratory. The results of scanned areas and threats identified are displayed to the user and overlaid on satellite imagery.commercial components from GE Healthcare. An array of commercial gamma cameras modified to increase the system efficiency and energy range are used as position sensitive detectors. Unlike typical coded aperture systems, however, SORIS employs a non-planar mask and thus does not suffer the typical limitations of partially encoded regions giving it a wide field of view. Source identification is done using both low-statistics anomaly indicators and conventional high-statistics algorithms being developed by Pacific Northwest National Laboratory. The results of scanned areas and threats identified are displayed to the user and overlaid on satellite imagery.
Final report on MAGGIE. We set ambitious goals to model the functions of individual organisms and their community from molecular to systems scale. These scientific goals are driving the development of sophisticated algorithms to analyze large amounts of experimental measurements made using high throughput technologies to explain and predict how the environment influences biological function at multiple scales and how the microbial systems in turn modify the environment. By experimentally evaluating predictions made using these models we will test the degree to which our quantitative multiscale understanding wilt help to rationally steer individual microbes and their communities towards specific tasks. Towards this end we have made substantial progress towards understanding evolution of gene families, transcriptional structures, detailed structures of keystone molecular assemblies (proteins and complexes), protein interactions, biological networks, microbial interactions, and community structure. Using comparative analysis we have tracked the evolutionary history of gene functions to understand how novel functions evolve. One level up, we have used proteomics data, high-resolution genome tiling microarrays, and 5' RNA sequencing to revise genome annotations, discover new genes including ncRNAs, and map dynamically changing operon structures of five model organisms: For Desulfovibrio vulgaris Hildenborough, Pyrococcus furiosis, Sulfolobus solfataricus, Methanococcus maripaludis and Haiobacterium salinarum NROL We have developed machine learning algorithms to accurately identify protein interactions at a near-zero false positive rate from noisy data generated using tagfess complex purification, TAP purification, and analysis of membrane complexes. Combining other genome-scale datasets produced by ENIGMA (in particular, microarray data) and available from literature we have been able to achieve a true positive rate as high as 65% at almost zero false positives when applied to the manually curated training set. Applying this method to the data representing around a quarter of the fraction space for water soluble proteins in D. vulgaris, we obtained 854 reliable pair wise interactions. Further, we have developed algorithms to analyze and assign significance to protein interaction data from bait pull-down experiments and integrate these data with other systems biology data through associative biclustering in a parallel computing environment. We will 'fill-in' missing information in these interaction data using a 'Transitive Closure' algorithm and subsequently use 'Between Commonality Decomposition' algorithm to discover complexes within these large graphs of protein interactions. To characterize the metabolic activities of proteins and their complexes we are developing algorithms to deconvolute pure mass spectra, estimate chemical formula for m/z values, and fit isotopic fine structure to metabolomics data. We have discovered that in comparison to isotopic pattern fitting methods restricting the chemical formula by these two dimensions actually facilitates unique solutions for chemical formula generators. To understand how microbial functions are regulated we have developed complementary algorithms for reconstructing gene regulatory networks (GRNs). Whereas the network inference algorithms cMonkey and Inferelator developed enable de novo reconstruction of predictive models for GRNs from diverse systems biology data, the RegPrecise and RegPredict framework developed uses evolutionary comparisons of genomes from closely related organisms to reconstruct conserved regulons. We have integrated the two complementary algorithms to rapidly generate comprehensive models for gene regulation of understudied organisms. Our preliminary analyses of these reconstructed GRNs have revealed novel regulatory mechanisms and cis-regulatory motifs, as well asothers that are conserved across species. Finally, we are supporting scientific efforts in ENIGMA with data management solutions and by integrating all of the algorithms, software and data into a Knowledgebase. For instance, we have developed the RegPrecise database (http://regprecise.lbl.gov) which represents manually curated sets of regulons laying the basis for automatic annotation of regulatory interactions in closely related species. We are also in the midst of scaling up MicrobesOnline to handle the growing volume of sequence and functional genomics data. Over the last year our efforts have been focused on providing support for additional genomic and functional genomic data types. Similarly, we have developed several visualization tools to help with the exploration of complex systems biology datasets. A case in point is the Gaggle Genome Browser (GGB), which was enhanced with visualizations for plotting peptide detections and protein-DNA binding alongside transcriptome structure, plus the ability to interactively filter by signal intensity or p-value.
Progress has been made at Fermilab on the development of feed-forward and feed-back algorithms used to compensate SCRF cavity detuning, which is caused by Lorentz Forces and microphonics. Algorithms that have been developed and tested for the 1.3GHz (ILC-style) SCRF cavities (Capture Cavity II) will be reported.
Quantum computers can produce a quantum encoding of the solution of a system of differential equations exponentially faster than a classical algorithm can produce an explicit description. However, while high-precision quantum algorithms for linear ordinary differential equations are well established, the best previous quantum algorithms for linear partial differential equations (PDEs) have complexity poly(1/ϵ), where ϵ is the error tolerance. By developing quantum algorithms based on adaptive-order finite difference methods and spectral methods, we improve the complexity of quantum algorithms for linear PDEs to be poly(d,log(1/ϵ)), where d is the spatial dimension. Our algorithms apply high-precision quantum linear system algorithms to systems whose condition numbers and approximation errors we bound. We develop a finite difference algorithm for the Poisson equation and a spectral algorithm for more general second-order elliptic equations.
Our objective is to develop a mathematical model to optimize energy consumption at multiple levels in networked data centers, and develop abstract algorithms to optimize not only individual servers, but also coordinate the energy consumption of clusters of servers within a data center and across geographically distributed data centers to minimize the overall energy cost and consumption of brown energy of an enterprise. In this project, we have formulated a variety of optimization models, some stochastic others deterministic, and have obtained a variety of qualitative results on the structural properties, robustness, and scalability of the optimal policies. We have also systematically derived from these models decentralized algorithms to optimize energy efficiency, analyzed their optimality and stability properties. Finally, we have conducted preliminary numerical simulations to illustrate the behavior of these algorithms. We draw the following conclusion. First, there is a substantial opportunity to minimize both the amount and the cost of electricity consumption in a network of datacenters, by exploiting the fact that traffic load, electricity cost, and availability of renewable generation fluctuate over time and across geographical locations. Judiciously matching these stochastic processes can optimize the tradeoff between brown energy consumption, electricity cost, and response time. Second, given the stochastic nature of these three processes, real-time dynamic feedback should form the core of any optimization strategy. The key is to develop decentralized algorithms that can be implemented at different parts of the network as simple, local algorithms that coordinate through asynchronous message passing.
Prompt Gamma Neutron Activation (PGNAA) systems use the neutron-induced gamma-ray spectra from test objects in order to identify their compositions. The U.S. Army in particular uses these systems to identify the contents of field-recovered munitions in order to determine the presence of chemical warfare materiel (CWM) or explosives. These field-recovered munitions can have a variety of different fills, including experimental fills, have a large range of sizes, and be assessed in different field conditions. All these variations can have a significant effect on the neutron-induced gamma-ray spectrum and therefore a large impact on automatic fill identification algorithms. In order to develop robust identification algorithms, parametric studies of the effects of munition size, fill composition, and assessment conditions are very useful but time-consuming and expensive in the laboratory. Monte Carlo modeling of the system response to these variations is a very attractive alternative, provided the modeling accurately reflects real gamma spectra and can be performed quickly and inexpensively when compared to experiment. At Idaho National Laboratory we have used the Monte Carlo N-Particle (MCNP6) code [2] to calculate the response of the Portable Isotopic Neutron Spectroscopy (PINS) system to a number of simulated chemical warfare munitions as well as performed laboratory measurements with the system. Two versions of PINS system were used; one excited the test object with neutrons from a 252C f source and one with neutrons from a portable deuterium-deuterium (DD) neutron generator. The sets of measurements and simulations with the two different neutron sources provided experimental data for development of automatic fill identification algorithms as well as providing a good test of the agreement between the MCNP calculations and experiment.
This study introduces a new technique to compute direct normal irradiance (DNI) for improving the National Solar Radiation Data Base (NSRDB). A finite-surface integration algorithm is developed to compute solar radiation in differential solid angles and efficiently infer its contribution to a surface perpendicular to the solar direction. A lookup table of cloud bi-directional transmittance distribution function (BTDF) is developed by use of the discrete ordinates radiative transfer (DISORT) model for possible solar and observing directions and various cloud optical and microphysical properties. In each solar incident direction, DNI is given by the cloud BTDFs from approximately 200 differential solid angles. The simulated DNI is calibrated and evaluated using surface observations at the National Renewable Energy Laboratory's (NREL's) Solar Energy Research Laboratory (SRRL) and the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) facility.
Even after a century of development, the total hydropower potential from undeveloped rivers is still considered to be abundant in the United States. However, unlike evaluating hydropower potential at existing hydropower plants or non-powered dams, locating a feasible new hydropower plant involves many unknowns, and hence the total undeveloped potential is harder to quantify. In light of the rapid development of multiple national geospatial datasets for topography, hydrology, and environmental characteristics, a merit matrix based geospatial algorithm is proposed to help identify possible hydropower stream-reaches for future development. These hydropower stream-reaches sections of natural streams with suitable head, flow, and slope for possible future development are identified and compared using three different scenarios. A case study was conducted in the Alabama-Coosa-Tallapoosa (ACT) and Apalachicola-Chattahoochee-Flint (ACF) hydrologic subregions. It was found that a merit matrix based algorithm, which is based on the product of hydraulic head, annual mean flow, and average channel slope, can help effectively identify stream-reaches with high power density and small surface inundation. The identified stream-reaches can then be efficiently evaluated for their potential environmental impact, land development cost, and other competing water usage in detailed feasibility studies . Given that the selected datasets are available nationally (at least within the conterminous US), the proposed methodology will have wide applicability across the country.
In the Multiple Instance Learning scenario, the training data consists of instances grouped into bags, and each bag is labelled with whether it is positive, i.e. contains at least one positive instance. First, Active Learning, in which additional labels can be iteratively requested, has the potential to allow more accurate classifiers to be learned with less labels. Active Learning has been applied to the Multiple Instance Learning under two settings: when bag labels of unlabelled bags can be requested, and when instance labels within bags known to be positive can be requested. Second, Bayesian Active learning methods have the potential to learn accurate classifiers with few labels, because they explicitly track the classifier uncertainty and can thus address its knowledge gaps. Yet, there does not exist any Bayesian Active Learning method for the Multiple Instance Learning Scenario. In this work, we develop the first such method. We develop a Bayesian classifier for the Multiple Instance Learning scenario, show how it can be efficiently used for Bayesian Active Learning, and perform experiments assessing its performance. While its performance exceeds that when no Active Learning is used, it is sometimes better, sometimes worse than the naive baseline of uncertainty sampling, depending on the situation. This suggests future work: building more customizable Bayesian Active Learning methods for the Multiple Instance Scenario, customizable to whether bag or instance label accuracy is targeted, and the labeling budget.
X-ray refraction-enhanced radiography (RER) or phase contrast imaging is widely used to study internal discontinuities within materials. The resulting radiograph captures both the decrease in intensity caused by material absorption along the x-ray path, as well as the phase shift, which is highly sensitive to gradients in density. A significant challenge lies in effectively analyzing the radiographs to decouple the intensity and phase information and accurately ascertain the density profile. Conventional algorithms often yield ambiguous and unrealistic results due to difficulties in including physical constraints and other relevant information. We have developed an algorithm that uses a deep neural network to address these issues and applied it to extract the detailed density profile from an experimental RER. To generalize the applicability of our algorithm, we have developed a technique that quantitatively evaluates the complexity of the phase retrieval process based on the characteristics of the sample and the configuration of the experiment. Accordingly, this evaluation aids in the selection of the neural network architecture for each specific case. Beyond RER, the model has potential applications for other diagnostics where phase retrieval analysis is required.