SEARCH · Search NASA

Results for “bandwidth optimization”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2016

Livermore Big Artificial Neural Network Toolkit

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Essen, BrianVan↗

DOE OSTI2016

Livermore Big Artificial Neural Network Toolkit

Essen, Brian Van↗

DOE OSTI2024

Inverse design for waveguide dispersion with a differentiable mode solver

Inverse design of optical components based on adjoint sensitivity analysis has the potential to address the most challenging photonic engineering problems. However, existing inverse design tools based on finite-difference-time-domain (FDTD) models are poorly suited for optimizing waveguide modes for adiabatic transformation or perturbative coupling, which lies at the heart of many important photonic devices. Among these, dispersion engineering of optical waveguides is especially challenging in ultrafast and nonlinear optical applications involving broad optical bandwidths and frequency-dependent anisotropic dielectric material response. In this work, we develop gradient back-propagation through a general-purpose electromagnetic eigenmode solver and use it to demonstrate waveguide dispersion optimization for second harmonic generation with maximized phase-matching bandwidth. This optimization of three design parameters converges in eight steps, reducing the computational cost of optimization by ∼100x compared to exhaustive search and identifying new designs for broadband optical frequency doubling of laser sources in the 1.3–1.4 µm wavelength range. Furthermore, we demonstrate that the computational cost of gradient back-propagation is independent of the number of parameters, as required for optimization of complex geometries. This technique enables practical inverse design for a broad range of previously intractable photonic devices.

Gray, Dodd (ORCID:000000030469599X)↗

DOE OSTI2016

Fault-tolerant bandwidth reservation strategies for data transfers in high-performance networks

Many next-generation e-science applications need fast and reliable transfer of large volumes of data with guaranteed performance, which is typically enabled by the bandwidth reservation service in high-performance networks. One prominent issue in such network environments with large footprints is that node and link failures are inevitable, hence potentially degrading the quality of data transfer. We consider two generic types of bandwidth reservation requests (BRRs) concerning data transfer reliability: (i) to achieve the highest data transfer reliability under a given data transfer deadline, and (ii) to achieve the earliest data transfer completion time while satisfying a given data transfer reliability requirement. We propose two periodic bandwidth reservation algorithms with rigorous optimality proofs to optimize the scheduling of individual BRRs within BRR batches. The efficacy of the proposed algorithms is illustrated through extensive simulations in comparison with scheduling algorithms widely adopted in production networks in terms of various performance metrics.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Adaptive four-level modeling of laser cooling of solids

Laser cooling of rare-earth doped solids has been demonstrated across a wide range of material platforms, inspiring the development of simple phenomenological models such as the four-level model to elucidate the universal properties of laser cooling under various operating conditions. However, these models usually require the input of full absorption spectra that must be provided experimentally or by additional complicated atomic modeling. In this Letter, we propose that a four-level model, when extended to admit effective energy levels adaptive to the pumping photon energy, can accurately predict the cooling efficiency as a function of temperature and pumping frequency using only few inputs such as the absorption coefficient measured at a single frequency and temperature. Our model exploits the quasi-equilibrium properties of the excitation of rare-earth ions for the determination of the effective four energy levels. The model is validated against published experimental results for a span of materials including ytterbium/thulium-doped glass and crystals. With the verified model, we derive explicit expressions for the optimal frequency and the operating bandwidth of pumping lasers. Our model significantly simplifies the modeling process of laser cooling and is expected to stimulate further development of optical refrigeration.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2022

Deep Learning for Spectral Filling in Radio Frequency Applications

Due to the Internet of Things (IoT) proliferation, Radio Frequency (RF) channels are increasingly congested with new kinds of devices, which carry unique and diverse communication needs. This poses complex challenges in modern digital communications, and calls for the development of technological innovations that (i) optimize capacity (bitrate) in limited bandwidth environments, (ii) integrate cooperatively with already-deployed RF protocols, and (iii) are adaptive to the ever-changing demands in modern digital communications. In this paper we present methods for applying deep neural networks for spectral filling. Given an RF channel transmitting digital messages with a pre-established modulation scheme, we automatically learn novel modulation schemes for sending extra information, in the form of additional messages, “around” the fixed-modulation signals (i.e., without interfering with them). In so doing, we effectively increase channel capacity without increasing bandwidth. We further demonstrate the ability to generate signals that closely resemble the original modulations, such that the presence of extra messages is undetectable to third-party listeners. We present three computational experiments demonstrating the efficacy of our methods, and conclude by discussing the implications of our results for modern RF applications.

Setzler, Matthew D.↗

NASA NTRS1993

Rain rate duration statistics derived from the Mid-Atlantic coast rain gauge network

A rain gauge network comprised of 10 tipping bucket rain gauges located in the Mid-Atlantic coast of the United States has been in continuous operation since June 1, 1986. Rain rate distributions and estimated slant path fade distributions at 20 GHz and 30 GHz covering the first five year period were derived from the gauge network measurements, and these results were described by Goldhirsh. In this effort, rain rate time duration statistics are presented. The rain duration statistics are of interest for better understanding the physical nature of precipitation and to present a data base which may be used by modelers to convert to slant path fade duration statistics. Such statistics are important for better assessing optimal coding procedures over defined bandwidths.

Goldhirsh, Julius↗

NASA NTRS1997

Hierarchical Parallelism in Finite Difference Analysis of Heat Conduction

Based on the concept of hierarchical parallelism, this research effort resulted in highly efficient parallel solution strategies for very large scale heat conduction problems. Overall, the method of hierarchical parallelism involves the partitioning of thermal models into several substructured levels wherein an optimal balance into various associated bandwidths is achieved. The details are described in this report. Overall, the report is organized into two parts. Part 1 describes the parallel modelling methodology and associated multilevel direct, iterative and mixed solution schemes. Part 2 establishes both the formal and computational properties of the scheme.

Padovan, Joseph↗

NASA NTRS2011

Traveling-Wave Tube Efficiency Enhancement

Traveling-wave tubes (TWT's) are used to amplify microwave communication signals on virtually all NASA and commercial spacecraft. Because TWT's are a primary power user, increasing their power efficiency is important for reducing spacecraft weight and cost. NASA Glenn Research Center has played a major role in increasing TWT efficiency over the last thirty years. In particular, two types of efficiency optimization algorithms have been developed for coupled-cavity TWT's. The first is the phase-adjusted taper which was used to increase the RF power from 420 to 1000 watts and the RF efficiency from 9.6% to 22.6% for a Ka-band (29.5 GHz) TWT. This was a record efficiency at this frequency level. The second is an optimization algorithm based on simulated annealing. This improved algorithm is more general and can be used to optimize efficiency over a frequency bandwidth and to provide a robust design for very high frequency TWT's in which dimensional tolerance variations are significant.

Dayton, James A., Jr.↗

DOE OSTI2013

Active Measurement of Memory Resource Consumption

Hierarchical memory is a cornerstone of modern hardware design because it provides high memory performance and capacity at a low cost. However, the use of multiple levels of memory and complex cache management policies makes it very difficult to optimize the performance of applications running on hierarchical memories. As the number of compute cores per chip continues to rise faster than the total amount of available memory, applications will become increasingly starved for memory storage capacity and bandwidth, making the problem of performance optimization even more critical. We propose a new methodology for measuring and modeling the performance of hierarchical memories in terms on the application’s utilization of the key memory resources: capacity of a given memory level and bandwidth between two levels. This is done by actively interfering with the application’s use of these resources. The application’s sensitivity to reduced resource availability is measured by observing the effect of interference on application performance. The resulting resource-oriented model of performance both greatly simplifies application performance analysis and makes it possible to predict an application’s performance when running with various resource constraints. This is useful to predict performance for future memory-constrained architectures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

iez: Resource Contention Aware Load Balancing for Large-Scale Parallel File Systems

Parallel I/O performance is crucial to sustaining scientific applications on large-scale High-Performance Computing (HPC) systems. However, I/O load imbalance in the underlying distributed and shared storage systems can significantly reduce overall application performance. There are two conflicting challenges to mitigate this load imbalance: (i) optimizing systemwide data placement to maximize the bandwidth advantages of distributed storage servers, i.e., allocating I/O resources efficiently across applications and job runs; and (ii) optimizing client-centric data movement to minimize I/O load request latency between clients and servers, i.e., allocating I/O resources efficiently in service to a single application and job run. Moreover, existing approaches that require application changes limit wide-spread adoption in commercial or proprietary deployments. We propose iez, an “end-to-end control plane” where clients transparently and adaptively write to a set of selected I/O servers to achieve balanced data placement. Our control plane leverages realtime load information for distributed storage server global data placement while our design model leverages trace-based optimization techniques to minimize I/O load request latency between clients and servers. We evaluate our proposed system on an experimental cluster for two common use cases: synthetic I/O benchmark IOR for large sequential writes and a scientific application I/O kernel, HACC-I/O. Results show read and write performance improvements of up to 34% and 32%, respectively, compared to the state of the art.

Wadhwa, Bharti↗

DOE OSTI2016

Optimized Finite-Difference Coefficients for Acoustic Modeling.

Although using standard Taylor series coefficients for finite-difference operators is optimal in the sense that in the limit of infinitesimal space and time discretization, the solution approaches the correct analytic solution to the acousto-dynamic system of differential equations, other finite-difference operators may provide optimal computational run time given certain error bounds or source bandwidth constraints. This report describes the results of investigation of alternative optimal finite-difference coefficients based on several optimization/accuracy scenarios and provides recommendations for minimizing run time while retaining error within given error bounds.

58 GEOSCIENCES↗

NASA NTRS2000

A Simulation Study of Paced TCP

In this paper, we study the performance of paced TCP, a modified version of TCP designed especially for high delay- bandwidth networks. In typical networks, TCP optimizes its send-rate by transmitting increasingly large bursts, or windows, of packets, one burst per round-trip time, until it reaches a maximum window-size, which corresponds to the full capacity of the network. In a network with a high delay-bandwidth product, however, Transmission Control Protocol's (TCPs) maximum window-size may be larger than the queue size of the intermediate routers, and routers will begin to drop packets as soon as the windows become too large for the router queues. The TCP sender then concludes that the bottleneck capacity of the network has been reached, and it limits its send-rate accordingly. Partridge proposed paced TCP as a means of solving the problem of queueing bottlenecks. A sender using paced TCP would release packets in multiple, small bursts during a round-trip time in which ordinary TCP would release a single, large burst of packets. This approach allows the sender to increase its send-rate to the maximum window size without encountering queueing bottlenecks. This paper describes the performance of paced TCP in a simulated network and discusses implementation details that can affect the performance of paced TCP.

Kulik, Joanna↗

NASA NTRS1989

Integrated control-system design via generalized LQG (GLQG) theory

Thirty years of control systems research has produced an enormous body of theoretical results in feedback synthesis. Yet such results see relatively little practical application, and there remains an unsettling gap between classical single-loop techniques (Nyquist, Bode, root locus, pole placement) and modern multivariable approaches (LQG and H infinity theory). Large scale, complex systems, such as high performance aircraft and flexible space structures, now demand efficient, reliable design of multivariable feedback controllers which optimally tradeoff performance against modeling accuracy, bandwidth, sensor noise, actuator power, and control law complexity. A methodology is described which encompasses numerous practical design constraints within a single unified formulation. The approach, which is based upon coupled systems or modified Riccati and Lyapunov equations, encompasses time-domain linear-quadratic-Gaussian theory and frequency-domain H theory, as well as classical objectives such as gain and phase margin via the Nyquist circle criterion. In addition, this approach encompasses the optimal projection approach to reduced-order controller design. The current status of the overall theory will be reviewed including both continuous-time and discrete-time (sampled-data) formulations.

Bernstein, Dennis S.↗

NASA NTRS1981

Capacity of a multimode direct detection optical communication channel

The capacity is derived under both peak and average signal power constraints and without a signal bandwidth constraint. A random telegraph wave type signalling scheme of Kabanov is known to achieve capacity provided enough signalling bandwidth is available. In the absence of received background noise, an optimally coded PPM system is shown to achieve capacity with greatly reduced bandwidth as compared to Kabanov signals.

Tan, H. H.↗

DOE OSTI2020

An Analysis of System Balance and Architectural Trends Based on Top500 Supercomputers

Supercomputer design is a complex, multi-dimensional optimization process, wherein several subsystems need to be reconciled to meet a desired figure of merit performance for a portfolio of applications and a budget constraint. However, overall, the HPC community has been gravitating towards ever more FLOPS, at the expense of many other subsystems. To draw attention to overall system balance, in this paper, we analyze balance ratios and architectural trends in the world's most powerful supercomputers. Specifically, we have collected performance characteristics of systems between1993 and 2018 based on the Top500 lists, and then analyzed their architectures from diverse system design perspectives. Notably, our analysis studies the performance balance of the machines, across a variety of subsystems such as compute, memory, I/O, interconnect, intra-node connectivity and power. Our analysis reveals that balance ratios of the various subsystems need to be considered carefully alongside the application workload portfolio to provision the subsystem capacity and bandwidth specifications, which can help achieve optimal performance.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

An Analysis of System Balance and Architectural Trends Based on Top500 Supercomputers

Supercomputer design is a complex, multi-dimensional optimization process, wherein several subsystems need to be reconciled to meet a desired figure of merit performance for a portfolio of applications and a budget constraint. However, overall, the HPC community has been gravitating towards ever more Flops, at the expense of many other subsystems. To draw attention to overall system balance, in this paper, we analyze balance ratios and architectural trends in the world’s most powerful supercomputers. Specifically, we have collected the performance characteristics of systems between 1993 and 2019 based on the Top500 lists and then analyzed their architectures from diverse system design perspectives. Notably, our analysis studies the performance balance of the machines, across a variety of subsystems such as compute, memory, I/O, interconnect, intra-node connectivity and power. Our analysis reveals that balance ratios of the various subsystems need to be considered carefully alongside the application workload portfolio to provision the subsystem capacity and bandwidth specifications, which can help achieve optimal performance.

Khan, Awais↗

NASA NTRS1978

Bandwidth compression of multispectral satellite imagery

The results of two studies aimed at developing efficient adaptive and nonadaptive techniques for compressing the bandwidth of multispectral images are summarized. These techniques are evaluated and compared using various optimality criteria including MSE, SNR, and recognition accuracy of the bandwidth compressed images. As an example of future requirements, the bandwidth requirements for the proposed Landsat-D Thematic Mapper are considered.

Habibi, A.↗