Search NASA⌕ Search

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.

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

At least 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRS2005

Design Optimization Tool for Synthetic Jet Actuators Using Lumped Element Modeling

The performance specifications of any actuator are quantified in terms of an exhaustive list of parameters such as bandwidth, output control authority, etc. Flow-control applications benefit from a known actuator frequency response function that relates the input voltage to the output property of interest (e.g., maximum velocity, volumetric flow rate, momentum flux, etc.). Clearly, the required performance metrics are application specific, and methods are needed to achieve the optimal design of these devices. Design and optimization studies have been conducted for piezoelectric cantilever-type flow control actuators, but the modeling issues are simpler compared to synthetic jets. Here, lumped element modeling (LEM) is combined with equivalent circuit representations to estimate the nonlinear dynamic response of a synthetic jet as a function of device dimensions, material properties, and external flow conditions. These models provide reasonable agreement between predicted and measured frequency response functions and thus are suitable for use as design tools. In this work, we have developed a Matlab-based design optimization tool for piezoelectric synthetic jet actuators based on the lumped element models mentioned above. Significant improvements were achieved by optimizing the piezoceramic diaphragm dimensions. Synthetic-jet actuators were fabricated and benchtop tested to fully document their behavior and validate a companion optimization effort. It is hoped that the tool developed from this investigation will assist in the design and deployment of these actuators.

Gallas, Quentin↗
DOE OSTI2023

Efficient GPU Implementation of Automatic Differentiation for Computational Fluid Dynamics

Many scientific and engineering applications require repeated calculations of derivatives of output functions with respect to input parameters. Automatic Differentiation (AD) is a method that automates derivative calculations and can significantly speed up code development. In Computational Fluid Dynamics (CFD), derivatives of flux functions with respect to state variables (Jacobian) are needed for efficient solutions of the nonlinear governing equations. AD of flux functions on graphics processing units (GPUs) is challenging as flux computations involve many intermediate variables that create high register pressure and require significant memory traffic because of the need to store the derivatives. This paper presents a forward-mode AD method based on multivariate dual numbers that addresses these challenges and simultaneously reduces the floating-point operation count. The dimension of the multivariate dual numbers is optimized for performance. The flux computations are restructured to minimize the number of temporary variables and reduce register pressure. For effective utilization of memory bandwidth, shared memory is used to store the local flux Jacobian. This AD implementation is compared with several other Jacobian implementations on an NVIDIA V100 GPU (V100). For three-dimensional perfect-gas compressible-flow equations implemented in a practical CFD code, the AD implementation of a flux Jacobian based on multivariate dual numbers of dimension 5 outperforms all other GPU AD implementations on V100. Its performance is comparable with the optimized hand-differentiated version. Finally, the implementation achieves 75% of the peak floating-point throughput and 61 % of the peak global device memory bandwidth usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2000

Fixed-Order Mixed Norm Designs for Building Vibration Control

This study investigates the use of H2, mu-synthesis, and mixed H2/mu methods to construct full order controllers and optimized controllers of fixed dimensions. The benchmark problem definition is first extended to include uncertainty within the controller bandwidth in the form of parametric uncertainty representative of uncertainty in the natural frequencies of the design model. The sensitivity of H2 design to unmodeled dynamics and parametric uncertainty is evaluated for a range of controller levels of authority. Next, mu-synthesis methods are applied to design full order compensators that are robust to both unmodeled dynamics and to parametric uncertainty. Finally, a set of mixed H2/mu compensators are designed which are optimized for a fixed compensator dimension. These mixed norm designs recover the H2 design performance levels while providing the same levels of robust stability as the mu designs. It is shown that designing with the mixed norm approach permits higher levels of controller authority for which the H2 designs are destabilizing. The benchmark problem is that of an active tendon system. The controller designs are all based on the use of acceleration feedback.

Whorton, Mark S.↗
NASA NTRS1998

A Study of Fixed-Order Mixed Norm Designs for a Benchmark Problem in Structural Control

This study investigates the use of H2, p-synthesis, and mixed H2/mu methods to construct full-order controllers and optimized controllers of fixed dimensions. The benchmark problem definition is first extended to include uncertainty within the controller bandwidth in the form of parametric uncertainty representative of uncertainty in the natural frequencies of the design model. The sensitivity of H2 design to unmodelled dynamics and parametric uncertainty is evaluated for a range of controller levels of authority. Next, mu-synthesis methods are applied to design full-order compensators that are robust to both unmodelled dynamics and to parametric uncertainty. Finally, a set of mixed H2/mu compensators are designed which are optimized for a fixed compensator dimension. These mixed norm designs recover the H, design performance levels while providing the same levels of robust stability as the u designs. It is shown that designing with the mixed norm approach permits higher levels of controller authority for which the H, designs are destabilizing. The benchmark problem is that of an active tendon system. The controller designs are all based on the use of acceleration feedback.

Whorton, Mark S.↗
DOE OSTI2017

Stochastic optimization of GeantV code by use of genetic algorithms

GeantV is a complex system based on the interaction of different modules needed for detector simulation, which include transport of particles in fields, physics models simulating their interactions with matter and a geometrical modeler library for describing the detector and locating the particles and computing the path length to the current volume boundary. The GeantV project is recasting the classical simulation approach to get maximum benefit from SIMD/MIMD computational architectures and highly massive parallel systems. This involves finding the appropriate balance between several aspects influencing computational performance (floating-point performance, usage of off-chip memory bandwidth, specification of cache hierarchy, etc.) and handling a large number of program parameters that have to be optimized to achieve the best simulation throughput. This optimization task can be treated as a black-box optimization problem, which requires searching the optimum set of parameters using only point-wise function evaluations. Here, the goal of this study is to provide a mechanism for optimizing complex systems (high energy physics particle transport simulations) with the help of genetic algorithms and evolution strategies as tuning procedures for massive parallel simulations. One of the described approaches is based on introducing a specific multivariate analysis operator that could be used in case of resource expensive or time consuming evaluations of fitness functions, in order to speed-up the convergence of the black-box optimization problem.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1993

Optimal cube-connected cube multiprocessors

Many CFD (computational fluid dynamics) and other scientific applications can be partitioned into subproblems. However, in general the partitioned subproblems are very large. They demand high performance computing power themselves, and the solutions of the subproblems have to be combined at each time step. The cube-connect cube (CCCube) architecture is studied. The CCCube architecture is an extended hypercube structure with each node represented as a cube. It requires fewer physical links between nodes than the hypercube, and provides the same communication support as the hypercube does on many applications. The reduced physical links can be used to enhance the bandwidth of the remaining links and, therefore, enhance the overall performance. The concept and the method to obtain optimal CCCubes, which are the CCCubes with a minimum number of links under a given total number of nodes, are proposed. The superiority of optimal CCCubes over standard hypercubes was also shown in terms of the link usage in the embedding of a binomial tree. A useful computation structure based on a semi-binomial tree for divide-and-conquer type of parallel algorithms was identified. It was shown that this structure can be implemented in optimal CCCubes without performance degradation compared with regular hypercubes. The result presented should provide a useful approach to design of scientific parallel computers.

Sun, Xian-He↗
DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗
DOE OSTI2023

Scaling comb-driven resonator-based DWDM silicon photonic links to multi-Tb/s in the multi-FSR regime

The use of chip-based micro-resonator Kerr frequency combs in conjunction with dense wavelength-division multiplexing (DWDM) enables massively parallel intensity-modulated direct-detection data transmission with low energy consumption. Resonator-based modulators and filters used in such systems can limit the number of usable wavelength channels due to practical constraints on the maximum achievable free spectral range (FSR). In this work, we introduce the design of multi-Tb/s comb-driven resonator-based silicon photonic links by leveraging the multi-FSR regime. We demonstrate the viability of the link architecture with yield estimates that are supported by extensive wafer-scale measurements of 704 micro-resonators fabricated in a commercial complementary metal–oxide–semiconductor foundry. We show that a 2.80 Tb/s link is realizable with a ≥6 σ yield (∼99.999%), and that aggregate bandwidths of 3.76 Tb/s and 4.72 Tb/s are possible if yield targets are relaxed (3 σ and 1 σ , respectively). All designs represent a 1.94−3.28× boost to aggregate link bandwidth while maintaining BER≤10 −10 performance, with a theoretical bandwidth of 10.51 Tb/s being possible for sufficiently robust resonators. We use high-speed BER measurements to inform co-optimization of data rate and aggressor spacing ( λ ag ), limiting any additional loss-based power penalties to off-resonance insertion loss (IL) and routing loss. This work demonstrates that, through the multi-FSR regime, there is a clear path toward Kerr comb-driven ultra-broadband, high bandwidth silicon photonic links that can support next-generation data centers and high-performance computers.

James, Aneek (ORCID:0000000262527807)↗
DOE OSTI2017

Optimizing squeezing in a coherent quantum feedback network of optical parametric oscillators

Advances in the emerging field of coherent quantum feedback control (CQFC) have led to the development of new capabilities in the areas of quantum control and quantum engineering, with a particular impact on the theory and applications of quantum optical networks. For this study, we consider a CQFC network consisting of two coupled optical parametric oscillators (OPOs) and study the squeezing spectrum of its output field. The performance of this network as a squeezed-light source with desired spectral characteristics is optimized by searching over the space of model parameters with experimentally motivated bounds. We use the QNET package to model the network’s dynamics and the PyGMO package of global optimization algorithms to maximize the degree of squeezing at a selected sideband frequency or the average degree of squeezing over a selected bandwidth. The use of global search methods is critical for identifying the best possible performance of the CQFC network, especially for squeezing at higher-frequency sidebands and higher bandwidths. The results demonstrate that the CQFC network of two coupled OPOs makes it possible to vary the squeezing spectrum, effectively utilize the available pump power, and overall significantly outperform a single OPO. Additionally, the Hessian eigenvalue analysis shows that the squeezing generation performance of the optimally operated CQFC network is robust to small variations of phase parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRSDate not supplied

Globally Optimal Band Structure for Thermoelectrics in Realistic Systems

One of the ultimate questions in the field of thermoelectrics is the optimal band structure for the figure of merit. The observation made here is that a linear band dispersion, of any dimension, under acoustic-phonon-deformation-potential scattering comprises the theoretical regimen for delivering boxcar transport distribution, which has been mathematically proven to deliver optimum figure of merit. This is guaranteed by the interplay of the energy-dependencies of groupvelocity and density of states of linear dispersion as well as the energy-behavior of deformation-potential scattering. Then linear dispersion, capped with optimum bandwidth and combined with provisions of Park et al, npj Comput. Mater. 7, 43 2021, is the globally optimal band structure for thermoelectricity.

Junsoo Park↗
DOE OSTI2021

Machine-learning-aided cognitive reconfiguration for flexible-bandwidth HPC and data center networks [Invited]

This paper proposes a machine-learning (ML)-aided cognitive approach for effective bandwidth reconfiguration in optically interconnected datacenter/high-performance computing (HPC) systems. The proposed approach relies on a Hyper-X-like architecture augmented with flexible-bandwidth photonic interconnections at large scales using a hierarchical intra/inter-POD photonic switching layout. We first formulate the problem of the connectivity graph and routing scheme optimization as a mixed-integer linear programming model. A two-phase heuristic algorithm and a joint optimization approach are devised to solve the problem with low time complexity. Then, we propose an ML-based end-to-end performance estimator design to assist the network control plane with intelligent decision making for bandwidth reconfiguration. Numerical simulations using traffic distribution profiles extracted from HPC applications traces as well as random traffic matrices verify the accuracy performance of the ML design estimator ( < <#comment/> 9 % <#comment/> error) and demonstrate up to 5 × <#comment/> throughput gain from the proposed approach compared with the baseline Hyper-X network using fixed all-to-all intra/inter-portable data center interconnects.

Chen, Xiaoliang (ORCID:0000000278056237)↗
DOE OSTI2014

Dynamic characteristics of undoped and p-doped Fabry-Perot InAs/InP quantum dash based ridge waveguide lasers for access/metro networks

In this paper, we report the characteristics of InAs/InP quantum dashes (QDash) based lasers emitting around 1.55 μm. An unprecedented high modal gain of ∼100 cm{sup −1} is obtained for an optimized active structure by stacking 12 QDash layers. Directly modulated lasers allowed achieving a modulation bandwidth of ∼10 GHz and a Henry factor around 5. Thanks to p-type doping, the Henry factor value is reduced down to 2.7 while the modulation bandwidth still amounts to ∼10 GHz. This shows that doping of the active region is important to improve the dynamic characteristics of QDash lasers.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
NASA NTRS1972

Reciprocal - MSE and SNR as distinct performance measures in below-threshold communication.

The possible advantages of using algorithms that are minimum mean-square-error (MSE) optimal, or other averaging-type demodulators with frequency position modulation (FPM), are investigated. An attempt is made to describe the performance of the optimal and various suboptimal demodulators in terms of three parameters which depend on SNR and bandwidth expansion. The performance measures investigated are the reciprocal of the normalized mean-square error and the output SNR, which are different in the below-threshold region. The former is compared to the rate-distortion bound. The possible advantage of averaging-type discriminators from the point of view of the threshold is discussed.

Bar-David, I.↗
NASA NTRS1989

An electron tunneling sensor

New methods have been developed to implement position sensors based on electron tunneling. The electron tunneling methods enable position to be detected with sub-Angstrom resolution using a compact mechanical structure and simple electronic control elements. A prototype accelerometer is the first sensor based on these principles; it shows reliable operation with a noise-limited sensitivity and a bandwidth of approximately 3 kHz. Based on these results, it is expected that tunnel sensors optimized for many applications will enable an entirely new class of sensors to be developed.

Waltman, S. B.↗
NASA NTRS1991

A novel noncontacting waveguide backshort for millimeter and submillimeter wave frequencies

A new noncontacting waveguide backshort was developed for millimeter and submillimeter wave frequencies. It employs a metallic bar with rectangular or circular holes. The size and spacing of the holes are adjusted to provide a periodic variation of the guide impedance on the correct length scale to give a large reflection of RF frequency power. This design is mechanically rugged and can be easily fabricated for millimeter wave frequencies above 300 GHz where conventional backshorts are difficult to fabricate. Model experiments were performed at 4 to 6 GHz to optimize the design. Values of reflected power greater than 95 percent over a 30 percent bandwidth were achieved. The design was scaled to WR-10 band (75 to 110 GHz) with comparably good results.

Mcgrath, W. R.↗
NASA NTRS2010

Ka-Band Waveguide Two-Way Hybrid Combiner for MMIC Amplifiers

The design, simulation, and characterization of a novel Ka-band (32.05 0.25 GHz) rectangular waveguide two-way branch-line hybrid unequal power combiner (with port impedances matched to that of a standard WR-28 waveguide) has been created to combine input signals, which are in phase and with an amplitude ratio of two. The measured return loss and isolation of the branch-line hybrid are better than 22 and 27 dB, respectively. The measured combining efficiency is 92.9 percent at the center frequency of 32.05 GHz. This circuit is efficacious in combining the unequal output power from two Ka-band GaAs pseudomorphic high electron mobility transistor (pHEMT) monolithic microwave integrated circuit (MMIC) power amplifiers (PAs) with high efficiency. The component parts include the branch-line hybrid-based power combiner and the MMIC-based PAs. A two-way branch-line hybrid is a four-port device with all ports matched; power entering port 1 is divided in phase, and into the ratio 2:1 between ports 3 and 4. No power is coupled to port 2. MMICs are a type of integrated circuit fabricated on GaAs that operates at microwave frequencies, and performs the function of signal amplification. The power combiner is designed to operate over the frequency band of 31.8 to 32.3 GHz, which is NASA's deep space frequency band. The power combiner would have an output return loss better than 20 dB. Isolation between the output port and the isolated port is greater than 25 dB. Isolation between the two input ports is greater than 25 dB. The combining efficiency would be greater than 90 percent when the ratio of the two input power levels is two. The power combiner is machined from aluminum with E-plane split-block arrangement, and has excellent reliability. The flexibility of this design allows the combiner to be customized for combining the power from MMIC PAs with an arbitrary power output ratio. In addition, it allows combining a low-power GaAs MMIC with a high-power GaN MMIC. The arbitrary port impedance allows matching the output impedance of the MMIC PA directly to the waveguide impedance without transitioning first into a transmission line with characteristic impedance of 50 ohms. Thus, by eliminating the losses associated with a transition, the overall SSPA efficiency is enhanced. For reducing the cost and weight when required in very large quantities, such as in the beam-forming networks of phased-array antenna systems, the combiner can be manufactured using metal-plated plastic. Two hybrid unequal power combiners can be cascaded to realize a non-binary combiner (for e.g., a three-way) and can be synergistically optimized for low VSWR (voltage standing wave ratio), low insertion loss, high isolation, and wide bandwidth using commercial off-the-shelf electromagnetic software design tools.

Simons, Rainee N.↗
DOE OSTI2016

Optimizing Excited-State Electronic-Structure Codes for Intel Knights Landing: A Case Study on the BerkeleyGW Software

We profile and optimize calculations performed with the BerkeleyGW code on the Xeon-Phi architecture. BerkeleyGW depends both on hand-tuned critical kernels as well as on BLAS and FFT libraries. We describe the optimization process and performance improvements achieved. We discuss a layered parallelization strategy to take advantage of vector, thread and node-level parallelism. We discuss locality changes (including the consequence of the lack of L3 cache) and effective use of the on-package high-bandwidth memory. We show preliminary results on Knights-Landing including a roofline study of code performance before and after a number of optimizations. We find that the GW method is particularly well-suited for many-core architectures due to the ability to exploit a large amount of parallelism over plane-wave components, band-pairs, and frequencies.

97 MATHEMATICS AND COMPUTING↗