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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Spectral splitting optimization for high-efficiency solar photovoltaic and thermal power generation

Utilizing the full solar spectrum is desirable to enhance the conversion efficiency of a solar power generator. In practice, this can be achieved through spectral splitting between multiple converters in parallel. However, it is unclear which wavelength bands should be directed to each converter in order to maximize the efficiency. We developed a model of an ideal hybrid solar converter which utilizes both a single-junction photovoltaic cell and a thermal engine. We determined the limiting efficiencies of this hybrid strategy and the corresponding optimum spectral bandwidth directed to the photovoltaic cell. This optimum width is inversely proportional to the thermal engine efficiency and scales with the bandgap of the photovoltaic cell. This bandwidth was also obtained analytically through an entropy minimization scheme and matches well with our model. We show that the maximum efficiency of the system occurs when it minimizes the spectral entropy generation. This concept can be extended to capture generalized non-idealities to increase the usefulness of this technique for a range of full solar spectrum utilization technologies.

14 SOLAR ENERGY↗
DOE OSTI2024

Architecture and performance of Perlmutter's 35 PB ClusterStor E1000 all-flash file system

NERSC's newest system, Perlmutter, features a 35 PB all-flash Lustre file system built on HPE Cray ClusterStor E1000. Here, we present its architecture, early performance figures, and performance considerations unique to this architecture. We demonstrate the performance of E1000 OSSes through low-level Lustre tests that achieve over 90% of the theoretical bandwidth of the SSDs at the OST and LNet levels. We also show end-to-end performance for both traditional dimensions of I/O performance (peak bulk-synchronous bandwidth) and nonoptimal workloads endemic to production computing (small, incoherent I/Os at random offsets) and compare them to NERSC's previous system, Cori, to illustrate that Perlmutter achieves the performance of a burst buffer and the resilience of a scratch file system. Finally, we discuss performance considerations unique to all-flash Lustre and present ways in which users and HPC facilities can adjust their I/O patterns and operations to make optimal use of such architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Mechanisms of amplification of ultrashort electromagnetic pulses in gyrotron traveling wave tube with helically corrugated waveguide

A time-domain self consistent theory of a gyrotron traveling wave tube with a helically corrugated operating waveguide has been developed. Based on this model, the process of short pulse amplification was studied in regimes of grazing and intersection of the dispersion curves of the electromagnetic wave and the electron beam. In the first case, the possibility of amplification without pulse form distortion was demonstrated for the pulse spectrum width of the order of the gain bandwidth. In the second case, when the electrons' axial velocity was smaller than the wave's group velocity, it was shown that the slippage of the incident signal with respect to the electron beam provides feeding of the signal by “fresh” electrons without initial modulation. As a result, the amplitude of the output pulse can exceed the amplitude of its saturated value for the case of the grazing regime, and, for optimal parameters, the peak output power can be even larger than the kinetic power of the electron beam.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Case Study of Using Kokkos and SYCLs Performance-Portable Frameworks for Milc-Dslash Benchmark on NVIDIA, AMD and Intel GPUs

Six of the top ten supercomputers in the TOP500 list from June 2021 rely on NVIDIA GPUs to achieve their peak compute bandwidth. With the announcement of Aurora, Frontier, and El Capitan, Intel and AMD have also entered the domain of providing GPUs for scientific computing. A consequence of the increased diversity in the GPU landscape is the emergence of portable programming models such as Kokkos, SYCL, OpenCL, and OpenMP, which allow application developers to maintain a single-source code across a diverse range of hardware architectures. While the portable frameworks try to optimize the compute resource usage on a given architecture, it is the programmers responsibility to expose parallelism in an application that can take advantage of thousands of processing elements available on GPUs. In this paper, we introduce a GPU-friendly parallel implementation of Milc-Dslash that exposes multiple hierarchies of parallelism in the algorithm. Milc-Dslash was designed to serve as a benchmark with highly optimized matrix-vector multiplications to measure the resource utilization on the GPU systems. The parallel hierarchies in the Milc-Dslash algorithm are mapped onto a target hardware using Kokkos and SYCL programming models. We present the performance achieved by Kokkos and SYCL implementations of Milc-Dslash on NVIDIA A100 GPU, AMD MI100 GPU, and Intel Gen9 GPU. Additionally, we compare the Kokkos and SYCL performances with those obtained from the versions written in CUDA and HIP programming models on NVIDIA A100 GPU and AMD MI100 GPU, respectively.

Dufek, Amanda S↗
DOE OSTI2014

Spin-lasers: From threshold reduction to large-signal analysis

Lasers in which spin-polarized carriers are injected provide paths to different practical room temperature spintronic devices, not limited to magnetoresistive effects. Unlike the conventional understanding of spintronic devices, an optimal performance of such spin-lasers can arise for finite, not infinite, spin relaxation time. By considering spin-relaxation times of both electrons and holes, we elucidate advantages of spin-lasers over their conventional (spin-unpolarized) counterparts. In addition to the steady-state threshold reduction, spin-lasers can improve transient operation leading to shorter turn-on delay times, reduced ringing of emitted light, and an enhanced bandwidth.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

Quantum entanglement distribution coexisting with high-rate, broadband classical optical communications over a real-world fiber connecting remote, synchronized nodes

Compatibility with existing classical network infrastructure offers a scalable path towards deploying large-scale quantum networks. Here, we demonstrate O-band polarization-encoded quantum entanglement distribution over an installed 24.4-km fiber while coexisting with a state-of-the-art fully loaded C-band classical communications line system and a picosecond-level precision L-band synchronization signal. The classical system carries two 800-Gbps channels while the remainder of the C-band is filled with amplified spontaneous emission, as is standard for such state-of-the-art communications systems. We examine the spontaneous Raman scattering spectrum generated from this broadband C-band light and offer insights into wavelength allocation for O-band quantum channels. Optimal wavelength selection and narrow filtering enable well-preserved Bell state fidelity when coexisting with 21.4-dBm aggregate launch power across the C-band suitable for 36-Tbps transmission. To the best of our knowledge, this is the first implementation of entanglement-based quantum communications between two remote nodes coexisting with independent classical communications traffic. We demonstrate coexistence of quantum entanglement with ultra-high power levels and record classical bandwidth, offering promise for real-world entanglement-based networking integrated within high-capacity communications infrastructure.

Talcott, Gina M. [Northwestern U.] (ORCID:00000002↗
DOE OSTI2015

Advanced Imaging Optics Utilizing Wavefront Coding

Image processing offers a potential to simplify an optical system by shifting some of the imaging burden from lenses to the more cost effective electronics. Wavefront coding using a cubic phase plate combined with image processing can extend the system's depth of focus, reducing many of the focus-related aberrations as well as material related chromatic aberrations. However, the optimal design process and physical limitations of wavefront coding systems with respect to first-order optical parameters and noise are not well documented. We examined image quality of simulated and experimental wavefront coded images before and after reconstruction in the presence of noise. Challenges in the implementation of cubic phase in an optical system are discussed. In particular, we found that limitations must be placed on system noise, aperture, field of view and bandwidth to develop a robust wavefront coded system.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

GPU Direct I/O with HDF5

Exascale HPC systems are being designed with accelerators, such as GPUs, to accelerate parts of applications. In machine learning workloads as well as large-scale simulations that use GPUs as accelerators, the CPU (or host) memory is currently used as a buffer for data transfers between GPU (or device) memory and the file system. If the CPU does not need to operate on the data, then this is sub-optimal because it wastes host memory by reserving space for duplicated data. Furthermore, this “bounce buffer” approach wastes CPU cycles spent on transferring data. A new technique, NVIDIA GPUDirect Storage (GDS), can eliminate the need to use the host memory as a bounce buffer. Thereby, it becomes possible to transfer data directly between the device memory and the file system. This direct data path shortens latency by omitting the extra copy and enables higher-bandwidth. To take full advantage of GDS in existing applications, it is necessary to provide support with existing I/O libraries, such as HDF5 and MPI-IO, which are heavily used in applications. In this paper, we describe our effort of integrating GDS with HDF5, the top I/O library at NERSC and at DOE leadership computing facilities. We design and implement this integration using a HDF5 Virtual File Driver (VFD). The GDS VFD provides a file system abstraction to the application that allows HDF5 applications to perform I/O without the need to move data between CPUs and GPUs explicitly. We compare performance of the HDF5 GDS VFD with explicit data movement approaches and demonstrate superior performance with the GDS method.

Ravi, J↗
DOE OSTI2018

Countering sensor drift in x-ray micrscopy with fast and robust optimal control

In X-ray microscopy it is imperative that the relative position between the optics stage, that carries the X-ray focusing optics, and the sample stage follow a certain trajectory while either the optics or sample stage is being scanned. Main challenges in achieving this requirement include - open loop drift, environmental disturbance, measurement noise, sensor drift, and control hardware limit. The state-of-the-art in X-ray microscopy at Advanced Photon Source (APS) at Argonne National Laboratory (ANL) features an H ∞ control architecture applied to only the optics stage or both the optics and sample stage, achieving the objectives of large tracking bandwidth over 200 Hz, good positioning resolution on the order of nanometers, rejection of environmental disturbance, attenuation of measurement noise, good Xray diffraction image resolution and increased imaging bandwidth. However, an unaddressed issue in our existing robust control design is that the sensors and the fixtures that hold the sensors drift with time due to changing air temperature in the APS beamline. Since the drift of sensor itself is not measured, it affects the relative position between the focusing optics and sample resulting into imaging artifacts and reduced image resolution. In this article, we demonstrate the rejection of the sensor drift by directly measuring the displacement of the sensor with respect to the global reference frame. Both the measured sensor displacement (i.e. sensor drift) and optics stage displacement are incorporated in the H ∞ control architecture to achieve the above mentioned objectives in addition to minimal relative displacement between the optics stage and the sample stage. This will improve the Xray image resolution and reduce image artifacts.

Robust Control↗
DOE OSTI2013

RRI-GBT MULTI-BAND RECEIVER: MOTIVATION, DESIGN, AND DEVELOPMENT

We report the design and development of a self-contained multi-band receiver (MBR) system, intended for use with a single large aperture to facilitate sensitive and high time-resolution observations simultaneously in 10 discrete frequency bands sampling a wide spectral span (100-1500 MHz) in a nearly log-periodic fashion. The development of this system was primarily motivated by need for tomographic studies of pulsar polar emission regions. Although the system design is optimized for the primary goal, it is also suited for several other interesting astronomical investigations. The system consists of a dual-polarization multi-band feed (with discrete responses corresponding to the 10 bands pre-selected as relatively radio frequency interference free), a common wide-band radio frequency front-end, and independent back-end receiver chains for the 10 individual sub-bands. The raw voltage time sequences corresponding to 16 MHz bandwidth each for the two linear polarization channels and the 10 bands are recorded at the Nyquist rate simultaneously. We present the preliminary results from the tests and pulsar observations carried out with the Robert C. Byrd Green Bank Telescope using this receiver. The system performance implied by these results and possible improvements are also briefly discussed.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Combining quantum noise reduction resources: A practical approach

Optomechanical sensors are capable of transducing external perturbations to resolvable optical signals. A particular regime of interest is that of high-bandwidth force detection, where an impulse is delivered to the system over a short period of time. Exceedingly sensitive impulse detection has been proposed to observe very weak signals like those due to long-range interactions with dark matter that require much higher sensitivities than current sensors can provide. Quantum resources to go beyond the traditional standard quantum limit of these sensors include squeezing of the light used to transduce the signal, backaction evasion by measuring the optimal quadrature, and quantum nondemolition (QND) measurements that reduce backaction directly. These methods have been developed in the context of gravitational wave detection for target frequencies in the audio band range. Here, we provide the theoretical limits to quantum noise reduction for higher and broader frequency targets, such as those from dark matter signals, while combining quantum-enhanced readout techniques based on squeezed light and QND measurements with optomechanical sensors. Here, we demonstrate that backaction evasion through QND techniques dramatically reduces the technical challenges presented when using squeezed light for broadband force detection, paving the way for combining multiple quantum noise reduction techniques for enhanced sensitivity in the context of impulse metrology.

Optomechanics↗
DOE OSTI2018

Crossover-Induced Spin Fluctuation and Electron Pairing in Strongly Correlated Electrons

We investigate the two-dimensional (2D) Hubbard model and d-p model as a model for cuprate high-temperature superconductors, by employing an optimized variational Monte Carlo method. We improved the many-body wave function starting from the simple Gutzwiller function. On the basis of optimized variational wave functions, we show that there is a superconducting phase in the ground state of the 2D Hubbard model. The on-site repulsive Coulomb interaction U can bring about high-temperature superconductivity because its characteristic energy is of the order of eV. The attractive interaction between electrons is induced by the crossover from weakly to strongly correlated regions. High-temperature superconductivity is possible in the strongly correlated region, where U is greater than the bandwidth.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

OpenACC unified programming environment for GPU and FPGA multi-hybrid acceleration

Attached accelerators have been frequently used in recent High Per- formance Computing (HPC) systems because of their high performance/power ratio. In particular, the Graphics Processing Unit (GPU) is the most popu- lar accelerator owing to its high peak FLOPS performance and high memory bandwidth supported by HBM2, etc. However, the performance of GPU depends highly on a large degree of SIMD parallelism and has difficulty sustaining a high performance on programs with frequent branch operations or a partially low degree of parallelism.By contrast, a Field Programmable Gate Array (FPGA) has received attention as a different type of accelerator than GPU as a fully reconfigurable processor fitting the target applications. The high performance of FPGA is mainly provided by a pipelined operation and optimized circuit suitable for any operation even with frequent conditional branches. We have been focusing on the flexibility of FPGA to compensate for the weakness of GPU. We believe that the coupling of GPU with FPGA can result in one of the most powerful accelerating platforms available.However, the program coding of GPU and FPGA coupling can be quite difficult for application users. Traditionally, CUDA by NVIDIA has been the most popular programming language with the largest share of GPUs used in HPC, whereas a hardware description language such as Verilog HDL has been used in FPGA programming. OpenCL coding has recently become available even on high-end FPGAs. Moreover, several recent studies have also enabled the OpenACC coding for use in FPGA. In this study, we provide a unified programming system based on OpenACC for a platform equipped with both GPU and FPGA aiming at the next-generation accelerated supercomputer framework. Our programming environment is called Multi-Hybrid OpenACC Translator (MHOAT), and in this paper, we describe the basic concept and prototype system of MHOAT based on an evaluation on the amount of coding required and the performance of a hybrid multi-device accelerated system.

Tsunashima, Ryuta↗
DOE OSTI2017

Solar upconversion with plasmon-enhanced bimolecular complexes

Upconversion of sub-bandgap photons is a promising approach to exceed the Shockley-Queisser limit in solar technologies. However, due to the low quantum efficiencies and narrow absorption bandwidths of upconverters, existing systems have only led to fractional percent improvements in photovoltaic devices (~0.01%). In this project, we aimed to develop an efficient upconverting material that could improve cell efficiencies by at least one absolute percent. To achieve this goal, we first used thermodynamic calculations to determine cell efficiencies with realistic upconverting materials. Then, we designed, synthesized, and characterized nanoantennas that promise >100x enhancement in both the upconverter absorption cross-section and emissive radiative rate. Concurrently, we optimized the upconverer by designing new ionic and molecular complexes that promise efficient solid-state upconversion. Lastly, with Bosch, we simulated record-efficiency semi-transparent cells that will allow for ready incorporation of our upconverting materials. While we were not successful in designing record efficiency upconverters during our three years of funding, we gained significant insight into the existing limitations of upconverters and how to best address these challenges. Ongoing work is aimed at addressing these limitations, to make upconversion a cost-competitive solar technology in future years.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48% ($H_T$) and 28% (AD), with a cumulative gain of up to 2% in signal efficiency on those in-tolerance intervals. Transferring from simulation to \emph{real} collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56% ($H_T$) and 28% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the \emph{first} demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).

Ding, Zixin [Chicago U.]↗
DOE OSTI2018

A Faraday-effect polarimeter for fast magnetic dynamics measurement on DIII-D

A Faraday-effect-based radial-interferometer-polarimeter diagnostic has been developed to explore fast magnetic dynamics in high-performance DIII-D plasmas. The instrument measures radial magnetic field perturbations using three chords positioned near the magnetic axis. Newly developed solid-state sources operating at 650 GHz provide phase noise down to 0.01°/$\sqrt{kHz}$ and tunable bandwidth up to 10 MHz. Various systematic errors which can contaminate the polarimetric measurement have been investigated in detail. Distortion of circular polarization due to non-ideal optical components is calibrated using a rotating quarter wave plate technique. The impact of perpendicular magnetic field, i.e., the Cotton-Mouton effect, is evaluated. The error due to non-collinearity of probe beams is minimized to less than 0.5° for electron density up to 7 × 10 19 m -3 by alignment optimization. Optical feedback, due to multiple reflections induced by the double-pass configuration, is identified and reduced. Lastly, coherent and broadband high-frequency magnetic fluctuations for DIII-D H-mode plasmas are observed.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

A high-power, high-repetition-rate THz source for pump–probe experiments at Linac Coherent Light Source II

Experiments using a THz pump and an X-ray probe at an X-ray free-electron laser (XFEL) facility like the Linac Coherent Light Source II (LCLS II) require frequency-tunable (3 to 20 THz), narrow bandwidth (~10%), carrier-envelope-phase-stable THz pulses that produce high fields (>1 MV cm –1 ) at the repetition rate of the X-rays and are well synchronized with them. Herein, a two-bunch scheme to generate THz radiation at LCLS II is studied: the first bunch produces THz radiation in an electromagnet wiggler immediately following the LCLS II undulator that produces X-rays from the second bunch. The initial time delay between the two bunches is optimized to compensate for the path difference in THz transport. The two-bunch beam dynamics, the THz wiggler and radiation are described, as well as the transport system bringing the THz pulses from the wiggler to the experimental hall.

42 ENGINEERING↗