Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “limited memory”

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 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
NASA NTRS1984

Utilization of Historic Information in an Optimisation Task

One of the basic components of a discrete model of motor behavior and decision making, which describes tracking and supervisory control in unitary terms, is assumed to be a filtering mechanism which is tied to the representational principles of human memory for time-series information. In a series of experiments subjects used the time-series information with certain significant limitations: there is a range-effect; asymmetric distributions seem to be recognized, but it does not seem to be possible to optimize performance based on skewed distributions. Thus there is a transformation of the displayed data between the perceptual system and representation in memory involving a loss of information. This rules out a number of representational principles for time-series information in memory and fits very well into the framework of a comprehensive discrete model for control of complex systems, modelling continuous control (tracking), discrete responses, supervisory behavior and learning.

Boesser, T.↗
DOE OSTI2023

CMSSW Scaling Limits on Many-Core Machines

Today the LHC offline computing relies heavily on CPU resources, despite the interest in compute accelerators, such as GPUs, for the longer term future. The number of cores per CPU socket has continued to increase steadily, reaching the levels of 64 cores (128 threads) with recent AMD EPYC processors, and 128 cores on Ampere Altra Max ARM processors. Over the course of the past decade, the CMS data processing framework, CMSSW, has been transformed from a single-threaded framework into a highly concurrent one. The first multithreaded version was brought into production by the start of the LHC Run 2 in 2015. Since then, the framework's threading efficiency has gradually been improved by adding more levels of concurrency and reducing the amount of serial code paths. The latest addition was support for concurrent Runs. In this work we review the concurrency model of the CMSSW, and measure its scalability with real CMS applications, such as simulation and reconstruction, on mode rn many-core machines. We show metrics such as event processing throughput and application memory usage with and without the contribution of I/O, as I/O has been the major scaling limitation for the CMS applications.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1999

A Flight/Ground/Test Event Logging Facility

The onboard control software for spacecraft such as Mars Pathfinder and Cassini is composed of many subsystems including executive control, navigation, attitude control, imaging, data management, and telecommunications. The software in all of these subsystems needs to be instrumented for several purposes: to report required telemetry data, to report warning and error events, to verify internal behavior during system testing, and to provide ground operators with detailed data when investigating in-flight anomalies. Events can range in importance from purely informational events to major errors. It is desirable to provide a uniform mechanism for reporting such events and controlling their subsequent processing. Since radiation-hardened flight processors are several years behind the speed and memory of their commercial cousins, and since most subsystems require real-time control, and since downlink rates to earth can be very low from deep space, there are limits to how much of the data can be saved and transmitted. Some kinds of events are more important than others and should therefore be preferentially retained when memory is low. Some faults can cause an event to recur at a high rate, but this must not be allowed to consume the memory pool. Some event occurrences may be of low importance when reported but suddenly become more important when a subsequent error event gets reported. Some events may be so low-level that they need not be saved and reported unless specifically requested by ground operators.

Dvorak, Daniel↗
DOE OSTI2024

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in scientific computations due to conveniently offering a ``shared-memory''-like model and convenient interfaces that separate communication with synchronization. Traditionally, PGAS communication models have been applied to dense/contiguously distributed data, but most modern applications depict varied levels of sparsity. Existing PGAS models require certain adaptations to support distributed sparse computations, since associated computations often require matrix arithmetic, in addition to data movement. The Global Arrays toolkit from Pacific Northwest National Laboratory (PNNL) is one of the earliest PGAS models to combine one-sided data communication and distributed matrix operations and is still used in the popular NWChem quantum chemistry suite. Recently, we have expanded the Global Arrays toolkit to support common sparse operations, like sparse matrix-dense matrix multiplies (SpMM), sparse matrix-sparse matrix multiplication (SpGEMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). As it turns out, these operations are the bedrock of sparse Deep Learning (DL); sparse deep neural networks and Graph Neural Networks (GNNs) have gained increasing attention recently in achieving speedups on training and inference with reduced memory footprints. Unlike scientific applications in High Performance Computing (HPC), modern (distributed-memory capable) DL toolkits often rely on non-standardized and closed-source vendor software optimizations, creating challenges in software-hardware co-design at scale. Our goal is to support a variety of distributed-memory sparse matrix operations and helper functions in the newly created Sparse Global Arrays (SGA), such that it is possible to build portable and productive Machine Learning scenarios for algorithm/software and hardware codesign purposes. Contemporary data-parallel schemes for training/inference are undergoing a major overhaul since model replication limits scalability and causes resource inefficiencies. As such, we have adopted tensor parallelism in decomposing the model and inputs, to mitigate memory issues. Current implementation is built on top of MPI and uses CPUs to maximize the portability across the platforms.

Distributed computing, machine learning↗
NASA NTRS1991

New dynamic FET logic and serial memory circuits for VLSI GaAs technology

The complexity of GaAs field effect transistor (FET) very large scale integration (VLSI) circuits is limited by the maximum power dissipation while the uniformity of the device parameters determines the functional yield. In this work, digital GaAs FET circuits are presented that eliminate the DC power dissipation and reduce the area to 50% of that of the conventional static circuits. Its larger tolerance to device parameter variations results in higher functional yield.

Eldin, A. G.↗
DOE OSTI2022

Memory access optimization for particle operations in computational fluid dynamics-discrete element method simulations

Computational Fluid Dynamics - Discrete Element Method is used to model gas-solid systems in several applications in energy, pharmaceutical and petrochemical industries. Computational performance bottlenecks often limit the problem sizes that can be simulated at industrial scale. The data structures used to store several millions of particles in such large-scale simulations have a large memory footprint that does not fit into the processor cache hierarchies on current high-performance-computing platforms, leading to reduced computational performance. This paper specifically addresses this aspect of memory access bottlenecks in industrial scale simulations. The use of space-filling curves to improve memory access patterns is described and their impact on computational performance is quantified in both shared and distributed memory parallelization paradigms. The Morton space filling curve applied to uniform grids and k-dimensional tree partitions are used to reorder the particle data-structure thus improving spatial and temporal locality in memory. The performance impact of these techniques when applied to two benchmark problems, namely the homogeneous-cooling-system and a fluidized-bed, are presented. We report these optimization techniques lead to approximately two-fold performance improvement in particle focused operations such as neighbor-list creation and data-exchange, with ~ 1.5 times overall improvement in a fluidization simulation with 1.27 million particles.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Field-Deployable Quantum Memory for Quantum Networking

High-performance quantum memories are an essential component for regulating temporal events in quantum networks. As a component in quantum-repeaters, they have the potential to support the distribution of entanglement beyond the physical limitations of fiber loss. This will enable key applications such as quantum key distribution, network-enhanced quantum sensing, and distributed quantum computing. Here, we present a quantum memory engineered to meet real-world deployment and scaling challenges. The memory technology utilizes a warm rubidium vapor as the storage medium, and operates at room temperature, without the need for vacuum- and/or cryogenic- support. Here, we demonstrate performance specifications of high-fidelity retrieval (95%) and low operation error (10 –2 ) at a storage time of 160 µs for single-photon level quantum memory operations. We further show a substantially improved storage time (with classical-level light) of up to 1ms by suppressing atomic diffusions. The device is housed in an enclosure with a standard 2U rackmount form factor, and can robustly operate on a day scale in a noisy environment. This result marks an important step toward implementing quantum networks in the field.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

FPGA-based HPC accelerators: An evaluation on performance and energy efficiency

Hardware specialization is a promising direction for the future of digital computing. Reconfigurable technologies enable hardware specialization with modest non-recurring engineering cost, but their performance and energy efficiency compared to state-of-the-art processor architectures remain an open question. In this article, we use FPGAs to evaluate the benefits of building specialized hardware for numerical kernels found in scientific applications. In order to properly evaluate performance, we not only compare Intel Arria 10 and Xilinx U280 performance against Intel Xeon, Intel Xeon Phi, and NVIDIA V100 GPUs, but we also extend the Empirical Roofline Toolkit (ERT) to FPGAs in order to assess our results in terms of the Roofline model. We show design optimization and tuning techniques for peak FPGA performance at reasonable hardware usage and power consumption. As FPGA peak performance is known to be far less than that of a GPU, we also benchmark the energy efficiency of each platform for the scientific kernels comparing against microbenchmark and technological limits. Results show that while FPGAs struggle to compete in absolute terms with GPUs on memory- and compute-intensive kernels, they require far less power and can deliver nearly the same energy efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Efficiently evaluating loop integrals in the EFTofLSS using QFT integrals with massive propagators

We develop a new way to analytically calculate loop integrals in the Effective Field Theory of Large Scale-Structure. Previous available methods show severe limitations beyond the one-loop power spectrum due to analytical challenges and computational and memory costs. Our new method is based on fitting the linear power spectrum with cosmology-independent functions that resemble integer powers of quantum field theory massive propagators with complex masses. A remarkably small number of them is sufficient to reach enough accuracy. Similarly to former approaches, the cosmology dependence is encoded in the coordinate vector of the expansion of the linear power spectrum in our basis. We first produce cosmology-independent tensors where each entry is the loop integral evaluated on a given combination of basis vectors. For each cosmology, the evaluation of a loop integral amounts to contracting this tensor with the coordinate vector of the linear power spectrum. The 3-dimensional loop integrals for our basis functions can be evaluated using techniques familiar to particle physics, such as recursion relations and Feynman parametrization. We apply our formalism to evaluate the one-loop bispectrum of galaxies in redshift space. The final analytical expressions are quite simple and can be evaluated with little computational and memory cost. We show that the same expressions resolve the integration of all one-loop N-point function in the EFTofLSS. This method, which is originally presented here, has already been applied in the first one-loop bispectrum analysis of the BOSS data to constraint ΛCDM parameters and primordial non-Gaussianities [1, 2].

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Evaluating sealability of blended smart polymer and fiber additive for geothermal drilling with the effect of fracture opening size

Geothermal formations often contain extensive fracture networks. These fracture networks contribute to the significant loss of drilling fluids during geothermal drilling. Multiple loss circulation materials (LCM) such as fiber, granules, and pills have been proposed to tackle this problem but with only limited success. Recent advances in materials science have led to the development of thermoset shape memory polymers (SMP) to address the lost circulation problem. In this paper, we evaluate a thermoset SMP performance in sealing near wellbore fractures of different sizes in geothermal wells. The SMP performance was assessed using granite disks and cylindrical granite cores having fracture sizes of 1000 μm and 3000 μm. A static filtration test was performed using cedar fiber, CaCO 3 , and SMP. Results showed cedar fiber performed better than the CaCO 3 ., reducing fluid loss by 89% and improving sealing pressure by 200 psi. A novel dynamic testing unit that allows for high-temperature testing under flowing conditions was used in this study. The analysis showed that 3% by weight SMP and fiber blends could bridge and plug the 1000 μm fracture. For a larger fracture of 3000 μm width, there was a need to increase the weight concentration of the SMP to 6% to plug the fracture opening effectively. We showed the influence of key parameters such as the type of LCM, concentration, and particle size distribution in optimizing the performance of drilling fluid loss treatment.

02 PETROLEUM↗
DOE OSTI2026

Knowledge-guided graph machine learning for spatially distributed prediction of daily discharge and nitrogen export dynamics

Spatially distributed prediction of streamflow and nitrogen export dynamics is essential for precision management of agricultural watersheds. While temporal deep learning models such as Long Short-Term Memory (LSTM) have shown strong performance at basin scales, their ability to generalize spatially is limited by insufficient representation of spatial dependencies and flow paths, particularly under data-scarce conditions. To address this gap, we propose HydroGraphNet, a knowledge-guided graph machine learning framework that integrates process-based knowledge and explicit spatial learning into temporal modeling. This framework incorporates directed graph topology to encode watershed connectivity and upstream inflows, with mass balance constraints to improve physical consistency. To enhance generalization in sparsely monitored regions, HydroGraphNet is pretrained on synthetic data generated by the SWAT+ (Soil and Water Assessment Tool Plus) model. We evaluated HydroGraphNet in the Upper Sangamon River Basin (44 HUC-12 subwatersheds, 2001–2020) against two LSTM baselines: a lumped basin-level model and a distributed variant. When benchmarked on SWAT+ simulations in pretraining, HydroGraphNet improved test NSEs by 8.9% (discharge) and 13.7% (NO₃–N load) in temporal extrapolation, and by 27.1% and 34.7% in spatial extrapolation, relative to the Lumped LSTM baseline. After fine-tuning with USGS monitoring data, the model achieved mean test NSE (KGE) scores of 0.768 (0.861) for discharge and 0.626 (0.664) for NO₃–N load, substantially outperforming baselines. Attribution analysis further highlighted the importance of upstream inflow representation and graph-based spatial learning in capturing cross-subwatershed dependencies. The model also reproduced seasonal hydrological and biogeochemical patterns consistent with known processes, demonstrating its robustness and process fidelity for spatially distributed prediction. Altogether, HydroGraphNet advances the integration of physical knowledge and spatially explicit learning in hydrological modeling, offering a generalizable framework for distributed modeling to support spatially targeted water quality management in data-scarce watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Enhanced ferroelectricity in ultrathin films grown directly on silicon

Ultrathin ferroelectric materials could potentially enable low-power logic and nonvolatile memories. As ferroelectric materials are made thinner, however, the ferroelectricity is usually suppressed. Size effects in ferroelectrics have been thoroughly investigated in perovskite oxides—the archetypal ferroelectric system. Perovskites, however, have so far proved unsuitable for thickness scaling and integration with modern semiconductor processes. In this paper we report ferroelectricity in ultrathin doped hafnium oxide (HfO 2 ), a fluorite-structure oxide grown by atomic layer deposition on silicon. We demonstrate the persistence of inversion symmetry breaking and spontaneous, switchable polarization down to a thickness of one nanometre. Our results indicate not only the absence of a ferroelectric critical thickness but also enhanced polar distortions as film thickness is reduced, unlike in perovskite ferroelectrics. This approach to enhancing ferroelectricity in ultrathin layers could provide a route towards polarization-driven memories and ferroelectric-based advanced transistors. This work shifts the search for the fundamental limits of ferroelectricity to simpler transition-metal oxide systems—that is, from perovskite-derived complex oxides to fluorite-structure binary oxides—in which ‘reverse’ size effects counterintuitively stabilize polar symmetry in the ultrathin regime.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Fourier-based three-dimensional multistage transformer for aberration correction in multicellular specimens

High-resolution tissue imaging is often compromised by sample-induced optical aberrations that degrade resolution and contrast. Although wavefront sensor-based adaptive optics (AO) can measure these aberrations, such hardware solutions are typically complex, expensive to implement and slow when serially mapping spatially varying aberrations across large fields of view. Here we introduce AOViFT (adaptive optical vision Fourier transformer)—a machine learning-based aberration sensing framework built around a three-dimensional multistage vision transformer that operates on Fourier domain embeddings. AOViFT infers aberrations and restores diffraction-limited performance in puncta-labeled specimens with substantially reduced computational cost, training time and memory footprint compared to conventional architectures or real-space networks. We validated AOViFT on live gene-edited zebrafish embryos, demonstrating its ability to correct spatially varying aberrations using either a deformable mirror or postacquisition deconvolution. By eliminating the need for the guide star and wavefront sensing hardware and simplifying the experimental workflow, AOViFT lowers technical barriers for high-resolution volumetric microscopy across diverse biological samples.

Alshaabi, Thayer [Howard Hughes Medical Institute,↗
DOE OSTI2024

Characterization of throughput on the AXI DMA bus for burst data transfer over Ethernet

cThe Xilinx AXI Direct Memory Access (AXI DMA) module is an efficient solution for medium-speed data transfer in Xilinx SoC FPGAs, supporting data rates greater than 1000 Gbps even in very suboptimal operating modes. It facilitates direct transfer of AXI stream data into processor memory without constant software intervention, which reduces overhead and ensures consistent data logging. By utilizing the FPGA's available memory, large circular buffers (1-5 GiB) are used to buffer data and accommodate network limitations, enabling high-rate data bursts. In this study, we measured the performance of AXI DMA under conditions simulating its lowest practical data transfer speeds. The Arbitrary Length Data Sender was used to transmit AXI stream packets at 32-bit width and 100 MHz frequency, a narrow width and slow speed. Results show that the AXI DMA can transfer up to 3192.76 Mbps with large packet sizes but experiences reduced performance for smaller packets, as low as 2.6 Mbps for 4-byte packets. For Ethernet-limited applications, packet sizes between 8,000 and 16,000 bytes provided optimal transfer speeds of 874 to 1600 Mbps. These findings suggest that the AXI DMA is not the limiting factor in systems where packet sizes exceed 8,000 bytes.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars

Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse data sets has thus far hampered a direct intercomparison of different approaches. Here we perform the first comprehensive study of variants of NN-based learning and inference for astronomical time series, aiming to provide the community with an overview on relative performance and, hopefully, a set of best-in-class choices for practical implementations. In both supervised and self-supervised contexts, we study the effects of different time-series-compatible layer choices, namely the dilated temporal convolutional neural network (dTCNs), long-short term memory NNs, gated recurrent units and temporal convolutional NNs (tCNNs). Additionally, we also study the efficacy and performance of encoder-decoder (i.e., autoencoder) networks compared to direct classification networks, different pathways to include auxiliary (non-time-series) metadata, and different approaches to incorporate multi-passband data (i.e., multiple time series per source). Performance—applied to a sample of 17,604 variable stars (VSs) from the MAssive Compact Halo Objects (MACHO) survey across 10 imbalanced classes—is measured in training convergence time, classification accuracy, reconstruction error, and generated latent variables. We find that networks with recurrent NNs generally outperform dTCNs and, in many scenarios, yield to similar accuracy as tCNNs. In learning time and memory requirements, convolution-based layers perform better. We conclude by discussing the advantages and limitations of deep architectures for VS classification, with a particular eye toward next-generation surveys such as the Legacy Survey of Space and Time, the Roman Space Telescope, and Zwicky Transient Facility.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1981

Selecting an image analysis minicomputer system

Factors to be weighed when selecting a minicomputer system as the basis for an image analysis computer facility vary depending on whether the user organization procures a new computer or selects an existing facility to serve as an image analysis host. Some conditions not directly related to hardware or software should be considered such as the flexibility of the computer center staff, their encouragement of innovation, and the availability of the host processor to a broad spectrum of potential user organizations. Particular attention must be given to: image analysis software capability; the facilities of a potential host installation; the central processing unit; the operating system and languages; main memory; disk storage; tape drives; hardcopy output; and other peripherals. The operational environment, accessibility; resource limitations; and operational supports are important. Charges made for program execution and data storage must also be examined.

Danielson, R.↗
NASA NTRS2006

Electronics Shielding and Reliability Design Tools

It is well known that electronics placement in large-scale human-rated systems provides opportunity to optimize electronics shielding through materials choice and geometric arrangement. For example, several hundred single event upsets (SEUs) occur within the Shuttle avionic computers during a typical mission. An order of magnitude larger SEU rate would occur without careful placement in the Shuttle design. These results used basic physics models (linear energy transfer (LET), track structure, Auger recombination) combined with limited SEU cross section measurements allowing accurate evaluation of target fragment contributions to Shuttle avionics memory upsets. Electronics shielding design on human-rated systems provides opportunity to minimize radiation impact on critical and non-critical electronic systems. Implementation of shielding design tools requires adequate methods for evaluation of design layouts, guiding qualification testing, and an adequate follow-up on final design evaluation including results from a systems/device testing program tailored to meet design requirements.

Wilson, John W.↗
NASA NTRS2013

FPGA Flash Memory High Speed Data Acquisition

The purpose of this research is to design and implement a VHDL ONFI Controller module for a Modular Instrumentation System. The goal of the Modular Instrumentation System will be to have a low power device that will store data and send the data at a low speed to a processor. The benefit of such a system will give an advantage over other purchased binary IP due to the capability of allowing NASA to re-use and modify the memory controller module. To accomplish the performance criteria of a low power system, an in house auxiliary board (Flash/ADC board), FPGA development kit, debug board, and modular instrumentation board will be jointly used for the data acquisition. The Flash/ADC board contains four, 1 MSPS, input channel signals and an Open NAND Flash memory module with an analog to digital converter. The ADC, data bits, and control line signals from the board are sent to an Microsemi/Actel FPGA development kit for VHDL programming of the flash memory WRITE, READ, READ STATUS, ERASE, and RESET operation waveforms using Libero software. The debug board will be used for verification of the analog input signal and be able to communicate via serial interface with the module instrumentation. The scope of the new controller module was to find and develop an ONFI controller with the debug board layout designed and completed for manufacture. Successful flash memory operation waveform test routines were completed, simulated, and tested to work on the FPGA board. Through connection of the Flash/ADC board with the FPGA, it was found that the device specifications were not being meet with Vdd reaching half of its voltage. Further testing showed that it was the manufactured Flash/ADC board that contained a misalignment with the ONFI memory module traces. The errors proved to be too great to fix in the time limit set for the project.

Gonzalez, April↗