Search NASA⌕ Search

SEARCH · Search NASA

Results for “spatial 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 127 records · Page 7

Locality Aware Concurrent Start for Stencil Applications

Stencil computations are at the heart of many physical simulations used in scientific codes. Thus, there exists a plethora of optimization efforts for this family of computations. Among these techniques, tiling techniques that allow concurrent start have proven to be very efficient in providing better performance for these critical kernels. Nevertheless, with many core designs being the norm, these optimization techniques might not be able to fully exploit locality (both spatial and temporal) on multiple levels of the memory hierarchy without compromising parallelism. It is no longer true that the machine can be seen as a homogeneous collection of nodes with caches, main memory and an interconnect network. New architectural designs exhibit complex grouping of nodes, cores, threads, caches and memory connected by an ever evolving network-on-chip design. These new designs may benefit greatly from carefully crafted schedules and groupings that encourage parallel actors (i.e. threads, cores or nodes) to be aware of the computational history of other actors in close proximity. In this paper, we provide an efficient tiling technique that allows hierarchical concurrent start for memory hierarchy aware tile groups. Each execution schedule and tile shape exploit the available parallelism, load balance and locality present in the given applications. We demonstrate our technique on the Intel Xeon Phi architecture with selected and representative stencil kernels. We show improvement ranging from 5.58% to 31.17% over existing state-of-the-art techniques.

Locality Aware execution, jagged tiling↗

A Cut-Cell Approach for 2D Cartesian Meshes that Preserves Orthogonal Grid Sweep Ordering

In this paper, we present a cut-cell methodology for solving the two-dimensional neutral-particle transport equation on an orthogonal Cartesian grid. We allow the rectangular cell to be subdivided into two polygonal subcells. We ensure that this division (or cut) conserves the volumes of the materials in the subcells and we utilize a step-characteristics (SC) slice balance approach (SBA) to calculate the angular fluxes exiting the cell as well as the average scalar fluxes in each subcell. Solving the discrete ordinates transport equation on an arbitrary mesh has historically been difficult to parallelize while maintaining good parallel efficiency. However on Cartesian meshes, the KBA algorithm maintains good parallel efficiency using a direct solve. The ability to preserve this algorithm was a driving factor in the development of our cut-cell method. This method also provides a more accurate depiction of a material interface in a cell, which leads to more accurate solutions downstream of this cell. As a result, fewer spatial cells can be utilized, resulting in reduced memory requirements. We apply this approach in the 2D/3D discrete ordinates neutral-particle transport code Denovo, where we analyze a 2D 3 x 3 lattice of pincells. We show that, for eigenvalue problems, a significant increase in accuracy for a given mesh size is gained by utilizing the cut-cell, SC equations instead of the standard homogenized-cell, SC equations.

99 GENERAL AND MISCELLANEOUS↗

An effective online data monitoring and saving strategy for large-scale climate simulations

Large-scale climate simulation models have been developed and widely used to generate historical data and study future climate scenarios. These simulation models often have to run for a couple of months to understand the changes in the global climate over the course of decades. This long-duration simulation process creates a huge amount of data with both high temporal and spatial resolution information; however, how to effectively monitor and record the climate changes based on these large-scale simulation results that are continuously produced in real time still remains to be resolved. Due to the slow process of writing data to disk, the current practice is to save a snapshot of the simulation results at a constant, slow rate although the data generation process runs at a very high speed. This study proposes an effective online data monitoring and saving strategy over the temporal and spatial domains with the consideration of practical storage and memory capacity constraints. Finally, our proposed method is able to intelligently select and record the most informative extreme values in the raw data generated from real-time simulations in the context of better monitoring climate changes.

54 ENVIRONMENTAL SCIENCES↗

Efficacy of Code Optimization on Cache-based Processors

The current common wisdom in the U.S. is that the powerful, cost-effective supercomputers of tomorrow will be based on commodity (RISC) micro-processors with cache memories. Already, most distributed systems in the world use such hardware as building blocks. This shift away from vector supercomputers and towards cache-based systems has brought about a change in programming paradigm, even when ignoring issues of parallelism. Vector machines require inner-loop independence and regular, non-pathological memory strides (usually this means: non-power-of-two strides) to allow efficient vectorization of array operations. Cache-based systems require spatial and temporal locality of data, so that data once read from main memory and stored in high-speed cache memory is used optimally before being written back to main memory. This means that the most cache-friendly array operations are those that feature zero or unit stride, so that each unit of data read from main memory (a cache line) contains information for the next iteration in the loop. Moreover, loops ought to be 'fat', meaning that as many operations as possible are performed on cache data-provided instruction caches do not overflow and enough registers are available. If unit stride is not possible, for example because of some data dependency, then care must be taken to avoid pathological strides, just ads on vector computers. For cache-based systems the issues are more complex, due to the effects of associativity and of non-unit block (cache line) size. But there is more to the story. Most modern micro-processors are superscalar, which means that they can issue several (arithmetic) instructions per clock cycle, provided that there are enough independent instructions in the loop body. This is another argument for providing fat loop bodies. With these restrictions, it appears fairly straightforward to produce code that will run efficiently on any cache-based system. It can be argued that although some of the important computational algorithms employed at NASA Ames require different programming styles on vector machines and cache-based machines, respectively, neither architecture class appeared to be favored by particular algorithms in principle. Practice tells us that the situation is more complicated. This report presents observations and some analysis of performance tuning for cache-based systems. We point out several counterintuitive results that serve as a cautionary reminder that memory accesses are not the only factors that determine performance, and that within the class of cache-based systems, significant differences exist.

VanderWijngaart, Rob F.↗

An Integrated Framework for Memory-Centric Analysis: From Trace Collection to Co-Design

The memory wall phenomenon—where advances in processor performance significantly outpace those in memory subsystems—poses a fundamental challenge for contemporary computing systems. In memory-bound applications, memory subsystem behavior dominates performance, yet existing analysis approaches present significant limitations: detailed microarchitectural simulators require days to weeks to simulate modest workloads; hardware performance counters provide only aggregate statistics that obscure temporal and spatial access patterns; and scaled simulation approaches face challenges in capturing certain behaviors that emerge at larger scales. These limitations reflect a processor-centric design philosophy increasingly misaligned with memory-bound workloads where detailed understanding of memory access patterns, cache hierarchy interactions, and contention is critical for effective optimization. This paper presents an integrated framework for memory-centric analysis that enables effective hardware-software co-design. We describe practical trace collection techniques, including hardware-assisted processor tracing with minimal overhead and portable software-based instrumentation with statistical sampling. We present multi-perspective analysis methods that examine memory behavior from temporal, sequential, spatial, and relational viewpoints, revealing distinct optimization opportunities invisible in aggregate metrics. We detail an architectural modeling framework that uses sampled traces with temporal interpolation and confidence-based filtering to evaluate cache and memory configurations. Evaluation on representative benchmarks demonstrates that this framework achieves practical accuracy (L2 cache errors of 2.64\%, confidence-filtered L3 errors of 9.92\%, bandwidth errors of 7.33\%) while providing substantial speedup (26.8×) over cycle-accurate simulation, enabling rapid design space exploration. We demonstrate how this integrated framework enables systematic identification of both hardware optimizations (memory controller tuning, bank partitioning, NUMA configuration) and software optimizations (data layout restructuring, prefetching strategies, memory-aware scheduling). Through this comprehensive treatment of the memory-centric analysis pipeline—from trace collection through architectural modeling to co-design application—we provide researchers and practitioners with practical techniques for addressing memory bottlenecks in contemporary computing systems.

Gajaria, Dhruv Mayur↗

Inductive predictions of hydrologic events using a Long Short-Term Memory network and the Soil and Water Assessment Tool

We present machine learning methods to predict hydrologic features such as streamflow and soil moisture from spatially and temporally varying hydrological and meteorological data. Here, we used a temporal reduction technique to reduce computation and memory requirements and trained a Long Short-Term Memory (LSTM) network to predict soil moisture and streamflow over multiple watersheds. We show LSTM networks can be trained in a fraction of the time required by complex process-based and attention-based models such as Soil and Water Assessment Tool (SWAT) and GeoMAN without sacrificing accuracy. We also demonstrate that outside data - sourced from a watershed other than the target - can be used to train LSTM to comparable or even superior prediction accuracy. The success of LSTM in such spatially-inductive settings shows hydrologic features can be predicted with minimal prior knowledge of the watershed in question. Finally, we make all methodologies of this work publicly available as an end-to-end software pipeline that facilitates rapid prototyping of hydrologic learners.

97 MATHEMATICS AND COMPUTING↗

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↗

Differential equations for cosmological correlators

Cosmological fluctuations retain a memory of the physics that generated them in their spatial correlations. The strength of correlations varies smoothly as a function of external kinematics, which is encoded in differential equations satisfied by cosmological correlation functions. In this work, we provide a broader perspective on the origin and structure of these differential equations. As a concrete example, we study conformally coupled scalar fields in a power-law cosmology. The wavefunction coefficients in this model have integral representations, with the integrands being the product of the corresponding flat-space results and “twist factors” that depend on the cosmological evolution. Similar twisted integrals arise for loop amplitudes in dimensional regularization, and their recent study has led to the discovery of rich mathematical structures and powerful new tools for computing multi-loop Feynman integrals in quantum field theory. The integrals of interest in cosmology are also part of a finite-dimensional basis of master integrals, which satisfy a system of first-order differential equations. We develop a formalism to derive these differential equations for arbitrary tree graphs. The results can be represented in graphical form by associating the singularities of the differential equations with a set of graph tubings. Upon differentiation, these tubings grow in a local and predictive fashion. In fact, a few remarkably simple rules allow us to predict — by hand — the equations for all tree graphs. While the rules of this “kinematic flow” are defined purely in terms of data on the boundary of the spacetime, they reflect the physics of bulk time evolution. We also study the analogous structures in tr ϕ 3 theory, and see some glimpses of hidden structure in the sum over planar graphs. This suggests that there is an autonomous combinatorial or geometric construction from which cosmological correlations, and the associated spacetime, emerge.

Cosmological models↗

Fracture Characterization Via AI‐Assisted Analysis of Temperature Logs

Abstract Fractures control fluid flow, mass transport, and heat transfer in a geothermal reservoir. This makes accurate characterization of fracture networks a prerequisite for optimal design and control of a reservoir's exploitation. We develop a deep‐learning procedure to identify fracture locations via interpretation of temporally and spatially continuous downhole temperature measurements. A long short‐term memory fully convolutional network (LSTM‐FCN) is used both to capture long‐term dependencies in sequential temperature data and to distill local features around fractures. A wellbore and fractured‐reservoir thermal model is established to generate temperature data for network training. The trained LSTM‐FCN exhibits a unique ability to detect multiple fractures intersecting a borehole. We use the LSTM‐FCN algorithm to evaluate the effectiveness of different‐stage wellbore temperature measurements on fracture detection in a complex fractured system. Our experiments reveal that the use of various‐stage temperature information as an input feature set improves the robustness of fracture detection to noise interference. This study indicates the practical feasibility of obtaining accurate fracture‐network reconstructions from temperature signals, at reasonable computational cost.

Yang, Xiaoyu↗

Enhancement of carrier lifetimes in type-II quantum dot/quantum well hybrid structures

We investigate optical transitions and carrier dynamics in hybrid structures containing type-I GaAs/AlGaAs quantum wells (QWs) and type-II GaSb/AlGaAs quantum dots (QDs). We show that the optical recombination of photocreated electrons confined in the QWs with holes in the QDs and wetting layer can be modified according to the QW/QD spatial separation. In particular, for low spacer thicknesses, the QW optical emission can be suppressed due to the transference of holes from the QW to the GaSb layer, favoring the optical recombination of spatially separated carriers, which can be useful for optical memory and solar cell applications. Time-resolved photoluminescence (PL) measurements reveal non-exponential recombination dynamics. We demonstrate that the PL transients can only be quantitatively described by considering both linear and quadratic terms of the carrier density in the bimolecular recombination approximation for type-II semiconductor nanostructures. We extract long exciton lifetimes from 700 ns to 5 μs for QDs depending on the spacer layer thickness.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Four-wave-mixing gap solitons

We report an experimental demonstration of generating gap soliton trains in a four-wave-mixing (FWM) signal. Such spatial FWM surfacelike gap soliton trains are induced in a periodically modulated self-defocusing atomic medium by the cross-phase modulation, which can be reshaped under different experimental conditions, such as different atomic densities, nonlinear dispersions, and dressing fields. Controlling spatial gap solitons can have important applications in image memory, processing, and communication.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Exploring Hardware Support For Scaling Irregular Applications on Multi-node Multi-core Architectures

With the recent emergence of large-scale knowledge dis- covery, data mining and social network analysis, irregular applications have gained renewed interest. Classic cache-based high-performance architectures do not provide optimal performances with such kind of workloads, mainly due to the very low spatial and temporal locality of the irregular control and memory access patterns. In this paper, we present a multi-node, multi-core, fine-grained multi-threaded shared-memory system architecture specifically designed for the execution of large-scale irregular applications, and built on top of three pillars, that we believe are fundamental to support these workloads. First, we offer transparent hardware support for Partitioned Global Address Space (PGAS) to provide a large globally-shared address space with no software library overhead. Second, we employ multi-threaded multi-core processing nodes to achieve the necessary latency tolerance required by accessing global memory, which potentially resides in a remote node. Finally, we devise hardware support for inter-thread synchronization on the whole global address space. We first model the performances by using an analytical model that takes into account the main architecture and application characteristics. We describe the hardware design of the proposed cus- tom architectural building blocks that provide support for the above- mentioned three pillars. Finally, we present a limited-scale evaluation of the system on a multi-board FPGA prototype with typical irregular kernels and benchmarks. The experimental evaluation demonstrates the architecture performance scalability for different configurations of the whole system.

FPGA↗

MACORD: Online Adaptive Machine Learning Framework for Silent Error Detection

Future HPC systems with ever-increasing resource capacity (such as compute cores, memory and storage) may significantly increase the risks on reliability. Silent data corruptions (SDCs) or silent errors are one of the major sources that corrupt HPC execution results. Unlike fail-stop errors, SDCs are rather harmful and dangerous in that they cannot be detected by hardware. We propose an online machine-learning based silent data corruption detection framework (abbreviated as MACORD) for detecting SDCs in HPC applications. In particular, we comprehensively investigate the prediction ability of a multitude of machine-learning algorithms in our study, and enable the detector to automatically select the best-fit algorithms at runtime to adapt to the data dynamics. Our learning framework exhibits low memory overhead (less than 1%), since it takes only spatial features (i.e., neighboring data values for each data point in the current time step) into the training data. Experiments based on real-world scientific applications/benchmarks show that our framework can get the detection sensitivity (i.e., recall) up to 99% while the false positive rate is limited to 0.1% in most cases, which is one order of magnitude improvement compared with the latest state-of-art spatial technique.

Subasi, Omer↗

Particle simulation of plasmas on the massively parallel processor

Particle simulations, in which collective phenomena in plasmas are studied by following the self consistent motions of many discrete particles, involve several highly repetitive sets of calculations that are readily adaptable to SIMD parallel processing. A fully electromagnetic, relativistic plasma simulation for the massively parallel processor is described. The particle motions are followed in 2 1/2 dimensions on a 128 x 128 grid, with periodic boundary conditions. The two dimensional simulation space is mapped directly onto the processor network; a Fast Fourier Transform is used to solve the field equations. Particle data are stored according to an Eulerian scheme, i.e., the information associated with each particle is moved from one local memory to another as the particle moves across the spatial grid. The method is applied to the study of the nonlinear development of the whistler instability in a magnetospheric plasma model, with an anisotropic electron temperature. The wave distribution function is included as a new diagnostic to allow simulation results to be compared with satellite observations.

Gledhill, I. M. A.↗

Index grating lifetime in photorefractive GaAs

The index grating lifetime in liquid encapsulated Czochralski-grown undoped semi-insulating GaAs was measured using a beam coupling technique. The largest lifetime measure was about 8 s under a read beam intensity of 0.7 mW/sq cm with the grating periodicity being 0.63 microns. The measured value decreases to milliseconds as the read beam intensity and the grating periodicity increase to about 10 mW/sq cm and 4 microns, respectively. This range of grating lifetime in this material is adequate for its use in real-time spatial light modulators, reconfigurable beam steering devices, and dynamic memory elements, for optical computing. In addition, the results suggest that the lifetime is sensitive to residual imperfections in the crystal.

Cheng, Li-Jen↗

Quantitative Monitoring for Enhanced Geothermal Systems Using Double-Difference Waveform Inversion with Spatially-Variant Total-Variation Regularization

Double-difference waveform inversion is a promising tool for quantitative monitoring for enhanced geothermal systems (EGS). The method uses time-lapse seismic data to jointly inverts for reservoir changes. Due to the ill-posedness of waveform inversion, it is a great challenge to obtain reservoir changes accurately and efficiently, particularly when using timelapse seismic reflection data. To improve reconstruction, we develop a spatially-variant total-variation regularization scheme into double-difference waveform inversion to improve the inversion accuracy and robustness. The new regularization scheme employs different regularization parameters in different regions of the model to obtain an optimal regularization in each area. We compare the results obtained using a spatially-variant parameter with those obtained using a constant regularization parameter. Utilizing a spatially-variant regularization scheme, the target monitoring regions are well reconstructed and the image noise is significantly reduced outside the monitoring regions. Our numerical examples demonstrate that the spatially-variant total-variation regularization scheme provides the flexibility to regularize local regions based on the a priori spatial information without increasing computational costs and the computer memory requirement.

ACCURACY↗

Comprehension of Spatial Constraints by Neural Logic Learning from a Single RGB-D Scan

Autonomous industrial assembly relies on the precise measurement of spatial constraints as designed by computer-aided design (CAD) software such as SolidWorks. This paper proposes a framework for an intelligent industrial robot to understand the spatial constraints for model assembly. An extended generative adversary network (GAN) with a 3D long short-term memory (LSTM) network was designed to composite 3D point clouds from a single RGB-D scan. The spatial constraints of the segmented point clouds are identified by a neural-logic network that incorporates general knowledge of spatial constraints in terms of first-order logic. The model was designed to comprehend a complete set of spatial constraints that are consistent with industrial CAD software, including left, right, above, below, front, behind, parallel, perpendicular, concentric, and coincident relations. The accuracy of 3D model composition and spatial constraint identification was evaluated by the RGB-D scans and 3D models in the ABC dataset. The proposed model achieved 57.23% intersection over union (IoU) in 3D model composition, and over 99% in comprehending all spatial constraints.

Wang, Dali↗

Scaling kinetic Monte-Carlo simulations of grain growth with combined convolutional and graph neural networks

Graph neural networks (GNN) have emerged as a promising machine learning method for microstructure simulations such as grain growth. However, accurate modeling of realistic grain boundary networks requires large simulation cells, which GNN has difficulty scaling up to. To alleviate the computational costs and memory footprint of GNN, we suggest a hybrid architecture combining a convolutional neural network (CNN) based bijective autoencoder to compress the spatial dimensions, and a GNN that evolves the microstructure in the latent space of reduced spatial sizes. Our results demonstrate that the new design significantly reduces computational costs with using fewer message passing layer (from 12 down to 3) compared with GNN alone. The reduction in computational cost becomes more pronounced as the spatial size increases, indicating strong computational scalability. For the largest mesh evaluated (160 3 ), our method reduces memory usage and runtime in inference by 117× and 115×, respectively, compared with GNN-only baseline. More importantly, it shows higher accuracy and stronger spatiotemporal capability than the GNN-only baseline, especially in long-term testing. Such combination of scalability and accuracy is essential for simulating realistic material microstructures over extended time scales. The improvements can be attributed to the bijective autoencoder’s ability to compress information losslessly from spatial domain into a high dimensional feature space, thereby producing more expressive latent features for the GNN to learn from, while also contributing its own spatiotemporal modeling capability. Training data are generated from stochastic grain growth simulations, providing realistic variability for learning robust microstructure evolution. Comprehensive system validation confirms that the model is accurate, robust, and scalable.

36 MATERIALS SCIENCE↗