Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “compute in 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 775 records · Page 43
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Quantifying Information without Entropy: Identifying Intermittent Disturbances in Dynamical Systems

A system’s response to disturbances in an internal or external driving signal can be characterized as performing an implicit computation, where the dynamics of the system are a manifestation of its new state holding some memory about those disturbances. Identifying small disturbances in the response signal requires detailed information about the dynamics of the inputs, which can be challenging. This paper presents a new method called the Information Impulse Function (IIF) for detecting and time-localizing small disturbances in system response data. The novelty of IIF is its ability to measure relative information content without using Boltzmann’s equation by modeling signal transmission as a series of dissipative steps. Since a detailed expression of the informational structure in the signal is achieved with IIF, it is ideal for detecting disturbances in the response signal, i.e., the system dynamics. Those findings are based on numerical studies of the topological structure of the dynamics of a nonlinear system due to perturbated driving signals. The IIF is compared to both the Permutation entropy and Shannon entropy to demonstrate its entropy-like relationship with system state and its degree of sensitivity to perturbations in a driving signal.

42 ENGINEERING↗
DOE OSTI2021

The Effect of the Flux Separability Approximation on Multigroup Neutron Transport

The angular dependence of flux-weighted multigroup cross sections is commonly neglected when generating multigroup libraries. The error of this flux separability approximation is typically not isolated from other error sources due to a lack of availability of library generation and corresponding solvers that cannot relax this approximation. These errors can now be isolated and quantified with the availability of a multigroup Monte Carlo transport and multigroup library-generation capability in the OpenMC Monte Carlo transport code. This work will discuss relevant details of the OpenMC implementation, provide an example case useful for detailing the type of errors one can expect from making the flux separability approximation, and end with more realistic problems which show the impact of the approximation and highlight how it can strongly arise from an energy-dependent resonance absorption effect. Since the angle-dependence is intrinsically linked to the energy group structure, these examples also show that relaxing the flux separability approximation with angle-dependent cross sections could be used to reduce either the fine-tuning required to set a multigroup energy structure for a specific reactor type or the number of energy groups required to obtain a desired level of accuracy for a given problem. This trade-off could increase the costs of generating multigroup cross sections, and has the potential to require more memory for storing the multigroup library during the transport calculations, but it can significantly reduce the computational time required since the runtime of a discrete ordinates or method of characteristics neutron transport solver scales roughly linearly with the number of groups.

42 ENGINEERING↗
DOE OSTI2023

Machine Learning-Based Model Predictive Control of Two-Time-Scale Systems

In this study, we present a general form of nonlinear two-time-scale systems, where singular perturbation analysis is used to separate the dynamics of the slow and fast subsystems. Machine learning techniques are utilized to approximate the dynamics of both subsystems. Specifically, a recurrent neural network (RNN) and a feedforward neural network (FNN) are used to predict the slow and fast state vectors, respectively. Moreover, we investigate the generalization error bounds for these machine learning models approximating the dynamics of two-time-scale systems. Next, under the assumption that the fast states are asymptotically stable, our focus shifts toward designing a Lyapunov-based model predictive control (LMPC) scheme that exclusively employs the RNN to predict the dynamics of the slow states. Additionally, we derive sufficient conditions to guarantee the closed-loop stability of the system under the sample-and-hold implementation of the controller. A nonlinear chemical process example is used to demonstrate the theory. In particular, two RNN models are constructed: one to model the full two-time-scale system and the other to predict solely the slow state vector. Both models are integrated within the LMPC scheme, and we compare their closed-loop performance while assessing the computational time required to execute the LMPC optimization problem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

The Locus Algorithm IV: Performance metrics of a grid computing system used to create catalogues of optimised pointings

This paper discusses the requirements for and performance metrics of the the Grid Computing system used to implement the Locus Algorithm to identify optimum pointings for differential photometry of 61,662,376 stars and 23,779 quasars. Initial operational tests indicated a need for a software system to analyse the data and a High Performance Computing system to run that software in a scalable manner. Practical assessments of the performance of the software in a serial computing environment were used to provide a benchmark against which the performance metrics of the HPC solution could be compared, as well as to indicate any bottlenecks in performance. These performance metrics indicated a distinct split in the performance dictated more by differences in the input data than by differences in the design of the systems used. This indicates a need for experimental analysis of system performance, and suggests that algorithmic complexity analyses may lead to incorrect or naive conclusions, especially in systems with high data I/O overhead such as grid computing. Further, it implies that systems which reduce or eliminate this bottleneck such as in-memory processing could lead to a substantial increase in performance.

Creaner, Oisín↗
DOE OSTI2021

Systems and methods for rapid processing and storage of data

Systems and methods of building massively parallel computing systems using low power computing complexes in accordance with embodiments of the invention are disclosed. A massively parallel computing system in accordance with one embodiment of the invention includes at least one Solid State Blade configured to communicate via a high performance network fabric. In addition, each Solid State Blade includes a processor configured to communicate with a plurality of low power computing complexes interconnected by a router, and each low power computing complex includes at least one general processing core, an accelerator, an I/O interface, and cache memory and is configured to communicate with non-volatile solid state memory.

Stalzer, Mark A.↗
DOE OSTI2021

Productive Programming of Distributed Systems with the SHAD C++ Library

High-performance computing (HPC) is often perceived as a matter of making large-scale systems (e.g., clusters) run as fast as possible, regardless the required programming effort. However, the idea of "bringing HPC to the masses" has recently emerged. Inspired by this vision, we have designed SHAD, the Scalable High-performance Algorithms and Data-structures library. SHAD is open source software, written in C++, for C++ developers. Unlike other HPC libraries for distributed systems, which rely on SPMD models, SHAD adopts a shared-memory programming abstraction, to make C++ programmers feel at home. Underneath, SHAD manages tasking and data-movements, moving the computation where data resides and taking advantage of asynchrony to tolerate network latency. At the bottom of his stack, SHAD can interface with multiple runtime systems: this not only improves developer’s productivity, by hiding the complexity of such software and of the underlying hardware, but also greatly enhance code portability. Thanks to its abstraction layers, SHAD can indeed target different systems, ranging from laptops to HPC clusters, without any need for modifying the user-level code. We have prototyped and open-sourced the implementation of (a subset of) the C++ standard library (STL) targeting multi-node HPC clusters. Our work allows plain STL-based C++ code to scale on HPC systems, with no need for rewriting the code to exploit the complex hardware. SHAD is available under Apache v2 License at https://github.com/pnnl/SHAD. In this paper we overview the design of the SHAD library, depicting its main components: runtime systems abstractions for tasking; parallel and distributed data-structures; STL-compliant interfaces and algorithms.

Castellana, Vito G.↗
DOE OSTI2020

A parallel strategy for density functional theory computations on accelerated nodes

Using the Löwdin orthonormalization of tall-skinny matrices as a proxy-app for wavefunction-based Density Functional Theory solvers, we investigate a distributed memory parallel strategy focusing on Graphics Processing Unit (GPU)-accelerated nodes as available on some of the top ranked supercomputers at the present time. Here we present numerical results in the strong limit regime, as it is particularly relevant for First-Principles Molecular Dynamics. We also examine how matrix product-based iterative solvers provide a competitive alternative to dense eigensolvers on GPUs, allowing to push the strong scaling limit of these computations to a larger number of distributed tasks. Our strategy, which relies on replicated Gram matrices and efficient collective communications using the NCCL library, leads to a time-to-solution under 0.5 s for the Löwdin orthonormalization of a tall-skinny matrix of 3000 columns on Summit at Oak Ridge Leadership Facility (OLCF). Given the similarity in computational operations between one iteration of a DFT solver and this proxy-app, this shows the possibility of solving accurately the DFT equations well under a minute for 3000 electronic wave functions, and thus perform First-Principles molecular dynamics of physical systems much larger than traditionally solved on CPU systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Design Considerations for GPU-based Mixed Integer Programming on Parallel Computing Platforms

Mixed Integer Programming (MIP) is a powerful abstraction in combinatorial optimization that finds real-life application across many significant sectors. The recent proliferation of graphical processing unit (GPU)-based accelerated computing architectures in large-scale parallel computing or supercomputing presents new opportunities as well as challenges in the advancement of MIP solver technology to effectively use the new accelerated computing platforms and scale to large parallel systems. Here, we recount the conventional processor-based strategies and focus on configurations where the most promising intersection lies between parallel MIP solver approaches and the specific strengths of accelerated parallel platforms. We note that the best potential lies in solving problems whose individual matrix sizes (of the linear program relaxation) fit entirely within one accelerator's memory and whose branch-and-bound (or branch-and-cut) trees cannot be fully contained within a small number of computational nodes. Additionally, we identify ideal features of computational linear algebra support on GPU accelerators that would help advance this direction of scalable parallel solution of MIP problems on GPU-based accelerated computing architectures.

Perumalla, Kalyan↗
DOE OSTI2021

Autonomous nondestructive evaluation of resistance spot welded joints

The application of non-destructive evaluation approaches has attracted strong interests in modern automotive industries. Here, we present an autonomous deep-computing framework to analyze raw videos from infrared systems and to predict weld nugget shape and size with unprecedented accuracy and speed. In a comprehensive training and testing experiment with 90 videos (seven sets of welding material stack-ups), a new method was developed to assemble sufficient datasets for neural network training. Our framework successfully predicts all the nugget shapes with F1 scores that range from 0.84 to 0.92. The total training time on Nvidia DGX station takes less than 10 min for each set of welding material stack-up. The real inference time of an individual dataset (with 30 video frames) takes about 0.005 s. The procedure and methods developed in the study can be applied to other image-based weld property prediction, as well as other manufacturing processes. Furthermore, our well-trained neural networks take limited memory resources (2.3 MB) and are suitable for embedded microprocessors for in-situ welding quality control as edge computing within an intelligent welding framework.

42 ENGINEERING↗
DOE OSTI2020

Andes Data Analysis System at the Oak Ridge Leadership Computing Facility

Andes is a (704)-node commodity-type Linux® cluster. Each of Andes’s 704 nodes contain two 16-core 3.0 GHz AMD EPYC 7302 processors with AMD’s Simultaneous Multithreading (SMT) Technology and 256GB of main memory. Andes also has nine large memory GPU nodes. These nodes each have 1TB of main memory and two NVIDIA K80 GPUs with two 14-core 2.30 GHz Intel Xeon processors with HT Technology.

AMD EPYC↗
DOE OSTI2024

High-Q cavity interface for color centers in thin film diamond

Quantum information technology offers the potential to realize unprecedented computational resources via secure channels distributing entanglement between quantum computers. Diamond, as a host to optically-accessible spin qubits, is a leading platform to realize quantum memory nodes needed to extend such quantum links. Photonic crystal (PhC) cavities enhance light-matter interaction and are essential for an efficient interface between spins and photons that are used to store and communicate quantum information respectively. Here, we demonstrate one- and two-dimensional PhC cavities fabricated in thin-film diamonds, featuring quality factors (Q) of 1.8 × 10 5 and 1.6 × 10 5 , respectively, the highest Qs for visible PhC cavities realized in any material. Importantly, our fabrication process is simple and high-yield, based on conventional planar fabrication techniques, in contrast to the previous with complex undercut processes. We also demonstrate fiber-coupled 1D PhC cavities with high photon extraction efficiency, and optical coupling between a single SiV center and such a cavity at 4 K achieving a Purcell factor of 18. The demonstrated photonic platform may fundamentally improve the performance and scalability of quantum nodes and expedite the development of related technologies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Image processing tools for petabyte-scale light sheet microscopy data

Light sheet microscopy is a powerful technique for high-speed three-dimensional imaging of subcellular dynamics and large biological specimens. However, it often generates datasets ranging from hundreds of gigabytes to petabytes in size for a single experiment. Conventional computational tools process such images far slower than the time to acquire them and often fail outright due to memory limitations. To address these challenges, we present PetaKit5D, a scalable software solution for efficient petabyte-scale light sheet image processing. This software incorporates a suite of commonly used processing tools that are optimized for memory and performance. Notable advancements include rapid image readers and writers, fast and memory-efficient geometric transformations, high-performance Richardson–Lucy deconvolution and scalable Zarr-based stitching. These features outperform state-of-the-art methods by over one order of magnitude, enabling the processing of petabyte-scale image data at the full teravoxel rates of modern imaging cameras. The software opens new avenues for biological discoveries through large-scale imaging experiments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Explore Spatio‐Temporal Learning of Large Sample Hydrology Using Graph Neural Networks

Abstract Streamflow forecasting over gauged and ungauged basins play a vital role in water resources planning, especially under the changing climate. Increased availability of large sample hydrology data sets, together with recent advances in deep learning techniques, has presented new opportunities to explore temporal and spatial patterns in hydrological signatures for improving streamflow forecasting. The purpose of this study is to adapt and benchmark several state‐of‐the‐art graph neural network (GNN) architectures, including ChebNet, Graph Convolutional Network (GCN), and GraphWaveNet, for end‐to‐end graph learning. We explicitly represent river basins as nodes in a graph, learn the spatiotemporal nodal dependencies, and then use the learned relations to predict streamflow simultaneously across all nodes in the graph. The efficacy of the developed GNN models is investigated using the Catchment Attributes and MEteorology for Large‐sample Studies (CAMELS) data set under two settings, fixed graph topology (transductive learning), and variable graph topology (inductive learning), with the latter applicable to prediction in ungauged basins (PUB). Results indicate that GNNs are generally robust and computationally efficient, achieving similar or better performance than a baseline model trained using the long short‐term memory (LSTM) network. Further analyses are conducted to interpret the graph learning process at the edge and node levels and to investigate the effect of different model configurations. We conclude that graph learning constitutes a viable machine learning‐based method for aggregating spatiotemporal information from a multitude of sources for streamflow forecasting

Sun, Alexander Y.↗
DOE OSTI2022

Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning

Abstract Infrasound is generated by a variety of natural and anthropogenic sources. Infrasonic waves travel through the dynamic atmosphere, which can change on the order of minutes to hours. Infrasound propagation largely depends on the wind and temperature structure of the atmosphere. Numerical weather prediction models are available to provide atmospheric specifications, but uncertainties in these models exist and they are computationally expensive to run. Machine learning has proven useful in predicting tropospheric weather using Long Short‐Term Memory (LSTM) networks. An LSTM network is utilized to make atmospheric specification predictions up to ∼30 km for three different training and testing scenarios: (a) the model is trained and tested using only radiosonde data from the Albuquerque, NM, USA station, (b) the model is trained on radiosonde stations across the contiguous US, excluding the Albuquerque, NM, USA station, which was reserved for testing, and (c) the model is trained and tested on radiosonde stations across the contiguous US. Long Short‐Term Memory predictions are compared to a state‐of‐the‐art reanalysis model and show cases where the LSTM outperforms, performs equally as well, or underperforms in comparison to the state‐of‐the‐art. Regional and temporal trends in model performance across the US are also discussed. Results suggest that the LSTM model is a viable tool for predicting atmospheric specifications for infrasound propagation modeling.

54 ENVIRONMENTAL SCIENCES↗