Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “matrix multiplication”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Visualization of newt aragonitic otoconial matrices using transmission electron microscopy

Otoconia are calcified protein matrices within the gravity-sensing organs of the vertebrate vestibular system. These protein matrices are thought to originate from the supporting or hair cells in the macula during development. Previous studies of mammalian calcitic, barrel-shaped otoconia revealed an organized protein matrix consisting of a thin peripheral layer, a well-defined organic core and a flocculent matrix inbetween. No studies have reported the microscopic organization of the aragonitic otoconial matrix, despite its protein characterization. Pote et al. (1993b) used densitometric methods and inferred that prismatic (aragonitic) otoconia have a peripheral protein distribution, compared to that described for the barrel-shaped, calcitic otoconia of birds, mammals, and the amphibian utricle. By using tannic acid as a negative stain, we observed three kinds of organic matrices in preparations of fixed, decalcified saccular otoconia from the adult newt: (1) fusiform shapes with a homogenous electron-dense matrix; (2) singular and multiple strands of matrix; and (3) more significantly, prismatic shapes outlined by a peripheral organic matrix. These prismatic shapes remain following removal of the gelatinous matrix, revealing an internal array of organic matter. We conclude that prismatic otoconia have a largely peripheral otoconial matrix, as inferred by densitometry.

NASA Discipline Neuroscience↗
NASA NTRS2012

Design and Implementation of the PALM-3000 Real-Time Control System

This paper reflects, from a computational perspective, on the experience gathered in designing and implementing realtime control of the PALM-3000 adaptive optics system currently in operation at the Palomar Observatory. We review the algorithms that serve as functional requirements driving the architecture developed, and describe key design issues and solutions that contributed to the system's low compute-latency. Additionally, we describe an implementation of dense matrix-vector-multiplication for wavefront reconstruction that exceeds 95% of the maximum sustained achievable bandwidth on NVIDIA Geforce 8800GTX GPU.

PALM-3000↗
NASA NTRS2012

Characterization of Delaminations and Transverse Matrix Cracks in Composite Laminates Using Multiple-Angle Ultrasonic Inspection

Delaminations and transverse matrix cracks often appear concurrently in composite laminates. Normal-incidence ultrasound is excellent at detecting delaminations, but is not optimum for matrix cracks. Non-normal incidence, or polar backscattering, has been shown to optimally detect matrix cracks oriented perpendicular to the ultrasonic plane of incidence. In this work, a series of six composite laminates containing slots were loaded in tension to achieve various levels of delamination and ply cracking. Ultrasonic backscattering was measured over a range of incident polar and azimuthal angles, in order to characterize the relative degree of damage of the two types. Sweptpolar- angle measurements were taken with a curved phased array, as a step toward an array-based approach to simultaneous measurement of combined flaws.

Johnston, Patrick H.↗
NASA NTRS1997

Stress Intensity Factor Solutions for Multiple Edge Cracks in Ceramic Matrix Composites

NASA Lewis Research Center conducted a study to determine the stress intensity factor solutions for periodic arrays of bridged cracks for various crack spacings and crack lengths. Initially, the stress intensity factor of an array of unbridged multiple edge cracks was determined under constant global displacement as well as at a point load along the crack wake. These solutions are expected to contribute toward the development of a damage-based life-prediction methodology for CMC engine components.

Ghosn, Louis↗
NASA NTRS1999

Signal processing applications of massively parallel charge domain computing devices

The present invention is embodied in a charge coupled device (CCD)/charge injection device (CID) architecture capable of performing a Fourier transform by simultaneous matrix vector multiplication (MVM) operations in respective plural CCD/CID arrays in parallel in O(1) steps. For example, in one embodiment, a first CCD/CID array stores charge packets representing a first matrix operator based upon permutations of a Hartley transform and computes the Fourier transform of an incoming vector. A second CCD/CID array stores charge packets representing a second matrix operator based upon different permutations of a Hartley transform and computes the Fourier transform of an incoming vector. The incoming vector is applied to the inputs of the two CCD/CID arrays simultaneously, and the real and imaginary parts of the Fourier transform are produced simultaneously in the time required to perform a single MVM operation in a CCD/CID array.

Fijany, Amir↗
NASA NTRS1986

Free vibration characteristics of multiple load path blades by the transfer matrix method

The determination of free vibrational characteristics is basic to any dynamic design, and these characteristics can form the basis for aeroelastic stability analyses. Conventional helicopter blades are typically idealized as single-load-path blades, and the transfer matrix method is well suited to analyze such blades. Several current helicopter dynamic programs employ transfer matrices to analyze the rotor blades. In this paper, however, the transfer matrix method is extended to treat multiple-load-path blades, without resorting to an equivalent single-load-path approximation. With such an extension, these current rotor dynamic programs which employ the transfer matrix method can be modified with relative ease to account for the multiple load paths. Unlike the conventional blades, the multiple-load-path blades require the introduction of the axial degree-of-freedom into the solution process to account for the differential axial displacements of the different load paths. The transfer matrix formulation is validated through comparison with the finite-element solutions.

Murthy, V. R.↗
NASA NTRS2020

Shape Estimation for Elongated Deformable Object using B-spline Chained Multiple Random Matrices Model

In this paper, a B-spline chained multiple random matrix models (RMMs) representation is proposed to model geometric characteristics of an elongated deformable object. The hyper degrees of freedom structure of the elongated deformable object make its shape estimation challenging. Based on the likelihood function of the proposed B-spline chained multiple RMMs, an expectation-maximization (EM) method is derived to estimate the shape of the elongated deformable object. A split and merge method based on the Euclidean minimum spanning tree (EMST) is proposed to provide initialization for the EM algorithm. The proposed algorithm is evaluated for the shape estimation of the elongated deformable objects in scenarios, such as the static rope with various configurations (including configurations with intersection), the continuous manipulation of a rope and a plastic tube, and the assembly of two plastic tubes. The execution time is computed and the accuracy of the shape estimation results is evaluated based on the comparisons between the estimated width values and its ground-truth, and the intersection over union (IoU) metric.

Gang Yao↗
NASA NTRS2009

Economical Implementation of a Filter Engine in an FPGA

A logic design has been conceived for a field-programmable gate array (FPGA) that would implement a complex system of multiple digital state-space filters. The main innovative aspect of this design lies in providing for reuse of parts of the FPGA hardware to perform different parts of the filter computations at different times, in such a manner as to enable the timely performance of all required computations in the face of limitations on available FPGA hardware resources. The implementation of the digital state-space filter involves matrix vector multiplications, which, in the absence of the present innovation, would ordinarily necessitate some multiplexing of vector elements and/or routing of data flows along multiple paths. The design concept calls for implementing vector registers as shift registers to simplify operand access to multipliers and accumulators, obviating both multiplexing and routing of data along multiple paths. Each vector register would be reused for different parts of a calculation. Outputs would always be drawn from the same register, and inputs would always be loaded into the same register. A simple state machine would control each filter. The output of a given filter would be passed to the next filter, accompanied by a "valid" signal, which would start the state machine of the next filter. Multiple filter modules would share a multiplication/accumulation arithmetic unit. The filter computations would be timed by use of a clock having a frequency high enough, relative to the input and output data rate, to provide enough cycles for matrix and vector arithmetic operations. This design concept could prove beneficial in numerous applications in which digital filters are used and/or vectors are multiplied by coefficient matrices. Examples of such applications include general signal processing, filtering of signals in control systems, processing of geophysical measurements, and medical imaging. For these and other applications, it could be advantageous to combine compact FPGA digital filter implementations with other application-specific logic implementations on single integrated-circuit chips. An FPGA could readily be tailored to implement a variety of filters because the filter coefficients would be loaded into memory at startup.

Kowalski, James E.↗
DOE OSTI2025

Fast and Scalable FFT-Based GPU-Accelerated Algorithms for Block-Triangular Toeplitz Matrices with Application to Linear Inverse Problems Governed by Autonomous Dynamical Systems

In this work, we present an efficient and scalable algorithm for performing matrix-vector multiplications (matvecs) for block Toeplitz matrices. Such matrices, which are shift-invariant with respect to their blocks, arise in the context of solving inverse problems governed by autonomous systems, and time-invariant systems in particular. In this article, we consider inverse problems that infer unknown parameters from observational data of a linear time-invariant dynamical system given in the form of partial differential equations (PDEs). Matrix-free Newton-conjugate-gradient methods are often the gold standard for solving these inverse problems, but they require numerous actions of the Hessian on a vector. Matrix-free adjoint-based Hessian matvecs require solution of a pair of linearized forward/adjoint PDE solves per Hessian action, which may be prohibitive for large-scale inverse problems. Time invariance of the forward PDE problem leads to a block Toeplitz structure of the discretized parameter-to-observable (p2o) map defining the mapping from inputs (parameters) to outputs (observables) of the PDEs. This block Toeplitz structure enables us to exploit two key properties: (1) compact storage of the p2o map and its adjoint, and (2) efficient fast Fourier transform–based Hessian matvecs. The proposed algorithm is mapped onto large multi-GPU clusters and achieves more than 80% of peak bandwidth on NVIDIA A100 GPUs. Excellent weak scaling is shown for up to 48 A100 GPUs. For the targeted problems, the implementation executes Hessian matvecs within fractions of a second, which is orders of magnitude faster than can be achieved by conventional matrix-free Hessian matvecs via forward/adjoint PDE solves.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Compute in‐Memory with Non‐Volatile Elements for Neural Networks: A Review from a Co‐Design Perspective

Abstract Deep learning has become ubiquitous, touching daily lives across the globe. Today, traditional computer architectures are stressed to their limits in efficiently executing the growing complexity of data and models. Compute‐in‐memory (CIM) can potentially play an important role in developing efficient hardware solutions that reduce data movement from compute‐unit to memory, known as the von Neumann bottleneck. At its heart is a cross‐bar architecture with nodal non‐volatile‐memory elements that performs an analog multiply‐and‐accumulate operation, enabling the matrix‐vector‐multiplications repeatedly used in all neural network workloads. The memory materials can significantly influence final system‐level characteristics and chip performance, including speed, power, and classification accuracy. With an over‐arching co‐design viewpoint, this review assesses the use of cross‐bar based CIM for neural networks, connecting the material properties and the associated design constraints and demands to application, architecture, and performance. Both digital and analog memory are considered, assessing the status for training and inference, and providing metrics for the collective set of properties non‐volatile memory materials will need to demonstrate for a successful CIM technology.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Dynamic flux surrogate-based partitioned methods for interface problems

Loosely coupled partitioned methods for multiphysics problems treat each subproblem as a separate entity and advance them independently in time. In so doing these methods enable code reuse, increase concurrency and provide a convenient framework for plug-and-play multiphysics simulations. However, mathematically loosely coupled schemes are equivalent to a single step of an iterative solution method, which can compromise their accuracy and stability. We present a new data-driven partitioned method for coupled parametric PDEs that can improve upon the accuracy of traditional loosely coupled methods without incurring a performance penalty. To that end, we replace conventional field transfers across the interface by a surrogate for the dynamics of the interface flux exchanged between the subdomains. To develop this surrogate we apply dynamic mode decomposition to a non-standard staggered-in-time state, comprising the interface flux and small solution patches near the interface. The new approach shifts the main computational burden to an offline training phase, whereas application of the surrogate in the online phase amounts to a single matrix–vector multiplication. In conclusion, we provide stability analysis of the surrogate-based partitioned scheme and include numerical results that demonstrate its potential.

Dynamic mode decomposition (DMD)↗
DOE OSTI2022

Current and future federal and state sampling guidance for per- and polyfluoroalkyl substances in environmental matrices

Per- and polyfluoroalkyl substances (PFAS) are a class of emerging contaminants composed of an estimated 5000 to 10,000 human-made, fluorinated, organic chemicals. Due to the complexity of PFAS, the need for multiple environmental matrix considerations and the absence of a promulgated federal standard for environmental sampling and analysis, U.S. states have begun developing health-based regulatory and/or guidance values for a limited number of PFAS in environmental matrices. As there is a growing body of science to inform PFAS sampling guidance standard development, it is important to understand which U.S. states are implementing sampling guidelines and how they plan to handle emerging PFAS. This critical review discusses the current and impending federal and state sampling guidelines for PFAS in environmental matrices, the data gaps surrounding PFAS sampling guidance in U.S. states, and the future impacts of impending guidance documents and regulations. Ten federal guidance documents are available for PFAS sampling guidance and analysis. The maximum number of PFAS covered in these guidance documents is 25 analytes spanning across 8 unique media. While the EPA has developed several different sampling and analytical guidelines for PFAS, there is no formal regulation of PFAS or requirements of states to enforce these guidelines. Consequently, only 31 states have informally adopted sampling guidelines, while the other 19 states have no guidance documentation in place for PFAS. The introduction of new PFAS sampling guidelines by the EPA, as well as updated analytical guidelines that target more PFAS or total organofluoride, is expected to continuously shift the landscape of federal and state guidance for PFAS sampling moving forward.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Energy efficient photonic memory based on electrically programmable embedded III-V/Si memristors: switches and filters

Abstract Over the past few years, extensive work on optical neural networks has been investigated in hopes of achieving orders of magnitude improvement in energy efficiency and compute density via all-optical matrix-vector multiplication. However, these solutions are limited by a lack of high-speed power power-efficient phase tuners, on-chip non-volatile memory, and a proper material platform that can heterogeneously integrate all the necessary components needed onto a single chip. We address these issues by demonstrating embedded multi-layer HfO 2 /Al 2 O 3 memristors with III-V/Si photonics which facilitate non-volatile optical functionality for a variety of devices such as Mach-Zehnder Interferometers, and (de-)interleaver filters. The Mach-Zehnder optical memristor exhibits non-volatile optical phase shifts > π with ~33 dB signal extinction while consuming 0 electrical power consumption. We demonstrate 6 non-volatile states each capable of 4 Gbps modulation. (De-) interleaver filters were demonstrated to exhibit memristive non-volatile passband transformation with full set/reset states. Time duration tests were performed on all devices and indicated non-volatility up to 24 hours and beyond. We demonstrate non-volatile III-V/Si optical memristors with large electric-field driven phase shifts and reconfigurable filters with true 0 static power consumption. As a result, co-integrated photonic memristors offer a pathway for in-memory optical computing and large-scale non-volatile photonic circuits.

Cheung, Stanley (ORCID:0000000248860013)↗
DOE OSTI2023

Real-space solution to the electronic structure problem for nearly a million electrons

We report a Kohn–Sham density functional theory calculation of a system with more than 200 000 atoms and 800 000 electrons using a real-space high-order finite-difference method to investigate the electronic structure of large spherical silicon nanoclusters. Our system of choice was a 20 nm large spherical nanocluster with 202 617 silicon atoms and 13 836 hydrogen atoms used to passivate the dangling surface bonds. To speed up the convergence of the eigenspace, we utilized Chebyshev-filtered subspace iteration, and for sparse matrix–vector multiplications, we used blockwise Hilbert space-filling curves, implemented in the PARSEC code. For this calculation, we also replaced our orthonormalization + Rayleigh–Ritz step with a generalized eigenvalue problem step. We utilized all of the 8192 nodes (458 752 processors) on the Frontera machine at the Texas Advanced Computing Center. We achieved two Chebyshev-filtered subspace iterations, yielding a good approximation of the electronic density of states. Our work pushes the limits on the capabilities of the current electronic structure solvers to nearly 106 electrons and demonstrates the potential of the real-space approach to efficiently parallelize large calculations on modern high-performance computing platforms.

Chemistry↗
DOE OSTI2023

Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware

In-memory computing with emerging non-volatile memory devices (eNVMs) has shown promising results in accelerating matrix-vector multiplications. However, activation function calculations are still being implemented with general processors or large and complex neuron peripheral circuits. Here, we present the integration of Ag-based conductive bridge random access memory (Ag-CBRAM) crossbar arrays with Mott rectified linear unit (ReLU) activation neurons for scalable, energy and area-efficient hardware (HW) implementation of deep neural networks. We develop Ag-CBRAM devices that can achieve a high ON/OFF ratio and multi-level programmability. Compact and energy-efficient Mott ReLU neuron devices implementing ReLU activation function are directly connected to the columns of Ag-CBRAM crossbars to compute the output from the weighted sum current. We implement convolution filters and activations for VGG-16 using our integrated HW and demonstrate the successful generation of feature maps for CIFAR-10 images in HW. Our approach paves a new way toward building a highly compact and energy-efficient eNVMs-based in-memory computing system.

Mott insulators↗
DOE OSTI2023

Solving the electronic structure problem for over 100000 atoms in real space

Using a real-space high-order finite-difference approach, we investigate the electronic structure of large spherical silicon nanoclusters. Within Kohn-Sham density functional theory and using pseudopotentials, we report the self-consistent field convergence of a system with over 100000 atoms: a Si 107,641 ⁢H 9,084 nanocluster with a diameter of 16 nm. Our approach uses Chebyshev-filtered subspace iteration to speed up the convergence of the eigenspace, and blockwise Hilbert space-filling curves to speed up sparse matrix-vector multiplications, all of which are implemented in the parsec code. For the largest system, we utilized 2048 nodes (114 688 cores) on the Frontera machine in the Texas Advanced Computing Center. Our quantitative analysis of the electronic structure shows how it gradually approaches its bulk counterpart as a function of nanocluster size. The band gap is enlarged due to quantum confinement in nanoclusters, but decreases as the system size increases, as expected. In conclusion, our work serves as a proof of concept for the capacity of the real-space approach in efficiently parallelizing very large calculations using high-performance computer platforms, which can straightforwardly be replicated in other systems with more than 10 5 atoms.

0-dimensional systems↗