Energy Efficient Deep Neural Network Processing: Digital CMOS Limits and Prospects for Analog In-Memory Computing.
Abstract not provided.
Marinella, Matthew↗
SEARCH · Engineering Papers
Results for “analog computing”
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.
Enabling High-Speed, High-Resolution Space-based Focal Plane Arrays with Analog In-Memory Computing Presentation Slides
Explore the source record for details and available documents.
Xiao, Tianyao↗
CrossSim: a hardware/software co-design tool for analog in-memory computing
Explore the source record for details and available documents.
Chapman, George William↗
Efficient Neural Network Processing with Analog In-Memory Computing.
Abstract not provided.
Marinella, Matthew↗
Exploring strongly correlated quantum spin systems with quantum computers
At inception, quantum annealing leveraged quantum mechanics for classical optimization tasks. However, as machine coherence increases, the realization of quantum spin systems has emerged as an even more fruitful application of this computational model. Alternatives to the standard gate model deserve exploration, to achieve useful quantum advantage via analog quantum computing. The recent demonstration of so-called coherent quantum annealing with 1,000s of qubits, further expands the potential for this hardware to explore quantum system dynamics where the effects of quantum fluctuations can be carefully controlled and observed directly. Implementing existing celebrated spin models—or in fact new and dedicated ones—into quantum annealers will lead to observation and detection of quantum phenomena not yet observed, or not visualized directly, in experimental physics laboratories. Rather than computing or simulating quantum systems, these quantum computers allow one to simply build quantum systems, and experiment on them in an uniquely controlled way, with characterization down to the constitutive degree of freedom. This provides an unprecedented opportunity for understanding the physics of quantum spin systems. Keywords: Theoretical physics currently abounds of interesting theoretical spin models to explore frustration, strongly correlated spins, spin liquids, fractionalized excitations, and topological matter. However enticing, such models are generally only weak proxies for the properties of actual materials. In quantum annealers these models could be realized and experimented upon. Moreover, many more realistic models of such materials could be realized in quantum annealers. Employed in this way, quantum annealers provide an extraordinary versatile platform to explore quantum effects that are hard to find, detect, and characterize in natural materials.
36 MATERIALS SCIENCE↗
Effect of Gamma Radiation on TaOₓ ECRAM
Electrochemical random access memory (ECRAM) is an emerging three-terminal nonvolatile memory (NVM) with highly controllable channel conductance which is promising for use as an analog memory (or synapse) in analog in-memory computing (IMC) systems. Energy-efficient analog IMC computing is particularly desirable for power-constrained, high-radiation environments such as satellites. However, little is known about the suitability of ECRAM for use in a total ionizing dose (TID) environment. Here, this work investigates the effect of Co-60 gamma radiation on the channel conductance and noise—two properties critical for analog IMC systems—of a TaO x -based ECRAM up to 17.3 Mrad(SiO 2 ) for both low- and high-channel-conductance state devices. A transient increase in conductance is observed in response to radiation which consists of two elements: an immediate increase in conductivity due to photocurrent and a secondary increase in conductivity, which has a slower rise and saturation and can persist for hours after exposure. This secondary, persistent photoconductivity is attributed to charging caused by hole trapping. These transient effects would not likely occur in a space environment due to the low dose rate compared with this experiment. No permanent change is found in the low conductance state (LCS) following exposure and the minor shift in the high conductance change would be less significant than the regular retention decay in this state. A permanent increase in the random telegraph noise is observed, possibly due to increased traps created in the channel. This work demonstrates that TaO x -based ECRAM is suitable for use in spaceborne analog IMC systems that are subject to significant TID.
ECRAM↗
Tracking the topology of neural manifolds across populations
Neural manifolds summarize the intrinsic structure of the information encoded by a population of neurons. Advances in experimental techniques have made simultaneous recordings from multiple brain regions increasingly commonplace, raising the possibility of studying how these manifolds relate across populations. However, when the manifolds are nonlinear and possibly code for multiple unknown variables, it is challenging to extract robust and falsifiable information about their relationships. We introduce a framework, called the method of analogous cycles, for matching topological features of neural manifolds using only observed dissimilarity matrices within and between neural populations. We demonstrate via analysis of simulations and in vivo experimental data that this method can be used to correctly identify multiple shared circular coordinate systems across both stimuli and inferred neural manifolds. Conversely, the method rejects matching features that are not intrinsic to one of the systems. Further, as this method is deterministic and does not rely on dimensionality reduction or optimization methods, it is amenable to direct mathematical investigation and interpretation in terms of the underlying neural activity. We thus propose the method of analogous cycles as a suitable foundation for a theory of cross-population analysis via neural manifolds.
97 MATHEMATICS AND COMPUTING↗
Frequency-domain computing using nonlinear acoustic-wave device on lithium niobate
Abstract Multiply-accumulation are crucial computing operations in signal processing, numerical simulations, and machine learning. In recent years, optical analog approaches have demonstrated higher computing performance and better power efficiency than their digital counterparts. However, analog computing chips usually need large areas and complex structures for parallel computing, as a single device element only executes one computing operation at a single time. Here, we demonstrate frequency-domain computing using the nonlinear acoustic-wave devices on lithium niobate, featuring a normalized external second-harmonic generation conversion efficiency of ~ 5.7 × 10-4 W-1. The second-order sum-frequency nonlinear process of lithium niobate enables multiplication of inputs encoded in the frequency domain. Compared to the analog schemes, our device features a notably simpler design, and nanofabrication requires only one lift-off. Using a single acoustic-wave device within an area of 0.03 mm2, we can simultaneously conduct over 130,000 multiply-accumulation operations. Our acoustic-wave device shows applications in real and complex vector convolutions and image processing. This demonstration sets the stage for experimental realizations into frequency-domain integrated nonlinear acoustic computing systems, potentially shaping future developments in acoustic neural networks and quantum computing.
chai, mingzhao (ORCID:0009000466226341)↗
Low Power, Radiation Resilient Synchronous Edge Processing for Remote Monitoring
Next-generation space remote sensing systems may be equipped with imaging arrays that sense data at a rate that outstrips the processing capability of any computing hardware that can operate within a satellite’s power budget. This project developed novel convolutional and recurrent neural networks to detect and estimate point-like events amid clutter, and investigated their efficient and accurate implementation on analog in-memory computing systems that are 10-1000× more energy-efficient than digital processors. This project leveraged two memory devices at different levels of technological maturity: a large-scale analog computing prototype using commercial SONOS charge-trap memory, and electrochemical memory (ECRAM) with intrinsic radiation hardness. We experimentally demonstrated end-to-end analog processing of our neural networks on SONOS and characterized the radiation response of both SONOS and ECRAM. We advanced the state-of-the-art in ECRAM precision and reliability, and developed co-design methods to enable accurate long-term operation of SONOS analog accelerators in space radiation environments.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
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↗
Massively parallel and universal approximation of nonlinear functions using diffractive processors
Nonlinear computation is essential for a wide range of information processing tasks, yet implementing nonlinear functions using optical systems remains a challenge due to the weak and power-intensive nature of optical nonlinearities. Overcoming this limitation without relying on nonlinear optical materials could unlock unprecedented opportunities for ultrafast and parallel optical computing systems. Here, we demonstrate that large-scale nonlinear computation can be performed using linear optics through optimized diffractive processors composed of passive phase-only surfaces. In this framework, the input variables of nonlinear functions are encoded into the phase of an optical wavefront—e.g., via a spatial light modulator (SLM)—and transformed by an optimized diffractive structure with spatially varying point-spread functions to yield output intensities that approximate a large set of unique nonlinear functions–all in parallel. We provide proof establishing that this architecture serves as a universal function approximator for an arbitrary set of bandlimited nonlinear functions, also covering wavelength-multiplexed nonlinear functions as well as multi-variate and complex-valued functions that are all-optically cascadable. Our analysis also indicates the successful approximation of typical nonlinear activation functions commonly used in neural networks, including the sigmoid, tanh, ReLU (rectified linear unit), and softplus. We numerically demonstrate the parallel computation of one million distinct nonlinear functions, accurately executed at wavelength-scale spatial density at the output of a diffractive optical processor. Furthermore, we experimentally validated this framework using in situ optical learning and approximated 35 unique nonlinear functions in a single shot using a compact setup consisting of an SLM and an image sensor. These results establish diffractive optical processors as a scalable platform for massively parallel universal nonlinear function approximation, paving the way for new capabilities in analog optical computing based on linear materials.
Rahman, Md Sadman Sakib [University of California,↗
Demonstration of Decentralized Physics-Driven Learning
In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain, neurons and synapses self-adjust based on local information. Contrastive learning algorithms have recently been proposed to train physical systems, such as fluidic, mechanical, or electrical networks, to perform machine-learning tasks from local evolution rules. However, to date, such systems have only been implemented in silico due to the engineering challenge of creating elements that autonomously evolve based on their own response to two sets of global boundary conditions. Here, we introduce and implement a physics-driven contrastive learning scheme for a network of variable resistors, using circuitry to locally compare the response of two identical networks subjected to the two different sets of boundary conditions. Using this method, our system effectively trains itself, optimizing its resistance values without the use of a central processor or external information storage. Once the system is trained for a specified allostery, regression, or classification task, the task is subsequently performed rapidly and automatically by the physical imperative to minimize power dissipation in response to the given voltage inputs. Here, we demonstrate that, unlike typical computers, such learning systems are robust to extreme damage (and thus manufacturing defects) due to their decentralized learning. Our twin-network approach is therefore readily scalable to extremely large or nonlinear networks, where its distributed nature will be an enormous advantage; a laboratory network of only 500 edges will already outpace its in silico counterpart.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Determining the leading-order contact term in neutrinoless double β decay
We present a method to determine the leading-order (LO) contact term contributing to the nn → ppe - e - amplitude through the exchange of light Majorana neutrinos. Our approach is based on the representation of the amplitude as the momentum integral of a known kernel (proportional to the neutrino propagator) times the generalized forward Compton scattering amplitude n ( p 1 ) n ( p 2 ) W + ( k ) → \( p\left({p}_1^{\prime}\right)p\left({p}_2^{\prime}\right){W}^{-}(k) \) , in analogy to the Cottingham formula for the electromagnetic contribution to hadron masses. We construct model-independent representations of the integrand in the low- and high-momentum regions, through chiral EFT and the operator product expansion, respectively. We then construct a model for the full amplitude by interpolating between these two regions, using appropriate nucleon factors for the weak currents and information on nucleon-nucleon ( NN ) scattering in the 1 S 0 channel away from threshold. By matching the amplitude obtained in this way to the LO chiral EFT amplitude we obtain the relevant LO contact term and discuss various sources of uncertainty. We validate the approach by computing the analog I = 2 NN contact term and by reproducing, within uncertainties, the charge-independence-breaking contribution to the 1 S 0 NN scattering lengths. While our analysis is performed in the \( \overline{\mathrm{MS}} \) scheme, we express our final result in terms of the scheme-independent renormalized amplitude \( {\mathcal{A}}_{\nu}\left(\left|\mathbf{p}\right|,\left|\mathbf{p}^{\prime}\right|\right) \) at a set of kinematic points near threshold. We illustrate for two cutoff schemes how, using our synthetic data for \( {\mathcal{A}}_{\nu } \) , one can determine the contact-term contribution in any regularization scheme, in particular the ones employed in nuclear-structure calculations for isotopes of experimental interest.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
Insights into the Properties of MXenes and MXene Analogs from Atomistic Simulation
We review the properties that have been predicted for MXenes and MXene analogs from computational simulation with a focus on structural and electronic properties, energy storage, and ion transport. Methods considered range from quantum mechanical approaches to classical molecular dynamics. We conclude by reviewing current limitations and outstanding questions for simulation and MXene properties that have been little explored to-date.
Muraleedharan, Murali Gopal↗
Diffusion-limited hydrolysis in polymeric materials
Polymer degradation under aggressive environmental stressors often develops heterogeneities due to diffusion-limited reaction phenomena. This is well established for diffusion-limited oxidation (DLO), which is known to occur for most polymeric materials at elevated temperatures but has been less summarized for the conditions of diffusion-limited hydrolysis (DLH). Here, an overview of hydrolysis for several materials and a computational model, analogous to the underlying equations for DLO, able to define this diffusion-reaction system is presented. A systematic study of the influence of various parameters, such as water diffusivity, reaction rate and order, and a more in-depth focus on residual isocyanate hydrolysis in a polymeric methylene diphenyl diisocyanate (pMDI) based polyurethane (PU) foam is given. For this system, we present experimental data for model ‘input’ parameters and discuss predictions for different conditions. We conceptually compare the behavior of diffusion-limited oxidation to that of diffusion-limited hydrolysis (DLH). With the mathematical framework and key material properties presented herein, any DLH phenomena following Fickian diffusion behavior can be understood, modeled, and predicted.
36 MATERIALS SCIENCE↗
Atomic-scale control of tunneling in donor-based devices
Atomically precise donor-based quantum devices are a promising candidate for solid-state quantum computing and analog quantum simulations. However, critical challenges in atomically precise fabrication have meant systematic, atomic scale control of the tunneling rates and tunnel coupling has not been demonstrated. Here using a room temperature grown locking layer and precise control over the entire fabrication process, we reduce unintentional dopant movement while achieving high quality epitaxy in scanning tunnelling microscope (STM)-patterned devices. Using the Si(100)2 × 1 surface reconstruction as an atomically-precise ruler to characterize the tunnel gap in precision-patterned single electron transistors, we demonstrate the exponential scaling of the tunneling resistance on the tunnel gap as it is varied from 7 dimer rows to 16 dimer rows. We demonstrate the capability to reproducibly pattern devices with atomic precision and a donor-based fabrication process where atomic scale changes in the patterned tunnel gap result in the expected changes in the tunneling rates.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Exponential Escape Rate of Filamentary Incubation in Mott Spiking Neurons
Mott materials such as vanadium oxides, when subject to a strong applied voltage, present an inhomogeneous insulator-to-metal transition with formation of metallic filaments within the insulating bulk. This property is enabling the development of compact and power-efficient neuromorphic devices known as Mott neurons. However, the nature of the transition has not been fully understood yet, as it may be attributed to different effects, including Joule self-heating and hot-carrier injection. Moreover, the experimental determination of the threshold voltage needed to induce the transition has proven to be challenging, as the transition becomes increasingly unpredictable when the threshold is approached. The physical understanding of these issues would not only deepen our understanding of Mott insulators, but would also be an important step toward the realization of neuromorphic devices based on such materials. In this work we use numerical simulations based on the Mott resistor network model to study the nature of the filament incubation and formation process. Here, we show that both electronic and thermal effects, in the form of current density focusing and Joule self-heating, respectively, contribute to the filamentary incubation and growth. Remarkably, we find that the percolation of the metallic filaments near the threshold is intrinsically stochastic, qualitatively similar to the familiar Arrhenius activated behavior and to the stochastic firing of biological neurons. More precisely, we characterize the filament percolation as a Poisson point process, which has the same probability distribution as mathematical models of neuronal firing with an exponential escape rate. Finally, we support the numerical simulation results by performing experiments in VO 2 that are in agreement with the exponential escape rate behavior. Thus, we establish a functionality of Mott insulators that opens a path toward implementing neuromorphic hardware with quantum materials.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Phase dynamics in an AC-driven multiterminal Josephson junction analog
In the presence of an AC drive, multiterminal Josephson junctions exhibit the inverse AC Josephson effect, where the oscillations of the superconducting phase of each junction can lock onto one another or onto the external drive. The competition between these different phase-locked states results in a complex array of quantized voltage plateaus whose stability strongly depend on the circuit parameters of the shunted junctions. This phase diagram cannot be explored with low-temperature transport experiments alone, given the breadth of the parameter space, so we present an easily tunable analog circuit whose dynamical properties emulate those of a three-terminal junction. We focus on the observation of the multiterminal inverse AC Josephson effect, and we discuss how to identify Shapiro steps associated with each of the three junctions as well as their quartet states. We only observe integer phase-locked states in strongly overdamped networks, but fractional Shapiro steps appear as well when the quality factor of the junctions increases. Finally, we discuss the role of transverse coupling in the synchronization of the junctions.
36 MATERIALS SCIENCE↗