It is known from the literature of Cellular nonlinear Networks (CNNs) and from the literature of coherent optical computing devices that wave phenomena can be used to solve a number of computing problems. We demonstra...
详细信息
It is known from the literature of Cellular nonlinear Networks (CNNs) and from the literature of coherent optical computing devices that wave phenomena can be used to solve a number of computing problems. We demonstrate the design of linear signal processing devices (spectrum analyzers, filters) using spin waves (magnetic excitations). The said spin waves are an especially attractive medium for on-chip, wave-based computing algorithms, as they are characterized by short wavelengths (<100 nm), high frequency (10-100 GHz), and carry energy in the electronvolt range. Spin-wave-based hardware could be a very natural implementation for wave-based computing, and could significantly outperform electrical (analog or digital) implementations.
We present a combined experimental and simulation study of the physical implementation of coherently coupled oscillator networks composed of spin-torque oscillators (STOs). Based on published works and on our recent e...
详细信息
We present a combined experimental and simulation study of the physical implementation of coherently coupled oscillator networks composed of spin-torque oscillators (STOs). Based on published works and on our recent experiments, we review the behavior of individual oscillators and arrays of coupled oscillators. We construct models that are calibrated by experiments, and our simulations demonstrate that an array of coherently coupled STOs exhibits the basic functionality of an associative memory.
The operation of an array of coupled oscillators underlying the associative memory function is demonstrated for various interconnection topologies (cross-connect and star-coupled). Three types of nonlinear oscillators...
详细信息
The operation of an array of coupled oscillators underlying the associative memory function is demonstrated for various interconnection topologies (cross-connect and star-coupled). Three types of nonlinear oscillators (Andronov-Hopf, phase-locked loop, and spin torque) and their synchronization behavior are compared. Frequency-shift keying scheme of encoding input and memorized data is introduced. The speed of synchronization of oscillators and the evolution of the degree of match are studied as a function of device parameters.
Building oscillator based computing systems with emerging nano-device technologies has become a promising solution for unconventional computing tasks like computer vision and pattern recognition. However, simulation a...
详细信息
ISBN:
(纸本)9781479987191
Building oscillator based computing systems with emerging nano-device technologies has become a promising solution for unconventional computing tasks like computer vision and pattern recognition. However, simulation and analysis of these systems is both time and compute intensive due to the nonlinearity of new devices and the complex behavior of coupled oscillators. In order to speed up the simulation of coupled oscillator systems, we propose a simplified phase model to perform phase and frequency synchronization prediction based on a synthesis of earlier models. Our model can predict the frequency locking behavior with several orders of magnitude speedup compared to direct evaluation, enabling the effective and efficient simulation of the large numbers of oscillators required for practical computing systems.
Probabilistic machine intelligence paradigms such as Bayesian Networks (BNs) are widely used in critical real-world applications. However they cannot be employed efficiently for large problems on conventional computin...
详细信息
ISBN:
(纸本)9781467378499
Probabilistic machine intelligence paradigms such as Bayesian Networks (BNs) are widely used in critical real-world applications. However they cannot be employed efficiently for large problems on conventional computing systems due to inefficiencies resulting from layers of abstraction and separation of logic and memory. We present an unconventional nanoscale magneto-electric machine paradigm, architected with the principle of to efficiently implement causal inference in BNs. It leverages emerging straintronic magneto-tunneling junctions in a novel mixed-signal circuit framework for direct computations on probabilities, while blurring the boundary between memory and computation. Initial evaluations, based on extensive bottom-up simulations, indicate up to four orders of magnitude inference runtime speedup vs. best-case performance of 100-core microprocessors, for BNs with a million random variables. These could be the target applications for emerging magneto-electric devices to enable capabilities for leapfrogging beyond present day computing.
We introduce holographic (optically inspired) algorithms, which are suited for implementation on massively parallel, locally interconnected arrays of nanoscale devices. This computing method is inspired by optical sig...
详细信息
ISBN:
(纸本)9781479960071
We introduce holographic (optically inspired) algorithms, which are suited for implementation on massively parallel, locally interconnected arrays of nanoscale devices. This computing method is inspired by optical signal processing, but it neither relies on optical wave propagation nor optical hardware. We describe implementations on digital semiconductor circuitry and on magnetoelectronic devices.
暂无评论