arXiv subjects

Emily Toomey

Publications and source records attributed to Emily Toomey.

6 recordsLinked to original sources

arXiv2020

A superconducting nanowire spiking element for neural networks

As the limits of traditional von Neumann computing come into view, the brain's ability to communicate vast quantities of information using low-power spikes has become an increasing source of inspiration for alternative architectures. Key to the success of these largescale neural networks is a power-efficient spiking element that is scalable and easily interfaced with traditional control electronics. In this work, we present a spiking element fabricated from superconducting nanowires that has pulse energies on the order of ~10 aJ. We demonstrate that the device reproduces essential characteristics of biological neurons, such as a refractory period and a firing threshold. Through simulations using experimentally measured device parameters, we show how nanowire-based networks may be used for inference in image recognition, and that the probabilistic nature of nanowire switching may be exploited for modeling biological processes and for applications that rely on stochasticity.

q-bio.NC↗

arXiv2019

Design and Characterization of Superconducting Nanowire-Based Processors for Acceleration of Deep Neural Network Training

Training of deep neural networks (DNNs) is a computationally intensive task and requires massive volumes of data transfer. Performing these operations with the conventional von Neumann architectures creates unmanageable time and power costs. Recent studies have shown that mixed-signal designs involving crossbar architectures are capable of achieving acceleration factors as high as 30,000x over the state of the art digital processors. These approaches involve utilization of non-volatile memory (NVM) elements as local processors. However, no technology has been developed to-date that can satisfy the strict device requirements for the unit cell. This paper presents the superconducting nanowire-based processing element as a cross-point device. The unit cell has many programmable non-volatile states that can be used to perform analog multiplication. Importantly, these states are intrinsically discrete due to quantization of flux, which provides symmetric switching characteristics. Operation of these devices in a crossbar is described and verified with electro-thermal circuit simulations. Finally, validation of the concept in an actual DNN training task is shown using an emulator.

cs.ET↗

arXiv2019

Cryogenic Memory Architecture Integrating Spin Hall Effect based Magnetic Memory and Superconductive Cryotron Devices

One of the most challenging obstacles to realizing exascale computing is minimizing the energy consumption of L2 cache, main memory, and interconnects to that memory. For promising cryogenic computing schemes utilizing Josephson junction superconducting logic, this obstacle is exacerbated by the cryogenic system requirements that expose the technology's lack of high-density, high-speed and power-efficient memory. Here we demonstrate an array of cryogenic memory cells consisting of a non-volatile three-terminal magnetic tunnel junction element driven by the spin Hall effect, combined with a superconducting heater-cryotron bit-select element. The write energy of these memory elements is roughly 8 pJ with a bit-select element, designed to achieve a minimum overhead power consumption of about 30%. Individual magnetic memory cells measured at 4 K show reliable switching with write error rates below $10^{-6}$, and a 4x4 array can be fully addressed with bit select error rates of $10^{-6}$. This demonstration is a first step towards a full cryogenic memory architecture targeting energy and performance specifications appropriate for applications in superconducting high performance and quantum computing control systems, which require significant memory resources operating at 4 K.

physics.app-ph↗

arXiv2019

A Power Efficient Artificial Neuron Using Superconducting Nanowires

With the rising societal demand for more information-processing capacity with lower power consumption, alternative architectures inspired by the parallelism and robustness of the human brain have recently emerged as possible solutions. In particular, spiking neural networks (SNNs) offer a bio-realistic approach, relying on pulses analogous to action potentials as units of information. While software encoded networks provide flexibility and precision, they are often computationally expensive. As a result, hardware SNNs based on the spiking dynamics of a device or circuit represent an increasingly appealing direction. Here, we propose to use superconducting nanowires as a platform for the development of an artificial neuron. Building on an architecture first proposed for Josephson junctions, we rely on the intrinsic nonlinearity of two coupled nanowires to generate spiking behavior, and use electrothermal circuit simulations to demonstrate that the nanowire neuron reproduces multiple characteristics of biological neurons. Furthermore, by harnessing the nonlinearity of the superconducting nanowire's inductance, we develop a design for a variable inductive synapse capable of both excitatory and inhibitory control. We demonstrate that this synapse design supports direct fanout, a feature that has been difficult to achieve in other superconducting architectures, and that the nanowire neuron's nominal energy performance is competitive with that of current technologies.

q-bio.NC↗

arXiv2018

Bridging the gap between nanowires and Josephson junctions: a superconducting device based on controlled fluxon transfer across nanowires

The basis for superconducting electronics can broadly be divided between two technologies: the Josephson junction and the superconducting nanowire. While the Josephson junction (JJ) remains the dominant technology due to its high speed and low power dissipation, recently proposed nanowire devices offer improvements such as gain, high fanout, and compatibility with CMOS circuits. Despite these benefits, nanowire-based electronics have largely been limited to binary operations, with devices switching between the superconducting state and a high-impedance resistive state dominated by uncontrolled hotspot dynamics. Unlike the JJ, they cannot increment an output through successive switching, and their operation speeds are limited by their slow thermal reset times. Thus, there is a need for an intermediate device with the interfacing capabilities of a nanowire but a faster, moderated response allowing for modulation of the output. Here, we present a nanowire device based on controlled fluxon transport. We show that the device is capable of responding proportionally to the strength of its input, unlike other nanowire technologies. The device can be operated to produce a multilevel output with distinguishable states, which can be tuned by circuit parameters. Agreement between experimental results and electrothermal circuit simulations demonstrates that the device is classical and may be readily engineered for applications including use as a multilevel memory.

physics.app-ph↗

arXiv2017

Frequency pulling and mixing of relaxation oscillations in superconducting nanowires

Many superconducting technologies such as rapid single flux quantum computing (RSFQ) and superconducting quantum interference devices (SQUIDs) rely on the modulation of nonlinear dynamics in Josephson junctions for functionality. More recently, however, superconducting devices have been developed based on the switching and thermal heating of nanowires for use in fields such as single photon detection and digital logic. In this paper, we use resistive shunting to control the nonlinear heating of a superconducting nanowire and compare the resulting dynamics to those observed in Josephson junctions. We show that interaction of the hotspot growth with the external shunt produces high frequency relaxation oscillations with similar behavior as observed in Josephson junctions due to their rapid time constants and ability to be modulated by a weak periodic signal. In particular, we use a microwave drive to pull and mix the oscillation frequency, resulting in phase locked features that resemble the AC Josephson effect. New nanowire devices based on these conclusions have promising applications in fields such as parametric amplification and frequency multiplexing.

cond-mat.supr-con↗