Special Issue: Nonsilicon, Non-von Neumann Computing—Part II
Volume 108, Issue 8
Special Issue Papers
This article provides new insights into fundamental limitations of the tunnel FETs (tFETs) for desirable energy-efficient operations, and how to possibly overcome them.
Deep Learning Neural Network Architectures
This article considers heterogeneous machine-learning-specific integrated circuits (MSICs) as a new non-von Neumann architecture implementing deep learning neural networks for diverse applications.
As an example of emerging optical technologies in computing, this article considers low-complexity silicon-photonics-enabled integrated optical vector–matrix multiplier for deep neural computations.
Analog Computing Architecture
This article examines the resurgence of analog computing. Tools enabling design of large-scale field-programmable analog arrays (FPAAs) as ubiquitous analog-mixed-signal, low-power sensors are elaborated, and their future potentials are commented on.
New Spin on Spintronics
This article shows how spin-orbitronics can successfully overcome impediments to technology transfer of racetrack memory, as FLASH and magnetic hard disk drives approach their fundamental physical limits.
This article discusses p-bits (probabilistic bits), an interme- diary between the classical (deterministic) bits and the (quantum) q-bits, as an alternative computational paradigm for solving several problems of current interest.
This article provides a perspective on quantum computing from a leading industry laboratory, for providing access to users not acquainted with the hardware and to accommodate new applications.
This article considers architecture of emerging quantum computers, and explores the value of breaking some basic abstractions traditionally used in the design of computational hardware and software.