dcsimg

Nonsilicon, Non-von Neumann Computing—Part II

Volume 108, Issue 8 | August 2020

Guest Editors:

Sankar Basu
Randal E. Bryant
Giovanni De Micheli
Thomas Theis
Lloyd Whitman

Special Issue Papers

Scanning the Issue

By S. Basu, R. E. Bryant, G. De Micheli, T. Theis, and L. Whitman

Foundational Issues

Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing

By S. Dutta, H. Jeong, Y. Yang, V. Cadambe, T. M. Low, and P. Grover

This article considers fundamental limits and novel strategies regarding resiliency of computation by invoking information-theoretic principles for basic building blocks of scientific computation and data analytics (“dwarfs”).

Tunnel-FET Switching Is Governed by Non-Lorentzian Spectral Line Shape

By S. K. Vadlamani, S. Agarwal, D. T. Limmer, S. G. Louie, F. R. Fischer, and E. Yablonovitch

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

The Heterogeneous Deep Neural Network Processor With a Non-von Neumann Architecture

By D. Shin and H.-J. Yoo

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.

Silicon Photonics Codesign for Deep Learning

By Q. Cheng, J. Kwon, M. Glick, M. Bahadori, L. P. Carloni, and K. Bergman

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

Large-Scale Field-Programmable Analog Arrays

By J. Hasler

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

Magnetic Racetrack Memory: From Physics to the Cusp of Applications Within a Decade

By R. Bläsing, A. A. Khan, P. Ch. Filippou, C. Garg, F. Hameed, J. Castrillon, and S. S. P. Parkin

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.

From Charge to Spin and Spin to Charge: Stochastic Magnets for Probabilistic Switching

By K. Y. Camsari, P. Debashis, V. Ostwal, A. Z. Pervaiz, T. Shen, Z. Chen, S. Datta, and J. Appenzeller

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.

Quantum Computing

Challenges and Opportunities of Near-Term Quantum Computing Systems

By A. D. Córcoles, A. Kandala, A. Javadi-Abhari, D. T. McClure, A. W. Cross, K. Temme, P. D. Nation, M. Steffen, and J. M. Gambetta

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.

Resource-Efficient Quantum Computing by Breaking Abstractions

By Y. Shi, P. Gokhale, P. Murali, J. M. Baker, C. Duckering, Y. Ding, N. C. Brown, C. Chamberland, A. Javadi-Abhari, A. W. Cross, D. I. Schuster, K. R. Brown, M. Martonosi, and F. T. Chong

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.