检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON NANOTECHNOLOGY 2015年第6期14卷 980-991页

作者： Khasanvis, Santosh Li, Mingyu Rahman, Mostafizur Salehi-Fashami, Mohammad Biswas, Ayan K. Atulasimha, Jayasimha Bandyopadhyay, Supriyo Moritz, Csaba Andras Univ Massachusetts Amherst MA 01002 USA Virginia Commonwealth Univ Richmond VA 23284 USA

Probabilistic graphical models are powerful mathematical formalisms for machine learning and reasoning under uncertainty that are widely used for cognitive computing. However, they cannot be employed efficiently for large problems (with variables in the order of 100K or larger) on conventional systems, due to inefficiencies resulting from layers of abstraction and separation of logic and memory in CMOS implementations. In this paper, we present a magnetoelectric probabilistic technology framework for implementing probabilistic reasoning functions. The technology leverages straintronic magneto-tunneling junction (S-MTJ) devices in a novel mixed-signal circuit framework for direct computations on probabilities while enabling in-memory computations with persistence. Initial evaluations of the Bayesian likelihood estimation operation occurring during Bayesian Network inference indicate up to 127 x lower area, 214 x lower active power, and 70 x lower latency compared to an equivalent 45-nm CMOS boolean implementation.

关键词： Probabilistic graphical models Bayesian networks non-boolean computing mixed-signal nanoscale memory-in-computing

来源：评论

学校读者我要写书评

暂无评论

Skewed Straintronic Magnetotunneling-Junction-Based Ternary Content-Addressable Memory-Part I

引用

IEEE TRANSACTIONS ON ELECTRON DEVICES 2017年第7期64卷 2835-2841页

作者： Manasi, Susmita Dey Al-Rashid, Md Mamun Atulasimha, Jayasimha Bandyopadhyay, Supriyo Trivedi, Amit Ranjan Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA Virginia Commonwealth Univ Dept Mech & Nucl Engn Med Coll Virginia Campus Richmond VA 23284 USA Virginia Commonwealth Univ Elect & Comp Engn Med Coll Virginia Campus Richmond VA 23284 USA Virginia Commonwealth Univ Dept Elect & Comp Engn Med Coll Virginia Campus Richmond VA 23284 USA

This paper presents a ternary content-addressable memory (TCAM) cell based on a skewed straintronic magnetotunneling junction (MTJ) switch. A straintronic magnetotunneling junction (s-MTJ) is a three-terminal switch, where the resistance between two of the terminals switches when a potential is applied to the third (gate) terminal that induces strain in the magnetostrictive free-layer. An s-MTJ is a highly energy-efficient switch that would dissipate only similar to aJ of energy during switching. This paper discusses a novel variant of s-MTJ, namely skewed s-MTJ (ss-MTJ), where the MTJ switching can be controlled by two gate terminals. The current through an ss-MTJ is minimum when the potentials at the first and second gate terminals (V-2 and V-3, respectively) obey the relation V-3 = V-2 + V-F. Here, V-F is a fixed voltage ("offset voltage"). Current in an ss-MTJ increases steeply when V-2 and V-3 deviate from the above "match" condition. This unconventional I-V characteristic of an ss-MTJ is exploited to design a non-boolean TCAM cell based on just one transistor, one trench capacitor, and one ss-MTJ. We also discuss search and write operations in the ss-MTJ-TCAM cell, and show that the cell requires very small voltages to operate because of the unique I-V characteristics of the ss-MTJ.

关键词： Nanomagnets non-boolean computing straintronics ternary content-addressable memory (TCAM)

来源：评论

学校读者我要写书评

暂无评论

Reading Nanomagnetic Energy Minimizing Coprocessor

引用

IEEE TRANSACTIONS ON NANOTECHNOLOGY 2018年第2期17卷 368-372页

作者： Roxy, Kawsher A. Bhanja, Sanjukta Univ S Florida Dept Elect Engn Tampa FL 33620 USA

Nanomagnetic coprocessor enacts an energy minimization framework to solve the quadratic optimization problem often arisen in a computer vision paradigm. Our approach relies on the fact that the Hamiltonian of a system of coupled nano-magnets is quadratic. Therefore, a wide class of quadratic energy minimization can be solved directly by the relaxation physics of a grid of nanomagnets. The solutions of such problems are obtained from reading the magnetic state of the cells, in other words, the resistance. This monograph explores the methods to detect the magnetic states, and also considers the dimensional variation of each cell of the coprocessor and inspects the resultant change in resistance. We measure at most 7.8% change in resistance due to the process imperfection of in-house fabrication processes. This requires a read circuitry that can handle the largest deviation. Unlike STT-MRAM, the circular magnets do not have shape anisotropy but, here we show that with an additional preamplifier circuit, we are able to improve sense margin by at least 73%.

关键词： Enery minimization nanomagnet MEMCoP non-boolean computing spintronic devices read circuit

来源：评论

学校读者我要写书评

暂无评论

Physical Implementation of Coherently Coupled Oscillator Networks

引用

IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS 2015年第1期1卷 76-84页

作者： Pufall, Matthew R. Rippard, William H. Csaba, Gyorgy Nikonov, Dmitri E. Bourianoff, George I. Porod, Wolfgang Natl Inst Stand & Technol Boulder CO 80305 USA Univ Notre Dame Ctr Nano Sci & Technol Notre Dame IN 46556 USA Intel Corp Hillsboro OR 97006 USA Intel Corp Austin TX 78746 USA

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.

关键词： Associative processing non-boolean computing oscillator synchronization spin-torque oscillators (STOs)

来源：评论

学校读者我要写书评

暂无评论

An Expanded Benchmarking of Beyond-CMOS Devices Based on boolean and Neuromorphic Representative Circuits

引用

IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS 2017年第1期3卷 101-110页

作者： Pan, Chenyun Naeemi, Azad Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA

The latest results of benchmarking research are presented for a variety of beyond-CMOS charge- and spin-based devices. In addition to improving the device-level models, several new device proposals and a few majorly modified devices are investigated. Deep pipelining circuits are employed to boost the throughput of low-power devices. Furthermore, the benchmarking methodology is extended to interconnect-centric analyses and non-boolean logic applications. In contrast to boolean circuits, non-boolean circuits based on the cellular neural network demonstrate that spintronic devices can potentially outperform conventional CMOS devices.

关键词： Beyond-CMOS technology cellular neural network (CNN) domain wall motion ferro-electric FET interconnect magnetoelectric non-boolean computing spin diffusion spin hall effect (SHE) spintronics throughput tunneling FET (TFET)

来源：评论

学校读者我要写书评

暂无评论

Straintronics: Digital and Analog Electronics With Strain-Switched Nanomagnets

IEEE OPEN JOURNAL OF NANOTECHNOLOGY

引用

IEEE OPEN JOURNAL OF NANOTECHNOLOGY 2020年第1期1卷 57-64页

作者： Bandyopadhyay, Supriyo Virginia Commonwealth Univ Dept Elect & Comp Engn Richmond VA 23284 USA

The search for a binary switch that is more energy-efficient than a transistor has led to many ideas, notable among which is the notion of using a nanomagnet with two stable magnetization orientations that will encode the binary bits 0 and 1. The nanomagnet is switched between them with electrically generated mechanical strain. A tiny amount of voltage is required for switching, with energy dissipation on the order of a few to few tens of aJ. Logic gates and memory, predicated on this technology, have been demonstrated in our group. While they indeed dissipate very little energy, they are unfortunately plagued by unacceptably high switching error probability that hinders their application in most types of boolean logic. Fortunately, they can still be used in applications that are more forgiving of switching errors, e.g. probabilistic computing, analog arithmetic circuits, belief networks, artificial neurons, restricted Boltzmann machines, image processing, and others where the collective activity of many devices acting cooperatively elicit the computing or signal processing function and the failure of a single or few devices does not matter critically. These ultra-energy-efficient strain-switched nanomagnets can also be used for non-computing devices such as microwave oscillators that perform better than spin-torque-nano-oscillators. This short review provides an introduction to this exciting burgeoning field.

关键词： Switches Logic gates Energy dissipation MOSFET Switching circuits Fluctuations Straintronics nanomagnets non-boolean computing energy-efficient information processing

来源：评论

学校读者我要写书评

暂无评论

Coupled-Oscillator Associative Memory Array Operation for Pattern Recognition

引用

IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS 2015年第1期1卷 85-93页

作者： Nikonov, Dmitri E. Csaba, Gyorgy Porod, Wolfgang Shibata, Tadashi Voils, Danny Hammerstrom, Dan Young, Ian A. Bourianoff, George I. Intel Corp Components Res Hillsboro OR 97124 USA Univ Notre Dame Ctr Nano Sci & Technol Notre Dame IN 46556 USA Univ Tokyo Elect Engn Tokyo 1138656 Japan Portland State Univ Dept Elect Engn Portland OR 97207 USA Def Adv Res Projects Agcy Arlington VA 22203 USA

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.

关键词： Array associative memory neural networks non-boolean computing oscillator phase-locked loop (PLL) sparse representation spin torque

来源：评论

学校读者我要写书评

暂无评论

A Simplified Phase Model for Oscillator Based computing

A Simplified Phase Model for Oscillator Based Computing

引用

IEEE-Computer-Society Annual Symposium on VLSI (ISVLSI)

作者： Fang, Yan Yashin, Victor V. Chiarulli, Donald M. Levitan, Steven P. Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15260 USA Univ Pittsburgh Dept Chem Engn Pittsburgh PA 15260 USA Univ Pittsburgh Dept Comp Sci Pittsburgh PA 15260 USA

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.

关键词： non-boolean computing Oscillator Based computing Coupled Oscillators Phase Model Synchronization

来源：评论

学校读者我要写书评

暂无评论

Signal processing with optically-inspired algorithms 14

Signal processing with optically-inspired algorithms

引用

14th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA)

作者： Csaba, Gyoergy Papp, Adam Porod, Wolfgang Univ Notre Dame NDnano Ctr Nano Sci & Technol Notre Dame IN 46556 USA

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.

关键词： non-boolean computing Optical computing Nanocomputing Pattern recognition Spin waves Cellular Networks

来源：评论

学校读者我要写书评

暂无评论

Neural network based on parametrically-pumped oscillators

Neural network based on parametrically-pumped oscillators

引用

23rd IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Csaba, Gyorgy Ytterdal, Trond Porod, Wolfgang Univ Notre Dame NDnano Ctr Nano Sci & Technol Notre Dame IN 46556 USA Norwegian Univ Sci & Technol Dept Elect & Telecommun Trondheim Norway

ISBN: (纸本)9781509061136

We demonstrate that sub-harmonic injection locked oscillators (SHILOs) can serve as building blocks of neural networks. After numerically studying the locking properties of injection-locked ring-oscillator models, we show that resistively or capacitively interconnected networks of such oscillators fall into well-defined ground states, which ground states, in turn, depend on the strength of interconnections. We argue that these networks may serve as efficient hardware implementations for emerging neural network-based processing devices.

关键词： Oscillatory computing non-boolean computing Novel computing architectures

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：