检索结果-内蒙古大学图书馆

High-quality and large-grain epi-like Si film by NiSi2-seed initiated lateral epitaxial crystallization（SILEC）

Science China(Information Sciences) 2020年第12期63卷 272-274页

作者： Yuancheng YANG Baotong ZHANG Xiaoqiao DONG Xiaokang LI Shuang SUN Qifeng CAI Ran BI Xiaoyan XU Ming LI Ru HUANG Key Laboratory of Microelectronic Devices and Circuits Institute of MicroelectronicsPeking University

Dear editor,Three-dimensional monolithic integration (3D-MI)has recently emerged for both "more Moore"and "more than Moore" applications, because of its high integration density, high bandwidth and multi-functions [1]. With 3D-MI, different types of devices can be stacked on the same platform and in a single process flow.

关键词： 3D monolithic integration (3D-MI) NiSi2-seed low-temperature crystallization epitaxial barrier layer metal contamination

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Special Operator for Neural Networks Based on Noise Reduction and Super Resolution

Design and Implementation of a Special Operator for Neural N...

引用

International Conference on ASIC

作者： Hongli Tian Xiaodi Xing Jian Zhang Shaodi Wang Yuan Wang Key Laboratory of Microelectronics Devices and Circuits (MoE) MPW Center School of Integrated Circuits Peking University Beijing Zhicun (Witmem) Technology Co. Ltd Beijing Advanced Innovation Center for Integrated Circuits Beijing China

This paper designs and implements a dedicated operator called FUSE, which implements the function of image fusion in any channel and is applied to the noise reduction and super-resolution neural network designed by Witmem. The FUSE operator we designed uses 32 parallel pipeline calculations, which are internally divided into two clock domains based on the proportion of input and output data volume. We design an algorithm to search for weight address index, making the FUSE operator applicable to images of any size. Under the 28 nm standard CMOS technology, We propose the architecture of the operator and implement the hardware design. FUSE’s area is 236460.2 μm 2 , interface frequency is 1GHz, internal working frequency is 500MHz, and the throughput is 13.7GOPS when image channel is 3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel tunnel FET design through hybrid modulation with optimized subthreshold characteristics and high drive capability

引用

Science China(Information Sciences) 2020年第2期63卷 245-247页

作者： Yang ZHAO Qianqian HUANG Ru HUANG Key Laboratory of Microelectronic Devices and Circuits (MOE) Institute of Microelectronics Peking University National Key Laboratory of Science and Technology on Micro/Nano Fabrication Peking University

Dear editor,As CMOS technology scaling down, the reduction of supply voltage and power consumption becomes extremely difficult due to the subthreshold swing(SS) limitation (60 m V/dec) at room *** FET (TFET) with band-to-band tunneling (BTBT) mechanism is regarded as one of the most promising emerging low-power devices due to its sub-60 m V/dec SS and ultra-low off-current

关键词： A novel tunnel FET design through hybrid modulation with optimized subthreshold characteristics and high drive capability FET

来源：评论

学校读者我要写书评

暂无评论

Microscopic mechanism of imprint in hafnium oxide-based ferroelectrics

引用

Nano Research 2022年第4期15卷 3667-3674页

作者： Peng Yuan Ge-Qi Mao Yan Cheng Kan-Hao Xue Yunzhe Zheng Yang Yang Pengfei Jiang Yannan Xu Yuan Wang Yuhao Wang Yaxin Ding Yuting Chen Zhiwei Dang Lu Tai Tiancheng Gong Qing Luo Xiangshui Miao Qi Liu Key Laboratory of Microelectronic Devices and Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesNo.3Beitucheng West RoadBeijing 100029China University of Chinese Academy of Sciences 19 Yuquan RoadBeijing 100049China School of Integrated Circuits School of Optical and Electronic InformationHuazhong University of Science and Technology1037 Luoyu RoadWuhan 430074China Key Laboratory of Polar Materials and Devices(MOE) Department of ElectronicsEast China Normal University100 Guilin RoadShanghai 430079China Department of Mathematics and Theories Peng Cheng LaboratoryNo.2Xingke 1st StreetShenzhen 518055China

Hafnia-based ferroelectrics have greatly revived the field of ferroelectric memory(FeRAM),but certain reliability issues must be satisfactorily resolved before they can be widely applied in commercial *** particular,the imprint phenomenon severely jeopardizes the read-out reliability in hafnia-based ferroelectric capacitors,but its origin remains unclear,which hinders the development of its recovery *** this work,we have systematically investigated the imprint mechanism in TiN/Hf_(0.5)Zr_(0.5)O_(2)(HZO)/TiN ferroelectric capacitors using experiments and first-principles *** is shown that carrier injection-induced charged oxygen vacancies are at the heart of imprint in HZO,where other mechanisms such as domain pinning and dead layer are less *** imprint model based on electron de-trapping from oxygen vacancy sites has been proposed that can satisfactorily explain several experimental facts such as the strong asymmetric imprint,leakage current variation,and so *** on this model,an effective imprint recovery method has been proposed,which utilizes unipolar rather than bipolar voltage *** remarkable recovery performances demonstrate the prospect of improved device reliability in hafnia-based FeRAM devices.

关键词： hafnia-based ferroelectric imprint build-in electric field oxygen vacancy recovery

来源：评论

学校读者我要写书评

暂无评论

CROSSCUT: A Multi-Core Neuromorphic Accelerator Improving Resource-Utilization

CROSSCUT: A Multi-Core Neuromorphic Accelerator Improving Re...

引用

IEEE International Symposium on circuits and Systems (ISCAS)

作者： Youming Yang Yi Zhong Zilin Wang Tao Zhang Li Lun Yingying Cui Xiaoxin Cui Song Jia Yuan Wang Key Laboratory of Microelectronic Devices and Circuits MPW Center (MoE) School of Integrated Circuits Peking University Beijing China Beijing Laboratory of Future Integrated Circuit Technology and Science Beijing China Beijing Advanced Innovation Center for Integrated Circuits Beijing China

ISBN: (数字)9798350356830

ISBN: (纸本)9798350356847

Neuromorphic computing is attracting significant attention due to its bio-mimetic characteristics. Consequently, neuromorphic hardware platforms have emerged as innovative computing architectures for acceleration. However, the fixed nature of data flow and resources leads to considerable inefficiencies in storage and computation, thereby limiting both utilization efficiency and overall performance. This severely hinders the deployment of edge artificial intelligence (AI) models. To address these issues, we present a multi-core neuromorphic accelerator named CROSSCUT. This crossbar-based system supports both spiking neural network (SNN) and artificial neural network (ANN) paradigms and has a capacity of 256K neurons and 288M synapses. By leveraging the Neuron Package Mechanism (NPM) and Synapse Compress Mechanism (SCM), CROSSCUT can increase input data scale by 64 times and reduce wasted resources and computations by 46.7%, ensuring high compatibility with diverse network structures in machine learning models. Additionally, a Tree-Mesh hybrid network on chip (NoC) is constructed for inter-core communication. Implemented on Xilinx XCVU9P FPGA, CROSSCUT can achieve a peak performance of 431.9 GSOPS/s and 121.13 GSOPS/W energy efficiency. The inference accuracy on MNIST is 98.2%.

关键词： Adaptation models Neuromorphic engineering Computational modeling Neurons Spiking neural networks Hardware Energy efficiency Integrated circuit modeling Synapses Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Design and fabrication of etchless lithium niobate photonic crystal nanobeam cavity for efficient photon manipulation 15

Design and fabrication of etchless lithium niobate photonic ...

引用

15th International Conference on Information Optics and Photonics, CIOP 2024

作者： Jiang, Zhi Yao, Danyang Gao, Yu Ran, Xu Wang, Jianguo Gan, Xuetao Liu, Yan Hao, Yue Han, Genquan State Key Laboratory of Wide-Bandgap Semiconductor Devices and Integrated Technology School of Microelectronics Faculty of integrated circuits Xidian University Xi’an710071 China Key Laboratory of Light Field Manipulation and Information Acquisition Ministry of Industry and Information Technology Shaanxi Key Laboratory of Optical Information Technology School of Physical Science and Technology Northwestern Polytechnical University Xi’an710129 China Hangzhou Institute of Technology Xidian University Hangzhou311200 China

ISBN: (数字)9781510686175

ISBN: (纸本)9781510686168

Recently, a novel approach that uses low-refractive-index polymers as loading materials coated on lithium niobate (LN) can dramatically simplify fabrication challenges for etching LN. On this platform, various devices operating in the transverse magnetic (TM) polarized state based on optical bound states in the continuum (BIC) have been demonstrated. However, in this configuration, the propagation loss of TM mode exhibits sensitivity to waveguide width, which limits design flexibility in waveguide structures. To this end, we designed transverse magnetic electric (TE) polarized photonic crystal structures with the same fabrication process using a y-cut LN on insulator (LNOI) substrate. The fabricated photonic crystal nanobeam cavity (PCNBC) achieves a Q factor over one order of magnitude higher than any previously reported PCNBCs on the etchless LNOI platform and retains a high transmission. To verify the strong photon manipulation ability, additional experiments such as thermo-optic tuning and optical bistability generation have been made. These results demonstrate the potential of our devices for efficient on-chip photon manipulation. © 2024 SPIE.

关键词： Optical bistability

来源：评论

学校读者我要写书评

暂无评论

On-Chip Incremental Learning based on Unsupervised STDP Implementation

On-Chip Incremental Learning based on Unsupervised STDP Impl...

引用

IEEE International Conference on Artificial Intelligence circuits and Systems (AICAS)

作者： Guang Chen Jian Cao Shuo Feng Zilin Wang Yi Zhong Qibin Li Xiongbo Zhao Xing Zhang Yuan Wang School of Software and Microelectronics Peking University Beijing China Key Laboratory of Microelectronic Devices and Circuits (MoE) MPW Center Peking University Beijing China School of Integrated Circuits Peking University Beijing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (数字)9798350383638

ISBN: (纸本)9798350383645

Spiking neural network (SNN), a bio-inspired neuron network, utilizes a learning rule named spike-timing-dependent plasticity (STDP) to achieve high-performance unsupervised learning. However, it may suffer from catastrophic forgetting when the distribution of new data significantly differs from that of old data. To address this issue, an incremental learning implementation for ship classification is presented in this paper. We develop an incremental learning algorithm based on STDP and corresponding platform. A competitive SNN is built into our algorithm, and add-STDP is utilized to update the weights of network for efficient learning. To enhance learning performance, we incorporate weight decay. And to avoid catastrophic forgetting, we incorporate data replay. The corresponding learning platform consists of the FPGA Zynq 7100 and the STDP neuromorphic prototype chip, and our algorithm is executed on the chip. We evaluate the ship classification task on our platform, which demonstrates the superior potential of our on-chip implementation for incremental learning.

关键词： Incremental learning Neuromorphics Neurons Prototypes Spiking neural networks Classification algorithms System-on-chip

来源：评论

学校读者我要写书评

暂无评论

High-spatiotemporal-resolution chip analysis using a fiber-coupled quantum sensor based on diamond N-V centers

引用

Physical Review Applied 2025年第2期23卷 024050-024050页

作者： Youwei Liu Fazhan Zhao Jing Li Zhenfeng Li Lei Wang Bo Li Key Laboratory of Science and Technology on Silicon Devices Institute of Microelectronics Chinese Academy of Sciences 100029 Beijing China School of Integrated Circuits University of Chinese Academy of Sciences 101408 Beijing China Communication and Information Engineering Center Institute of Microelectronics Chinese Academy of Sciences 100029 Beijing China

We propose a chip analysis method using a fiber-optic quantum sensor based on diamond nitrogen-vacancy (N-V) centers to capture the magnetic field associated with short-pulse currents in chips. The fiber-coupled diamond N-V sensor was precisely positioned at the target region of the chip. We performed real-time monitoring of the N-V center fluorescence responses to pulsing magnetic fields generated by the pulse signals in the test chip through continuous-wave optically detected magnetic resonance. This allowed the accurate reconstruction of the chip internal node signal variations. We successfully achieved a time resolution of 200 ns, which was consistent with the metastable state lifetime of the N-V centers at room temperature. Furthermore, we evaluated the shot noise–limited magnetic sensitivity, which was found to be 6.3nT/Hz1/2. The proposed system exhibited swift responsivity to short pulse currents in the chip, providing highly accurate spatial localization of magnetic field variations. It satisfied the demand for rapid response and precise positioning in chip testing. Overall, this study validates the potential application of N-V centers in the domain of chip security analysis, offering a solution for chip diagnostics.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Impact of O_(2)post oxidation annealing on the reliability of SiC/SiO_(2)MOS capacitors

引用

Chinese Physics B 2021年第7期30卷 461-466页

作者： Peng Liu Ji-Long Hao Sheng-Kai Wang Nan-Nan You Qin-Yu Hu Qian Zhang Yun Bai Xin-Yu Liu Key Laboratory of Microelectronics Devices&Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesBeijing 100029China University of Chinese Academy of Sciences Beijing 100049China High-Frequency High-Voltage Device and Integrated Circuits R&D Center Institute of MicroelectronicsChinese Academy of SciencesBeijing 100029China

The effects of dry O_(2)post oxidation annealing(POA)at different temperatures on SiC/SiO_(2)stacks are comparatively studied in this *** results show interface trap density(Dit)of SiC/SiO_(2)stacks,leakage current density(Jg),and time-dependent dielectric breakdown(TDDB)characteristics of the oxide,are affected by POA temperature and are closely ***,Dit,Jg,and inverse median lifetime of TDDB have the same trend against POA temperature,which is instructive for SiC/SiO_(2)interface quality ***,area dependence of TDDB characteristics for gate oxide on SiC shows different electrode areas lead to same slope of TDDB Weibull curves.

关键词： SiC O_(2)post oxidation annealing interface traps MOS

来源：评论

学校读者我要写书评

暂无评论

Long-term and short-term plasticity independently mimicked in highly reliable Ru-doped Ge_(2)Sb_(2)Te_(5) electronic synapses

引用

InfoMat 2024年第8期6卷 85-96页

作者： Qiang Wang Yachuan Wang Yankun Wang Luyue Jiang Jinyan Zhao Zhitang Song Jinshun Bi Libo Zhao Zhuangde Jiang Jutta Schwarzkopf Shengli Wu Bin Zhang Wei Ren Sannian Song Gang Niu State Key Laboratory for Manufacturing Systems Engineering Electronic Materials Research LaboratoryKey Laboratory of the Ministry of Education&International Center for Dielectric ResearchSchool of Electronic Science and EngineeringXi'an Jiaotong UniversityXi'anthe People's Republic of China School of Integrated Circuits Peking UniversityBeijingthe People's Republic of China Beijing Microelectronics Technology Institute Beijingthe People's Republic of China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual information and Applicationsand School of SoftwareXi'an Jiaotong UniversityXi'anthe People's Republic of China State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghaithe People's Republic of China Key Laboratory of Microelectronics Device and Integrated Technology The Institute of Microelectronics of Chinese Academy of SciencesBeijingthe People's Republic of China University of Chinese Academy of Sciences Beijingthe People's Republic of China The State Key Laboratory for Manufacturing Systems Engineering&The International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technology Xi'an Jiaotong UniversityXi'anthe People's Republic of China Leibniz-Institut für Kristallzüchtung Max-Born-Straße 2BerlinGermany Key Laboratory of Physical Electronics and Devices Ministry of EducationSchool of Electronic Science and EngineeringXi'an Jiaotong UniversityXi'anthe People's Republic of China The International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technology Xi'an Jiaotong UniversityXi'anthe People's Republic of China

In order to fulfill the complex cognitive behaviors in neuromorphic systems with reduced peripheral circuits,the reliable electronic synapses mimicked by single device that achieves diverse long-term and short-term plasticity are *** change random access memory(PCRAM)is of great potential for artificial synapses,which faces,however,difficulty to realize short-term plasticity due to the long-lasting resistance *** work reports the ruthenium-doped Ge_(2)Sb_(2)Te_(5)(RuGST)based PCRAM,demonstrating a series of synaptic behaviors of short-term potentiation,pair-pulse facilitation,longterm depression,and short-term plasticity in the same single *** optimized RuGST electronic synapse with the high transformation temperature of hexagonal phase>380C,the outstanding endurance>108 cycles,the low resistance drift factor of 0.092,as well as the extremely high linearity with correlation coefficients of 0.999 and 0.976 in parts of potentiation and *** investigations also go insight to mechanisms of Ru doping according to thorough microstructure characterization,revealing that Ru dopant is able to enter GST lattices thus changing and stabilizing atomic arrangement of *** leads to the short-term plasticity realized by RuGST ***,the proposed RuGST electronic synapses performs a high accuracy of94.1%in a task of image recognition of CIFAR-100 database using ResNet *** work promotes the development of PCRAM platforms for large-scale neuromorphic systems.

关键词： electronic synapses neuromorphic computing PCRAM Ru-doped Ge_(2)Sb_(2)Te_(5)

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：