检索结果-内蒙古大学图书馆

16th International symposium on Applied Reconfigurable computing

作者： Misra, Ashish Kindratenko, Volodymyr Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9783030445331;9783030445348

Deep Neural Networks (DNNs) have been successfully applied in many fields. Considering performance, flexibility, and energy efficiency, Field Programmable Gate Array (FPGA) based accelerator for DNNs is a promising solution. the existing frameworks however lack the possibility of reusability and friendliness to design a new network with minimum efforts. Modern high-level synthesis (HLS) tools greatly reduce the turnaround time of designing and implementing complex FPGA-based accelerators. this paper presents a framework for hardware accelerator for DNNs using high level specification. A novel architecture is introduced that maximizes data reuse and external memory bandwidth. this framework allows to generate a scalable HLS code for a given pre-trained model that can be mapped to different FPGA platforms. Various HLS compiler optimizations have been applied to the code to produce efficient implementation and high resource utilization. the framework achieves a peak performance of 23 frames per second for SqueezeNet on Xilinx Alveo u250 board.

关键词： Accelerator design high level synthesis FPGA

来源：评论

学校读者我要写书评

暂无评论

Trusted Virtual Machine Model Based on high-performance Cipher Coprocessor 6th

Trusted Virtual Machine Model Based on High-Performance Ciph...

引用

6th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2020

作者： Liu, Haidong Guo, Songhui Sun, Lei Guo, Song Information Engineering University Zhengzhou450000 China

ISBN: (纸本)9789811579806

In the cloud computing environment, with the complex network environment, the virtualization platform faces many security problems. At the same time, trusted computing can greatly enhance the architecture security of virtualization platform systems, but there are many problems when trusted computing is deployed directly in the cloud environment. therefore, this paper proposes a trusted virtual machine model based on high-performance cipher coprocessor to solve the security problems such as the isolation and insufficient performance of virtual TPM (vTPM) on the existing virtual platform. In this model, virtio technology was used to realize the virtualization of TPM, and a management architecture was designed to manage the life cycle of vTPM. the analysis shows that the model can complete the isolation of vTPM, and protect the security of vTPM during the migration process through the migration control server, and can strengthen the security of the virtualization platform. Finally, the simulation results show that the model is more feasible and suitable for cloud platform than hardware TPM. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

performance Evaluation of Manifold Algorithms on a P300 Paradigm Based Online BCI Dataset 15th

Performance Evaluation of Manifold Algorithms on a P300 Para...

引用

15th Mediterranean Conference on Medical and Biological Engineering and computing (MEDICON)

作者： Chatterjee, Bipra Palaniappan, Ramaswamy Gupta, Cota Navin Indian Inst Technol Neural Engn Lab Dept Biosci & Bioengn Gauhati India Univ Kent Data Sci Res Grp Sch Comp Chatham Kent England

ISBN: (纸本)9783030316358;9783030316341

Healthcare field is highly benefited by incorporating BCI for detection and diagnosis of some health related detriment as well as rehabilitation and restoration of certain disabilities. An EEG dataset acquired from 15 high-functioning ASD patients, while they were undergoing a P300 experiment in a virtual reality platform, was analysed in this paper using three algorithms. performance of Bayes Linear Discriminant Analysis (BLDA) was predominant over Convolutional Neural Network (CNN) and Random Undersampling (RUS) Boosting. BLDA rendered 73% overall accuracy in predicting target and the best accuracy for each subject using CNN or BLDA yielded an overall accuracy of 76%.

关键词： Brain-computer Interfaces CNN BLDA RUSBoosting

来源：评论

学校读者我要写书评

暂无评论

A Research Retrospective on AMD's Exascale computing Journey 23

A Research Retrospective on AMD's Exascale Computing Journey

引用

Proceedings of the 50th Annual International symposium on computer architecture

作者： Gabriel H. Loh Michael J. Schulte Mike Ignatowski Vignesh Adhinarayanan Shaizeen Aga Derrick Aguren Varun Agrawal Ashwin M. Aji Johnathan Alsop Paul Bauman Bradford M. Beckmann Majed Valad Beigi Sergey Blagodurov Travis Boraten Michael Boyer William C. Brantley Noel Chalmers Shaoming Chen Kevin Cheng Michael L. Chu David Cownie Nicholas Curtis Joris Del Pino Nam Duong Alexandru Duțu Yasuko Eckert Christopher Erb Chip Freitag Joseph L. Greathouse Sudhanva Gurumurthi Anthony Gutierrez Khaled Hamidouche Sachin Hossamani Wei Huang Mahzabeen Islam Nuwan Jayasena John Kalamatianos Onur Kayiran Jagadish Kotra Alan Lee Daniel Lowell Niti Madan Abhinandan Majumdar Nicholas Malaya Srilatha Manne Susumu Mashimo Damon McDougall Elliot Mednick Michael Mishkin Mark Nutter Indrani Paul Matthew Poremba Brandon Potter Kishore Punniyamurthy Sooraj Puthoor Steven E. Raasch Karthik Rao Gregory Rodgers Marko Scrbak Mohammad Seyedzadeh John Slice Vilas Sridharan René van Oostrum Eric van Tassell Abhinav Vishnu Samuel Wasmundt Mark Wilkening Noah Wolfe Mark Wyse Adithya Yalavarti Dmitri Yudanov Advanced Micro Devices Inc. Bellevue WA USA Advanced Micro Devices Inc. Austin TX USA Advanced Micro Devices Inc. Santa Clara CA USA Advanced Micro Devices Inc. Boxborough MA USA Advanced Micro Devices Inc. Santa Clara WA USA Advanced Micro Devices Inc Bellevue WA USA Advanced Micro Devices Inc. Rochester NY USA Advanced Micro Devices Inc. Orlando FL USA Advanced Micro Devices Inc. San Diego CA USA Advanced Micro Devices Inc. Folsom CA USA

ISBN: (纸本)9798400700958

the pace of advancement of the top-end supercomputers historically followed an exponential curve similar to (and driven in part by) Moore's Law. Shortly after hitting the petaflop mark, the community started looking ahead to the next milestone: Exascale. However, many obstacles were already looming on the horizon, such as the slowing of Moore's Law, and others like the end of Dennard Scaling had already arrived. Anticipating significant challenges for the overall high-performance computing (HPC) community to achieve the next 1000x improvement, the U.S. Department of Energy (DOE) launched the Exascale computing Program to enable and accelerate fundamental research across the many technologies needed to achieve exascale *** had the opportunity to contribute to the so-called "*Forward" programs from the DOE, which were a series of public-private partnerships focused on research and co-design activities covering compute architectures, interconnects, memory systems, chiplets and packaging, software stacks, applications, and more. Some of the research from these programs can now be found in the world's first exascale supercomputer, some were a little ahead of their time and may have an impact in the coming years, and others simply did not pan out. In this paper, we provide a retrospective of AMD's nearly decade-long research journey covering how we tried to predict the architecture of a supercomputer a decade into the future, what we got right, what we got wrong, and some of the insights and learnings that we discovered along the way.

关键词： exascale

来源：评论

学校读者我要写书评

暂无评论

Generator from Edges: Reconstruction of Facial Images 15th

Generator from Edges: Reconstruction of Facial Images

引用

15th International symposium on Visual computing, ISVC 2020

作者： Takano, Nao Alaghband, Gita Computer Science and Engineering University of Colorado Denver Denver United States

ISBN: (纸本)9783030645588

Applications that involve supervised training require paired images. Researchers of single image super-resolution (SISR) create such images by artificially generating blurry input images from the corresponding ground truth. Similarly we can create paired images with the canny edge. We propose Generator From Edges (GFE) [Fig. 1]. Our aim is to determine the best architecture for GFE, along with reviews of perceptual loss [1, 2]. To this end, we conducted three experiments. First, we explored the effects of the adversarial loss often used in SISR. In particular, we uncovered that it is not an essential component to form a perceptual loss. Eliminating adversarial loss will lead to a more effective architecture from the perspective of hardware resource. It also means that considerations for the problems pertaining to generative adversarial network (GAN) [3], such as mode collapse, are not necessary. Second, we reexamined VGG loss and found that the mid-layers yield the best results. By extracting the full potential of VGG loss, the overall performance of perceptual loss improves significantly. third, based on the findings of the first two experiments, we reevaluated the dense network to construct GFE. Using GFE as an intermediate process, reconstructing a facial image from a pencil sketch can become an easy task. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A survey of multicast communication in optical network-on-chip (Onoc) 10th

A survey of multicast communication in optical network-on-ch...

引用

10th International symposium on Parallel architectures, Algorithms and Programming, PAAP 2019

作者： Yang, Wen Chen, Yawen Huang, Zhiyi Zhang, Haibo Gu, Huaxi Yu, Cui Department of Computer Science University of Otago Dunedin9016 New Zealand State Key Laboratory of ISN Xidian University Xi’an710071 China Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province China Jiliang University Hangzhou310018 China

Optical Network-on-Chip (ONoC) is an emerging chip-level optical interconnection technology to realise high-performance and power-efficient inter-core communication for many-core processors. For on-chip networks, multicast communication is an important communication pattern, which is not only widely used in parallel computing applications in Chip Multi-Processors (CMPs), but also commonly adopted in emerging areas such as neuromorphic computing. However, the opti-misation of multicast communication in an ONoC is not well studied and there is a significant room to improve the performance. In this paper, we present a comprehensive survey of the multicast communication in an ONoC, covering the development of both architecture design and networking design as well as our recent research outcomes. Moreover, we propose the design challenges and future research directions for optimis-ing multicast in an ONoC, which can provide guidance and insight for the future researchers and chip developers. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

MMPDNet: Multi-Stage & Multi-Attention Progressive Image Denoising

MMPDNet: Multi-Stage & Multi-Attention Progressive Image Den...

引用

International Conference on Ubiquitous computing and Communications and International symposium on Cyberspace and Security (IUCC-CSS)

作者： Jiangbo Xue Jiu Liang Jinhe He Yu Zhang Yanda Hu School of Computer Science ShaanXi Normal University Xi'an China School of Computer Science ShaanXi Normal UniversityXi'anChina

ISBN: (纸本)9781665466684

Deep convolutional neural networks (CNNs) have gained great success in many low-level tasks of computer vision, especially in the task of image denoising. However, there are two major drawbacks for denoising tasks, one is that it is very hard to choose a strategy to make deeper CNN convergence, other is that mainstream approaches do not do well a complex balance between spatial details and high-level features information while reconstructing clean images. In this paper, we proposed a novel multi-stage and multi-attention architecture of CNN for image denoising. In detail, our model is a multi-stage network, in each stage, we separate degraded inputs into different patches to learn the reconstruct mapping, thus, the overall denoising process is divided into several easily convergence steps. Meanwhile, a channel-spatial attention module is proposed to learn high-level features from different dimensions. Furthermore, an effectively supervised module is employed between every two-stage to refine the reconstructed results. the resulting multi-stage and multi-attention architecture, named MMPDNet, and its extensive experiment results deliver strong performance gains on some primary real-word denoising datasets, including SIDD and DND.

关键词： Noise reduction computer architecture performance gain Feature extraction Ubiquitous computing Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

Simulation of high-Definition Pixel-Headlights 15th

Simulation of High-Definition Pixel-Headlights

引用

15th International symposium on Visual computing, ISVC 2020

作者： Waldner, Mirko Bertram, Torsten TU Dortmund University Institute of Control Theory and Systems Engineering Dortmund Germany

ISBN: (纸本)9783030645557

this contribution presents a novel algorithm for real-time simulation of adaptive matrix- and pixel-headlights for motor vehicles. the simulation can generate the light distribution of a pair of pixel-headlamps with a resolution of more than one and a half million matrix-elements per light module in real-time. this performance is achieved by dividing the superposition process of the matrix-light-sources into an offline and an online part. the offline part creates a light database that is used by the online component to generate the illumination in memory access efficient way. For an ideal pixel-headlight the run-time of the approach is nearly constant by increasing the number of matrix-lights. this contribution evaluates the visual quality of the simulation. It also presents the changes in the run-time for different pixel-headlamp resolutions and solid angle discretizations. © 2020, Springer Nature Switzerland AG.

关键词： Headlights

来源：评论

学校读者我要写书评

暂无评论

基于国产处理器的智能大数据一体机架构及应用研究

引用

南京邮电大学学报（自然科学版） 2024年第4期44卷 1-16页

作者：陈国良汤晓宇尤帅姚小良梅超君林时俊刘尚东吴少刚孙雅薇王汝传季一木南京邮电大学计算机学院江苏南京210023 南京邮电大学高性能计算与大数据处理研究所江苏南京210023 国家高性能计算中心南京分中心江苏南京210023 龙芯中科技术股份有限公司北京101111 北方信息控制研究院集团有限公司江苏南京211153

分析比较国内外智能芯片产品现状,概述智能芯片的相关软硬件技术栈,针对国内大数据与人工智能产业支撑体系尚不完善、尚未建立国产化信息处理安全保障体系的问题,提出基于国产芯片自主研发的智能大数据一体机研究与设计。解决基础设施... 详细信息

分析比较国内外智能芯片产品现状,概述智能芯片的相关软硬件技术栈,针对国内大数据与人工智能产业支撑体系尚不完善、尚未建立国产化信息处理安全保障体系的问题,提出基于国产芯片自主研发的智能大数据一体机研究与设计。解决基础设施的运维部署、海量数据存储以及时效性处理等问题,通过对比异构计算系统的分析研究,文中提出的基于国产CPU和NPU异构硬件加速的一体化计算平台具有信息安全、领域普适性强、运行效率高等特点。

关键词：国产芯片大数据一体机大数据处理智能计算信息安全

来源：评论

学校读者我要写书评

暂无评论

Network and Application Layer Services for high performance Communications in Buildings 15

Network and Application Layer Services for High Performance ...

引用

15th IEEE International symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Cosmas, John Jawad, Nawar Ali, Kareem Meunier, Ben Zhang, Yue Li, Wei Gregorczyk, Marcin Mazurczyk, Wojciech Cabaj, Krzysztof Lacaud, Mathias Negru, Daniel Navas, Sara Cuerva Davila, Ignacio Losas Zarakovitis, Charilaos C. Koumaras, Harilaos Kourtis, Michail-Alexandros Brunel Univ Coll Engn Design & Phys Sci London England Univ Leicester Sch Engn Leicester Leics England Viavi Solut Stevenage Herts England Warsaw Univ Technol Warsaw Poland Joada SAS Bordeaux France Ferovial SAS Madrid Spain CI3 Madrid Spain NCSR DEMOKRITOS Athens Greece

ISBN: (纸本)9781728157849

the Internet of Radio Light (IoRL) project has developed a high performance buildings communications system with Mobile Edge computing (MEC) facilities that can potentially provide intelligent SDN/NFV services over 1G bits/second for each room in the property up to a total of 10G bits/second, with latency from the user terminal to the property gateway of less than 0.5ms and with location estimation accuracy of less than 10 cm. Communications performance at this level of performance and intelligence will allow for innovative application and network layer services so that people can live, work and play from their home instead of being dependent on fossil fuels for physical transportation for their social interactions.

关键词： 5G Home Communication System mm Wave Communications Virtual Network Functions and Software Defined Networks Network and Application Layer Services

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：