检索结果-内蒙古大学图书馆

Automatic-SSD: Full Hardware Automation over New Memory for High Performance and Energy Efficient PCIe Storage Cards

学校读者我要写书评

暂无评论

Automatic-SSD: Full Hardware Automation over New Memory for ...

IEEE International Conference on computer-Aided Design

作者： Gyuyoung Park Myoungsoo Jung Computer Architecture and Memory Systems Laboratory Korea Advanced Institute of Science and Technology Daejeon Korea

ISBN: (数字)9781665423243

We propose Automatic-SSD that converts all storage management logic into hardware, which enable energy efficient, high performance fast memory based block storage. To achieve low operating power, Automatic-SSD directly reads or writes host-side data to underlying backend storage media without internal DRAM caches. To realize such DRAM-less approach with better performance and make it more energy efficient, Automatic-SSD also removes the internal processor(s) and firmware execution therein by fully automating the backend request management and data transfers over all pipelined hardware modules. We prototype Automatic-SSD on a middle-end FPGA custom board, employing massive numbers of phase change memories as representative of new memory technologies. Our evaluation results show that, compared to a conventional firmware-based approach, Automatic-SSD shows up 28.8× and 25.4× better bandwidth and latency behaviors, respectively, while consuming only 5% of the total energy, on overage.

关键词： Microprogramming Nonvolatile memory Hardware Phase change random access memory Memory management Power demand Media

Bayesian uncertainty analysis for underwater 3D reconstruction with neural radiance fields

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lian, Haojie Li, Xinhao Qu, Yilin Du, Jing Meng, Zhuxuan Liu, Jie Chen, Leilei Key Laboratory of In-situ Property-improving Mining of Ministry of Education Taiyuan University of Technology Taiyuan100190 China Henan International Joint Laboratory of Structural Mechanics and Computational Simulation College of Architecture and Civil Engineering Huanghuai University Zhumadian463000 China School of Marine Science and Technology Northwestern Polytechnical University Xi’an710072 China Unmanned Vehicle Innovation Center Ningbo Institute of Northwestern Polytechnical University Ningbo315103 China Key Laboratory of Unmanned Underwater Vehicle Technology of Ministry of Industry and Information Technology Northwestern Polytechnical University Xi’an710072 China Center for Strategic Assessment and Consulting Academy of Military Science Beijing100091 China Computer Engineering Department Taiyuan Institute of Technology Taiyuan030008 China

Neural radiance fields (NeRFs) are a deep learning technique that can generate novel views of 3D scenes using sparse 2D images from different viewing directions and camera poses. As an extension of conventional NeRFs in underwater environment, where light can get absorbed and scattered by water, SeaThru-NeRF was proposed to separate the clean appearance and geometric structure of underwater scene from the effects of the scattering medium. Since the quality of the appearance and structure of underwater scenes is crucial for downstream tasks such as underwater infrastructure inspection, the reliability of the 3D reconstruction model should be considered and evaluated. Nonetheless, owing to the lack of ability to quantify uncertainty in 3D reconstruction of underwater scenes under natural ambient illumination, the practical deployment of NeRFs in unmanned autonomous underwater navigation is limited. To address this issue, we introduce a spatial perturbation field Dω based on Bayes’ rays in SeaThru-NeRF and perform Laplace approximation to obtain a Gaussian distribution N(0, Σ) of the parameters ω, where the diagonal elements of Σ correspond to the uncertainty at each spatial location. We also employ a simple thresholding method to remove artifacts from the rendered results of underwater scenes. Numerical experiments are provided to demonstrate the effectiveness of this approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Uncertainty analysis

Understanding the Runtime Overheads of Deep Learning Inference on Edge Devices

学校读者我要写书评

暂无评论

Understanding the Runtime Overheads of Deep Learning Inferen...

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Xiu Ma Guangli Li Lei Liu Huaxiao Liu Xiaobing Feng College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

With the growing ubiquity of the Internet of Things, in-the-edge inference of deep neural network models has been a major driver for promoting the widespread use of intelligent applications. As model inference characteristics are crucial for optimizing and deploying deep neural networks on hardware platforms, many studies focus on analyzing the performance of neural networks such as latency, accuracy, throughput, and energy consumption. However, few existing works have ever discussed the runtime overheads hidden in neural network inference, despite the overheads are non-negligible for edge applications. The lack of in-depth analysis of the overheads hinders the understanding of how hardware designs and model structures impact on-device inference performance. In this paper, we characterize the runtime overheads of deep learning inference on representative edge devices by leveraging state-of-the-art neural network models, performing a systematical analysis from the perspective of end-to-end performance, hardware platforms, memory bandwidth, and neural network model structures. Based on experimental results, the crucial insights are offered to facilitate the design and configure of resource-efficient networks and pick appropriate models on the specific platform, which provides a comprehensive view of runtime overheads of in-the- edge neural network inference for architects and developers.

关键词： Deep learning Performance evaluation Analytical models Runtime Roads Neural networks Throughput

Deformation mechanism and collapse treatment of the rock surrounding a shallow tunnel based on on-site monitoring

学校读者我要写书评

暂无评论

Journal of Mountain science 2020年第12期17卷 2897-2914页

作者： QIU Hong-zhi CHEN Xiao-qing WU Qi-hong WANG Ren-chao ZHAO Wan-yu QIAN Ke-jiang School of Architecture and Civil Engineering Chengdu UniversityChengdu 610106China Key Laboratory of Mountain Hazards and Earth Surface Processes Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610041China Hunan International Scientific and Technological Innovation Cooperation Base of Advanced Construction and Maintenance Technology of Highway Changsha University of Science&TechnologyChangsha 410114China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

When tunnels are constructed at shallow depths in areas with poor geological conditions,such as portal sections,valleys and hillsides in regions with granitic bedrock,considerable excavation-induced deformation of the surrounding rock may occur,potentially resulting in tunnel *** main reason for these problems is the lack of understanding of the deformation mechanism and evolution of the soft granitic rock surrounding the tunnel and the adoption of inappropriate construction technology and *** article analyzes the deformation mechanism of the rock surrounding a shallow tunnel based on in situ monitoring data as a case study and suggests that certain measures should be taken to effectively control the deformation of the surrounding rock and to minimize the potential for tunnel *** results show that the deformation of the granitic soil surrounding the tunnel can be divided into three stages:the rapid deformation stage,the slow deformation stage and the stabilization *** construction methods should be carefully selected to ensure safety during tunnel excavation in the first *** avoid secondary disasters caused by tunnel collapses,three treatment measures may be implemented as part of safety management:enhancing the monitoring of the surrounding rock deformation,adjusting the construction methods and optimizing the support *** particular,accurate monitoring data and timely information feedback play a vital role in tunnel ***,engineers with considerable engineering experience and professional knowledge are needed to analyze the monitoring data and make accurate predictions of tunnel deformation to ensure that reasonable measures are taken in the process of shallow tunnel excavation.

关键词： Shallow tunnel Surrounding rock deformation Field monitoring Treatment for collapse Information feedback

A Survey on Indoor Visible Light Positioning Systems: Fundamentals, Applications, and Challenges

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Zhiyu Yang, Yang Chen, Mingzhe Guo, Caili Cheng, Julian Cui, Shuguang The Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Faculty of Applied Science School of Engineering The University of British Columbia KelownaBCV1V 1V7 Canada The Chinese University of Hong Kong Shenzhen518172 China

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

A systematic view of leakage risks in deep neural network systems

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Hu, Xing Liang, Ling Chen, Xiaobing Deng, Lei Ji, Yu Ding, Yufei Du, Zidong Guo, Qi Sherwood, Timothy Xie, Yuan State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Department of Electrical and Computer Engineering University of California Santa Barbara United States Department of Computer Science University of California Santa Barbara United States Tsinghua University China University of California Santa Barbara United States

As deep neural networks (DNNs) continue their reach into a wide range of application domains, the neural network architecture of DNN models becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. In observing the large gap between the architectural surfaces exploration and the model integrity study, this paper first presents the formulated schema of the model leakage risks. Then, we propose DeepSniffer, a learning-based model extraction framework, to obtain the complete model architecture information without any prior knowledge of the victim model. It is robust to architectural and system noises introduced by the complex memory hierarchy and diverse run-time system optimizations. Taking GPU platforms as a showcase, DeepSniffer performs model extraction by learning both the architecture-level execution features of kernels and the inter-layer temporal association information introduced by the common practice of DNN design. We demonstrate that DeepSniffer works experimentally in the context of an off-the-shelf Nvidia GPU platform running a variety of DNN models. The extracted models are directly helpful to the attempting of crafting adversarial inputs. The DeepSniffer project has been released in https://***/xinghu7788/DeepSniffer. © 2021, CC0.

关键词： Deep neural networks

Sampling methods for efficient training of graph convolutional networks: A survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Xin Yan, Mingyu Deng, Lei Li, Guoqi Ye, Xiaochun Fan, Dongrui State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100086 China Department of Precision Instrument Center for Brain Inspired Computing Research Tsinghua University Beijing100084 China School of Computer Science and Technology University of Chinese Academy of Sciences

—Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Pressure induced transition from chiral charge order to time-reversal symmetry-breaking superconducting state in Nb-doped CsV3Sb5

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Graham, J.N. Islam, S.S. Sazgari, V. Li, Y. Deng, H. Janka, G. Zhong, Y. Gerguri, O. Král, P. Doll, A. Bialo, I. Chang, J. Salman, Z. Suter, A. Prokscha, T. Yao, Y. Okazaki, K. Luetkens, H. Khasanov, R. Wang, Z. Yin, J.-X. Guguchia, Z. PSI Center for Neutron and Muon Sciences CNM Villigen5232 Switzerland Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement Ministry of Education School of Physics Beijing Institute of Technology Beijing100081 China Beijing Key Lab of Nanophotonics and Ultrafine Optoelectronic Systems Beijing Institute of Technology Beijing100081 China Department of Physics Southern University of Science and Technology Guangdong Shenzhen518055 China Institute for Solid States Physics The University of Tokyo Kashiwa Japan Physik-Institut Universität Zürich Winterthurerstrasse 190 ZürichCH-8057 Switzerland AGH University of Science and Technology Faculty of Physics and Applied Computer Science Kraków30-059 Poland International Center for Quantum Materials Beijing Institute of Technology Zhuhai319000 China Trans-scale Quantum Science Institute The University of Tokyo Tokyo Japan Material Innovation Research Center The University of Tokyo Kashiwa Japan

The experimental realisation of unconventional superconductivity and charge order in kagome systems AV3Sb5 is of critical importance. We conducted a highly systematic study of Cs(V1−xNbx)3Sb5 with x=0.07 (Nb0.07-CVS) by employing a unique combination of tuning parameters such as doping, hydrostatic pressure, magnetic fields, and depth, using muon spin rotation, AC susceptibility, and STM. We uncovered tunable magnetism in the normal state of Nb0.07-CVS, which transitions to a time-reversal symmetry (TRS) breaking superconducting state under pressure. Specifically, our findings reveal that the bulk of Nb0.07-CVS (at depths >20 nm from the surface) experiences TRS breaking below T∗ = 40 K, lower than the charge order onset temperature, TCO = 58 K. However, near the surface ( © 2024, CC BY.

关键词： Magnetic susceptibility

An advanced YOLOv3 method for small object detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Baokai He, Fengjie Du, Shiqiang Li, Jiacheng Liu, Wenjie Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education Chinese National Information Technology Research Institute Northwest Minzu University Gansu Lanzhou730030 China China Mobile Design Institute Co. Ltd. Shaanxi Branch Shaanxi Xi’an710000 China College of Mathematics and Computer Science Northwest Minzu University Gansu Lanzhou730030 China

Small object detection has important application value in the fields of autonomous driving and drone scene analysis. As one of the most advanced object detection algorithms, YOLOv3 suffers some challenges when detecting small objects, such as the problem of detection failure of small objects and occluded objects. To solve these problems, an improved YOLOv3 algorithm for small object detection is proposed. In the proposed method, the dilated convolutions mish (DCM) module is introduced into the backbone network of YOLOv3 to improve the feature expression ability by fusing the feature maps of different receptive fields. In the neck network of YOLOv3, the convolutional block attention module (CBAM) and multi-level fusion module are introduced to select the important information for small object detection in the shallow network, suppress the uncritical information, and use the fusion module to fuse the feature maps of different scales, so as to improve the detection accuracy of the algorithm. In addition, the Soft-NMS and Complete-IoU (CloU) strategies are applied to candidate frame screening, which improves the accuracy of the algorithm for the detection of occluded objects. The ablation experiment of the MS COCO2017 object detection task proves the effectiveness of several modules introduced in this paper for small object detection. The experimental results on the MS COCO2017, VOC2007, and VOC2012 datasets show that the Average Precision (AP) of this method is 16.5%, 8.71%, and 9.68% higher than that of YOLOv3, respectively. © 2022, CC BY.

关键词： Convolution