检索结果-内蒙古大学图书馆

IEEE International Conference on computer-Aided Design

作者： Ying Wang Mengdi Wang Bing Li Huawei Li Xiaowei Li State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing P.R. China Capital Normal University Beijing P.R. China

ISBN: (数字)9781665423243

Deep Reinforcement Learning (DRL) is substantially resource-consuming, and it requires large-scale distributed computing-nodes to learn complicated tasks, like video-game and Go play. This work attempts to down-scale a distributed DRL system into a specialized many-core chip and achieve energy-efficient on-chip DRL. With the customized Network-on-Chip that handles the communication of on-chip data and control-signals, we proposed a Synchronous Asynchronous RL architecture (SARLA) and the according many-core chip that completely avoids the unnecessary data duplication and synchronization activities in multi-node RL systems. In evaluation, the SARLA system achieves considerable energy-efficiency boost over the GPU-based implementations for typical DRL workloads built with OpenAI-gym.

关键词： system-on-chip computer architecture Reinforcement learning Neural networks Servers Parallel processing Training

来源：评论

学校读者我要写书评

暂无评论

A fine-grained component-level power measurement method

A fine-grained component-level power measurement method

引用

International Green computing Conference

作者： Zehan Cui Yan Zhu Yungang Bao Mingyu Chen Chinese Academy and Sciences Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN

ISBN: (纸本)9781457712227

The ever growing energy consumption of computer systems have become a more and more serious problem in the past few years. Power profiling is a fundamental way for us to better understand where, when and how energy is consumed. This paper presents a direct measurement method to measure the power of main computer components with fine time granularity. To achieve this goal, only small amount of extra hardware are employed. An approach to synchronize power dissipation with program phases has also been proposed in this paper. Based on the preliminary version of our tools, we measure the power of CPU, memory and disk when running SPEC CPU2006 benchmarks, and prove that measurement with fine time granularity is essential. The phenomenon we observe from memory power may be served as a guide for memory management or architecture design towards energy efficiency.

关键词： Power measurement Current measurement Wires Voltage measurement Connectors Central Processing Unit Time measurement

来源：评论

学校读者我要写书评

暂无评论

Quick and Accurate False Data Detection in Mobile Crowd Sensing

Quick and Accurate False Data Detection in Mobile Crowd Sens...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Kun Xie Xiaocan Li Xin Wang Gaogang Xie Dongliang Xie Zhenyu Li Jigang Wen Zulong Diao College of Computer Science and Electronics Engineering Hunan University Changsha China Department of Electrical and Computer Engineering State University of New York at Stony Brook State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences State key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications

With the proliferation of smartphones, a novel sensing paradigm called Mobile Crowd Sensing (MCS) has emerged very recently. However, the attacks and faults in MCS cause a serious false data problem. Observing the intrinsic low dimensionality of general monitoring data and the sparsity of false data, false data detection can be performed based on the separation of normal data and anomalies. Although the existing separation algorithm based on Direct Robust Matrix Factorization (DRMF) is proven to be effective, requiring iteratively performing Singular Value Decomposition (SVD) for low-rank matrix approximation would result in a prohibitively high accumulated computation cost when the data matrix is large. In this work, we observe the quick false data location feature from our empirical study of DRMF, based on which we propose an intelligent Light weight Low Rank and False Matrix Separation algorithm (LightLRFMS) that can reuse the previous result of the matrix decomposition to deduce the one for the current iteration step. Our algorithm can largely speed up the whole iteration process. From a theoretical perspective, we validate that LightLRFMS only requires one round of SVD computation and thus has very low computation cost. We have done extensive experiments using a PM 2.5 air condition trace and a road traffic trace. Our results demonstrate that LightLRFMS can achieve very good false data detection performance with the same highest detection accuracy as DRMF but with up to 10 times faster speed thanks to its lower computation cost.

关键词： Sparse matrices Sensors Matrix decomposition Monitoring Matrix converters Roads Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

An intelligent method for test data generation based on optimized interval arithmetic

International Journal of Database Theory and Application

引用

International Journal of Database Theory and Application 2014年第1期7卷 11-24页

作者： Xing, Ying Gong, Yun-Zhan Wang, Ya-Wen Zhang, Xu-Zhou State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Liaoning Technical University Huludao 125105 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

Path-oriented test data generation is in essence a Constraint Satisfaction Problem solved by search strategies, among which backtracking algorithms are widely used. In this paper, the backtracking algorithm Branch & Bound is introduced to generate path-oriented test data automatically. A model based on state space search is proposed to construct the search tree dynamically. Aiming at the programs containing constraints of strongly related variables even equalities, the static analysis technique interval arithmetic is optimized for the precise judgment of the assignment to each variable. The analysis on conflict is made accurate via distance for further domain reduction, thus ensuring the precise direction of the next search step. Experiments show that the proposed method outperformed other methods used in static test data generation. Specifically, it produces excellent results when variables are strongly related even when they are in equalities, and generation time increases stably and linearly with the increment of number of expressions including both equalities and inequalities.© 2014 SERSC.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Convergence analysis for combinatorial optimization problems based on Ito process

引用

Journal of Computational Information systems 2010年第10期6卷 3147-3154页

作者： Yu, Ruiguo Dong, Wenyong Lei, Ming School of Computer Science and Technology Tianjin University Tianjin 300072 China Computer School Wuhan University Wuhan 430079 China Institute of Automation Chinese Acad. of Sci. Beijing 100086 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin 300191 China

The paper provided some theoretical results about the convergence of ITO algorithm for combinatorial optimization problems. The transform probability of wave operator and move operator studied in detail. The almost sure convergence to the global optimum is obtained by transforming the search process of ITO algorithm to the discrete sub-martingale. Furthermore, the expected time of one particle in ITO algorithm is analyzed. © 2010 Binary Information Press October, 2010.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

Towards High-resolution 3D Anomaly Detection via Group-Level...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TileSpMSpV: A Tiled Algorithm for Sparse Matrix-Sparse Vector Multiplication on GPUs 22

TileSpMSpV: A Tiled Algorithm for Sparse Matrix-Sparse Vecto...

引用

Proceedings of the 51st International Conference on Parallel Processing

作者： Haonan Ji Huimin Song Shibo Lu Zhou Jin Guangming Tan Weifeng Liu Super Scientific Software Laboratory China University of Petroleum-Beijing China China Northeastern University United States of America State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781450397339

Sparse matrix-sparse vector multiplication (SpMSpV) is an important primitive for graph algorithms and machine learning applications. The sparsity of the input and output vectors makes its floating point efficiency in general lower than sparse matrix-vector multiplication (SpMV) and sparse matrix-matrix multiplication (SpGEMM). Existing parallel SpMSpV methods focused on various row- and column-wise storage formats and merging operations. However, the data locality and sparsity pattern of the input matrix and vector are largely ignored. We in this paper propose TileSpMSpV, a tiled algorithm for accelerating SpMSpV on GPUs. Firstly, tile-wise storage structures are developed for fast positioning a group of nonzeros in matrix and vectors. Then, we develop the TileSpMSpV algorithm on top of the storage structures. In addition, to accelerate directional optimization breadth-first search (BFS) by using TileSpMSpV, we propose a TileBFS algorithm including three kernels called Push-CSC, Push-CSR and Pull-CSC. In the experiments running on a high-end NVIDIA GPU and using 2757 sparse matrices, the TileSpMSpV algorithm outperforms TileSpMV, cuSPARSE and CombBLAS by a factor of on average 1.83, 17.18 and 17.20 (up to 7.68, 1050.02 and 235.90), respectively. Moreover, our TileBFS algorithm outperforms Gunrock and GSwitch by a factor of on average 2.88 and 4.52 (up to 21.35 and 1000.85), respectively.

关键词： GPU Sparse matrix BFS Tiling SpMSpV

来源：评论

学校读者我要写书评

暂无评论

Reduction Criteria for Probabilistic Models with Spatial Restrictions on States

Reduction Criteria for Probabilistic Models with Spatial Res...

引用

International Conference on Networks Security, Wireless Communications and Trusted computing, NSWCTC

作者： Niu Jun Guosun Zeng Embedded System and Service Computing Key Laboratory Ministry of Education Shanghai China College of Information Engineering Zhejiang Business and Technology Institute Ningbo China Department of Computer Science and Technology University of Tongji Shanghai China

ISBN: (纸本)9781424465972;9780769540115

Partial order reduction techniques have been used to combat the state explosion problem in model checking procedures for concurrent systems with probabilistic behaviors. There are some results that give criteria on applying partial order reduction for verifying quantitative time properties and reward-based properties on actions. However, there are many situations that reward-based properties are expressed on states rather than on actions because actions are triggered in no time and the quantities can not be obtained easily. This paper presents reduction criteria for a probabilistic temporal logic that allows specification of restrictions on quantitative measures given by spatial resources function for the states of the considered system and provides the proof of the correctness.

关键词： Explosions computer networks Concurrent computing Embedded computing Educational technology Probabilistic logic Communication system security computer security Information security Wireless communication

来源：评论

学校读者我要写书评

暂无评论

A Generalized Model with Spatial Resources Labels

A Generalized Model with Spatial Resources Labels

引用

International Conference on Biomedical Engineering and computer Science (ICBECS)

This paper proposes a generalized model by extending Markov chain with spatial resources labels, which can describe the functional and performance properties and some basic characteristics such as nondeterminacy and randomicity. The syntax and semantics of the new model are shown based on the existing temporal logics such as CSRL and pathCSRL. The model checking procedure is discussed and thus the practicability of the new model is intuitive. Based on the existing models, the proposed model includes spatial resources labels only by adding the spatial information to the existing labels of states, so the treatment of the state explosion problem is similar to that in the existing models.

关键词： Educational technology Paper technology Logic Labeling Educational institutions Embedded system Embedded computing computer science education systems engineering education computer science

来源：评论

学校读者我要写书评

暂无评论

LIR-OSGi: Extends OSGi to support distributed and heterogeneous ubiquitous computing system

LIR-OSGi: Extends OSGi to support distributed and heterogene...

引用

International Conference on Pervasive computing and Applications (ICPCA)

作者： Jinzhao Liu Xiaojuan Lu Dan Wang Xin Liu Yongqiang Lu Yu Chen Department of Computer Science and Technology Beijing University of Technology Beijing China General Hospital of PLA Second Artillery USA Research Institute of Information Technology Key Laboratory of Pervasive Computing Ministry of Education Tsinghua University Beijing China System Software and Software Engineering Group Laboratory of Pervasive Computing Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781457702099

As an emerging portable service platform, OSGi is now taking a more and more important role in Ubiquitous computing environment. As a module management framework, OSGi provides the functions of dynamic loading and unloading software modules at runtime. But its use is limited because it is centralized and single programming language supported. In this paper we present LIR-OSGi, an extended framework of OSGi, which is designed to add the distribution and programming language independence to OSGi. Meanwhile it is easy to use for developers because of the transparence of service invocation and automation of distribution. Not like OSGi which can be applied only on the Java platform, LIR-OSGi makes programs which may be written in different programming languages be able to call each other transparently so that it can be applied in many different platforms such as DotNet Framework and so on. This brings much convenience to the program development in a distributed and heterogeneous environment.

关键词： Servers Sockets Indexes Program processors Logic gates Dynamic compiler

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：