检索结果-内蒙古大学图书馆

43rd IEEE conference on Local computer Networks (LCN)

作者： Comer, Douglas Rastegatnia, Adib Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

ISBN: (纸本)9781538644133

Software Defined Networking (SDN) offers flexibility to program a network based on a set of network requirements. programming the networks using SDN is not completely straightforward because a programmer must deal with low level details. To solve the problem, researchers proposed a set of network programming languages that provide a set of high level abstractions to hide low level hardware details. Most of the proposed languages provide abstractions related to packet processing and flows, and still require a programmer to specify low-level match-action fields to configure and monitor a network. Recently, in an attempt to raise the level at which programmers work, researchers have begun to investigate Intent-based, descriptive northbound interfaces. The work is still in early stages, and further investigation is required before intent-based systems will be adopted by enterprise networks. To help achieve the goal of moving to an intent-based design, we propose an SDN-based network programming framework, the Open Software Defined Framework (OSDF). OSDF provides a high level Application programming Interface (API) that can be used by managers and network administrators to express network requirements for applications and policies for multiple domains. OSDF also provides a set of high level network operation services that handle common network configuration, monitoring, and Quality of Service (QoS) provisioning. OSDF is equipped with a policy conflict management module to help a network administrator detect and resolve policy conflicts. The paper shows how OSDF can be used and explains application-based policies. Finally, the paper reports the results of both testbed measurements and simulations that are used to evaluate the framework from multiple perspectives, including functionality and performance.

关键词： Network topology programming Monitoring Topology Quality of service program processors

来源：评论

学校读者我要写书评

暂无评论

Distributed Data Analytics Framework for Smart Transportation 20

Distributed Data Analytics Framework for Smart Transportatio...

引用

20th IEEE International conference on high performance Computing and Communications (HPCC) / 16th IEEE International conference on Smart City (SmartCity) / 4th IEEE International conference on Data Science and Systems (DSS)

作者： Howard, Alexander J. Lee, Tim Mahar, Sara Intrevado, Paul Myung-kyung, Diane Univ San Francisco Data Sci Program San Francisco CA 94117 USA

ISBN: (纸本)9781538666142

As the amount data from IoT devices on transportation systems increases, developing a robust pipeline to stream, store and process data became critical. In this study, We explore prediction accuracy and computational performance of various supervised and unsupervised algorithms perform on distributed systems for developing a smart transportation data pipeline. Using a subset of New York City Taxi & Limousine Commission data, we evaluate Logistic Regression, Random Forrest Regressors and Classifiers, Principal Component Analysis, and Gradient Boosted Regression and Classification Tree machine learning techniques on a commodity computer as well as on a distributed system. Employing Amazon S3, EC2 and EMR, MongoDB, and Spark, we identify the conditions-data size and algorithm-under which the performance of distributed systems excel.

关键词： Distributed computing Distributed information systems Machine learning Smart transportation

来源：评论

学校读者我要写书评

暂无评论

Parallelization implementation of Bayesian algorithms based on Spark platform

Parallelization implementation of Bayesian algorithms based ...

引用

IEEE International conference on Smart Cloud (SmartCloud)

作者： Hong Liu Hong Guo Wei Hu College of Computer Science Wuhan University Of Science And Technology Wuhan China

ISBN: (数字)9781728155067

ISBN: (纸本)9781728155074

With the rapid development of Internet technology, all kinds of data are growing exponentially. How to effectively manage and utilize these data has become the focus of research in the era of big data. Under the requirement of massive data processing, aiming at the time requirement of massive data processing which cannot be met by traditional single-machine serial, this paper proposes a Spark computing framework, studies Bayesian algorithm in data mining, realizes the establishment method of parallel Bayesian algorithm and optimizes it. By using Spark memory computing framework, the efficiency of iteration is high. The computational performance of the parallel computing program is investigated. By comparing Spark parallel computing with traditional single-machine serial experiments, it is found that the algorithm can effectively improve the speed of text classification. With the expansion of cluster size, the performance of classification accuracy, time performance and acceleration ratio is better. Parallel Bayesian algorithm based on Spark platform is feasible, which solves the problem that traditional single computer cannot handle large-scale data, and can effectively deal with all kinds of classification problems.

关键词： Sparks Bayes methods Classification algorithms Training Distributed databases Parallel processing Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning Attentions: Residual Attentional Siamese Network for high performance Online Visual Tracking 31

Learning Attentions: Residual Attentional Siamese Network fo...

引用

31st IEEE/CVF conference on computer Vision and Pattern Recognition (CVPR)

作者： Wang, Qiang Teng, Zhu Xing, Junliang Gao, Jin Hu, Weiming Maybank, Stephen University of Chinese Academy of Sciences Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Computer Science and Information Systems Birkbeck College University of London UK

ISBN: (纸本)9781538664209

Offline training for object tracking has recently shown great potentials in balancing tracking accuracy and speed. However, it is still difficult to adapt an offline trained model to a target tracked online. This work presents a Residual Attentional Siamese Network (RASNet) for high performance object tracking. The RASNet model reformulates the correlation filter within a Siamese tracking framework, and introduces different kinds of the attention mechanisms to adapt the model without updating the model online. In particular, by exploiting the offline trained general attention, the target adapted residual attention, and the channel favored feature attention, the RASNet not only mitigates the over-fitting problem in deep network training, but also enhances its discriminative capacity and adaptability due to the separation of representation learning and discriminator learning. The proposed deep architecture is trained from end to end and takes full advantage of the rich spatial temporal information to achieve robust visual tracking. Experimental results on two latest benchmarks, OTB-2015 and VOT2017, show that the RASNet tracker has the state-of-the-art tracking accuracy while runs at more than 80 frames per second.

关键词： Target tracking Correlation Feature extraction Training Adaptation models Visualization Object tracking

来源：评论

学校读者我要写书评

暂无评论

Interlayer Cooling Network Design for high-performance 3D ICs Using Channel Patterning and Pruning

引用

IEEE TRANSACTIONS ON computer-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2018年第4期37卷 770-781页

作者： Zhu, Hengliang Hu, Feng Zhou, Hao Pan, David Z. Zhou, Dian Zeng, Xuan Fudan Univ State Key Lab ASIC & Syst Dept Microelect Shanghai 200433 Peoples R China Univ Texas Austin Dept Elect & Comp Engn Austin TX 78712 USA Univ Texas Dallas Dept Elect Engn Richardson TX 75080 USA

Interlayer liquid cooling network has been considered as one of the effective cooling mechanisms for heat dissipation in three dimensional integrated circuits (3D ICs). In this paper, an optimization approach is proposed for 3D IC interlayer cooling network design with consideration of cooling energy minimization and thermal constraints. First, a channel patterning technique is proposed which adopts straight-channel patterns and corner-barrier patterns to efficiently reduce the temperature of hotspots in the chip. Second, an iterative channel pruning process is proposed for cooling network optimization that reduces the temperature gradient and cooling energy. Furthermore, algebraic multigrid-preconditioned generalized conjugate residual solver is applied for thermal simulation in this optimization process to achieve better computational efficiency. Experimental results have shown that the proposed optimization approach can produce optimal interlayer cooling networks with 11.3%-61.3% cooling energy savings and 49.3%-59.4% pumping pressure savings in comparison with the first place winner of 2015 computer-aided design contest at International conference on computer-Aided Design.

关键词： Algebraic multigrid (AMG) cooling system optimization interlayer cooling network thermal simulation three dimensional integrated circuit (3D IC)

来源：评论

学校读者我要写书评

暂无评论

A high-performance and high-Reliability RAIS5 Storage Architecture with Adaptive Stripe 18th

A High-Performance and High-Reliability RAIS5 Storage Archit...

引用

18th International conference on Algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Mei, Linjun Feng, Dan Zeng, Lingfang Chen, Jianxi Liu, Jingning Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan Natl Lab Optoelect Key Lab Informat Storage SystMinist Educ China Wuhan 430074 Peoples R China

ISBN: (纸本)9783030050511;9783030050504

In the era of big data, the traditional RAID storage system has been incapable of meeting the requirements of performance and reliability for the large amount of data storage and computing. In view of the situation, Solid State Disks (SSDs), which can provide better performance than Hard Disk Drives (HDDs), are widely used to construct storage arrays in enterprise environments. Today many studies on Redundant Array of Independent SSDs (RAIS) storage systems concentrate more on improving write performance, and show less attention on the reconstruction performance of RAIS storage systems. In this paper, we proposed RAIS5AS, a novel RAIS5 storage architecture with adaptive stripe for improving the performance and reliability of RAIS5. RAIS5AS distinguishes between logical stripe and physical stripe. Logical stripe is a traditional RAID stripe. Physical stripe consists of the blocks (in a logical stripe) which have been written data. When handling write requests, RAIS5AS uses physical stripe as the basic processing unit to choose which blocks are read to compute the new parity block. When recovering data, RAIS5AS skips the unused failed blocks. In addition, RAIS5AS simplifies the synchronization process of RAIS5 storage system. We have implemented the proposed scheme and carried out a series of experiments. RAIS5AS on average improves write performance and reconstruction performance of the basic RAIS5 by up to 7.92% and 95.65% respectively, and those of JOR by 9.16% and 14.57% respectively.

关键词： Physical stripe performance Reconstruction time RAIS5

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of wake flowfield behind the C-130 with Cargo ramp open

Numerical simulation of wake flowfield behind the C-130 with...

引用

作者： Ghoreyshi, Mehdi Bergeron, Keith Lofthouse, Andrew J. High Performance Computing Research Center United States NSRDEC United States U.S. Air Force Academy CO80840 United States U.S. Army Natick Research Development and Engineering Center NatickMA01760 United States

Simulation results are presented for a C-130 aircraft configured to perform cargo airdrop operations. Flight operations with the cargo ramp open lead to strong vortical flow structures and unsteady flows, which can adversely affect airdrop operations and parachute deployments. The results document complex wake structures formed behind the C-130 with the cargo ramp open at 0 and 50% flap settings. In particular, the wake contains two asymmetric counter-rotating vortices formed between the open ramp and the upsweep section of the aircraft and near the rear edges of the ramp. The flow separates along these edges because of the sharp turn that flow makes as it enters the cargo compartment. The separated flow then rolls up into two vortices. These vortices move outward and upward, and then they pass very near the lower surface of the horizontal stabilizer. These vortical flows lead to unsteady airloads on the horizontal stabilizer, and thus the aircraft. The wake effects are larger behind the upper upsweep section and are minimum at the lower positions. Grid and time sensitivity studies are performed for several geometries to ensure numerical simulations are accurate for the separated and vortical flows. The results show that, as the grid becomes more refined in the region behind the upsweep section of the aircraft, the localized wake structures and unsteady effects are better captured by the flow solver.

关键词： Horizontal stabilizers

来源：评论

学校读者我要写书评

暂无评论

CRState: In-Kernel Checkpoint/Restart of OpenCL program Execution on GPU

CRState: In-Kernel Checkpoint/Restart of OpenCL Program Exec...

引用

International conference on Parallel and Distributed Systems (ICPADS)

作者： Genlang Chen Jiajian Zhang Qiuru Lin Hai Jiang Chaoyi Pang Ningbo Institute of Technology Zhejiang University Ningbo China Ningbo Research Institute Zhejiang University Ningbo China College of Computer Science Zhejiang University Hangzhou China Department of Computer Science Arkansas State University AR USA

ISBN: (纸本)9781728125848

Checkpoint/restart is an important mechanism to achieve fault tolerance, load balancing and resources sharing in a preemptive system. As Graphics Processing Unit (GPU) becomes quite popular in high performance computing as well as OpenCL programs are portable across various CPUs and GPUs, checkpoint/restart of OpenCL programs on GPUs is in demand. However, due to the intricacy of computation states inside GPUs, there is no effective checkpoint/restart scheme for heterogeneous devices now. This paper proposes a feasible system, CRState, to achieve checkpoint/restart in GPU kernels. With the assistant of a pre-compiler, the primitives are inserted into programs. In run-time, the computation state existing in the underlying hardware is concretized and reconstructed at application level and is ported to heterogeneous devices. Comprehensive experiments have been conducted to demonstrate CRState's feasibility and effectiveness. The experimental results also indicate that CRState has the potential to reschedule resources and balance workload across heterogeneous devices.

关键词： GPU OpenCL Checkpoint/restart Computation state Preemption Graphics Processing Unit GRAPPER PICK UP application layer central processing units high performance Computing Heterogeneous

来源：评论

学校读者我要写书评

暂无评论

A Parameter Optimization Framework Based on OpenFOAM with HPC and Database Support

A Parameter Optimization Framework Based on OpenFOAM with HP...

引用

International conference on Information Systems and computer Aided Education (ICISCAE)

作者： Jin, Wei Xu, Xinhai Tang, Yuhua Zhou, Houcun Ren, Xiaoguang Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China Natl Innovat Inst Def Technol Artificial Intelligence Res Ctr Beijing 100000 Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781538657386

In CFD simulations, parameters in the mathematical models wil affect the accuracy of the simulation results. Both manual and automatic approaches have been proposed to optimize the parameters for more accurate simulation results. OpenFOAM, which is an open-source CFD software, has been widely used in recent years. In this paper, we focused on the cavitating flow problems and designed a parameter optimization framework based on OpenFOAM with HPC and database support. We implemented the framework with SAO approach, and carried out tests considering the multi-phase solver interPhaseChangeFoam in OpenFOAM. The overall results show the framework with HPC and database support is effective in parameter optimization.

关键词： Cavitation

来源：评论

学校读者我要写书评

暂无评论

Virtualization for Scientific Workload

Virtualization for Scientific Workload

引用

International Scientific and Technical conference on Modern computer Network Technologies (MoNeTeC)

作者： Zacharov, I. Panarin, O. Ryabinkin, E. Izotov, K. Teslyuk, A. Skolkovo Inst Sci & Technol Ctr Computat & Data Intens Sci & Engn Moscow Russia Kurchatov Inst Complex Simulat & Data Proc Mega Sci Facil Natl R Moscow Russia

ISBN: (纸本)9781538694565

The computationally intensive applications (HPC) and the data analytics within the Big Data applications (BDA) constitute a combined workflow for the scientific discovery. Yet, the development and the execution environment for the HPC and the BDA have different origins and also within a single discipline there are large differences for the requirements for the provisioning of the libraries and tools within the Linux Operating System. Traditionally the HPC library versioning is addressed with the software Modules and other multi-root building frameworks by the system of administration. This does not necessary provide for the compatibility between different systems where the programs should be running. Such compatibility is required for the effective sharing of the code between scientific institutions and deployment on the centralized Supercomputing resources (Centers of Collective Usage). The flexibility of the software build model and the flexibility of subsequent deployment in the target computer center may be provided by the Virtualization and/or Containerization of the software. The Virtualization framework addresses also the problem of the unification between the HPC and the BDA workflow for a common scientific discovery model. Therefore virtualization is chosen as the software basis of the recent cluster deployment at Skoltech computer center. In the framework of this deployment model we have investigated the implications for the program run time when deployed in a virtualized environment. For the multitude of the scientific goals no compromise on the machine performance and program scalability can be accepted by the users of the system. Therefore a measurement of these parameters was undertaken for a representative range of scientific applications and for a multitude of running environments including the usage of CPU, GPU and high Speed networks. In this article we report a joined work between the Skolkovo Institute of Technology (Skoltech) and the National Re

关键词： virtualization containers supercomputing high performance computing

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：