检索结果-内蒙古大学图书馆

21st international Parallel and Distributed Processing symposium, IPDPS 2007

作者： Aumage, Olivier Brunet, Élisabeth Furmento, Nathalie Namyst, Raymond INRIA LABRI Université Bordeaux 1 351 cours de la Libération F-33405 Talence France

ISBN: (纸本)1424409101

Communication libraries have dramatically made progress over the fifteen years, pushed by the success of cluster architectures as the preferred platform for high performance distributed computing. However, many potential optimizations are left unexplored in the process of mapping application communication requests onto low level network commands. The fundamental cause of this situation is that the design of communication subsystems is mostly focused on reducing the latency by shortening the critical path. In this paper, we present a new communication scheduling engine which dynamically optimizes application requests in accordance with the NICs capabilities and activity. The optimizing code is generic and portable. The database of optimizing strategies may be dynamically extended. © 2007 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

OeIM: An optoelectronic interconnection middleware for the exascale computer 21

OeIM: An optoelectronic interconnection middleware for the e...

引用

21st IEEE international Conference on high performance computing and Communications, 17th IEEE international Conference on Smart City and 5th IEEE international Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Shao, En Tan, Guangming Wang, Zhan Sun, Ninghui State Key Laboratory of Computer Architecture Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728120584

During the improved process of hardware technology and program optimization in the high-performance computer (HPC), the overall computing ability of supercomputer increases correspondingly. As a large-scale system and a milestone to the HPC community shortly, the envisioned exascale computer will be comprised of nearly 5000 interconnected nodes and tens of thousands of computing nodes. Interconnection innovations in such a system are critical to improving overall computing ability. In this paper, we investigate optoelectronic interconnection in an exascale computer system design. Here, we propose a new software stack called Optoelectronic Interconnection Middleware (OeIM) to enable efficient utilization of the optical interconnection. OeIM allows for the use of two novel functions, namely the reconfigurable function and the running-time function. We evaluate OeIM using both communication benchmark (IMB) and real-world motif applications (Linpack, HPCG, and Graph500) in a prototyped exascale computer. The experiment shows that OeIM reduced latency by form 20 to 35% in the large-range communication, improved throughput by 30% in the long-distance communication, and improved the motif applications by more than 10%. Together, our results demonstrate that OeIM is an effective bridge between the optical switching device and system scheduler to improve communication capability. © 2019 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Subtlenoise: sonification of distributed computing operations 21

Subtlenoise: sonification of distributed computing operation...

引用

21st international Conference on computing in high Energy and Nuclear Physics (CHEP)

作者： Love, P. A. Univ Lancaster Dept Phys Lancaster LA1 4YB England

The operation of distributed computing systems requires comprehensive monitoring to ensure reliability and robustness. There are two components found in most monitoring systems: one being visually rich time-series graphs and another being notification systems for alerting operators under certain pre-defined conditions. In this paper the sonification of monitoring messages is explored using an architecture that fits easily within existing infrastructures based on mature opensource technologies such as ZeroMQ, Logstash, and Supercollider (a synth engine). Message attributes are mapped onto audio attributes based on broad classification of the message (continuous or discrete metrics) but keeping the audio stream subtle in nature. The benefits of audio rendering are described in the context of distributed computing operations and may provide a less intrusive way to understand the operational health of these systems.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating Modifying Teacher Avatar Clip Sequencing Based on Eye-Tracked Visual Attention in Educational VR 21

Evaluating Modifying Teacher Avatar Clip Sequencing Based on...

引用

21st IEEE international symposium on Mixed and Augmented Reality (ISMAR)

作者： Khokhar, Adil Borst, Christoph W. Univ Louisiana Lafayette Lafayette LA 70504 USA

ISBN: (数字)9781665453653

ISBN: (纸本)9781665453653

We evaluate a novel virtual reality (VR) avatar animation architecture that is responsive to a viewer's eye gaze and we demonstrate that it can be used to improve teacher agents that are based on the playback of a recorded teacher. Our architecture modifies the playing, seeking, rewinding, stopping, and pausing of a teacher recording to create appropriate teacher avatar behavior based on a viewer's eye-tracked visual attention. We present preliminary results from our experiment that evaluated how subjects perceived three different teacher avatar behavioral responses.

关键词： Human-centered computing-Human computer interaction (HCI)-Interaction paradigms-Virtual reality Human-centered computing-Human computer interaction (HCI)-HCI design and evaluation methods-User studies

来源：评论

学校读者我要写书评

暂无评论

Making JavaScript Better By Making It Even Slower

Making JavaScript Better By Making It Even Slower

引用

IEEE 21st Annual international symposium on Modeling, Analysis and Simulation of computer and Telecommunication (MASCOTS)

作者： Swiech, Maciej Dinda, Peter Northwestern Univ Dept EECS Evanston IL 60208 USA

ISBN: (纸本)9780769551029

On mobile devices, such as smartphones and tablets, client-side JavaScript is a significant contributor to power consumption, and thus battery lifetime. We claim that this is partially due to JavaScript interpretation running faster than is necessary to maintain a satisfactory user experience, and we propose that JavaScript implementations include a user-configurable throttle. To evaluate our claim we developed a web proxy system, named JSSlow, that reduces power consumption by transcoding client-side JavaScript and injecting "sleep" invocations. This can be done safely, even given JavaScript's single-threaded nature, through the use of continuation passing, and the proxy model requires neither server nor client-side changes. Using JSSlow we studied the 120 most popular sites and found that the technique could reduce power consumption by an average of 5% on Android phones. We also considered buggy code (52% reduction) and advertising (10% reduction). To evaluate the system's impact on the user experience, we conducted a user study consisting of interactive tasks the user carried out on. The perceived performance impact varies by user and site, with the variation being highest on the most interactive sites, such as games. This argues for making the throttle user-configurable in some cases.

关键词： Mobile computing Human computer Interaction performance Evaluation World Wide Web

来源：评论

学校读者我要写书评

暂无评论

Cloud computing and emerging IT platforms: Vision, hype, and reality for delivering computing as the 5th utility

引用

FUTURE GENERATION computer SYstEMS-THE international JOURNAL OF ESCIENCE 2009年第6期25卷 599-616页

作者： Buyya, Rajkumar Yeo, Chee Shin Venugopal, Srikumar Broberg, James Brandic, Ivona Univ Melbourne Dept Comp Sci & Software Engn Grid Comp & Distributed Syst GRIDS Lab Melbourne Vic 3053 Australia Manjrasoft Pty Ltd Melbourne Vic Australia Vienna Univ Technol Inst Informat Syst A-1040 Vienna Austria

With the significant advances in Information and Communications Technology (ICT) over the last half century, there is an increasingly perceived vision that computing will one day be the 5th utility (after water, electricity, gas, and telephony). This computing utility, like all other four existing utilities. will provide the basic level of computing service that is considered essential to meet the everyday needs of the general Community. To deliver this vision, a number Of computing paradigms have been proposed, of which the latest one is known as Cloud computing. Hence, in this paper, we define Cloud computing and provide the architecture for creating Clouds with market-oriented resource allocation by leveraging technologies such as Virtual Machines (VMs). We also provide insights on market-based resource management strategies that encompass both customer-drive service management and computational risk management to sustain Service Level Agreement (SLA)-oriented resource allocation. In addition, we reveal our early thoughts on interconnecting Clouds for dynamically creating global Cloud exchanges and markets. Then, we present some representative Cloud platforms, especially those developed in industries, along with our Current work towards realizing market-oriented resource allocation of Clouds as realized in Aneka enterprise Cloud technology. Furthermore, we highlight the difference between high performance computing (HPC) workload and Internet-based services workload. We also describe a meta-negotiation infrastructure to establish global Cloud exchanges and markets, and illustrate a case study of harnessing 'storage Clouds' for high performance content delivery. Finally, we conclude with the need for convergence of competing IT paradigms to deliver our 21st century vision. (C) 2008 Elsevier B.V. All rights reserved.

关键词： Cloud computing Data Centers Utility computing Virtualization Market-oriented resource allocation

来源：评论

学校读者我要写书评

暂无评论

A performance model of many-to-one collective communications for parallel computing

A performance model of many-to-one collective communications...

引用

21st international Parallel and Distributed Processing symposium, IPDPS 2007

作者： Lastovetsky, Alexey O'Flynn, Maureen School of Computer Science and Informatics Belfield Dublin 4 Ireland

ISBN: (纸本)1424409101

This paper presents a performance model of Many-to-One collective communications for MPI platforms on a switched Ethernet network. The model is based on empirical findings from observation of Many-to-One operations over a wide range of message sizes. The model reflects a significant increase in the execution time for medium-sized messages, persistently observed for different parallel platforms and MPI implementations and not reflected in traditional communication performance models. We also demonstrate that the use of the model can significantly improve the performance of parallel applications, intensively using Many-to-One communications. © 2007 IEEE.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

A Self-Reconfiguring Cache architecture to Improve Control Quality in Cyber-Physical Systems 21

A Self-Reconfiguring Cache Architecture to Improve Control Q...

引用

21st IEEE international symposium on Real-Time computing (ISORC)

作者： Haque, Mohammad Shihabul Vasudevan, S. Nihar, S. Easwaran, Arvind Kumar, Akash Tay, Y. C. Nanyang Technol Univ Singapore Singapore Tech Univ Dresden Dresden Germany

ISBN: (纸本)9781538658475

Quality of control is a critical concern in Cyber-Physical Systems (CPS) which are comprised of multiple intercommunicating control applications. Due to complex timing behaviour of these systems, poor quality of control can lead to catastrophe. Recent studies showed that, conflict miss increment in the processor cache memory shared by concurrently running control applications can degrade control quality in CPS significantly. Increasing cache associativity can help to reduce conflict misses. However, the existing reconfigurable cache architectures that allow runtime modification of cache associativity are not capable to guaranty a newly chosen associativity's suitability for the forthcoming control quality requirement. Moreover, they have timing and energy related overheads. In this regard, this paper presents a novel, self-reconfiguring cache memory architecture "SeReMo". When conflict misses increase significantly, SeReMo reconfigures its associativity to better suit the current as well as future control quality demand. To trigger reconfiguration, a low-overhead, non-strictly inclusive cache hierarchy-specific approach is used. Configurations with different associativity are generated using modules made of 4 cache lines and 7 special bits. Special replacement policy and indexing scheme are used to suit modular reconfiguration. SPEC CPU 2006 benchmark trace-driven simulation reveals that SeReMo reduces average number of conflict misses per line to 1/12951 of the state-of-the-art reconfigurable cache architecture at maximum (to 1/830 on average). As a result, execution time and energy consumption reduce by 48 hours at maximum (by 2/3 on average) and by 2907 Joules at maximum (86% on average) respectively.

关键词： Cache memory Indexing Energy consumption Switches Proposals computer architecture Runtime"

来源：评论

学校读者我要写书评

暂无评论

Efficient virtual channel organization and congestion avoidance in multicore NoC systems 26

Efficient virtual channel organization and congestion avoida...

引用

26th IEEE international symposium on computer architecture and high performance computing Workshops, SBAC-PADW 2014

作者： Oveis-Gharan, Masoud Khan, Gul N. Electrical and Computer Engineering Ryerson University 350 Victoria St TorontoONM5B 2K3 Canada

ISBN: (纸本)9781479970148

Dynamically Allocated Multi Queues (DAMQ) is an effective mechanism to achieve Virtual Channel (VC) based flow control with maximum buffer utilization in multi-core Network-on-Chip (NoC) systems. We present a new methodology to remedy some of the drawbacks of DAMQ technique. The architectural design of a DAMQ router inputport that uses minimal hardware is introduced. Our input-port design saves 70% of combinational-logic and 14.7% register hardware as compared to conventional Link-List input-port. We also present an efficient mechanism to remove traffic congestion in on-chip communication for NoC systems. It improves latency and throughput by 30% and 23% respectively as compared to conventional dynamic Virtual Channel design. © 2014 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-based IDS for cloud and mobile devices 21

Autoencoder-based IDS for cloud and mobile devices

引用

21st IEEE/ACM international symposium on Cluster, Cloud and Internet computing (CCGrid)

作者： Faber, Kamil Faber, Lukasz Sniezynski, Bartlomiej AGH Univ Sci & Technol Inst Comp Sci Krakow Poland

ISBN: (纸本)9781728195865

Along with the popularization of cloud computing and the increase in responsibilities of mobile devices, there is a need for intrusion detection systems available for working in these two new areas. At the same time, the increase in computational power of mobile devices gives us the possibility to use them to do a part of data preprocessing. Similarly, more complex operations can be executed in the cloud - this concept is known as mobile cloud computing. In this paper, we propose an autoencoder-based intrusion detection system applicable to cloud and mobile environments. The system provides multiple data gathering points, allowing to monitor either fully controlled networks, like virtual networks in the cloud, or mobile devices scattered in different networks. The monitoring process uses both mobile devices and cloud computational power. Gathered network traffic records are sent to a proper intrusion detection node, which executes the detection process. In case of suspicious behavior, an alert of a possible intrusion can be sent to the device owner. The detection process is based on an autoencoder neural network, which brings significant advantages: an anomaly-based approach, training only on benign samples, and a good performance. To improve detection results, we created time-window-based features, and there is also a possibility to share computed statistics between intrusion detection nodes. In the experiments, we construct three models using pure network flows data and time-window-based features. The results show that the autoencoder-based approach can detect with a high performance attacks not known during the training process. We also prove that created derived features have a significant impact on detection results.

关键词： intrusion detection system autoencoder machine learning security mobile cloud 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：