检索结果-内蒙古大学图书馆

MemScale: Active low-power modes for main memory

MemScale: Active low-power modes for main memory

Proceedings of the sixteenth international conference on Architectural support for programming languages and operating systems

作者： Deng, Qingyuan Meisner, David Ramos, Luiz Wenisch, Thomas F. Bianchini, Ricardo Dept. of Computer Science Rutgers University United States Advanced Computer Architecture Lab. University of Michigan United States

ISBN: (纸本)9781450302661

Main memory is responsible for a large and increasing fraction of the energy consumed by servers. Prior work has focused on exploiting DRAM low-power states to conserve energy. However, these states require entire DRAM ranks to be idled, which is difficult to achieve even in lightly loaded servers. In this paper, we propose to conserve memory energy while improving its energyproportionality by creating active low-power modes for it. Specifically, we propose MemScale, a scheme wherein we apply dynamic voltage and frequency scaling (DVFS) to the memory controller and dynamic frequency scaling (DFS) to the memory channels and DRAM devices. MemScale is guided by an operating system policy that determines the DVFS/DFS mode of the memory subsystem based on the current need for memory bandwidth, the potential energy savings, and the performance degradation that applications are willing to withstand. Our results demonstrate that Mem-Scale reduces energy consumption significantly compared to modern memory energy management approaches. We conclude that the potential benefits of the MemScale mechanisms and policy more than compensate for their small hardware cost. Copyright © 2011 ACM.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

In search of theoretical foundations for UX research and practice

In search of theoretical foundations for UX research and pra...

引用

30th ACM Conference on Human Factors in Computing Systems, CHI 2012

作者： Obrist, Marianna Roto, Virpi Vermeeren, Arnold Väänänen-Vainio-Mattila, Kaisa Law, Effie Lai-Chong Kuutti, Kari Culture Lab School of Computing Science Newcastle University Newcastle upon TyneNE1 7RU United Kingdom Aalto University School of Art Design and Architecture P.O.Box 31000 Aalto00076 Finland Delft University of Technology Fac. of Ind. Design Engineering Landbergstraat 15 NL CE Delft2628 Netherlands Tampere University of Technology Unit of Human-Centered Tech P.O.Box 589 TampereFI-33101 Finland University of Leicester Department of Computer Science LeicesterLE1 7RH United Kingdom University of Oulu Department of Information Processing Science Oulu90014 Finland

In this paper we point out the relevance of and the need for a theoretical discussion around UX research and practice. Although there is a good coverage of methodological and design related topics in the HCI literature, there is still a lack of theoretical focus in the rapidly increasing work on user experience (UX). We analyzed 122 individual items on theories collected in a CHI'11 special interest group session on UX theories and theoretical frameworks. The data set was filtered and categorized in several iterations, resulting in 56 items distributed over 7 major theory categories and related to 9 relevant disciplines. The categories are an initial mapping of the field and point towards the directions for further conceptual and theoretical clarification. Our results help to explore the multi-disciplinary nature of UX and to build a more solid foundation for UX research and practice. © 2012 Authors.

关键词： Group theory

来源：评论

学校读者我要写书评

暂无评论

A collaborative memory system for high-performance and cost-effective clustered architectures 11

A collaborative memory system for high-performance and cost-...

引用

1st Workshop on architectures and Systems for Big Data, ASBD 2011 - Held in Conjunction with the 20th International Conference on Parallel architectures and Compilation Techniques, PACT 2011

作者： Samih, Ahmad Wang, Ren Maciocco, Christian Tai, Tsung-Yuan Charlie Solihin, Yan System Architecture Lab Hillsboro OR United States Dept. of Electical and Computer Engineering North Carolina State University Raleigh NC United States

ISBN: (纸本)9781450314398

With the fast development of highly integrated distributed systems (cluster systems), especially those encapsulated within a single platform [28, 9], designers have to face interesting memory hierarchy design choices that attempt to avoid disk storage swapping. Disk swapping activities slow down application execution drastically. Leveraging remote free memory through Memory Collaboration has demonstrated its cost-effectiveness compared to overprovisioning for peak load requirements. Recent studies propose several ways on accessing the under-utilized remote memory in static system configurations, without detailed exploration on the dynamic memory collaboration. Dynamic collaboration is an important aspect given the run-time memory usage fluctuations in clustered systems. In this paper, we propose an Autonomous Collaborative Memory System (ACMS) that manages memory resources dynamically at run time, to optimize performance, and provide QoS measures for nodes engaging in the system. We implement a prototype realizing the proposed ACMS, experiment with a wide range of real-world applications, and show up to 3x performance speedup compared to a non collaborative memory system, without perceivable performance impact on nodes that provide memory. Based on our experiments, we conduct detailed analysis on the remote memory access overhead and provide insights for future optimizations. Copyright 2012 ACM.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

An ant-based rule for UMDA's update strategy

An ant-based rule for UMDA's update strategy

引用

Lecture Notes in computer Science

作者： Fernandes, C.M. Lima, C.F. Laredo, J.L.J. Rosa, A.C. Merelo, J.J. Department of Computer's Architecture and Technology University of Granada Spain Portugal Informatics Lab. University of Algarve Gambelas Campus 8000-117 Faro Portugal

ISBN: (纸本)9783642213137

This paper investigates an update strategy for the Univariate Marginal Distribution Algorithm (UMDA) probabilistic model inspired by the equations of the Ant Colony Optimization (ACO) computational paradigm. By adapting ACO's transition probability equations to the univariate probabilistic model, it is possible to control the balance between exploration and exploitation by tuning a single parameter. It is expected that a proper balance can improve the scalability of the algorithm on hard problems with bounded difficulties and experiments conducted on such problems with increasing difficulty and size confirmed these assumptions. These are important results because the performance is improved without increasing the complexity of the model, which is known to have a considerable computational effort. © 2011 Springer-Verlag.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Structural health monitoring via dynamic visualization

Structural health monitoring via dynamic visualization

引用

2011 7th International Conference on Computational Intelligence and Security, CIS 2011

作者： Sun, Peng Guo, Xin College of Computer Science Northwestern Polytechnical University Xi'an China Lab. of Structural Engineering and Earthquake Resistance Xi'an University of Architecture and Technology Xi'an China

ISBN: (纸本)9780769545844

Visualization modeling based on DAQ (Data Acquisition) of SHM (Structural Health Monitoring) system helps nondestructive and Intelligent evaluation on structure. It makes up the shortage of traditional visual methods and speeds up mastering the state of structural health. It promotes the security of structure greatly. Using simulation data from the Key laboratory of Structural Engineering and Earthquake Resistance, the DynaTree method completes dynamic data visualization on SHM with OpenInventor toolkit. © 2011 IEEE.

关键词： Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Robust embedded software design through early analysis of quality faults 11

Robust embedded software design through early analysis of qu...

引用

Proceedings of the 4th India Software Engineering Conference

作者： Das, Dipankar Chakrabarti, P.P. Sinha, Purnendu Electrical and Software Architecture Group GM India Science Lab. Bangalore 560066 India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur 721302 India

ISBN: (纸本)9781450305594

While providing correct functionality has been the thrust of most software design efforts, embedded software poses several additional challenges. Among them is designing robust software which can tolerate inaccurate inputs (coming from degraded sensors), failure of software components, and wearing-out of electro-mechanical parts it controls. For this, a design space exploration is performed and several design options are evaluated for their ability to tolerate quality (or accuracy degradation) faults. While a model-based approach enables an early analysis of quality faults, modeling and analyzing the effects of quality faults is a challenge. In this work we propose a quality fault-tolerance analysis framework which is used on operation-level models of embedded software, and an abstraction of quality-faults suitable for this analysis. The proposed method consists of characterizing individual components of the model, and then using the pre-characterized behaviors to quickly evaluate the software design. Characterization is a one-time effort and results of the same can be reused when a new design is evaluated. This results in additional speedup of upto 6-10× faster evaluation of designs, thereby facilitating a quick early evaluation of design options.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Cuckoo directory: A scalable directory for many-core systems

Cuckoo directory: A scalable directory for many-core systems

引用

IEEE Symposium on High-Performance computer architecture

作者： Michael Ferdman Pejman Lotfi-Kamran Ken Balet Babak Falsafi Computer Architecture Lab Carnegie Mellon University USA Parallel Systems Architecture Lab école Polytechnique Fédérale de Lausanne Switzerland

Growing core counts have highlighted the need for scalable on-chip coherence mechanisms. The increase in the number of on-chip cores exposes the energy and area costs of scaling the directories. Duplicate-tag-based directories require highly associative structures that grow with core count, precluding scalability due to prohibitive power consumption. Sparse directories overcome the power barrier by reducing directory associativity, but require storage area over-provisioning to avoid high invalidation rates. We propose the Cuckoo directory, a power- and area-efficient scalable distributed directory. The cuckoo directory scales to high core counts without the energy costs of wide associative lookup and without gross capacity over-provisioning. Simulation of a 16-core CMP with commercial server and scientific workloads shows that the Cuckoo directory eliminates invalidations while being up to four times more power-efficient than the Duplicate-tag directory and 24% more power-efficient and up to seven times more area-efficient than the Sparse directory organization. Analytical projections indicate that the Cuckoo directory retains its energy and area benefits with increasing core count, efficiently scaling to at least 1024 cores.

关键词： Organizations Coherence Scalability Aggregates System-on-a-chip Servers Hardware

来源：评论

学校读者我要写书评

暂无评论

A scalable parallel ray tracing algorithm for satellite imagery

A scalable parallel ray tracing algorithm for satellite imag...

引用

IEEE International Conference on computer Research and Development

作者： Li, Yu-Gang Zhao, Kun Huang, Yu-Qing Qiu, Zhen-Ge Liu, Zhi-Yong Beijing Lab. of Intelligent Information Technology School of Computer Science BIT Beijing 100081 China Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100081 China Institute of Computing Technology Chinese Academy Sciences Beijing China

ISBN: (纸本)9781612848372

Ray-tracing, can produce high-quality images, however, the use of ray-tracing has been limited due to its high demands on computational power and memory bandwidth, especially in the case of satellite imagery. In this paper, we propose a scalable parallel ray tracing algorithm of satellite imagery on a cluster of multi-core architecture. The algorithm combines demand-driven and data-driven models in order to reduce communication on the cost of maintaining redundant data. In order to make the most of computer's parallelism and increase computational efficiency, it combines two levels of parallelisms, the TLP parallelism brought by the many core architecture and the inter-node parallelism via MPI and OpenMP. Experiment results show that the algorithm is highly scalability. © 2011 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Red balloon, green balloon, sensors in the sky 11

Red balloon, green balloon, sensors in the sky

引用

13th International Conference on Ubiquitous Computing, UbiComp'11 and the Co-located Workshops

作者： Kuznetsov, Stacey Davis, George Noel Paulos, Eric Gross, Mark D. Cheung, Jian Chiu Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA United States Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA United States Computational Design Lab. School of Architecture Carnegie Mellon University Pittsburgh PA United States

ISBN: (纸本)9781450309103

Spectacle computing is a novel strategy for vibrantly projecting information into the public sphere using expressive and tangible media. We demonstrate an example of this computing meme with large, glowing balloons that change color based on input from attached air quality sensors (exhaust, diesel, or volatile organic compounds). In two public installations (city street and public park) and a deployment with six everyday citizens, we invited stakeholders to playfully explore and actively participate in visualizing surrounding air quality. We also created a do-it-yourself (DIY) kit that includes a printed circuit board, electronic parts and instructions for building the air quality balloons. In a workshop, six non-expert users successfully assembled functional balloons, validating our technology as a DIY tool for public air quality visualization. Our deployments and workshop highlight play and spectacle as essential elements for public participation and activism. We outline design guidelines for future spectacle computing projects that engage stakeholders with environmental data and empower them to transform urban landscapes. © 2011 ACM.

关键词： Printed circuit boards

来源：评论

学校读者我要写书评

暂无评论

A computer-supported collaborative learning platform based on clouds

引用

Journal of Computational Information Systems 2011年第11期7卷 3811-3818页

作者： Li, Jiandun Peng, Junjie Zhang, Wu Han, Fangfang Yuan, Qin Joint Lab of Cloud Computing School of Computer Engineering and Science Shanghai University Shanghai 200072 China Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

computer-supported collaborative learning (CSCL) is an emerging branch of learning science concerned with studying how people can learn together with the help of computers. As an indispensable ingredient, computer mediation evolves through couples of phases, e.g. centralized server, peer-to-peer network, grid computing. Nevertheless, with daily rising trend on requirement's dynamic changes in service, existing models fall short to respond on demand. Thus, in this paper, by taking advantage of cloud computing, we propose a feasible CSCL platform and the experiments show that it can not only fulfill the basic requirement of CSCL, but also respond to learner's dynamic need on demand. Copyright © 2011 Binary Information Press.

关键词： Peer to peer networks

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：