检索结果-内蒙古大学图书馆

2011 IEEE 2nd International Conference on Software Engineering and Service Science, ICSESS 2011

作者： Yun, Long Yang, Yan Wang, Jing Zhu, Ge Dept. of Computer Science and Technology Heilongjiang University Key Lab. of Database and Parallel Computing Heilongjiang Province Harbin China

ISBN: (纸本)9781424496969

Memory-based collaborative filtering algorithms have been widely adopted in many popular recommender systems, however the rating data are very sparse, which affects prediction accuracy greatly. To solve this problem, we use expert opinions to improve prediction accuracy. Firstly, we propose a novel similarity measure in order to highlight users' background. Then, combining users' ratings with expert opinions, the prediction get a right balance in both expert professional opinions and similar users. Finally, since SVD-based collaborative filtering algorithms shows good performance on the prevention of noise, we use it to smooth the prediction. Experiments of MovieLens have shown that our proposed method improves recommendation quality obviously. © 2011 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Designing fast architecture-sensitive tree search on modern multicore/many-core processors

Designing fast architecture-sensitive tree search on modern ...

引用

作者： Kim, Changkyu Chhugani, Jatin Satish, Nadathur Sedlar, Eric Nguyen, Anthony D. Kaldewey, Tim Lee, Victor W. Brandt, Scott A. Dubey, Pradeep Intel Corporation Parallel Computing Lab United States Oracle Corporation United States University of California Santa Cruz United States

In-memory tree structured index search is a fundamental database operation. Modern processors provide tremendous computing power by integrating multiple cores, each with wide vector units. There has been much work to exploit modern processor architectures for database primitives like scan, sort, join, and aggregation. However, unlike other primitives, tree search presents significant challenges due to irregular and unpredictable data accesses in tree traversal. In this article, we present FAST, an extremely fast architecturesensitive layout of the index tree. FAST is a binary tree logically organized to optimize for architecture features like page size, cache line size, and Single Instruction Multiple Data (SIMD) width of the underlying hardware. FAST eliminates the impact of memory latency, and exploits thread-level and data-level parallelism on both CPUs and GPUs to achieve 50 million (CPU) and 85 million (GPU) queries per second forlarge trees of 64M elements, with even better results on smaller trees. These are 5X (CPU) and 1.7X (GPU) faster than the best previously reported performance on the same architectures. We also evaluated FAST on the Intel® Many Integrated Core architecture (IntelR MIC), showing a speedup of 2.4X-3X over CPU and 1.8X-4.4X over GPU. FAST supports efficient bulk updates by rebuilding index trees in less than 0.1 seconds for datasets as large as 64M keys and naturally integrates compression techniques, overcoming the memory bandwidth bottleneck and achieving a 6X performance improvement over uncompressed index search for large keys on CPUs. © 2011 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Emerging applications for multi/many-core processors

Emerging applications for multi/many-core processors

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Victor W. Lee Yen-Kuang Chen J. Chhugani C. Kim D. Kim C.J. Hughes N. Rajagopalan Satish M. Smelyanskiy P. Dubey Parallel Computing Lab Intel Labs Intel Corporation Santa Clara California USA Parallel Computing Lab Intel Labs Intel Corporation Santa Clara California USA

There has always been a strong relationship between computer applications and computer architectures. Advances in computer architecture enable new usage models; new usage models challenge new architectures. For many decades, the interplays between applications and architectures have resulted in significant progress in the computer technologies. Recently, the computer industry adopts the multi/many-core architecture for better performance, energy efficiency and reliability. This industry-wide movement towards multi/many-core architectures opens up many opportunities for developing new classes of applications. This paper uses a few emerging applications as examples to illustrate the interplay between applications and architecture. It further discusses the key characteristics of emerging applications and how multi/many-core architecture addresses the needs of the new applications. The paper closes with recommendations for new application developers to allow better utilization of new multi/many-core processors.

关键词： Computer architecture Synchronization Data models Computers parallel processing Bandwidth Program processors

来源：评论

学校读者我要写书评

暂无评论

异构平台数学库MAGMA性能测试与分析

异构平台数学库MAGMA性能测试与分析

引用

2012全国高性能计算学术年会

作者： Xiao Xuan-ji 肖玄基 Zhang Yun-quan 张云泉 Li Yu-cheng 李玉成 Yuan Liang 袁良 Lab of Parallel Computing Institute of SoftwareChinese Academy of SciencesBeijing 100190China Gra 中国科学院软件研究所并行计算实验室北京 100190 中国科学院研究生院北京 100190 Lab of Parallel Computing Institute of SoftwareChinese Academy of SciencesBeijing 100190China Sta 中国科学院软件研究所并行计算实验室北京 100190 中国科学院软件研究所计算机科学国家重点实验室北京 100190

MAGMA是第一个面向下一代体系架构(多核CPU和GPU)开源的线性代数软件包，它采用了诸多针对异构平台的优化方法，包括了混合同步，通信避免和动态任务调度系统.它在功能，数据存储，接口上与LAPACK相似，可以发挥GPU的巨大计算能力进行... 详细信息

MAGMA是第一个面向下一代体系架构(多核CPU和GPU)开源的线性代数软件包，它采用了诸多针对异构平台的优化方法，包括了混合同步，通信避免和动态任务调度系统.它在功能，数据存储，接口上与LAPACK相似，可以发挥GPU的巨大计算能力进行数值计算.本文首先对MAGMA中的矩阵分解算法进行分析;然后通过测试结果，分析 MAGMA有效的优化和并行方法，为 MAGMA使用、优化提供有益的建议;最后本文提出了一种对于矩阵分块算法的自适应调优的方法，经过测试，对于SGEQRF函数加速比达到1.09.

关键词：异构平台线性代数软件包性能测试矩阵分解算法图形处理器高性能计算

来源：评论

学校读者我要写书评

暂无评论

Improving Rating Estimation in Recommender Using Demographic Data and Expert Opinions

Improving Rating Estimation in Recommender Using Demographic...

引用

2011 2nd IEEE International Conference on Software Engineering and Service Science(2011年第二届 IEEE 软件工程与服务科学国际会议 ICSESS 2011)

作者： Long Yun Yan Yang Jing Wang Ge Zhu Dept. of Computer Science and Technology Heilongjiang University Key Lab. of Database and Parallel Computing Heilongjiang Province Harbin China

关键词： Recommendation Collaborative Filtering Data Sparsity Expert Demography

来源：评论

学校读者我要写书评

暂无评论

Inverse scattering pre-stack depth imaging and it's comparison to some depth migration methods for imaging rich fault complex structure

引用

AIP Conference Proceedings 2011年第1期1454卷 83-86页

作者： Nurhandoko, Bagus Endar B. Sukmana, Indriani Mubarok, Syahrul Deny, Agus Widowati, Sri Kurniadi, Rizal Wave Inversion and Subsurface Fluid Imaging Research Laboratory WISFIR Basic Science Center A 4th floor Physics Department FMIPA Institut Teknologi Bandung Indonesia Rock Fluid Imaging Lab. Parallel Cluster Computing Center Bandung Jl. Sukasenang Raya no.2 Indonesia Department of Physics Institut Teknologi Bandung Indonesia

Migration is important issue for seismic imaging in complex structure. In this decade, depth imaging becomes important tools for producing accurate image in depth imaging instead of time domain imaging. The challenge of depth migration method, however, is in revealing the complex structure of subsurface. There are many methods of depth migration with their advantages and weaknesses. In this paper, we show our propose method of pre-stack depth migration based on time domain inverse scattering wave equation. Hopefully this method can be as solution for imaging complex structure in Indonesia, especially in rich thrusting fault zones. In this research, we develop a recent advance wave equation migration based on time domain inverse scattering wave which use more natural wave propagation using scattering wave. This wave equation pre-stack depth migration use time domain inverse scattering wave equation based on Helmholtz equation. To provide true amplitude recovery, an inverse of divergence procedure and recovering transmission loss are considered of pre-stack migration. Benchmarking the propose inverse scattering pre-stack depth migration with the other migration methods are also presented, i.e.: wave equation pre-stack depth migration, waveequation depth migration, and pre-stack time migration method. This inverse scattering pre-stack depth migration could image successfully the rich fault zone which consist extremely dip and resulting superior quality of seismic image. The image quality of inverse scattering migration is much better than the others migration methods. © 2012 American Institute of Physics.

关键词： Inverse scattering Migration Seismic

来源：评论

学校读者我要写书评

暂无评论

Rupeas: Ruby powered event analysis DSL

Rupeas: Ruby powered event analysis DSL

引用

International Conference on Networked Sensing Systems

作者： Woehrle, Matthias Plessl, Christian Thiele, Lothar Computer Engineering and Networks Lab ETH Zurich Switzerland Paderborn Center for Parallel Computing University of Paderborn Germany

ISBN: (纸本)9781424479108

Wireless Sensor Networks (WSNs) are unique embedded computer systems for distributed sensing of a dispersed phenomenon. As WSNs are deployed in remote locations for longterm unattended operation, assurance of correct functioning of the system is of prime concern. Thus, the design and development of WSNs requires specialized tools to allow for testing. To this end, we present a novel language, Rupeas, for analyzing WSNs based on collected events during system operation. Rupeas is independent from test specifics and thus generally applicable for analyzing event logs of WSN test executions. © 2010 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Accelerating linpack performance with mixed precision algorithm on CPU+GPGPU heterogeneous cluster

Accelerating linpack performance with mixed precision algori...

引用

10th IEEE International Conference on Computer and Information Technology, CIT-2010, 7th IEEE International Conference on Embedded Software and Systems, ICESS-2010, 10th IEEE Int. Conf. Scalable computing and Communications, ScalCom-2010

作者： Wang, Lei Zhang, Yunquan Zhang, Xianyi Liu, Fangfang Lab of Parallel Computing Institute of Software Chinese Academy of Sciences Beijing 100190 China State Key Lab of Computing Science Chinese Academy of Sciences Beijing 100190 China Chinese Academy of Sciences Graduate University Beijing 100190 China

ISBN: (纸本)9780769541082

In this paper, the mixed precision algorithm to solve the linear system of equations and the implementation of HPL package are introduced. We use this mixed precision algorithm to improve HPL package on CPU+GPGPU heterogeneous clusters, which is named for GHPL, and give the implementation mechanisms in detail. The experimental results are measured on the platforms of multi-core CPUs and CPU+GPGPU heterogeneous clusters. From the experimental results, we can find out that our GHPL program has good scalability on all the experimental environments and can sustain more than 1.7Teraflops both on the cluster with 16 nodes containing 32 NVIDIA Tesla C1060 GPUs and on the cluster with 8 nodes containing 32 NVIDIA GeForce GTX 295 GPUs, while the average speedup of it with respect to HPL is 3.06 and 2.40 respectively. © 2010 IEEE.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Accelerating Linpack Performance with Mixed Precision Algorithm on CPU+GPGPU Heterogeneous Cluster

Accelerating Linpack Performance with Mixed Precision Algori...

引用

International Conference on Computer and Information Technology (CIT)

作者： Wang Lei Zhang Yunquan Zhang Xianyi Liu Fangfang Graduate University of Chinese Academy of Sciences Beijing Lab of Parallel Computing Institute of Software Beijing China State Key Lab of Computing Science Chinese Academy of Sciences Beijing China Lab of Parallel Computing Institute of Software Beijing State Key Lab of Computing Science Chinese Academy of Sciences Beijing

In this paper, the mixed precision algorithm to solve the linear system of equations and the implementation of HPL package are introduced. We use this mixed precision algorithm to improve HPL package on CPU + GPGPU heterogeneous clusters, which is named for GHPL, and give the implementation mechanisms in detail. The experimental results are measured on the platforms of multi-core CPUs and CPU + GPGPU heterogeneous clusters. From the experimental results, we can find out that our GHPL program has good scalability on all the experimental environments and can sustain more than 1.7Teraflops both on the cluster with 16 nodes containing 32 NVIDIA Tesla C1060 GPUs and on the cluster with 8 nodes containing 32 ATI GeForce GTX 295 GPUs, while the average speedup of it with respect to HPL is 3.06 and 2.40 respectively.

关键词： Graphics processing unit Clustering algorithms Convergence Niobium Linear systems Accuracy Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Real-time-component based software architecture for QoS-adaptive networked multimedia applications

Real-time-component based software architecture for QoS-adap...

引用

13th IEEE International Symposium on Object, Component, and Service-Oriented Real-Time Distributed computing, ISORC 2010

作者： Colmenares, Juan A. Kim, K.H. Zhang, Zhen Lim, Chadeok Rim, Kee-Wook Parallel Computing Lab. CS Division University of California Berkeley United States EECS Department DREAM Lab. University of California Irvine United States Electronics and Telecom Research Institute Daejeon Korea Republic of Department of Computer Science Sunmoon University Korea Republic of

ISBN: (纸本)9780769540375

Highly desirable types of networked multimedia applications should adapt to changes in the environmental conditions in which they operate, such as communication bandwidth, available memory, and battery lifetime, while providing the best possible quality of service (QoS). In this paper we present a software architecture that facilitates the development of adaptive networked multimedia applications which meet this requirement. The proposed software architecture is based on the Time-triggered Message-triggered Object (TMO) programming scheme and it is implemented as a thin layer on top of the TMO Support Middleware (TMOSM). The new layer, called the QoS Adaptation Support Layer (QASL), includes monitoring and runtime reconfiguration facilities that allow us to easily incorporate QoS-adaptation capabilities into TMO-based multimedia applications. In addition, we introduce a novel, practical approach for establishing the QoS configurations that guide the adaptive behavior of a networked multimedia application. A QoS configuration contains a set of parameters that specify the quality-related characteristics of the media streams which a receiver expects from a sender. We also present a strategy used in QASL for selecting, from a given set of QoS configurations, an optimal configuration by reflecting currently observed environmental conditions. Finally, the effectiveness of the QoS-adaptation mechanisms implemented in QASL is evaluated with the use of a heterogeneous network based multi-party videoconference application. © 2010 IEEE.

关键词： Middleware

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：