检索结果-内蒙古大学图书馆

International Conference on Parallel Architecture and Compilation Techniques (PACT)

作者： Sayan Ghosh Barbara Chapman Computer Science Department High Performance Computing Tools Research Group University of Houston Houston TX USA

GPUs are slowly becoming ubiquitous devices in high performance computing. Nvidia's newly released version 4.0 of the CUDA API[2] for GPU programming offers multiple ways to program on GPUs and emphasizes on Multi-GPU environments which are common in modern day compute clusters. However, despite of the subsequent progress in FLOP counts, the bane of large scale computing systems have been increased energy consumption and cooling costs. Since the energy (power X time) of a system has an obvious correlation with the user program, hence different programming techniques on GPUs could have a relation to the overall system energy consumption.

关键词： Graphics processing unit Kernel Programming high performance computing Energy consumption Instruction sets Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Multifrontal factorization of sparse SPD matrices on GPUs

Multifrontal factorization of sparse SPD matrices on GPUs

引用

25th IEEE International Parallel and distributed Processing Symposium, IPDPS 2011

作者： George, Thomas Saxena, Vaibhav Gupta, Anshul Singh, Amik Choudhury, Anamitra R. High Performance Computing Group IBM Research India New Delhi 110070 India Department of Mathematical Sciences IBM T.J. Watson Research Center Yorktown Heights NY United States Department of Electronics and Computer Engineering IIT Roorkee India

ISBN: (纸本)9780769543857

Solving large sparse linear systems is often the most computationally intensive component of many scientific computing applications. In the past, sparse multifrontal direct factorization has been shown to scale to thousands of processors on dedicated supercomputers resulting in a substantial reduction in computational time. In recent years, an alternative computing paradigm based on GPUs has gained prominence, primarily due to its affordability, power-efficiency, and the potential to achieve significant speedup relative to desktop performance on regular and structured parallel applications. However, sparse matrix factorization on GPUs has not been explored sufficiently due to the complexity involved in an efficient implementation and concerns of low GPU utilization. In this paper, we present an adaptive hybrid approach for accelerating sparse multifrontal factorization based on a judicious exploitation of the processing power of the host CPU and GPU. We present four different policies for distributing and scheduling the workload between the host CPU and the GPU, and propose a mechanism for a runtime selection of the appropriate policy for each step of sparse Cholesky factorization. This mechanism relies on auto-tuning based on modeling the best policy predictor as a parametric classifier. We estimate the classifier parameters from the available empirical computation time data such that the expected computation time is minimized. This approach is readily adaptable for using the current or an extended set of policies for different CPU-GPU combinations as well as for different combinations of dense kernels for both the CPU and the GPU. © 2011 IEEE.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

ANCAEE: A Novel Clustering Algorithm for Energy Efficiency in Wireless Sensor Networks

引用

Wireless Sensor Network 2011年第9期3卷 307-312页

作者： A. P. Abidoye N. A. Azeez A. O. Adesina K. K. Agbele Wireless Sensor Networks & Natural Language Research Group Grid Computing & Distributed Systems Laboratory Department of Computer Science University of the Western Cape

One of the major constraints of wireless sensor networks is limited energy available to sensor nodes because of the small size of the batteries they use as source of power. Clustering is one of the routing techniques that have been using to minimize sensor nodes’ energy consumption during operation. In this paper, A Novel Clustering Algorithm for Energy Efficiency in Wireless Sensor Networks (ANCAEE) has been proposed. The algorithm achieves good performance in terms of minimizing energy consumption during data transmission and energy consumptions are distributed uniformly among all nodes. ANCAEE uses a new method of clusters formation and election of cluster heads. The algorithm ensures that a node transmits its data to the cluster head with a single hop transmission and cluster heads forward their data to the base station with multi-hop transmissions. Simulation results show that our approach consumes less energy and effectively extends network utilization.

关键词： Sensor Nodes Clusters Cluster heads Wireless Sensor Networks Base Station Clustering Algorithms Energy Efficiency

来源：评论

学校读者我要写书评

暂无评论

Managing dynamic enterprise and urgent workloads on clouds using layered queuing and historical performance models

Managing dynamic enterprise and urgent workloads on clouds u...

引用

作者： Bacigalupo, David A. Van Hemert, Jano Chen, Xiaoyu Usmani, Asif Chester, Adam P. He, Ligang Dillenberger, Donna N. Wills, Gary B. Gilbert, Lester Jarvis, Stephen A. School of Electronics and Computer Science University of Southampton United Kingdom Data-Intensive Research Group School of Informatics University of Edinburgh United Kingdom BRE Centre for Fire Safety Engineering School of Engineering University of Edinburgh United Kingdom IBM T.J. Watson Research Centre Yorktown Heights NY United States High Performance Systems Group Department of Computer Science University of Warwick United Kingdom

The automatic allocation of enterprise workload to resources can be enhanced by being able to make what-if response time predictions whilst different allocations are being considered. We experimentally investigate an historical and a layered queuing performance model and show how they can provide a good level of support for a dynamic-urgent cloud environment. Using this we define, implement and experimentally investigate the effectiveness of a prediction-based cloud workload and resource management algorithm. Based on these experimental analyses we: (i) comparatively evaluate the layered queuing and historical techniques;(ii) evaluate the effectiveness of the management algorithm in different operating scenarios;and (iii) provide guidance on using prediction-based workload and resource management. © 2011 Elsevier B.V. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Kernel Framework for Large-Scale Data Modeling and Classification

An Energy-Efficient Kernel Framework for Large-Scale Data Mo...

引用

IEEE International Symposium on Parallel and distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Paul D. Yoo Jason W.P. Ng Albert Y. Zomaya Department Computer Engineering Etisalat British Telecom (BT) Innovation Centre Khalifa University of Science Technology and Research Abu Dhabi UAE Centre of Distributed and High Performance Computing School of Information Technologies (J12) University of Sydney NSW Australia

Energy-efficient computing has now become a key challenge not only for data-center operations, but also for many other energy-driven systems, with the focus on reducing of all energy-related costs, and operational expenses, as well as its corresponding and environmental impacts. Intelligent machine-learning systems are typically performance driven. For instance, most non-parametric model-free approaches are often known to require high computational cost in order to find the global optima. Designing more accurate machine-learning systems to satisfy the market needs will hence lead to a higher likelihood of energy waste due to the increased computational cost. This paper thus introduces an energy-efficient framework for large-scale data modeling and classification. It can achieve a test error comparable to or better than the state-of-the-art machine-learning models, while at the same time, maintaining a low computational cost when dealing with large-scale data. The effectiveness of the proposed approaches has been demonstrated by our experiments with two large-scale KDD datasets: Mtv-1 and Mtv-2.

关键词： Electromyography Machine learning Energy efficiency distributed processing

来源：评论

学校读者我要写书评

暂无评论

Multifrontal Factorization of Sparse SPD Matrices on GPUs

Multifrontal Factorization of Sparse SPD Matrices on GPUs

引用

International Symposium on Parallel and distributed Processing (IPDPS)

作者： Thomas George Vaibhav Saxena Anshul Gupta Amik Singh Anamitra R. Choudhury High Performance Computing Group IBM Research India New Delhi India Department of Mathematical Sciences IBM Thomas J. Watson Research Center Yorktown Heights USA Department of Electronics and Computer Engineering Indian Institute of Technology Roorkee India

关键词： Graphics processing unit Sparse matrices Kernel Instruction sets Symmetric matrices Computational modeling Libraries

来源：评论

学校读者我要写书评

暂无评论

Designing topology-aware collective communication algorithms for large scale InfiniBand clusters: Case studies with Scatter and Gather

Designing topology-aware collective communication algorithms...

引用

2010 IEEE International Symposium on Parallel and distributed Processing, Workshops and Phd Forum, IPDPSW 2010

作者： Kandalla, Krishna Subramoni, Hari Vishnu, Abhinav Panda, Dhabaleswar K. Department of Computer Science and Engineering Ohio State University United States Pacific Northwest National Laboratory High Performance Computing Group United States

ISBN: (纸本)9781424465347

Modern high performance computing systems are being increasingly deployed in a hierarchical fashion with multi-core computing platforms forming the base of the hierarchy. These systems are usually comprised of multiple racks, with each rack consisting of a finite number of chassis, and each chassis having multiple compute nodes or blades, based on multi-core archi- tectures. The networks are also hierarchical with mul- tiple levels of switches. Message exchange operations between processes that belong to different racks involve multiple hops across different switches and this directly affects the performance of collective operations. In this paper, we take on the challenges involved in detecting the topology of large scale InfiniBand clusters and leveraging this knowledge to design efficient topology-aware algorithms for collective operations. We also propose a communication model to analyze the communication costs involved in collective operations on large scale supercomputing systems. We have analyzed the performance characteristics of two collectives, MPI Gather and MPI Scatter, on such systems and we have proposed topology-aware algorithms for these operations. Our experimental results have shown that the proposed algorithms can improve the performance of these collective operations by almost 54% at the micro-benchmark level. © 2010 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A taxonomy of autonomic application management in grids

A taxonomy of autonomic application management in grids

引用

16th IEEE International Conference on Parallel and distributed Systems, ICPADS 2010

作者： Rahman, Mustafizur Ranjan, Rajiv Buyya, Rajkumar Cloud Computing and Distributed Systems Laboratory Department of Computer Science and Software Engineering University of Melbourne Australia Service Oriented Computing Research Group School of Computer Science and Engineering University of New South Wales Australia

ISBN: (纸本)9780769543079

In this paper, we propose a taxonomy that characterizes and classifies different components of autonomic application management in Grids. We also survey several representative Grid systems developed by various projects world-wide to demonstrate the comprehensiveness of the taxonomy. The taxonomy not only highlights the similarities and differences of state-of-the-art technologies utilized in autonomic application management from the perspective of Grid computing, but also identifies the areas that require further research initiatives. © 2010 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Robust task scheduling for volunteer computing systems

Robust task scheduling for volunteer computing systems

引用

作者： Lee, Young Choon Zomaya, Albert Y. Siegel, Howard Jay Centre for Distributed and High Performance Computing School of Information Technologies University of Sydney Sydney NSW 2006 Australia Department of Electrical and Computer Engineering Department of Computer Science Colorado State University Fort Collins CO 80523-1373 United States

performance perturbations are a natural phenomenon in volunteer computing systems. Scheduling parallel applications with precedence-constraints is emerging as a new challenge in these systems. In this paper, we propose two novel robust task scheduling heuristics, which identify best task-resource matches in terms of makespan and robustness. Our approach for both heuristics is based on a proactive reallocation (or schedule expansion) scheme enabling output schedules to tolerate a certain degree of performance degradation. Schedules are initially generated by focusing on their makespan. These schedules are scrutinized for possible rescheduling using additional volunteer computing resources to increase their robustness. Specifically, their robustness is improved by maximizing either the total allowable delay time or the minimum relative allowable delay time over all allocated volunteer resources. Allowable delay times may occur due to precedence constraints. In this paper, two proposed heuristics are evaluated with an extensive set of simulations. Based on simulation results, our approach significantly contributes to improving the robustness of the resulting schedules. © 2009 Springer science+Business Media, LLC.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Special Issue of the Journal of Parallel and distributed computing: Novel architectures for high-performance computing

引用

Journal of Parallel and distributed computing 2011年第2期71卷 333-333页

作者： Charles Gillan Simon McIntosh-Smith Nico Sanna Stan Scott Thomas Steinke Principal Engineer for Telecommunications Software Institute of Electronics Communications and Information Technology (ECIT) Queen’s University Belfast United Kingdom Head of Microelectronics Department of Computer Science University of Bristol United Kingdom Chief Technology Manager CASPUR Italy Professor of Computational Science and Director of Research High Performance and Distributed Computing Queen’s University Belfast United Kingdom Head of Heterogeneous Computing Group Zuse Institute Berlin (ZIB) Germany

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：