检索结果-内蒙古大学图书馆

25th IEEE international parallel and distributed Processing symposium, Workshops and Phd Forum, IPDPSW 2011

作者： Sandrieser, Martin Benkner, Siegfried Pllana, Sabri Department of Scientific Computing Faculty of Computer Science University of Vienna Austria

ISBN: (纸本)9780769543857

Heterogeneous many-core architectures offer a way to cope with energy consumption limitations of various computing systems from small mobile devices to large datacenters. However, programmers typically must consider a large diversity of architectural information to develop efficient software. In this paper we present our ongoing work towards a Platform Description Language (PDL) that enables to capture key architectural patterns of commonly used heterogeneous computing systems. PDL architecture patterns support programmers and toolchains by providing platform information in a well-defined and explicit manner. We have developed a source-to-source compiler that utilizes PDL descriptors to transform sequential task-based programs to a form that is convenient for execution on heterogeneous many-core computing systems. We show various usage scenarios of our PDL and demonstrate our approach for a commonly used scientific kernel. © 2011 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Using hardware transactional memory for high-performance computing

Using hardware transactional memory for high-performance com...

引用

25th IEEE international parallel and distributed Processing symposium, Workshops and Phd Forum, IPDPSW 2011

作者： Ljungkvist, Karl Tillenius, Martin Black-Schaffer, David Holmgren, Sverker Karlsson, Martin Larsson, Elisabeth Department of Information Technology Uppsala University Sweden

ISBN: (纸本)9780769543857

This work investigates the benefits of transactional memory for high-performance and scientific computing by examining n-body and unstructured mesh applications on a prototype computer system with transactional memory support in hardware. Transactional memory systems have the potential to both improve performance, through reduced lock overhead, and ease development, by providing simplified synchronization semantics. To date, only a few early experiments have been presented on actual transactional memory hardware, with none of them investigating the benefits of transactional memory for scientific computing. We investigate straight-forward implementations to see if replacing locks by transactions can yield better performance and compete with more complex algorithms. Our experiments show that using transactions is the fastest way to concurrently update shared floating-point variables, which is of interest in many scientific computing applications. However, if it is possible, avoiding concurrent updates altogether yields the best performance. © 2011 IEEE.

关键词： Locks (fasteners)

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired parallel computing structures for high reliability servomotor control applications

Bio-inspired parallel computing structures for high reliabil...

引用

2011 10th international symposium on parallel and distributed computing, ISPDC 2011

作者： Chindriş, V. Szász, Cs. Department of Electrical Engineering Technical University of Cluj Cluj-N Ro-400114 Romania

ISBN: (纸本)9780769545400

Taking inspiration from biological organism's cell based structure, the paper is focused on modeling and implementation of bio-inspired artificial hardware structures for high reliability industrial control applications. As it known, living organisms offers the ability to grow with fault-tolerance and self-repair. These remarkable capabilities can be associated with principles to engine complex novel VLSI systems (embryonic machines) which would be more advantageous in many control applications where robustness and high reliability requirements are imposed. The theoretical approaches and developed artificial models were acquired in hardware redundant embryonic structure, built on a FPGA-based artificial cell network topology. In order to improve the developed embryonic system real-time control capabilities, also parallel computing techniques were implemented. The computer simulations and laboratory experimental results prove the validity of the previous theoretical assumptions and considerations. © 2011 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

parallelGDB: A parallel Graph Database based on Cache Specialization 11

<i>ParallelGDB</i>: A Parallel Graph Database based on Cache...

引用

15th international Database Engineering and Applications symposium (IDEAS)

作者： Barguno, Luis Muntes-Mulero, Victor Dominguez-Sal, David Valduriez, Patrick UPC DAMA Barcelona Spain INRIA LIRMM Rocquencourt France

ISBN: (纸本)9781450306270

The need for managing massive attributed graphs is becoming common in many areas such as recommendation systems, proteomics analysis, social network analysis or bibliographic analysis. This is making it necessary to move towards parallel systems that allow managing graph databases containing millions of vertices and edges. Previous work on distributed graph databases has focused on finding ways to partition the graph to reduce network traffic and improve execution time. However, partitioning a graph and keeping the information regarding the location of vertices might be unrealistic for massive graphs. In this paper, we propose parallel-GDB, a new system based on specializing the local caches of any node in this system, providing a better cache hit ratio. parallelGDB uses a random graph partitioning, avoiding complex partition methods based on the graph topology, that usually require managing extra data structures. This proposed system provides an efficient environment for distributed graph databases.

关键词： Graph database Cache specialization Graph algorithms distributed and parallel computing distributed graphs

来源：评论

学校读者我要写书评

暂无评论

Privacy protection in service discovery for large-scale distributed computing systems

Privacy protection in service discovery for large-scale dist...

引用

25th IEEE international parallel and distributed Processing symposium, Workshops and Phd Forum, IPDPSW 2011

作者： Choi, Jun Yeol Li, Zhong Yuan Youn, Hee Yong Song, Ohyoung School of Information and Communication Engineering Sungkyunkwan University Suwon Korea Republic of School of Electrical and Electronics Engineering Chung-Ang University Seoul 156-756 Korea Republic of

ISBN: (纸本)9780769543857

Service discovery is one of the integral tasks of the system running in distributed computing environment. Even though numerous researches on service discovery have been conducted, the security and privacy issue have not yet been addressed adequately. Here letting only legitimate user and service provider for service discovery is a challenging problem. In this paper we present a scheme for secure service discovery by employing an incremental progressive exposure approach, where the user and service provider exchange only partial encrypted information at each step. They compare the information sent from the other party with their own information. The exchange operation continues until a mismatch occurs or the required service is found finally. Computer simulation reveals that the proposed approach significantly reduces the number of message exchanges compared to the existing progressive exposure scheme. © 2011 IEEE.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

distributed resource reservation in massively parallel processor arrays

Distributed resource reservation in massively parallel proce...

引用

25th IEEE international parallel and distributed Processing symposium, Workshops and Phd Forum, IPDPSW 2011

作者： Lari, Vahid Hannig, Frank Teich, Jürgen Hardware/Software Co-Design Department of Computer Science University of Erlangen Nuremberg Germany

ISBN: (纸本)9780769543857

This paper proposes a methodology for applications to automatically claim linear arrays of processing elements within massively parallel processor arrays at run-time depending on the available degree of parallelism or dynamic computing requirements. Using this methodology, parallel programs running on individual processing elements gain the capability of autonomously managing the available processing resources in their neighborhood. We present different protocols and architectural support for gathering and transporting the result of a resource exploration for informing a configuration loader about the number and location of the claimed resources. Timing and data overhead cost of four different approaches are mathematically evaluated. In order to verify and compare these decentralized algorithms, a simulation platform has been developed to compare the data overhead and scalability of each approach for different sizes of processor arrays. © 2011 IEEE.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Performance driven distributed scheduling of parallel hybrid computations

引用

THEORETICAL COMPUTER SCIENCE 2011年第32期412卷 4212-4225页

作者： Narang, Ankur Shyamasundar, Rudrapatna K. IBM Res India Inst Area New Delhi 110070 India Tata Inst Fundamental Res Bombay 400005 Maharashtra India

Exascale computing is fast becoming a mainstream research area. In order to realize exascale performance, it is necessary to have efficient scheduling of large parallel computations with scalable performance on a large number of cores/processors. The scheduler needs to execute in a pure distributed and online fashion, should follow affinity inherent in the computation and must have low time and message complexity. Further, it should also avoid physical deadlocks due to bounded resources including space/memory per core. Simultaneous consideration of these factors makes affinity driven distributed scheduling particularly challenging. We attempt to address this challenge for hybrid parallel computations which contain tasks that have pre-specified affinity to a place and also tasks that can be mapped to any place in the system. Specifically, we address two scheduling problems of the type P(m)[M(j), prec]C(max). This paper presents online distributed scheduling algorithms for hybrid parallel computations assuming both unconstrained and bounded space per place. We also present the time and message complexity for distributed scheduling of hybrid computations. To the best of our knowledge, this is the first time that distributed scheduling algorithms for hybrid parallel computations have been presented and analyzed for time and message bounds under both unconstrained space and bounded space. (C) 2011 Elsevier B.V. All rights reserved.

关键词： distributed scheduling Multithreaded computation Asymptotic complexity Deadlock free scheduling Work stealing Online algorithm

来源：评论

学校读者我要写书评

暂无评论

gSWAT platform for grid based hydrological model calibration and execution

gSWAT platform for grid based hydrological model calibration...

引用

2011 10th international symposium on parallel and distributed computing, ISPDC 2011

作者： Bacu, Victor Mihon, Danut Rodila, Denisa Stefanut, Teodor Gorgan, Dorian Computer Science Department Technical University of Cluj-Napoca Cluj-Napoca Romania

ISBN: (纸本)9780769545400

The assessment of the sustainability and vulnerability of a particular geographical region could be performed by simulating different scenarios based on environmental changes and water quality models. The gSWAT application allows the calibration of the SWAT models and the execution of different scenarios based on calibrated SWAT model over the Grid infrastructure. The requirements for running the SWAT models involves lots of input and output data, a high number of simulations that must be performed in the calibration process, recommend the Grid infrastructure for storing and execution SWAT models. This paper presents the gSWAT platform highlighting the architectural components and presenting some test cases to assess the system performances. © 2011 IEEE.

关键词： Grid computing

来源：评论

学校读者我要写书评

暂无评论

ENIGMA: distributed virtual disks for cloud computing

ENIGMA: Distributed virtual disks for cloud computing

引用

25th IEEE international parallel and distributed Processing symposium, Workshops and Phd Forum, IPDPSW 2011

作者： Zola, Matteo Bioglio, Valerio Anglano, Cosimo Gaeta, Rossano Grangetto, Marco Sereno, Matteo Dipartimento di Informatica Università del Piemonte Orientale Alessandria Italy Dipartimento di Informatica Università di Torino Italy

ISBN: (纸本)9780769543857

We propose ENIGMA, a distributed infrastructure that provides Cloud computing infrastructures with virtual disks by abstracting the storage resources provided by a set of physical nodes and exposing to Cloud computing users, applications, and Virtual Machines a set of virtual block storage devices, that can be used exactly as standard physical disks. ENIGMA is designed to provide large storage capacity, high availability, strong confidentiality, and data access performance comparable to that of traditional storage virtualization solutions. To achieve all these design goals, ENIGMA exploits erasure-coding techniques, whereby each sector of a virtual disk is encoded as a set of n fragments, that are independently stored on a set of physical storage nodes, k of which (k ≤ n) are sufficient to reconstruct that sector. We present the ENIGMA architecture and we show how the coding of sectors of a virtual disk ensures high availability in spite of failure of individual storage nodes as well as confidentiality in face of several types of attacks. We also briefly discuss performance results of ENIGMA. © 2011 IEEE.

关键词： Virtual storage

来源：评论

学校读者我要写书评

暂无评论

A fault-tolerant high performance cloud strategy for scientific computing

A fault-tolerant high performance cloud strategy for scienti...

引用

25th IEEE international parallel and distributed Processing symposium, Workshops and Phd Forum, IPDPSW 2011

作者： Okorafor, Ekpe Abuja Nigeria

ISBN: (纸本)9780769543857

Scientific computing often requires the availability of a massive number of computers for performing large scale experiments. Traditionally, high-performance computing solutions and installed facilities such as clusters and super computers have been employed to address these needs. Cloud computing provides scientists with a completely new model of utilizing the computing infrastructure with the ability to perform parallel computations using large pools of virtual machines (VMs). The infrastructure services (Infrastructure-as-a-service), provided by these cloud vendors, allow any user to provision a large number of compute instances. However, scientific computing is typically characterized by complex communication patterns and requires optimized runtimes. Today, VMs are manually instantiated, configured and maintained by cloud users. These coupled with the latency, crash and omission failures in service providers, results in an inefficient use of VMs, increased complexity in VM-management tasks, a reduction in the overall computation power and increased time for task completion. In this paper, a high performance cloud computing strategy is proposed that combines the adaptation of a parallel processing framework, such as the Message Passing Interface (MPI) and an efficient checkpoint infrastructure for VMs, enabling its effective use for scientific computing. By developing such a mechanism, we can achieve optimized runtimes comparable to native clusters, improve checkpoints with low interference on task execution and provide efficient task recovery. In addition, checkpointing is used to minimize the cost and volatility of resource provisioning, while improving overall reliability. Analysis and simulations show that the proposed approach compares favorably with the native cluster MPI implementations. © 2011 IEEE.

关键词： Message passing

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：