检索结果-内蒙古大学图书馆

International Symposium on Information Technology, ITSim

作者： Hitoshi, Oi Sho, Niboshi Computer Architecture and Operating Systems Group University of Aizu Aizu-Wakamatsu Japan

ISBN: (纸本)9781424467181

SPECmail2009 is a new benchmark suite for measuring the performance of corporate mail servers. It assumes the IMAP4 protocol for retrieving messages and a large fraction of transactions are for manipulating hierarchical messages and mail folders from the users connected via high-speed networks. In this paper, we present a performance analysis of SPECmail2009, including disk I/O behavior, quality of service metrics, and CPU time breakdown. The IMAP4's capability of directly manipulating the messages on the server makes SPECmail2009 a highly I/O-bound workload. Our experiments show that a combination of a small but fast access SCSI drive for indexing messages and larger but slower SATA drives for message files can be an option for building a cost-effective mail storage. Both of multiprocessing and multithreading are quite effective for SPECmail2009 especially in the user mode execution. © 2010 IEEE.

关键词： HIgh speed networks

来源：评论

学校读者我要写书评

暂无评论

Speeding up target address generation using a self-indexed FTB 8th

引用

8th International Euro-Par Conference on Parallel Processing, Euro-Par 2002

作者： Moure, Juan C. Rexachs, Dolores I. Luque, Emilio Computer Architecture and Operating Systems Group Universidad Autónoma de Barcelona Barcelona08193 Spain

ISBN: (纸本)3540440496

The fetch target buffer (FTB) holds information on basic blocks to predict taken branches in the fetch stream and also their target addresses. We propose a variation to FTB, the self-indexed FTB, which, through an extra level of indirection, provides the high hit rate of a relatively large, high-associative FTB with the fast access delay of a small, direct-mapped FTB. The critical and most frequent operation –predicting the next FTB entry– is speeded up, whilst less frequent operations –such as recovering from FTB misses– are slightly slowed down. The new design is both analyzed and simulated. Performance increase on a 512-entry FTB is estimated at between 15% and 30%. © Springer-Verlag Berlin Heidelberg 2002.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Optimizing a decoupled front-end architecture: The indexed fetch target buffer (iFTB)

Optimizing a decoupled front-end architecture: The indexed f...

引用

9th International Euro-Par Conference on Parallel Processing, Euro-Par 2003

作者： Moure, Juan C. Rexachs, Dolores I. Luque, Emilio Computer Architecture and Operating Systems Group Universidad Autónoma de Barcelona Barcelona08193 Spain

ISBN: (纸本)354040788X

A decoupled front-end architecture relies on a separate fetch predictor that is critical in determining the fetch bandwidth. The Fetch Target Buffer (FTB) is a multilevel fetch predictor design. In this paper we propose and analyze a variation of the FTB, the indexed Fetch Target Buffer (iFTB), that uses an extra, very fast, index table to speedup its operations. The iFTB achieves very accurate predictions by adapting a complex hybrid branch predictor to suit its short cycle time. With a low hardware cost, the iFTB delivers instructions between 15% and 45% faster than the FTB. © Springer-Verlag Berlin Heidelberg 2003.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Evaluation of an architecture enabling pluggable web services

Evaluation of an architecture enabling pluggable web service...

引用

IASTED International Conference on Parallel and Distributed Computing and Networks, as part of the 23rd IASTED International Multi-Conference on Applied Informatics

作者： Villoldo, Enric Jaén Serrat-Fernandez, Joan Computer Architecture an Operating Systems Group Universitat Autonoma de Barcelona Bellaterra Spain Network Management Group Universitat Politécnica de Catalunya Barcelona Spain

Web services are generally intended to be accessed by an unlimited number of users. The service provider decides when and how they should be modified or extended. But this unidirectional approach may not satisfy the needs of all the users. In fact, such a dependency forces users to create their own adaptations and proxy services. This situation cause, on one hand, the need to develop private versions of the service which could be otherwise public and therefore reusable. On the other hand, the use of proxies introduce some disadvantages, namely the additional overhead and network load cost, and the impossibility to cope with end-to-end adaptations. To overcome these problems we propose a community model for web services, where users can deploy adaptations in the hosting service without disturbing other users. In this paper we present the framework for this model and the experimental results of the developed prototype. These results show that the adaptations cause an imperceptible performance overhead.

关键词： Telecommunication services

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in Parallel Virtual Machine and Message Passing Interface 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Jack Dongarra Emilio Luque Tomàs Margalef

ISBN: (数字)9783540481584

ISBN: (纸本)9783540665496

Parallel Virtual Machine (PVM) and Message Passing Interface (MPI) are the most frequently used tools for programming according to the message passing paradigm, which is considered one of the best ways to develop parallel applications. This volume comprises 67 revised contributions presented at the Sixth European PVM/MPI Users' group Meeting, which was held in Barcelona, Spain, 26-29 September 1999. The conference was organized by the computer Science Department of the Universitat Autònoma de Barcelona. This conference has been previously held in Liverpool, UK (1998) and Cracow, Poland (1997). The first three conferences were devoted to PVM and were held at the TU Munich, Germany (1996), ENS Lyon, France (1995), and University of Rome (1994). This conference has become a forum for users and developers of PVM, MPI, and other message passing environments. Interaction between those groups has proved to be very useful for developing new ideas in parallel computing and for applying some of those already existent to new practical fields.

关键词： computer System Implementation Processor architectures

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of computational approaches to solve Multiple Sequence Alignment

Performance analysis of computational approaches to solve Mu...

引用

作者： Montañola, Alberto Roig, Concepció Guirado, Fernando Hernández, Porfidio Notredame, Cedric Distributed Computing Group Computer Science and Industrial Engineering Department Universitat de Lleida Lleida Spain Computer Architecture and Operating Systems Department Universitat Autònoma de Barcelona Cerdanyola del Vallès Spain Barcelona Spain

In the biotechnology field, the deployment of the Multiple Sequence Alignment (MSA) problem, which is a high performance computing demanding process, is one of the new challenges to address on the new parallel systems. The aim of this problem is to find similar regions on biological sequences. Furthermore, the goal of MSA applications is to align as much sequences as possible with a level of quality that makes the alignment biologically meaningful. An efficiency study of different MSA implementations, based on T-Coffee (one of the most used MSA aligners), has been performed in order to find new optimizations that may improve the average execution time on multi-core systems. We found that the current parallel implementations have some performance issues, affecting negatively the scalability of the process. Finally, the proposed implementation based on the usage of threads in conjunction with a message-passing library is presented, with the aim to optimize the execution of the MSA problem in multi-core-based clusters. © 2012 Springer Science+Business Media, LLC.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Improving single-thread fetch performance on a multithreaded processor

Improving single-thread fetch performance on a multithreaded...

引用

Euromicro Symposium on Digital System Design

作者： J.C. Moure R.B. Garcia D.I. Rexachs E. Luque Computer Architecture and Operating Systems Group Universidad Autónoma de Barcelona Barcelona Spain

Multithreaded processors, by simultaneously using both the thread-level parallelism and the instruction-level parallelism of applications, achieve larger instruction per cycle rate than single-thread processors. On a multi-thread workload, a clustered organization maximizes performances. On a single-thread workload, however, all but one of the clusters are idle, degrading single-thread performance significantly. Using a clustered multi-thread performance as a baseline, we propose and analyze several mechanisms and policies to improve single-thread execution exploiting the existing hardware without a significant multi-thread performance loss. We focus on the fetch unit, which is maybe the most performance-critical stage. Essentially, we analyze three ways of exploiting the idle fetch clusters: allowing a single thread accessing its neighbor clusters, use the idle fetch clusters to provide multiple-path execution, or use them to widen the effective single-three fetch block.

关键词： Yarn Parallel processing Performance analysis Performance loss Bandwidth Degradation Surface-mount technology computer architecture operating systems Application software

来源：评论

学校读者我要写书评

暂无评论

Improving Web Services Interoperability with Binding Extensions

Improving Web Services Interoperability with Binding Extensi...

引用

IEEE International Conference on Web Services (ICWS)

作者： Enric Jaen Villoldo Joan Serrat-Fernandez Emilio Luque Computer Architecture and Operating Systems University Autonoma de Barcelona Spain Network Management Group Polytechnic University of Catalonia Spain

Current Web services are able to interoperate successfully with most basic data types. However, due to the limited functionality of existing data binding tools, they still experiment difficulties manipulating more complex XML data types, forcing programmers to work at the XML level. In this paper we propose a business model for web services where data binding tools not only generate the WSDL, but also provide portable binding extensions for manipulating theXSD types. These binding extensions can be integrated into any other binding tool, overcoming their limitations. Because these extensions are written in XML, this model conforms to the principle of platform independence. In addition, this model does not suppose any extra programming effort to neither service providers or clients. The approach has been validated with the creation of several extensions, which has been ported into Java and PHP clients. Our preliminary results show no performance penalty.

关键词： Web services XML Contracts computer architecture operating systems Programming profession Java computer network management Service oriented architecture Software tools

来源：评论

学校读者我要写书评

暂无评论

Checking concurrent behavior in UML/OCL models 15

Checking concurrent behavior in UML/OCL models

引用

ACM/IEEE International Conference on Model Driven Engineering Languages and systems (MODELS)

作者： Nils Przigoda Christoph Hilken Robert Wille Jan Peleska Rolf Drechsler Group for Computer Architecture University of Bremen Bremen Germany Research Group Operating Systems & Distributed Systems University of Bremen Bremen Germany DFKI GmbH Cyber-Physical Systems Bremen Germany Universitat Bremen Bremen Bremen DE

ISBN: (纸本)9781467369084

The Unified Modeling Language (UML) is a defacto standard for software development and, together with the Object Constraint Language (OCL), allows for a precise description of a system prior to its implementation. At the same time, these descriptions can be employed to check the consistency and, hence, the correctness of a given UML/OCL model. In the recent past, numerous (automated) approaches have been proposed for this purpose. The behavior of the systems has usually been considered by means of sequence diagrams, state machines, and activity diagrams. But with the increasing popularity of design by contract, also composite structures, classes, and operations are frequently used to describe behavior in UML/OCL. However, for these description means no solution for the validation and verification of concurrent behavior is available yet. In this work, we propose such a solution. To this end, we discuss the possible interpretations of “concurrency” which are admissible according to the common UML/OCL interpretation and, afterwards, propose a methodology which exploits solvers for SAT Modulo Theories (i. e., SMT solvers) in order to check the concurrent behavior of UML/OCL models. How to address the resulting problems is described and illustrated by means of a running example. Finally, the application of the proposed method is demonstrated.

关键词： Unified modeling language Contracts Concurrent computing Computational modeling Standards Software Complex systems

来源：评论

学校读者我要写书评

暂无评论

Data resolution effects on a coupled data driven system for forest fire propagation prediction

引用

Procedia computer Science 2017年 108卷 1562-1571页

作者： À. Farguell A. Cortés T. Margalef J.R. Miro J. Mercader HPCA4SE research group Computer Architecture and Operating Systems department Universitat Autònoma de Barcelona 08193 Bellaterra Spain Servei Meteorològic de Catalunya 08029 Barcelona Spain

Every year, thousands of forest hectares are burned worldwide, causing important consequences on the atmosphere, biodiversity and economy. Proper prediction of the fire evolution allows to manage the fire fighting equipment properly. Therefore, it is crucial to use reliable and fast simulations in order to predict the evolution of the fire. WRF-SFIRE is a wildland fire simulator, which couples a meteorological model called Weather Research and Forecasting Model (WRF) and a forest fire simulator, SFIRE reproducing the interaction between the propagation of the fire and the atmosphere evolution. The mesh resolution used to solve the atmosphere evolution has a deep impact in the prediction of small scale meteorological effects. At the same time, the ability of introducing these small scale meteorological events into the forest fire simulation implies enhancements in the quality of the data that drives the simulation. Therefore, better fire propagation predictions are obtained. However, this improvement can be affected by the instability of the problem to be solved. This paper states an accuracy study changing the mesh resolution when running WRF-SFIRE using as example a real case that took place in Catalonia (northeast of Spain) in 2005.

关键词： WRF-SFIRE Accuracy Data resolution Data driven

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：