检索结果-内蒙古大学图书馆

McrEngine: A scalable checkpointing system using data-aware aggregation and compression

SCIENTIFIC programming 2013年第3-4期21卷 149-163页

作者： Islam, Tanzima Zerin Mohror, Kathryn Bagchi, Saurabh Moody, Adam de Supinski, Bronis R. Eigenmann, Rudolf Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA Lawrence Livermore Natl Lab Livermore CA USA

High performance computing (HPC) systems use checkpoint-restart to tolerate failures. Typically, applications store their states in checkpoints on a parallel file system (PFS). As applications scale up, checkpoint-restart incurs high overheads due to contention for PFS resources. The high overheads force large-scale applications to reduce checkpoint frequency, which means more compute time is lost in the event of failure. We alleviate this problem through a scalable checkpoint-restart system, mcrEngine. McrEngine aggregates checkpoints from multiple application processes with knowledge of the data semantics available through widely-used I/O libraries, e.g., HDF5 and netCDF, and compresses them. Our novel scheme improves compressibility of checkpoints up to 115% over simple concatenation and compression. Our evaluation with large-scale application checkpoints show that mcrEngine reduces checkpointing overhead by up to 87% and restart overhead by up to 62% over a baseline with no aggregation or compression.

关键词： Data-aware checkpoint restart distributed applications distributed systems fault tolerance aggregation bottleneck multiple-processor systems application-level checkpointing rollback recovery system reliability distributed programming fault tolerant computing software reliability system recovery

来源：评论

学校读者我要写书评

暂无评论

A distributed SOLUTION OF THE distributed TERMINATION PROBLEM

引用

INFORMATION PROCESSING LETTERS 1983年第1期17卷 43-46页

作者： RANA, SP Computer Centre Indian Institute of Technology Hauz Khas New Delhi-110029 India

Several algorithms introduced to solve the distributed termination problem depend upon a predesignated process to detect the global termination. A solution is presented that differs from these others in the crucial aspect that any of the n processes may initiate a detection wave and may possibly succeed in detecting the global termination condition. The resulting protocol is fairly simple. The solution is presented and its correctness and performance discussed. Similar works are mentioned, and the termination problem in the case of asynchronous communications is discussed.

关键词： distributed programming termination detection decentralized control

来源：评论

学校读者我要写书评

暂无评论

Towards logic programming based coordination in virtual worlds

Towards logic programming based coordination in virtual worl...

引用

31st Hawaii International Conference on System Sciences (HICSS-31)

作者： Tarau, P Dahl, V De Bosschere, K Univ Moncton Moncton NB E1A 3E9 Canada

ISBN: (纸本)0818682558

We propose a unified framework far coordination in multi-user Virtual Worlds, based an our experience with LogiMOO, a BinProlog+Linda based programmable shared Virtual World LogiMOO adopts unification for pattern retrieval while using exclusively deterministic operations, unlike most Prolog based Linda systems. Moving beyond the Linda framework LogiMOO is based an, we describe a coordination logic for agent programming based on ideas front (affine) linear logic and Java's synchronized object system as well as a set Of new primitives describing uniformly Linda operation, database updates and hypothetical assumptions. The main novelty is that our constructs emphasize an 'object based' approach, with synchronization information built in 'container objects' and allowing more flexible wait/notify negotiations between consumer/producer agent components, as well as inheritance and agent component reuse. Our experiments with agent coding in LogiMOO and Java and interaction with external visual and logic components, show the practicality of our constructs for real life programming.

关键词： coordination languages blackboard-based logic programming distributed programming groupware virtual worlds Internet applications

来源：评论

学校读者我要写书评

暂无评论

Title Model for Computer Networks Optimization

引用

IEEE LATIN AMERICA TRANSACTIONS 2011年第2期9卷 219-230页

作者： Pereira, J. H. S. Sato, L. M. Rosa, P. F. Kofuji, S. T. Univ Sao Paulo Escola Politecn RIDP Sao Paulo Brazil Univ Fed Uberlandia Fac Computacao BR-38400 Uberlandia MG Brazil

The TCP/IP architecture was consolidated as a standard to the distributed systems. However, there are several researches and discussions about alternatives to the evolution of this architecture and, in this study area, this work presents the Title Model to contribute with the application needs support by the cross layer ontology use and the horizontal addressing, in a next generation Internet. For a practical viewpoint, is showed the network cost reduction for the distributed programming example, in networks with layer 2 connectivity. To prove the title model enhancement, it is presented the network analysis performed for the message passing interface, sending a vector of integers and returning its sum. By this analysis, it is confirmed that the current proposal allows, in this environment, a reduction of 15,23% over the total network traffic, in bytes.

关键词： Message Passing Interface Ontology Optimization distributed programming Computer Networks

来源：评论

学校读者我要写书评

暂无评论

A Survey of Parallel programming Models and Tools in the Multi and Many-Core Era

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2012年第8期23卷 1369-1386页

作者： Diaz, Javier Munoz-Caro, Camelia Nino, Alfonso Indiana Univ Pervas Technol Inst Bloomington IN 47408 USA Univ Castilla La Mancha Grp SciCom Dept Tecnol & Sistemas Informac Escuela Super Informat Ciudad Real 13004 Spain

In this work, we present a survey of the different parallel programming models and tools available today with special consideration to their suitability for high-performance computing. Thus, we review the shared and distributed memory approaches, as well as the current heterogeneous parallel programming model. In addition, we analyze how the partitioned global address space (PGAS) and hybrid parallel programming models are used to combine the advantages of shared and distributed memory systems. The work is completed by considering languages with specific parallel support and the distributed programming paradigm. In all cases, we present characteristics, strengths, and weaknesses. The study shows that the availability of multi-core CPUs has given new impulse to the shared memory parallel programming approach. In addition, we find that hybrid parallel programming is the current way of harnessing the capabilities of computer clusters with multi-core nodes. On the other hand, heterogeneous programming is found to be an increasingly popular paradigm, as a consequence of the availability of multi-core CPUs+GPUs systems. The use of open industry standards like OpenMP, MPI, or OpenCL, as opposed to proprietary solutions, seems to be the way to uniformize and extend the use of parallel programming models.

关键词： Parallelism and concurrency distributed programming heterogeneous (hybrid) systems

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL-STUDY OF distributed APPLICATION PERFORMANCE

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 1985年第10期11卷 1162-1174页

作者： LANTZ, KA NOWICKI, WI THEIMER, MM STANFORD UNIV DEPT COMP SCICTR AERONAUT & SPACE INFORMAT SCISTANFORDCA 94305

Although the number of computer networks is growing rapidly, implementation of distributed applications is relatively infrequent. An example of a distributed graphics application is described to show that distributed applications can be accomplished more efficiently than local applications, even when common hardware is used. The most important factors in the network environment for system performance are user workstation speed, remote host speed, and the type of high-level protocols used. The performance degradation frequently occurring between networks of different bandwidths can be reduced substantially through structuring, batching, and pipelining high-level protocols. Additional performance improvements can be achieved through effective design and implementation of underlying transport protocols. The impacts of network bandwidth on system performance are rendered insignificant by proper attention to protocol design and implementation.

关键词： Protocol Implementation Concurrency distributed programming distributed Systems Performance Evaluation Protocol Design

来源：评论

学校读者我要写书评

暂无评论

Concepts of systems for information retrieval

Concepts of systems for information retrieval

引用

IEEE-Siberian Workshop on Modern Communication Technologies (SIBCOM-2001)

作者： Orzechowski, T Stanislaw Staszic Univ Min & Met Dept Telecommun PL-30059 Krakow Poland

ISBN: (纸本)0780366115

The main purpose of this article is to present conceptions, that could be used for realization of efficient communication between "end-users" and a specific system that includes assembled information ("data-storage" systems). It also shows advantages of using agent approach in realization of already mentioned tasks. It describes two different approaches, that respect specific of Internet and Intranets and a character of "data-storage". All presented aspects can be taken into consideration during analysis and planning a structure for local and global networks (users, servers, location of data, character of databases).

关键词： distributed programming CORBA RMI Mobile Agents retrieval information databases

来源：评论

学校读者我要写书评

暂无评论

The use of multi-agents' systems in e-learning platforms

The use of multi-agents' systems in e-learning platforms

引用

IEEE International Siberian Conference on Control and Communications

作者： Orzechowski, Tomasz AGH Univ Sci & Technol Dept Telecommun PL-30059 Krakow Poland

ISBN: (纸本)9781424403462

Computer networks do make our life easier and probably better. The different kind of data (both useful and useless information) is available close to us. We don't need to know where it is physically located to use existing services. The only we need is to have the access to the global network. In this way we often can decrease the time we need to do following things such as doing shopping, checking news, exchanging our opinions, etc. Some years ago it took much more time... But making our life easier by increasing our time needed to arrange our life is not the most important thing, in my opinion. The really most important is to allow people who live in different countries to exchange the knowledge and offer distance learning. This kind of the use of the global network guarantees that people can be better educated and the development of science will accelerate.

关键词： multi-agent systems mobile agents e-learning distributed programming information retrieval

来源：评论

学校读者我要写书评

暂无评论

InContext: Simple Parallelism for distributed Applications 11

InContext: Simple Parallelism for Distributed Applications

引用

20th International Symposium on High Performance distributed Computing

作者： Yoo, Sunghwan Lee, Hyojeong Killian, Charles Kulkarni, Milind Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

ISBN: (纸本)9781450305525

As networking services, such as DHTs, provide increasingly complex functionality, providing acceptable performance will require parallelizing their operations on individual nodes. Unfortunately, the event-driven style in which these applications have traditionally been written makes it difficult to reason about parallelism, and providing safe, efficient parallel implementations of distributed systems remains a challenge. In this paper, we introduce a declarative programming model based on contexts, which allows programmers to specify the sharing behavior of event handlers. Programs that adhere to the programming model can be safely parallelized according to an abstract execution model, with parallel behavior that is well-defined with respect to the expected sequential behavior. The declarative nature of the programming model allows conformance to be captured as a safety property that can be verified using a model checker. We develop a prototype implementation of our abstract execution model and show that distributed applications written in our programming model can be automatically and efficiently parallelized. To recover additional parallelism, we present an optimization to the implementation based on state snapshots that permits more events to proceed in parallel. We evaluate our prototype implementation through several case studies and demonstrate significant speedup over optimized sequential implementations.

关键词： distributed programming Mace

来源：评论

学校读者我要写书评

暂无评论

Performance Improvements of Parallel Applications thanks to MPI-4.0 Hints 34

Performance Improvements of Parallel Applications thanks to ...

引用

34th IEEE International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

作者： Moraru, Maxim Roussel, Adrien Taboada, Hugo Jaillet, Christophe Perache, Marc Krajecki, Michael Univ Reims LICIIS F-51097 Reims France CEA DAM DIF LRC DIGIT F-91297 Arpajon France Univ Paris Saclay CEA Lab Informat Haute Peiformance Calcul & Simulat Bruyeres Le Chatel France CEA DAM DIF F-91297 Arpajon France Univ Reims LRC DIGIT LICIIS F-51097 Reims France

ISBN: (数字)9781665451550

ISBN: (纸本)9781665451550

HPC systems have experienced significant growth over the past years, with modern machines having hundreds of thousands of nodes. Message Passing Interface (MPI) is the de facto standard for distributed computing on these architectures. On the MPI critical path, the message-matching process is one of the most time-consuming operations. In this process, searching for a specific request in a message queue represents a significant part of the communication latency. So far, no miracle algorithm performs well in all cases. This paper explores potential matching specializations thanks to hints introduced in the latest MPI 4.0 standard. We propose a hash-table-based algorithm that performs constant time message-matching for no wildcard requests. This approach is suitable for intensive point-to-point communication phases in many applications (more than 50% of CORAL benchmarks). We demonstrate that our approach can improve the overall execution time of real HPC applications by up to 25%. Also, we analyze the limitations of our method and propose a strategy for identifying the most suitable algorithm for a given application. Indeed, we apply machine learning techniques for classifying applications depending on their message pattern characteristics.

关键词： HPC distributed programming MPI Matching MPI 4.0 Sessions

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：