检索结果-内蒙古大学图书馆

Toward a realistic task scheduling model

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2006年第3期17卷 263-275页

作者： Sinnen, O Sousa, LA Sandnes, FE Univ Auckland Dept Elect & Comp Engn Auckland 1 New Zealand Univ Tecn Lisboa Inst Super Tecn INESC ID P-1000029 Lisbon Portugal Oslo Univ Coll Fac Engn Dept Comp Sci N-0310 Oslo Norway

Task scheduling is an important aspect of parallel programming. Most of the heuristics for this NP-hard problem are based on a very simple system model of the target parallel system. Experiments revealed the inappropriateness of this classic model to obtain accurate and efficient schedules for real systems. In order to overcome this shortcoming, a new scheduling model was proposed that considers the contention for communication resources. Even though the accuracy and efficiency improved with the consideration of contention, the new contention model is still not good enough. The crucial aspect is the involvement of the processor in communication. This paper investigates the involvement of the processor in communication and its impact on task scheduling. A new system model is proposed based on the contention model that is aware of the processor involvement. The challenges for the scheduling techniques are analyzed and two scheduling algorithms are proposed. Experiments on real parallel systems show the significantly improved accuracy and efficiency of the new model and algorithms.

关键词： parallel processing concurrent programming scheduling and task partitioning processor involvement heterogeneous system model

来源：评论

学校读者我要写书评

暂无评论

THE JOYCE LANGUAGE REPORT

引用

SOFTWARE-PRACTICE & EXPERIENCE 1989年第6期19卷 553-578页

作者： HANSEN, PB School of Computer and Information Science Syracuse University Syracuse New York 13244 U.S.A.

This paper defines a programming language for distributed processing called Joyce. Joyce is based on CSP and Pascal. A Joyce program defines concurrent agents which communicate through synchronous channels. The agents... 详细信息

关键词： programming languages concurrent programming Communicating agents Input/output channels Polling Recursion

来源：评论

学校读者我要写书评

暂无评论

Highly scalable Erlang framework for agent-based metaheuristic computing

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2016年第Part1期17卷 234-248页

作者： Turek, Wojciech Stypka, Jan Krzywicki, Daniel Anielski, Piotr Pietak, Kamil Byrski, Aleksander Kisiel-Dorohinicki, Marek AGH Univ Sci & Technol Fac Comp Sci Elect & Telecommun Al Mickiewicza 30 PL-30059 Krakow Poland

Difficult search and optimization problems, usually solved by metaheuristics, are very often implemented in concurrent and parallel environment, as many metaheuristics (e.g. population- or agent-based) are inherently easy to parallelize. Therefore search for easy-to-use, robust and efficient frameworks dedicated for such computing methods, especially in the era of ubiquitous many and multi-core systems, is very desirable. Indeed, the development of multi-core architectures is incredibly fast and multicore CPUs can be found nowadays not only in supercomputers, but also in ordinary laptops or even phones. Efficient use of multicore architectures requires applying suitable languages and technologies, like Erlang. Its concurrency model, based on lightweight processes and asynchronous message-passing, seems very well suited for running massively concurrent code on many cores. Most of existing Erlang industrial applications are deployed on computers with up to 24 CPU cores, and there are hardly any reports on using Erlang on architectures exceeding 32 physical cores. In this paper we present our experiences with developing a concurrent Erlang-based computing platform, scaling computationally-intensive and memory-intensive applications up to 64 cores, using as examples global optimization and urban traffic planning problems. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Metaheuristic computing concurrent programming Scalability Erlang

来源：评论

学校读者我要写书评

暂无评论

Universal constructions that ensure disjoint-access parallelism and wait-freedom

引用

DISTRIBUTED COMPUTING 2016年第4期29卷 251-277页

作者： Ellen, Faith Fatourou, Panagiota Kosmas, Eleftherios Milani, Alessia Travers, Corentin Univ Toronto 10 Kings Coll Rd Toronto ON Canada Fdn Res & Technol Hellas FORTH Inst Comp Sci N Plastira 100 Iraklion 70013 Crete Island Greece Univ Crete Voutes Campus Iraklion 70013 Crete Island Greece Univ Bordeaux LaBRI F-33400 Talence France CNRS F-33400 Talence France

A universal construction is a general mechanism for obtaining a concurrent implementation of an object from its sequential code. We show that there is no universal construction that is both disjoint-access parallel (guaranteeing the processes operating on different parts of an implemented object do not interfere with one another) and wait-free (guaranteeing progress for each nonfaulty process when accessing an object). In contrast, we present a universal construction which results in disjoint-access parallel, wait-free implementations of any object provided there is a bound on the number of data items accessed by each operation supported by the object.

关键词： concurrent programming Disjoint-access parallelism Wait-freedom Universal construction Impossibility result

来源：评论

学校读者我要写书评

暂无评论

Runtime analysis of atomicity for multithreaded programs

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2006年第2期32卷 93-110页

作者： Wang, LQ Stoller, SD SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA

Atomicity is a correctness condition for concurrent systems. Informally, atomicity is the property that every concurrent execution of a set of transactions is equivalent to some serial execution of the same transactions. In multithreaded programs, executions of procedures ( or methods) can be regarded as transactions. Correctness in the presence of concurrency typically requires atomicity of these transactions. Tools that automatically detect atomicity violations can uncover subtle errors that are hard to find with traditional debugging and testing techniques. This paper describes two algorithms for runtime detection of atomicity violations and compares their cost and effectiveness. The reduction-based algorithm checks atomicity based on commutativity properties of events in a trace;the block-based algorithm efficiently represents the relevant information about a trace as a set of blocks (i.e., pairs of events plus associated synchronizations) and checks atomicity by comparing each block with other blocks. To improve the efficiency and accuracy of both algorithms, we incorporate a multilockset algorithm for checking data races, dynamic escape analysis, and happen-before analysis. Experiments show that both algorithms are effective in finding atomicity violations. The block-based algorithm is more accurate but more expensive than the reduction-based algorithm.

关键词： concurrent programming testing and debugging Java data race atomicity

来源：评论

学校读者我要写书评

暂无评论

High performance finite element approximate inverse preconditioning

引用

APPLIED MATHEMATICS AND COMPUTATION 2008年第1-2期201卷 293-304页

作者： Giannoutakis, Konstantinos M. Gravvanis, George A. Democritus Univ Thrace Dept Elect & Comp Engn Sch Engn GR-67100 Xanthi Greece

A new parallel normalized optimized approximate inverse algorithm, based on the concept of the "fish bone" computational approach satisfying an antidiagonal data dependency, for computing classes of explicit approximate inverses, is introduced for symmetric multiprocessor systems. The parallel normalized explicit approximate inverses are used in conjunction with parallel normalized explicit preconditioned conjugate gradient square schemes, for the efficient solution of finite element sparse linear systems. The parallel design and implementation issues of the new proposed algorithms are discussed and the parallel performance is presented, using OpenMP. (c) 2007 Elsevier Inc. All rights reserved.

关键词： algorithm design and analysis concurrent programming numerical algorithms and problems sparse linear systems iterative solution techniques parallel algorithms parallelism and concurrency

来源：评论

学校读者我要写书评

暂无评论

THE EDEN SYSTEM - A TECHNICAL REVIEW

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 1985年第1期11卷 43-59页

作者： ALMES, GT BLACK, AP LAZOWSKA, ED NOE, JD Department of Computer Science University of Washington

The Eden project is a 5-year experiment in designing, constructing, and using an ''integrated distributed'' computing system. The goal is to combine the benefits of integration and distribution by supporting an object-based style of programming on top of a node machine/local network hardware base. The experimental hypothesis is that such an architecture will offer an environment conducive to building distributed applications. In evaluating the benefits (in terms of programmability) and the costs (in terms of necessary support) of the system architecture 3 years into the project, attention is focused on: 1. the concept, history, status, and context of the Eden system, 2. the way in which the task of supporting the Eden architecture is divided among the kernel, the programming language, and user-level (library) code, and 3. the experiences with paper designs and prototype implementations that led to this division of labor. It is shown how distributed applications make use of various aspects of the Eden architecture, and some preliminary evaluations are presented based on experiences to date.

关键词： Remote Procedure Call Capability concurrent Euclid concurrent programming Distributed Electronic Mail Distributed Program Distributed System Eden Object Oriented System

来源：评论

学校读者我要写书评

暂无评论

Generalised rely-guarantee concurrency: an algebraic foundation

引用

FORMAL ASPECTS OF COMPUTING 2016年第6期28卷 1057-1078页

作者： Hayes, Ian J. Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld Australia

The rely-guarantee technique allows one to reason compositionally about concurrent programs. To handle interference the technique makes use of rely and guarantee conditions, both of which are binary relations on states. A rely condition is an assumption that the environment performs only atomic steps satisfying the rely relation and a guarantee is a commitment that every atomic step the program makes satisfies the guarantee relation. In order to investigate rely-guarantee reasoning more generally, in this paper we allow interference to be represented by a process rather than a relation and hence derive more general rely-guarantee laws. The paper makes use of a weak conjunction operator between processes, which generalises a guarantee relation to a guarantee process, and introduces a rely quotient operator, which generalises a rely relation to a process. The paper focuses on the algebraic properties of the general rely-guarantee theory. The Jones-style rely-guarantee theory can be interpreted as a model of the general algebraic theory and hence the general laws presented here hold for that theory.

关键词： concurrent programming rely-guarantee concurrency program verification program algebra concurrent Kleene algebra

来源：评论

学校读者我要写书评

暂无评论

ALGORITHMS FOR ON-THE-FLY GARBAGE COLLECTION REVISITED

引用

INFORMATION PROCESSING LETTERS 1987年第4期24卷 211-216页

作者： VANDESNEPSCHEUT, JLA Department of Mathematics and Computing Science Groningen University P.O. Box 800 9700 AV Groningen The Netherlands

Dijkstra et al. (1978) have presented an algorithm for on-the-fly garbage collection. Ben-Ari (1984) presented a new algorithm that, though it is not much simpler, has a much simpler correctness proof. Each step in verifying the invariants is almost trivial and could be checked mechanically. Since the proof found in Ben-Ari (1984) is less trivial than the introduction would lead one to suspect, another proof is designed. It is shown how both a parallel program and its invariant are derived from a sequential program and its invariant, and a short, simple proof of the invariance is presented. The reasoning with invariants more clearly captures the quintessence and more clearly exposes the ''beauty'' of the algorithm than does the original offering.

关键词： concurrent programming correctness garbage collection program presentation

来源：评论

学校读者我要写书评

暂无评论

A criterion to enforce correctness of indirectly cooperating applications

引用

INFORMATION SCIENCES 1998年第3-4期110卷 279-302页

作者： Canals, G Godart, C Molli, P Munier, M Univ Henri Poincare LORIA F-54506 Vandoeuvre Nancy France

Cooperative applications are expected to become commonplace in the future. We are concerned hen with a special case of cooperation called indirect cooperation. The idea of the paper is that a Concurrency Control approach better fits to indirect cooperation than a concurrent programming one. In other words, there do exist syntactic correctness criteria which define a large sphere of security in which application programmers are released from the burden of interaction explicit programming. This paper argues this point of view and describes such a criterion: the COO-serializability. It applies for a class of applications which cooperate indirectly. (C) 1998 Elsevier Science Inc. All rights reserved.

关键词： cooperation concurrency control concurrent programming correctness criterion cooperative programming cooperative execution

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：