检索结果-内蒙古大学图书馆

Efficient algorithms for dynamic allocation of distributed memory

ALGORITHMICA 1999年第2期24卷 139-171页

作者： Leighton, T Schwabe, EJ MIT Dept Math Cambridge MA 02139 USA MIT Comp Sci Lab Cambridge MA 02139 USA Depaul Univ Sch CTI Chicago IL 60604 USA Northwestern Univ Evanston IL 60208 USA

We consider the problem of dynamically allocating and deallocating local memory resources among multiple users in a parallel or distributed system. Given a group of independent users and a collection of interconnected local memory devices, we want to render the fragmentation of the memory resources irrelevant by allowing any user to allocate space for his or her purposes as long as there is space available anywhere in the system. In effect, we would like it to appear to the users as though they are allocating memory from a single central pool of memory, even though the space is distributed throughout the system. Our goal is to devise an on-line allocation algorithm that minimizes two cost measures: first, the fraction? of unused space, which arises due to fragmentation of the memory;second, the slowdown needed by the system to service user requests, which arises due to the contention for access to the memory devices. We solve this distributed dynamic allocation problem in near-optimal Fashion by devising an algorithm that allows the memory to be used to 100% of capacity despite the fragmentation and guarantees that service delays will always be within a constant factor of optimal. The algorithm is completely on-line (no foreknowledge of user activity is assumed) and can accommodate any sequence of allocations and deallocations by the users that does not violate global memory bounds. We also consider the distributed dynamic allocation problem in the more restrictive setting where the local memory devices are connected by a low-degree fixed-connection network, rather than being fully interconnected. In this case, communication costs must be more explicitly considered in our allocation algorithms. We give allocation algorithms for butterfly and hypercube networks, and prove necessary and sufficient conditions on the total amount of memory space needed for near-optimal algorithms to exist.

关键词： dynamic allocation memory allocation parallel and distributed systems allocation algorithms

来源：评论

学校读者我要写书评

暂无评论

BRISK: a portable and flexible distributed instrumentation system

引用

SOFTWARE-PRACTICE & EXPERIENCE 2000年第12期30卷 1353-1373页

作者： Bakic, A Mutka, MW Rover, DT Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA Michigan State Univ Dept Elect & Comp Engn E Lansing MI 48824 USA

Researchers and practitioners in the area of parallel and distributed computing have been lacking a portable, flexible and robust distributed instrumentation system. This paper presents the reference implementation of Baseline Reduced Instrumentation System Kernel (BRISK). BRISK was developed as a part of a realtime system instrumentation and performance visualization project. The design is based on a simple distributed instrumentation system model for flexibility and extensibility. The basic implementation poses minimalistic system requirements and achieves high performance. The paper also shows evaluations of BRISK on both basic and advanced configurations. The first evaluation emphasizes local, simple performance metrics;and the second highlights aggregate performance, built-in clock synchronization and dynamic on-line sorting. Copyright (C) 2000 John Wiley & Sons, Ltd.

关键词： instrumentation parallel and distributed systems low interference high performance flexibility portability

来源：评论

学校读者我要写书评

暂无评论

Measuring the robustness of a resource allocation

引用

IEEE TRANSACTIONS ON parallel and distributed systems 2004年第7期15卷 630-641页

作者： Ali, S Maciejewski, AA Siegel, HJ Kim, JK Univ Missouri Dept Elect & Comp Engn Rolla MO 65409 USA Colorado State Univ Dept Elect & Comp Engn Ft Collins CO 80523 USA Colorado State Univ Dept Comp Sci Ft Collins CO 80523 USA Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

parallel and distributed systems may operate in an environment that undergoes unpredictable changes causing certain system performance features to degrade. Such systems need robustness to guarantee limited degradation despite fluctuations in the behavior of its component parts or environment. This research investigates the robustness of an allocation of resources to tasks in parallel and distributed systems. The main contributions of this paper are 1) a mathematical description of a metric for the robustness of a resource allocation with respect to desired system performance features against multiple perturbations in multiple system and environmental conditions, and 2) a procedure for deriving a robustness metric for an arbitrary system. For illustration, this procedure is employed to derive robustness metrics for three example distributed systems. Such a metric can help researchers evaluate a given resource allocation for robustness against uncertainties in specified perturbation parameters.

关键词： robustness robustness metric resource allocation resource management systems parallel and distributed systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of job arrival patterns and parallel scheduling performance

引用

PERFORMANCE EVALUATION 1999年 36-7卷 137-163页

作者： Squillante, MS Yao, DD Zhang, L IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA Chinese Univ Hong Kong SEEM Dept Shatin NT Peoples R China

In this paper we present a study of the job arrival patterns from a parallel computing system and the impact of such arrival patterns on the performance of parallel scheduling strategies. Using workload data from the Cornell Theory Center, we develop a class of traffic models to characterize these arrival patterns. Our analysis of the job arrival data illustrates traffic patterns that exhibit heavy-tailed behavior and other characteristics which are quite different from the arrival processes used in previous studies of parallel scheduling. We then investigate the impact of these arrival traffic patterns on the performance of parallel space-sharing strategies, including the derivation of some scheduling optimality results. (C) 1999 Published by Elsevier Science B.V. All rights reserved.

关键词： parallel scheduling traffic modeling queueing analysis heavy-tail distributions parallel and distributed systems

来源：评论

学校读者我要写书评

暂无评论

A Novel ACO-Based Static Task Scheduling Approach for Multiprocessor Environments

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE systems 2016年第5期9卷 800-811页

作者： Boveiri, Hamid Reza Islamic Azad Univ Shoushtar Branch Dept Comp Sci Sama Tech & Vocat Training Coll Shoushtar Iran

Optimized task scheduling is one of the most important challenges in parallel and distributed systems. In such architectures during compile step, each program is decomposed into the smaller segments so-called tasks. Tasks of a program may be dependent;some tasks may need data generated by the others to start. To formulate the problem, precedence constraints, required execution times of tasks, and communication costs among them are modeled using a directed acyclic graph (DAG) named task-graph. The tasks must be assigned to a predefined number of processors in such a way that the program completion time is minimized, and the precedence constraints are preserved. It is well known to be NP-hard in general form and most restricted cases;therefore, a number of heuristic and meta-heuristic approaches have so far been proposed in the literature to find near-optimum solutions for this problem. We believe that ant colony optimization (ACO) is one of the best methods to cope with such kind of problems presented by graph. ACO is a metaheuristic approach inspired from social behavior of real ants. It is a multi-agent approach in which artificial ants (agents) try to find the shortest path to solve the given problem using an indirect local communication called stigmergy. Stigmergy lets ACO to be fast and efficient in comparison with other metaheuristics and evolutionary algorithms. In this paper, artificial ants, in a cooperative manner, try to solve static task scheduling problem in homogeneous multiprocessor environments. Set of different experiments on various task-graphs has been conducted, and the results reveal that the proposed approach outperforms the conventional methods from the performance point of view.

关键词： Ant colony optimization (ACO) metaheuristics multiprocessor task scheduling parallel and distributed systems

来源：评论

学校读者我要写书评

暂无评论

Dissemination of state information in distributed autonomous systems

引用

COMPUTER COMMUNICATIONS 1998年第11期21卷 969-979页

作者： Chapin, SJ Spafford, EH Univ Virginia Dept Comp Sci Charlottesville VA 22903 USA Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

Many researchers are devising algorithms for task placement in distributed systems, but few are designing the necessary mechanisms to provide the information required by those algorithms. Fundamental to these mechanisms is an accurate means for information exchange between distributed systems. The MESSIAHS project investigated the construction of a set of mechanisms to support task placement in autonomous, heterogeneous, distributed systems. In this paper we describe the semantics of the protocols used to exchange system state information within MESSIAHS, and develop formal models to prove that the protocols accurately propagate system description information throughout the system. (C) 1998 Elsevier Science B.V.

关键词： parallel and distributed systems task scheduling autonomy state dissemination

来源：评论

学校读者我要写书评

暂无评论

MODELING AND VERIFICATION OF TIME-DEPENDENT systems USING TIME PETRI NETS

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 1991年第3期17卷 259-273页

作者： BERTHOMIEU, B DIAZ, M CNRS AUTOMAT ANAL SYST RES GRPSOFTWARE & TOOLS COMMUN SYSTF-31077 TOULOUSEFRANCE

This paper deals with describing and analyzing concurrent systems, such as communication systems, whose behavior is dependent on explicit values of time. An enumerative method is proposed in order to exhaustively validate the behavior of Merlin's time Petri net models. This new method, which allows one to formally verify time dependent systems, is applied to a simple illustrative example, the specification and verification of the alternating bit protocol.

关键词： MODELING parallel and distributed systems SPECIFICATION TIME TIME PETRI NETS VERIFICATION

来源：评论

学校读者我要写书评

暂无评论

Measuring robustness of computing systems

引用

SIMULATION MODELLING PRACTICE AND THEORY 2009年第9期17卷 1457-1467页

作者： Eslamnour, Behdis Ali, Shoukat Intel Corp Folsom CA 95630 USA Missouri Univ Sci & Technol Dept Elect & Comp Engn Rolla MO 65409 USA

System builders are becoming increasingly interested in robust design. We believe that a methodology for generating robustness metrics will help the robust design research efforts and, in general, is an important step in the efforts to create robust computing systems. The purpose of the research in this paper is to quantify the robustness of a resource allocation, with the eventual objective of setting a standard that could easily be instantiated for a particular computing system to generate a robustness metric. The paper exposes how not considering the uncertainties can result in gross overestimation of the system capacity, and shows a method for reducing the impact of uncertainty, and even use it to our advantage if the uncertainties are correlated. We present our theoretical foundation for a robustness metric and give its instantiation for a particular system. (C) 2009 Elsevier B.V. All rights reserved.

关键词： Robustness Robustness metric Resource allocation Resource management systems parallel and distributed systems Mahalanobis distance

来源：评论

学校读者我要写书评

暂无评论

Highly Scalable Self-Healing Algorithms for High Performance Scientific Computing

引用

IEEE TRANSACTIONS ON COMPUTERS 2009年第11期58卷 1512-1524页

作者： Chen, Zizhong Dongarra, Jack Colorado Sch Mines Dept Math & Comp Sci Golden CO 80401 USA Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

As the number of processors in today's high-performance computers continues to grow, the mean-time-to-failure of these computers is becoming significantly shorter than the execution time of many current high-performance computing applications. Although today's architectures are usually robust enough to survive node failures without suffering complete system failure, most of today's high-performance computing applications cannot survive node failures. Therefore, whenever a node fails, all surviving processes on surviving nodes usually have to be aborted and the whole application has to be restarted. In this paper, we present a framework for building self-healing high-performance numerical computing applications so that they can adapt to node or link failures without aborting themselves. The framework is based on FT-MPI and diskless checkpointing. Our diskless checkpointing uses weighted checksum schemes, a variation of Reed-Solomon erasure codes over floating-point numbers. We introduce several scalable encoding strategies into the existing diskless checkpointing and reduce the overhead to survive k failures in p processes from 2[log p].k((beta + 2 gamma)m + alpha) to (1 + O(root p/root m))(2).k(beta + 2 gamma)m, where alpha is the communication latency, 1/beta is the network bandwidth between processes, 1/gamma is the rate to perform calculations, and m is the size of local checkpoint per process. When additional checkpoint processors are used, the overhead can be reduced to (1 + O(root 1/m)).k(beta + 2 gamma)m, which is independent of the total number of computational processors. The introduced self-healing algorithms are scalable in the sense that the overhead to survive k failures in p processes does not increase as the number of processes p increases. We evaluate the performance overhead of our self-healing approach by using a preconditioned conjugate gradient equation solver as an example. Experimental results demonstrate that our self-healing scheme can surviv

关键词： Self-healing diskless checkpointing fault tolerance pipeline parallel and distributed systems high-performance computing Message Passing Interface

来源：评论

学校读者我要写书评

暂无评论

Polya Urn Latent Dirichlet Allocation: A Doubly Sparse Massively parallel Sampler

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2019年第7期41卷 1709-1719页

作者： Terenin, Alexander Magnusson, Mans Jonsson, Leif Draper, David Imperial Coll London Dept Math Stat Sect London SW7 2AZ England Linkoping Univ S-58183 Linkoping Sweden Univ Calif Santa Cruz Dept Appl Math & Stat Stat Santa Cruz CA 95064 USA

Latent Dirichlet Allocation (LDA) is a topic model widely used in natural language processing and machine learning. Most approaches to training the model rely on iterative algorithms, which makes it difficult to run LDA on big corpora that are best analyzed in parallel and distributed computational environments. Indeed, current approaches to parallel inference either don't converge to the correct posterior or require storage of large dense matrices in memory. We present a novel sampler that overcomes both problems, and we show that this sampler is faster, both empirically and theoretically, than previous Gibbs samplers for LDA. We do so by employing a novel Polya-urn-based approximation in the sparse partially collapsed sampler for LDA. We prove that the approximation error vanishes with data size, making our algorithm asymptotically exact, a property of importance for large-scale topic models. In addition, we show, via an explicit example, that-contrary to popular belief in the topic modeling literature-partially collapsed samplers can be more efficient than fully collapsed samplers. We conclude by comparing the performance of our algorithm with that of other approaches on well-known corpora.

关键词： Bayesian inference big data computational complexity gibbs sampling latent dirichlet allocation markov chain monte carlo natural language processing parallel and distributed systems topic models

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：