检索结果-内蒙古大学图书馆

An incremental ant colony optimization based approach to task assignment to processors for multiprocessor scheduling

引用

Frontiers of Information Technology & Electronic Engineering 2017年第4期18卷 498-510页

作者： Hamid Reza BOVEIRI Sama Technical and Vocational Training College Islamic Azad University Shoushtar Branch Shoushtar Iran

Optimized task scheduling is one of the most important challenges to achieve high performance in multiprocessor environments such as parallel and distributed systems. Most introduced task-scheduling algorithms are based on the so-called list scheduling technique. The basic idea behind list scheduling is to prepare a sequence of nodes in the form of a list for scheduling by assigning them some priority measurements, and then repeatedly removing the node with the highest priority from the list and allocating it to the processor providing the earliest start time （EST）. Therefore, it can be inferred that the makespans obtained are dominated by two major factors：（1） which order of tasks should be selected （sequence subproblem）; （2） how the selected order should be assigned to the processors （assignment subproblem）. A number of good approaches for overcoming the task sequence dilemma have been proposed in the literature, while the task assignment problem has not been studied much. The results of this study prove that assigning tasks to the processors using the traditional EST method is not optimum; in addition, a novel approach based on the ant colony optimization algorithm is introduced, which can find far better solutions.

关键词： Ant colony optimization List scheduling Multiprocessor task graph scheduling parallel and distributed systems

来源：评论

学校读者我要写书评

暂无评论

Wiley Encyclopedia of Computer Science and Engineering

引用

2007年

作者： Wah

ISBN: (数字)9780470050118

ISBN: (纸本)9780471383932

Wiley Encyclopedia of Computer Science and Engineering includes over 450 A to Z articles addressing the latest advances and findings in computer science and engineering, in addition to important topics of interest to computer scientists and engineers, including standards, electronic commerce, financial engineering, and computer education. Each article is written by an expert in his or her particular specialty and is peer-reviewed by two other experts to ensure that it is clear and precise. References and website of related interest accompany every article. Index of Topics Artificial Intelligence Vision Software systems, data and knowledge engineering Computer architectures, networks, and interconnects VLSI Technology Computer systems Performance evaluation and real-time computing Theory and Algorithms Applications About the Editor-in-Chief BENJAMIN W. WAH received his Ph.D. degree in computer science from the University of California, Berkeley, CA. He is currently the Franklin W. Woeltge Professor of Electrical and Computer Engineering and a Professor of the Coordinated Science Laboratory of the University of Illinois at Urbana-Champaign, Urbana, IL.

关键词： Applications Computer Vision Computing Milieux Data Foundation and Theory Hardware and Architecture Image Processing and Visualization Information systems parallel and distributed systems Software

来源：评论

学校读者我要写书评

暂无评论

Time-constrained loop scheduling with minimal resources

引用

Journal of Embedded Computing 2006年第1期2卷 103-117页

作者： O'Neil, Timothy W. Sha, Edwin H.-M. Department of Comp. Science University of Akron Akron OH 44325-4003 USA Department of Comp. Science Erik Jonsson School of Eng. & C.S. Box 830688 MS EC 31 Univ. of Texas at Dallas Richardson TX 75083-0688 USA. Tel.: +1 972 883 4193Fax: +1 972 883 2349[email protected]

Many applications commonly found in digital signal processing and image processing applications can be represented by data-flow graphs (DFGs). In our previous work, we proposed a new technique, extended retiming, which can be combined with minimal unfolding to transform a DFG into one which is rate-optimal. The result, however, is a DFG with split nodes, a concise representation for pipelined schedules. This model and the extraction of the pipelined schedule it represents have heretofore not been explored. In this paper, we develop new results regarding the construction of such graphs. We develop scheduling algorithms for such graphs, and then discuss a way to reduce the hardware requirements of such schedules. In the process, we state and prove a tight upper bound on the minimum number of processors required to execute the static schedule produced by our algorithms. We also construct an unfolding algorithm for split-node graphs and combine it with our scheduling methods to achieve rate-optimality in all cases. Finally, we demonstrate our methods on a specific example.

关键词： parallel and distributed systems compilers optimization modeling languages programmable signal processors

来源：评论

学校读者我要写书评

暂无评论

BaPipe: Balanced Pipeline parallelism for DNN Training

引用

parallel PROCESSING LETTERS 2022年第3N04期32卷 2250005-2250005页

作者： Zhao, Letian Xu, Rui Wang, Tianqi Tian, Teng Wang, Xiaotian Wu, Wei Ieong, Chio-In Jin, Xi Univ Sci & Technol China State Key Lab Particle Detect & Elect Hefei 230026 Peoples R China Univ Sci & Technol China Dept Phys Inst Microelect Hefei 230026 Peoples R China Huawei Technol Shenzhen 518129 Peoples R China

The size of deep neural networks (DNNs) grows rapidly as the complexity of the machine learning algorithm increases. distributed deep learning based on model parallelism has been widely used to satisfy the requirements of DNN training related to computation and memory. In this paper, we propose a training framework for pipeline parallelism called BaPipe (Balanced Pipeline) that can automatically explore methods to schedule pipeline parallelism and balanced partition strategies for DNN training on heterogeneous accelerator clusters. In BaPipe, each accelerator calculates the forward and backward propagation for the assigned partition of networks to implement an intra-batch pipeline parallelism strategy. By considering the parameters of DNN models as well as the computation, memory, and communication resources of each accelerator, BaPipe automatically selects the most suitable method of pipeline scheduling from among multiple proposed scheduling modes. It also uses a novel strategy to automatically investigate load balancing in the context of inter-layer partition, intra-layer partition, and coarse-grained partition. We trained such DNNs as VGG-16, ResNet-50, and Google's Neural Machine Translation (GNMT) on GPU clusters, and simulated the training-related performance of FPGA clusters. Compared with the state-of-the-art frameworks for data parallelism (DP) and pipeline parallelism, BaPipe provides a speedup of 3.2x and 4x of memory reduction on various homogeneous and heterogeneous platforms.

关键词： DNN training pipeline parallelism load balancing parallel and distributed systems

来源：评论

学校读者我要写书评

暂无评论

A Mobile Agent Team Works based on Load-Balancing Middleware for distributed Computing systems

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2019年第12期10卷 408-416页

作者： Benchara, Fatema Zahra Mohamed, Youssfi Hassan II Univ Casablanca ENSET Mohammedia Lab SSDIA Dept Comp Sci Mohammadia Morocco

The aim of this paper is to present a load balancing middleware for parallel and distributed systems. The great challenge is to balance the tasks between heterogeneous distributed nodes for parallel and distributed computing models based distributed systems, by the way to ensure HPC (High performance computing) of these models. Accordingly, the proposed middleware is based on mobile agent team work which implements an efficient method with two strategies: (i) Load balancing Strategy that determines the node tasks assignment based on node performance, and (ii) Rebalancing Strategy that detects the unbalanced nodes and enables tasks migration. The paper focuses on the proposed middleware and its cooperative mobile agent team work model strategies to dynamically balance the nodes, and scale up distributed computing systems. Indeed, some experimental results that highlight the performance and efficiency of the proposed middleware are presented.

关键词： Load balancing middleware parallel and distributed systems parallel and distributed computing models high performance computing mobile agents distributed computing

来源：评论

学校读者我要写书评

暂无评论

Multiprocessor Task Graph Scheduling Using a Novel Graph-Like Learning Automata

引用

INTERNATIONAL JOURNAL OF GRID AND distributed COMPUTING 2015年第1期8卷 41-54页

作者： Boveiri, H. R. Islamic Azad Univ Shushtar Branch Sama Tech & Vocat Training Coll Shushtar Iran

Optimized task scheduling is one of the most important challenges in multiprocessor environments such as parallel and distributed systems. In such these systems, each parallel program is decomposed into the smaller segments so-called tasks. Task execution times, precedence constrains and communication costs are modeled by using a directed acyclic graph (DAG) named task graph. The goal is to minimize the program finish-time (makespan) by means of mapping the tasks to the processor elements in such a way that precedence constrains are preserved. This problem is shown to be NP-hard in general form and some restricted ones. Therefore, utilization of heuristic and meta-heuristic approaches to solve this problem is logical. Learning automata (LA) is an abstract model to interact with stochastic environment, which tries to reform itself based on the environment feedback. Although a learning automaton itself is a simple component, a group of them by cooperating each other can show complicated behavior, and can coverage to desired solutions under appropriate learning algorithm. In this paper, an ingenious graph-like learning automata in which each task in the task graph is represented by a learning automaton tries to solve the multiprocessor task-scheduling problem in a collective manner. Set of different experiments on various real-world task-graphs has been done and archived results are so promising compared to the traditional methods and genetic algorithm.

关键词： Learning automata multiprocessor task scheduling parallel and distributed systems task graph

来源：评论

学校读者我要写书评

暂无评论

AN EMPIRICAL STUDY OF HIERARCHICAL DIVISION FOR MESH-STRUCTURED NETWORKS

引用

Journal of Interconnection Networks 2007年第3期8卷 285-304页

作者： DAJIN WANG Department of Computer Science Montclair State University Upper Montclair NJ 07043 USA

A parallel/distributed system consists of a collection of processes, which are distributed over a network of processors, and work in a cooperative manner to fulfill various tasks. A hierarchical approach is to group and organize the distributed processes into a logical hierarchy of multiple levels to achieve better system performance. It has been proposed as an effective way to solve various problems in distributed computing, such as distributed monitoring, resource scheduling, and network routing. In [21], we studied hierarchical configuration for mesh and hypercube networks to the end of achieving better system performance. In particular, we proposed theoretically optimal hierarchy for mesh and hypercube, so that the total traffic flow over the network is minimized. In this paper, we present the experimental results to establish the practical relevance of mesh hierarchy proposed in [21]. We simulated situations for multi-level division, real network loading scenarios, random data aggregation rates, and different division sizes other than derived in [21]. The simulation results not only show that the analytically obtained hierarchy works well for many realistic settings, but also offer some useful insights into the proposed hierarchy scheme.

关键词： Hierarchical architecture Hierarchy Interconnection networks Mesh parallel and distributed systems Simulation

来源：评论

学校读者我要写书评

暂无评论

A new mathematical model for optimizing the performance of parallel and discrete event simulation systems 08

A new mathematical model for optimizing the performance of p...

引用

Proceedings of the 2008 Spring simulation multiconference

作者： Syed S. Rizvi Khaled. M. Elleithy Aasia Riasat University of Bridgeport Bridgeport CT Institute of Business Management Karachi Pakistan

ISBN: (纸本)9781565553194

Null message algorithm is an important conservative time management protocol in parallel discrete event simulation systems for providing synchronization between the distributed computers with the capability of both avoiding and resolving the deadlock. However, the excessive generation of null messages prevents the widespread use of this algorithm. The excessive generation of null messages results due to an improper use of some of the critical parameters such as frequency of transmission and Lookahead values. However, if we could minimize the generation of null messages, most of the parallel discrete event simulation systems would be likely to take advantage of this algorithm in order to gain increased system throughput and minimum transmission delays. In this paper, a new mathematical model for optimizing the performance of parallel and distributed simulation systems is proposed. The proposed mathematical model utilizes various optimization techniques such as variance of null message elimination to improve the performance of parallel and distributed simulation systems. For the sake of simulation results, we consider both uniform and non-uniform distribution of Lookahead values across multiple output lines of an LP. Our experimental verifications demonstrate that an optimal NMA offers better scalability in parallel discrete event simulation systems if it is used with the proper selection of critical parameters.

关键词： discrete event simulation parallel and distributed systems null message algorithm

来源：评论

学校读者我要写书评

暂无评论

A new technique of switch & feedback job scheduling mechanism in a distributed system 09

A new technique of switch & feedback job scheduling mechanis...

引用

Proceedings of the 2009 Spring Simulation Multiconference

作者： Syed Rizvi Bevin Thomas Khaled Elleithy Aasia Riasat University of Bridgeport Bridgeport CT Institute of Business Management Karachi Pakistan

In this paper we investigate on a special type of job scheduler for distributed heterogeneous systems called the switch and feedback job scheduler. The main objective of the centralized job scheduler is to achieve maximum performance with reduced waiting time and faster response time for independent tasks by reordering the processor queue list based on the feedback received from each individual local processing system.

关键词： performance optimization job scheduling parallel and distributed systems

来源：评论

学校读者我要写书评

暂无评论

Agent middleware for heterogeneous scientific simulations 98

Agent middleware for heterogeneous scientific simulations

引用

Proceedings of the 1998 ACM/IEEE conference on Supercomputing

作者： Shirun Ho Satoshi Itoh Sigeo Ihara Richard D. Schlichting Parallel Application Hitachi Laboratory Real World Computing Partnership Central Research Laboratory Hitachi Ltd. The University of Arizona

ISBN: (纸本)9780897919845

The current technology of parallel and distributed systems allows users to exploit a variety of resources across networks. However, the support provided is often insufficient for computational scientists to simulate complicated real-world scenarios in which different kinds of scientific applications need to be combined to perform high fidelity simulations. As a result, users waste a large amount of time and effort developing custom techniques for performing semantic-level communication between heterogeneous scientific *** paper describes a new middleware system that provides high-level transparency in the form of agents that automatically transfer and transform data between simulations that use different mathematical and physical modeling approaches. Based on a specification that correlates different discrete points in finite difference method (FDM), finite element method (FEM) or particle simulations, the agents provide a variety of techniques for semantically transforming the values associated with correlated points and automatically determine to which processes the values must be transferred. To facilitate use and minimize impact on user programs, the agent system includes three types of library calls that manage task identification, register different kinds of discrete points and construct a correlation table according to the specification, and transfer messages that incorporate extraction and transformation of the values on the correlated points. Another library specially optimized for parallel simulations that use a SPMD (Single Program Multiple Data stream) structure is also offered to control communication through the agents.A prototype system has been developed on the Hitachi SR2201 parallel machine as well as workstation clusters, and applied to several example applications. These include an advanced device simulation that combines quantum transport simulation with electric potential simulation, and a simulation of thermal flow resulting from

关键词： molecular dynamics heterogeneous scientific simulation middleware electric potential simulation mesh correlative specification quantum device simulation particle thermal flow simulation parallel and distributed systems continuum simulation semantic transformation agent network

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：