检索结果-内蒙古大学图书馆

Proceedings of the 4th International ICST Conference on Simulation Tools and Techniques

作者： Aleksandar Milenkoski Biljana Stojcevska Oliver Popov SCSIT UACS Skopje Macedonia DSV SU Kista Sweden

ISBN: (纸本)9781936968008

The paper deals with the architecture and the performance of a system for gathering and processing simulation data where use case are communications transport protocols. The system is based on the ns-2 network simulator and the tcpeval tool for the evaluation of TCP and TCP related protocols. The work promotes the concept of a controlled simulation replication as central to achieve statistical accuracy of the simulation results. The later assures that in each case of the specific set of simulation runs, their number does not exceed the minimal one required by the desired and predefined accuracy. Moreover, the use of interprocess and inter-thread communication provided by Open MPI and OpenMP makes the execution of the system possible over a multiprocessor distributed architecture that eventually reduced the time needed to achieve the preferred precision. While the later work is in an early stage, the initial results of the benchmark tests indicate significant gains in time based on the metrics native to tcpeval.

关键词： statistical accuracy distributed execution TCP evaluation

来源：评论

学校读者我要写书评

暂无评论

Designing Self-Tuning Split-Map-Merge Applications for High Cost-Efficiency in the Cloud

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2017年第2期5卷 303-316页

作者： Rajan, Dinesh Thain, Douglas Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA

Cloud platforms are attractive for executing large concurrent applications that require access to a pool of resources for concurrently executing the partitions of their workloads. Historically, application designers have tuned concurrent applications for specific hardware and platforms. But such approaches are not viable in cloud platforms as applications can be deployed on a variety of platforms and the operating environments can vary in each deployment. In this work, we argue and demonstrate that concurrent applications in cloud platforms must be self-tuning. First, we show that applications must incorporate a model of the overheads of operation. Second, we show that applications must determine their resource requirements and tune their operation to the operating conditions using estimations from the model. We build two self-tuning applications, E-Sort and E-MAKER, and demonstrate their ability to achieve high cost-efficiency by determining the right scale of partitions and resources to use for operation and adapting their behavior according to the characteristics of the deployed environment.

关键词： Cloud computing distributed execution scientific applications data-intensive applications data partitioning workload decomposition resource provisioning

来源：评论

学校读者我要写书评

暂无评论

Predictive analytics using statistical, learning, and ensemble methods to support real-time exploration of discrete event simulations

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2016年 56卷 360-374页

作者： Budgaga, Walid Malensek, Matthew Pallickara, Sangmi Harvey, Neil Breidt, F. Jay Pallickara, Shrideep Colorado State Univ Dept Comp Sci Ft Collins CO 80523 USA Univ Guelph Sch Comp Sci Guelph ON N1G 2W1 Canada Colorado State Univ Dept Stat Ft Collins CO 80523 USA

Discrete event simulations (DES) provide a powerful means for modeling complex systems and analyzing their behavior. DES capture all possible interactions between the entities they manage, which makes them highly expressive but also compute-intensive. These computational requirements often impose limitations on the breadth and/or depth of research that can be conducted with a discrete event simulation. This work describes our approach for leveraging the vast quantity of computing and storage resources available in both private organizations and public clouds to enable real-time exploration of discrete event simulations. Rather than directly targeting simulation execution speeds, we autonomously generate and execute novel scenario variants to explore a representative subset of the simulation parameter space. The corresponding outputs from this process are analyzed and used by our framework to produce models that accurately forecast simulation outcomes in real time, providing interactive feedback and facilitating exploratory research. Our framework distributes the workloads associated with generating and executing scenario variants across a range of commodity hardware, including public and private cloud resources. Once the models have been created, we evaluate their performance and improve prediction accuracy by employing dimensionality reduction techniques and ensemble methods. To make these models highly accessible, we provide a user-friendly interface that allows modelers and epidemiologists to modify simulation parameters and see projected outcomes in real time. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Discrete event simulation Latin Hypercube Sampling distributed execution Cloud infrastructure

来源：评论

学校读者我要写书评

暂无评论

Fractional factorial design for parameter sweep experiments using Nimrod/E

引用

SCIENTIFIC PROGRAMMING 2008年第2-3期16卷 217-230页

作者： Peachey, T. C. Diamond, N. T. Abramson, D. A. Sudholt, W. Michailova, A. Amirriazi, S. Monash Univ Clayton Vic 3800 Australia Univ Zurich Inst Organ Chem CH-8057 Zurich Switzerland Univ Calif San Diego Dept Bioengn La Jolla CA 92093 USA San Diego Supercomp Ctr La Jolla CA USA

The techniques of formal experimental design and analysis are powerful tools for scientists and engineers. However, these techniques are currently underused for experiments conducted with computer models. This has motivated the incorporation of experimental design functionality into the Nimrod tool chain. Nimrod has been extensively used for exploration of the response of models to their input parameters;the addition of experimental design tools will combine the efficiency of carefully designed experiments with the power of distributed execution. This paper describes the incorporation of one type of design, the fractional factorial design, and associated analysis tools, into the Nimrod framework. The result provides a convenient environment that automates the design of an experiment, the execution of the jobs on a computational grid and the return of results, and which assists in the interpretation of those results. Several case studies are included which demonstrate various aspects of this approach.

关键词： Experimental design computer models distributed execution

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Concurrency for High Performance Computing

引用

ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 2017年第4期14卷 1–26页

作者： Matheou, George Evripidou, Paraskevas Univ Cyprus Nicosia Cyprus

In this work, we utilize dynamic dataflow/data-driven techniques to improve the performance of high performance computing (HPC) systems. The proposed techniques are implemented and evaluated through an efficient, portable, and robust programming framework that enables data-driven concurrency on HPC systems. The proposed framework is based on data-driven multithreading (DDM), a hybrid control-flow/dataflow model that schedules threads based on data availability on sequential processors. The proposed framework was evaluated using several benchmarks, with different characteristics, on two different systems: a 4-node AMD system with a total of 128 cores and a 64-node Intel HPC system with a total of 768 cores. The performance evaluation shows that the proposed framework scales well and tolerates scheduling overheads and memory latencies effectively. We also compare our framework to MPI, DDM-VM, and OmpSs@Cluster. The comparison results show that the proposed framework obtains comparable or better performance.

关键词： Data-driven multithreading distributed execution runtime system high performance computing

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of distributed object collection for web indexing

引用

COMPUTER COMMUNICATIONS 2000年第4期23卷 411-417页

作者： Jin, JS Kurniawati, R Univ New S Wales Sch Engn & Comp Sci Sydney NSW 2052 Australia

We propose a scheme for mobile and distributed objects collection over the World Wide Web. Using the approach, we can deploy a collector easily on the site being indexed. This and the availability of Java virtual machines virtually everywhere make finer grained task distribution possible compared to other approaches. We then develop a mathematical model for data transfer time using HTTP. We conclude that the proposed collector will do better in terms of total transfer time compared to a centralized collector, provided that we have a reasonable compression ratio (less than 80%) and the round-trip time is relatively big (above 100 ms). (C) 2000 Elsevier Science B.V. All rights reserved.

关键词： www spiders/robots distributed execution multimedia/image databases

来源：评论

学校读者我要写书评

暂无评论

Computation Offloading in Resource-Constrained Multi-Access Edge Computing

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第11期23卷 10665-10677页

作者： Li, Kexin Wang, Xingwei He, Qiang Wang, Jielei Li, Jie Zhan, Siyu Lu, Guoming Dustdar, Schahram Univ Elect Sci & Technol China Lab Intelligent Collaborat Comp Chengdu 611731 Peoples R China Trusted Cloud Comp & Big Data Key Lab Sichuan Prov Chengdu 611731 Peoples R China Northeastern Univ Coll Comp Sci & Engn Shenyang 110819 Peoples R China Northeastern Univ Coll Med & Biol Informat Engn Shenyang 110169 Peoples R China Hubei Univ Coll Comp Sci & Informat Engn Wuhan 430062 Peoples R China TU Wien Distributed Syst Grp A-1040 Vienna Austria

Recently, computation offloading methods have greatly improved the Quality of Experience (QoE) in Multi-access Edge Computing (MEC) by offloading tasks to the edge servers. Since well-coordinated actions of Terminal Devices (TDs) are critical to improving the performance of the entire individual system, many practical MEC-based applications, i.e., firefighting robots and unmanned aerial vehicles, require great teamwork among TDs. However, real-world scenarios are usually bound by resource conditions. For instance, network connectivity may weaken or experience interruptions during emergency situations. In cases where the communication medium is utilized by multiple TDs, achieving effective coordination poses a significant challenge. In this paper, we propose a computation offloading scheme based on Scheduled Multi-agent Deep Reinforcement Learning (SMDRL) to make the most efficient decision in a resource-constrained scenario. First, we design a virtual energy queue based on the MEC system and maximize the QoE (related to service delay and energy consumption) in a real-time manner. Subsequently, we propose a scheduled multi-agent deep reinforcement learning algorithm to support each TD in learning how to encode messages, select actions, and schedule itself based on the received messages. Furthermore, a TopK mechanism is introduced. This mechanism chooses the most crucial TDs to broadcast their messages, and then the computation offloading problem in a communication-constrained MEC environment can be solved in a low-communication manner. Also, we prove that even under limited communication conditions, our proposed methods can still lead to the close-to-optimal performance. The final performance analysis shows that the developed scheme has significant advantages over other representative schemes.

关键词： Multi-access edge computing task offloading distributed execution distributed execution resources constrained resources constrained deep reinforcement learning deep reinforcement learning resources constrained deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HiSCA: Overcoming the Limitation of Clustered Unicore Processors Through Hardware/Software Codesign

引用

CHINESE JOURNAL OF ELECTRONICS 2012年第3期21卷 439-444页

作者： Chen Hu Chen Shuming Chen Xiaowen Liu Sheng Natl Univ Def Technol Comp Sch Changsha 410073 Hunan Peoples R China

The partitioning of resources such as pipelines and register files among clusters has been proven to be an effective way to improve performance and scalability. However, improvements are limited by traditional binary instruction encoding schemes and centralized instruction execution control mechanism. Meanwhile, clustered processors may come at the cost of performance degradation due to limited data locality resulted from a lack of available registers and functional units. This paper introduces a Highly scalable clustered architecture (HiSCA) to improve the scalability and performance of clustered processors. The hardware/software instruction encoding scheme of HiSCA splits the instruction stream into chains of instructions (packs) and encodes common information within the same packs in dedicated instruction words, thus reducing the amount of information encoded in instruction words. The pipeline of HiSCA, which features in-order issuing, out-of-order execution and parallel but in-order commitment, release instruction issuing from the heavy burden of dynamic scheduling, and allows functional units to fetch data and manage their own execution. HiSCA scales efficiently to 32 clusters with 1024 general purpose registers. Experimental results also show that, for a 4-cluster/8-issue configuration, HiSCA can achieve an average of 13.3% performance speedup and a 4.6% improvement in frequency with minimal hardware overhead, as compared to a traditional clustered processor with nearly the same hardware complexity.

关键词： Clustered architecture Instruction encoding Instruction distribution distributed execution Inter-cluster communication

来源：评论

学校读者我要写书评

暂无评论

A fine-grained modality classification for global predicates

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2003年第8期14卷 807-816页

作者： Kshemkalyani, AD Univ Illinois Dept Comp Sci Chicago IL 60607 USA

Specifying and detecting predicates in a distributed execution is an important problem. distributed execution observation has classically used two modalwities-Possibly(phi) and Definitely(o)-for predicate phi. Based on the temporal interactions of intervals, the author identified a complete, orthogonal set of relationships R between pairs of intervals in a distributed execution. This paper shows how to map the rich, orthogonal classification of modalities of pairwise interval interactions, to the classical coarse-grained classification, Possibly(o) and Definitely(o), for specifying predicates defined on any number of processes. This increases the power of expressing the temporal modalities under which predicates can be specified, beyond the current PossiblylDefinitely classification. This paper also gives timestamp-based tests for the orthogonal modalities in the refined classification.

关键词： predicates causality synchronization distributed execution distributed system global state

来源：评论

学校读者我要写书评

暂无评论

distributed WWW programming using (Ciao-)Prolog and the PiLLoW library

引用

THEORY AND PRACTICE OF LOGIC PROGRAMMING 2001年第3期1卷 251-282页

作者： Cabeza, D Hermenegildo, M Univ Politecn Madrid CLIP Grp Fac Informat E-28660 Madrid Spain

We discuss from a practical point of view a number of issues involved in writing distributed Internet and WWW applications using LP/CLP systems. We describe PiLLoW, a public-domain Internet and WWW programming library for LP/CLP systems that we have designed to simplify the process of writing such applications. PiLLoW provides facilities for accessing documents and code on the WWW;parsing, manipulating and generating HTML and XML structured documents and data;producing HTML forms;writing form handlers and CGI-scripts;and processing HTML/XML templates. An important contribution of PiLLoW is to model HTML/XML code (and, thus, the content of WWW pages) as terms. The PiLLoW library has been developed in the context of the Ciao Prolog system, but it has been adapted to a number of popular LP/CLP systems, supporting most of its functionality. We also describe the use of concurrency and a high-level model of client-server interaction, Ciao Prolog's active modules, in the context of WWW programming. We propose a solution for client-side downloading and execution of Prolog code, using generic browsers. Finally, we also provide an overview of related work on the topic.

关键词： WWW HTML XML CGI HTTP distributed execution (Constraint) Logic Programming

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：