检索结果-内蒙古大学图书馆

Dynamic energy-aware scheduling for parallel task-based application in cloud computing

FUTURE GENERATION COMPUTER systems-THE INTERNATIONAL JOURNAL OF ESCIENCE 2018年第Part1期78卷 257-271页

作者： Juarez, Fredy Ejarque, Jorge Badia, Rosa M. BSC Workflows & Distributed Comp Grp Barcelona 08034 Spain Inst Tecnol Super Alamo Temapache Xoyotitla 92730 Veracruz Mexico CSIC Artificial Intelligence Res Inst IIIA Madrid Spain

Green Computing is a recent trend in computer science, which tries to reduce the energy consumption and carbon footprint produced by computers on distributed platforms Such as clusters, grids, and clouds. Traditional scheduling solutions attempt to minimize processing times without taking into account the energetic cost. One of the methods for reducing energy consumption is providing scheduling policies in order to allocate tasks on specific resources that impact over the processing times and energy consumption. In this paper, we propose a real-time dynamic scheduling system to execute efficiently task based applications on distributed computing platforms in order to minimize the energy consumption. Scheduling tasks on multiprocessors is a well known NP-hard problem and optimal solution of these problems is not feasible, we present a polynomial-time algorithm that combines a set of heuristic rules and a resource allocation technique in order to get good solutions on an affordable time scale. The proposed algorithm minimizes a multi-objective function which combines the energy-consumption and execution time according to the energy-performance importance factor provided by the resource provider or user, also taking into account sequence-dependent setup times between tasks, setup times and down times for virtual machines (VM) and energy profiles for different architectures. A prototype implementation of the scheduler has been tested with different kinds of DAG generated at random as well as on real task-based COMPSs applications. We have tested the system with different size instances and importance factors, and we have evaluated which combination provides a better solution and energy savings. Moreover, we have also evaluated the introduced overhead by measuring the time for getting the scheduling solutions for a different number of tasks, kinds of DAG, and resources, concluding that our method is suitable for run-time scheduling. (C) 2016 Elsevier B.V. All rights rese

关键词： distributed computing Cloud computing Green computing Task-based applications Energy-aware scheduling Multi-heuristic resource allocation

来源：评论

学校读者我要写书评

暂无评论

Coded matrix multiplication on a group-based model

arXiv

引用

arXiv 2019年

作者： Kim, Muah Sohn, Jy-yong Moon, Jaekyun School of Electrical Engineering KAIST Daejeon Korea Republic of

Coded distributed computing has been considered as a promising technique which makes large-scale systems robust to the "straggler" workers. Yet, practical system models for distributed computing have not been available that reflect the clustered or grouped structure of real-world computing servers. Neither the large variations in the computing power and bandwidth capabilities across different servers have been properly modeled. We suggest a group-based model to reflect practical conditions and develop an appropriate coding scheme for this model. The suggested code, called group code, employs parallel encoding for each group. We show that the suggested coding scheme can asymptotically achieve optimal computing time in regimes of infinite n, the number of workers. While theoretical analysis is conducted in the asymptotic regime, numerical results also show that the suggested scheme achieves near-optimal computing time for any finite but reasonably large n. Moreover, we demonstrate that the decoding complexity of the suggested scheme is significantly reduced by the virtue of parallel decoding. Copyright © 2019, The Authors. All rights reserved.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Automated Analysis of Task-parallel Execution Behavior via Artificial Neural Networks 32

Automated Analysis of Task-Parallel Execution Behavior via A...

引用

27th International Heterogeneity in Computing workshop in conjunction with 32nd IEEE International parallel and distributed Processing Symposium (IPDPS)

作者： Neill, Richard Drebes, Andi Pop, Antoniu Univ Manchester Sch Comp Sci Manchester Lancs England

ISBN: (纸本)9781538655559

We present an automated analysis technique that leverages artificial neural networks to identify possible causes for sub-optimal execution of task-parallel programs. Performance anomalies in task-parallel programs are often extremely difficult to analyze due to the complexity of the interactions between dynamic runtime systems and hardware. While Hardware Performance Monitoring is a common technique to capture hardware behavior, understanding how the resulting hardware event profiling data relates to task performance is often non-trivial and time-consuming. In this work, we present an automated technique for task-parallel performance analysis that identifies the hardware behaviors that have the greatest impact on task performance. Our technique uses artificial neural networks to model these relationships, allowing for isolation of the specific hardware events that have the most impact to slow down task execution. We show that our technique provides new insights into task-parallel execution behavior, allowing for acceleration of the performance optimization process.

关键词： Task analysis Hardware Monitoring Neural networks Neurons Predictive models Machine learning"

来源：评论

学校读者我要写书评

暂无评论

Resources Co-Allocation Optimization Algorithms for distributed Computing Environments 18

Resources Co-Allocation Optimization Algorithms for Distribu...

引用

47th International Conference on parallel Processing (ICPP) / International workshop on Embedded Multicore systems (EMS)

作者： Toporkov, Victor Yemelyanov, Dmitry Natl Res Univ Moscow Power Engn Inst Moscow Russia

ISBN: (纸本)9781450365239

In this work, we introduce slot selection and co-allocation algorithms for parallel jobs in distributed computing with non-dedicated and heterogeneous resources (clusters, CPU nodes equipped with multicore processors, networks etc.). A single slot is a time span that can be assigned to a task, which is a part of a parallel job. The job launch requires a co-allocation of a specified number of slots starting and finishing synchronously. The challenge is that slots associated with different heterogeneous resources of distributed computing environments may have arbitrary start and finish points, different performance, latency, pricing policies. Some existing algorithms assign a job to the first set of slots matching the resource request without any optimization (the first fit type), while other algorithms are based on an exhaustive search. In this paper, algorithms for efficient slot selection are studied and compared with known approaches. The novelty of the proposed approach is in a general algorithm selecting a set of slots efficiently according to the specified criterion.

关键词： Scheduling distributed Computing Resources Co-allocation Optimization Slot Job Window

来源：评论

学校读者我要写书评

暂无评论

parallel Algorithm for Incremental Betweenness Centrality on Large Graphs

引用

IEEE TRANSACTIONS ON parallel AND distributed systems 2018年第3期29卷 659-672页

作者： Jamour, Fuad Skiadopoulos, Spiros Kalnis, Panos KAUST Thuwal 23955 Saudi Arabia Univ Peloponnese Tripoli 22100 Greece

Betweenness centrality quantifies the importance of nodes in a graph in many applications, including network analysis, community detection and identification of influential users. Typically, graphs in such applications evolve over time. Thus, the computation of betweenness centrality should be performed incrementally. This is challenging because updating even a single edge may trigger the computation of all-pairs shortest paths in the entire graph. Existing approaches cannot scale to large graphs: they either require excessive memory (i.e., quadratic to the size of the input graph) or perform unnecessary computations rendering them prohibitively slow. We propose iCENTRAL;a novel incremental algorithm for computing betweenness centrality in evolving graphs. We decompose the graph into biconnected components and prove that processing can be localized within the affected components. iCENTRAL is the first algorithm to support incremental betweeness centrality computation within a graph component. This is done efficiently, in linear space;consequently, iCENTRAL scales to large graphs. We demonstrate with real datasets that the serial implementation of iCENTRAL is up to 3.7 times faster than existing serial methods. Our parallel implementation that scales to large graphs, is an order of magnitude faster than the state-of-the-art parallel algorithm, while using an order of magnitude less computational resources.

关键词： Betweenness centrality dynamic graph algorithms parallel graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation of an Operational Transformation Algorithm using Finite State Machines 12

Modeling and Simulation of an Operational Transformation Alg...

引用

12th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI)

作者： Gadea, Cristian Ionescu, Bogdan Ionescu, Dan Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON Canada

ISBN: (纸本)9781538646403

Although the principles of real-time collaborative editing have been explored since the eighties, team collaboration software facilitating the completion of tasks as a group continues to be a very hot research topic. A series of theoretical and practical results obtained by the research and industrial communities originated in the theory of distributed computing. They were devised for managing the concurrent nature of user actions and for maintaining the consistency of data as changes are introduced randomly, by multiple users and in real-time. As such, centralized collaborative editing servers were designed to allow users to work in parallel on a document from a typical web browser. In order to maintain the consistency of the content being modified at different sites in different orders, Operational Transformation (OT) mechanisms are at the core of collaboration servers enabling web-based co-editing. However, as expected of modern web application deployments, a centralized OT algorithm is required that must also exhibit properties such as scalability and reliability. In this paper, the processes involved in the client-server interactions of OT are modeled as real-time systems using Finite State Machine (FSM) theory. The consistency of the data is controlled by formal groups of FSMs. Hierarchical FSMs are used to define and simulate the real-time behavior of client and server components when processing and transforming changes initiated by users. The FSM-based OT implementation is tested using random inputs and the approach is shown to be helpful for organizing and managing the complex distributed aspects of such algorithms.

关键词： Collaborative Software Platforms distributed Computing systems Consistency and Concurrency Finite State Machines real-time systems

来源：评论

学校读者我要写书评

暂无评论

On-the-Fly Olive Tree Counting Using a UAS and Cloud Services

引用

REMOTE SENSING 2019年第3期11卷 316-316页

作者： Salami, Esther Gallardo, Antonia Skorobogatov, Georgy Barrado, Cristina UPC BarcelonaTECH Comp Architecture Dept Esteve Terrades 7 Castelldefels 08860 Spain

Unmanned aerial systems (UAS) are becoming a common tool for aerial sensing applications. Nevertheless, sensed data need further processing before becoming useful information. This processing requires large computing power and time before delivery. In this paper, we present a parallel architecture that includes an unmanned aerial vehicle (UAV), a small embedded computer on board, a communication link to the Internet, and a cloud service with the aim to provide useful real-time information directly to the end-users. The potential of parallelism as a solution in remote sensing has not been addressed for a distributed architecture that includes the UAV processors. The architecture is demonstrated for a specific problem: the counting of olive trees in a crop field where the trees are regularly spaced from each other. During the flight, the embedded computer is able to process individual images on board the UAV and provide the total count. The tree counting algorithm obtains an F-1 score of 99.09% for a sequence of ten images with 332 olive trees. The detected trees are geolocated and can be visualized on the Internet seconds after the take-off of the flight, with no further processing required. This is a use case to demonstrate near real-time results obtained from UAS usage. Other more complex UAS applications, such as tree inventories, search and rescue, fire detection, or stock breeding, can potentially benefit from this architecture and obtain faster outcomes, accessible while the UAV is still on flight.

关键词： UAS UAV image segmentation tree counting distributed services cloud computing

来源：评论

学校读者我要写书评

暂无评论

Data distribution service based distributed system test approach 12

Data distribution service based distributed system test appr...

引用

12th Turkish National Software Engineering Symposium, UYMS 2018

作者： Artaç, Saniye Asena Koyuncu, İlker Hatip Ipek, Aylin ROKETSAN A.Ş Turkey ROKETSAN A.Ş Turkey ROKETSAN A.Ş Turkey

The needs for fast and efficient data communication has been progressively bringing original and agile design needs of the developed systems today. As the scope and capability of the system increases, the need for rapid, accurate and real-time data sharing of a large number of hardware and software components in the environment arises. Data Distribution Service (DDS) technology is a middleware standard that has been used in the development of distributed systems and has become popular in many sectors in recent years. In this paper, the test approach applied to a DDS based system is discussed. This study, which we call "Data Distribution Based distributed System Test Aprroach", presents a flexible and expandable test infrastructure with the ability of dynamic environment recognition provided by DDS. In addition, the life cycle stages of the related system are designed as model based, and software test analysis and test design phases are also prepared in model based. In this study, it will presents a hybrid analysis that reliably delivering data communication by reducing efforts especially in distributed and real-time systems.

关键词： real time systems

来源：评论

学校读者我要写书评

暂无评论

real-time signal processing for sub-THz range grating-based distributed fiber sensing

Real-time signal processing for sub-THz range grating-based ...

引用

Conference on Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace systems

作者： Yao, Zheyi Hefferman, Gerald Ren, Kan Wei, Tao Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA Brown Univ Warren Alpert Med Sch Providence RI 02912 USA Nanjing Univ Sci & Technol Nanjing 210094 Jiangsu Peoples R China

ISBN: (数字)9781510616936

ISBN: (纸本)9781510616936

distributed optical fiber sensors are an increasingly utilized method of gathering distributed strain and temperature data. However, the large amount of data they generate present a challenge that limits their use in real-time, in-situ applications. This letter describes a parallel and pipelined computing architecture that accelerates the signal-processing speed of sub-terahertz fiber sensor (sub-THz-fs) arrays, maintaining high spatial resolution while allowing for expanded use for real-time sensing and control applications. The computing architecture described was successfully implemented in a field programmable gate array (FPGA) chip. The signal processing for the entire array takes only 12 system clock cycles. In addition, this design removes the necessity of storing any raw or intermediate data.

关键词： Fiber sensor

来源：评论

学校读者我要写书评

暂无评论

ON-DEVICE END-TO-END SPEECH RECOGNITION WITH MULTI-STEP parallel RNNS

ON-DEVICE END-TO-END SPEECH RECOGNITION WITH MULTI-STEP PARA...

引用

IEEE workshop on Spoken Language Technology (SLT)

作者： Boo, Yoonho Park, Jinhwan Lee, Lukas Sung, Wonyong Seoul Natl Univ Dept Elect & Comp Engn Seoul 08826 South Korea

ISBN: (纸本)9781538643341

Most of the current automatic speech recognition is performed on a remote server. However, the demand for speech recognition on personal devices is increasing, owing to the requirement of shorter recognition latency and increased privacy. End-to-end speech recognition that employs recurrent neural networks (RNNs) shows good accuracy, but the execution of conventional RNNs, such as the long short-term memory (LSTM) or gated recurrent unit (GRU), demands many memory accesses, thus hindering its real-time execution on smart-phones or embedded systems. To solve this problem, we built an end-to-end acoustic model (AM) using linear recurrent units instead of LSTM or GRU and employed a multi-step parallel approach for reducing the number of DRAM accesses. The AM is trained with the connectionist temporal classification (CTC) loss, and the decoding is conducted using weighted finite-state transducers (WFSTs). The proposed system achieves x4.8 real-time speed when executed on a single core of an ARM CPU-based system.

关键词： End-to-end speech recognition multi-step parallel RNN personal devices

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：