检索结果-内蒙古大学图书馆

international symposium on parallel and distributed Computing

作者： Anna Sasak-Okoń Marek Tudruj University of Maria Curie-Skłodowska Lublin Poland Polish-Japanese Academy of Information Technology Institute of Computer Science Polish Academy of Sciences Warsaw Poland

ISBN: (数字)9781728189468

ISBN: (纸本)9781728189475

The paper is concerned with the methodology for speculative query execution support in distributed Relational Database Management systems (RDBMS). The proposed approach is based on the analysis of the multigraph representations of the stream of input queries arriving to a RDBMS. As a result, the optimized set of speculative queries is found to support execution of current queries. The speculative query results are used to speed-up execution of the query input stream. The paper presents how the proposed speculative query execution approach can be implemented inside a novel distributed program design framework PEGASUS DA in which program execution decisions are taken based on the system-supported monitoring of the distributed application global states. The paper shows the architecture of the speculative support provided by such framework for the distributed RDBMS and the assumed speculation approach. The implementation issues of the multithreaded distributed support based on the RDBMS SQLite engines are discussed. distributed data synchronization and speculative query execution strategy as well as speculation results distribution are discussed. The proposed approach to distributed implementation of the speculative support to RDBMSs using the PEGASUS DA framework is illustrated on the example of the modifying query handling in a RDBMS facing the presented speculative query support for query execution.

关键词： Monitoring Synchronization Process control Relational databases Computer architecture distributed databases

来源：评论

学校读者我要写书评

暂无评论

The Coming Age of Pervasive Data Processing 18

The Coming Age of Pervasive Data Processing

引用

18th international symposium on parallel and distributed Computing (ISPDC)

作者： Rellermeyer, Jan S. Khorasani, Sobhan Omranian Graur, Dan Parthasarathy, Apourva Delft Univ Technol Distributed Syst Grp Delft Netherlands

ISBN: (纸本)9781728138015

Emerging Big Data analytics and machine learning applications require a significant amount of computational power. While there exists a plethora of large-scale data processing frameworks which thrive in handling the various complexities of data-intensive workloads, the ever-increasing demand of applications have made us reconsider the traditional ways of scaling (e.g., scale-out) and seek new opportunities for improving the performance. In order to prepare for an era where data collection and processing occur on a wide range of devices, from powerful HPC machines to small embedded devices, it is crucial to investigate and eliminate the potential sources of inefficiency in the current state of the art platforms. In this paper, we address the current and upcoming challenges of pervasive data processing and present directions for designing the next generation of large-scale data processing systems.

关键词： Big Data Machine Learning systems Performance Efficiency

来源：评论

学校读者我要写书评

暂无评论

12th international symposium on NASA Formal Methods, NFM 2020

12th International Symposium on NASA Formal Methods, NFM 202...

引用

12th international symposium on NASA Formal Methods, NFM 2020

ISBN: (纸本)9783030557539

The proceedings contain 25 papers. The special focus in this conference is on NASA Formal Methods. The topics include: Specification Quality Metrics Based on Mutation and Inductive Incremental Model Checking;formal Verification of parallel Prefix Sum;from Passive to Active: Learning Timed Automata Efficiently;benchmarking Software Model Checkers on Automotive Code;Strengthening Deterministic Policies for POMDPs;paRoT: A Practical Framework for Robust Deep Neural Network Training;parameter Synthesis and Robustness Analysis of Rule-Based Models;falsification of Cyber-Physical systems with Constrained Signal Spaces;a Transformation of Hybrid Petri Nets with Stochastic Firings into a Subclass of Stochastic Hybrid Automata;run-Time Assurance for Learning-Enabled systems;heterogeneous Verification of an Autonomous Curiosity Rover;generating Correct-by-Construction distributed Implementations from Formal Maude Designs;verifying Band Convergence for Sampled Control systems;model Checking Timed Hyperproperties in Discrete-Time systems;sampling distributed Schedulers for Resilient Space Communication;per-Location Simulation;preface;automated Requirements-Based Testing of Black-Box Reactive systems;neural Simplex Architecture;simplifying Neural Networks Using Formal Verification;constraining Counterexamples in Hybrid System Falsification: Penalty-Based Approaches;hpnmg: A C++ Tool for Model Checking Hybrid Petri Nets with General Transitions;constraint Caching Revisited.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Error-Reflective Consistency Model for distributed Data Stores 33

An Error-Reflective Consistency Model for Distributed Data S...

引用

33rd IEEE international parallel and distributed Processing symposium (IPDPS)

作者： Dexter, Philip Chiu, Kenneth Sendir, Bedri SUNY Binghamton Binghamton NY 13902 USA IBM Res Austin TX USA

ISBN: (纸本)9781728112466

Consistency models for distributed data stores offer insights and paths to reasoning about what a user of such a system can expect. However, often consistency models are defined or implemented in coarse-grained manners, making it difficult to achieve precisely the consistency required. Further, many domains are already written to handle anomalies in distributed systems, yet they have little opportunity for expressing or taking advantage of their leniency. We propose reflective consistency an active solution which adapts an underlying data store to changing loads and resource availability to meet a given consistency level. We implement reflective consistency in Cassandra, an existing distributed data store supporting per-read and per-write consistency. Our implementation allows users to express their anomaly leniency directly and the system will react to the presence of anomalies, changing Cassandra's consistency only when needed. Users of Reflective Cassandra can expect minimal overhead (anywhere from 1% to 14% depending on configuration) and a 50% decrease in the amount of costly strong reads.

关键词： distributed computing Database systems

来源：评论

学校读者我要写书评

暂无评论

distributed dispatching in the parallel server model 34

Distributed dispatching in the parallel server model

引用

34th international symposium on distributed Computing, DISC 2020

作者： Goren, Guy Vargaftik, Shay Moses, Yoram Technion - Israel Institute of Technology Haifa Israel VMware Research

ISBN: (纸本)9783959771689

With the rapid increase in the size and volume of cloud services and data centers, architectures with multiple job dispatchers are quickly becoming the norm. Load balancing is a key element of such systems. Nevertheless, current solutions to load balancing in such systems admit a paradoxical behavior in which more accurate information regarding server queue lengths degrades performance due to herding and detrimental incast effects. Indeed, both in theory and in practice, there is a common doubt regarding the value of information in the context of multi-dispatcher load balancing. As a result, both researchers and system designers resort to more straightforward solutions, such as the power-of-two-choices to avoid worst-case scenarios, potentially sacrificing overall resource utilization and system performance. A principal focus of our investigation concerns the value of information about queue lengths in the multi-dispatcher setting. We argue that, at its core, load balancing with multiple dispatchers is a distributed computing task. In that light, we propose a new job dispatching approach, called Tidal Water Filling, which addresses the distributed nature of the system. Specifically, by incorporating the existence of other dispatchers into the decision-making process, our protocols outperform previous solutions in many scenarios. In particular, when the dispatchers have complete and accurate information regarding the server queue lengths, our policies significantly outperform all existing solutions. © Guy Goren, Shay Vargaftik, and Yoram Moses;licensed under Creative Commons License CC-BY 34th international symposium on distributed Computing (DISC 2020).

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

DeStager: feature guided in-situ data management in distributed deep memory hierarchies

引用

distributed AND parallel databases 2019年第1期37卷 209-231页

作者： Zhang, Xuechen Zheng, Fang Bao Nguyen Washington State Univ Sch Engn & Comp Sci Vancouver WA 98686 USA IBM TJ Watson Res Ctr New York NY USA

In-situ analytics have been increasingly adopted by leadership scientific applications to gain fast insights into massive output data of simulations. With the current practice, systems buffer the output data in DRAM for analytics processing, constraining it to DRAM capacity un-used by the simulation. The rapid growth of data size requires alternative approaches to accommodating data-rich analytics, such as using solid-state disks to increase effective memory capacity. For this purpose, this paper explores software solutions for exploring the deep memory hierarchies expected on future high-end machines. Leveraging the fact that many analytics are sensitive to data features (regions-of-interest) hidden in the data being processed, the approach incorporates the knowledge of the data features into in-situ data management. It uses adaptive index creation/refinement to reduce the overhead of index management. In addition, it uses data features to predict data skew and improve load balance through controlling data distribution and placement on distributed staging servers. The experimental results show that such feature-guided optimizations achieve substantial improvements over state-of-the-art approaches for managing output data in-situ.

关键词： Indexing R-tree Octree In-situ Analytics SSDs

来源：评论

学校读者我要写书评

暂无评论

Performance Comparision of TPU, GPU, CPU on Google Colaboratory Over distributed Deep Learning

Performance Comparision of TPU, GPU, CPU on Google Colaborat...

引用

IEEE international symposium on Embedded Multicore Socs (MCSoC)

作者： Haklin Kimm Incheon Paik Hanke Kimm East Stroudsburg University East Stroudsburg PA USA School of Computer Science and Engineering University of Aizu Aizu-Wakamatsu City Fukushima Japan Stony Brook University Stony Brook NY USA

ISBN: (纸本)9781728187525

Deep Learning models need massive amounts compute powers and tend to improve performance running on special purpose processors accelerators designed to speed up compute-intensive applications. The accelerators like Tensor Processing Units (TPUs) and Graphics Processing Units (GPUs) are widely used as deep learning hardware platforms which can often achieve better performance than CPUs, with their massive parallel execution resources and high memory bandwidth. Google Colaboratory known as Colab is a cloud service based on Jupyter Notebook that allows the users to write and execute mostly Python in a browser and admits free access to TPUs and GPUs without extra configuration need, which are widely available cloud hardware platforms. In this paper, we present a through comparison of the hardware platforms on Google Colab that is benchmarked with distributed Bidirectional Long Short-Term Memory (dBLSTM) models upon the number of layers, the number of units each layer, and the numbers of input and output units the datasets. Human Activity Recognition (HAR) data from UCI machine-learning library have been applied to the proposed distributed bidirectional LSTM model to find the performance, strengths, bottlenecks of the hardware platforms of TPU, GPU and CPU upon hyperparameters, execution time, and evaluation metrics: accuracy, precision, recall and F1 score.

关键词： Deep learning Measurement Training Runtime Tensors Graphics processing units Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Extending the Concept of Voting Structures to Support Path-Based Replication Strategies

Extending the Concept of Voting Structures to Support Path-B...

引用

Pacific Rim international symposium on Dependable Computing

作者： Christian Linder Oliver Theel Carl von Ossietzky University Oldenburg Germany

ISBN: (纸本)9781665424776

Data replication is an important concept in distributed computing to provide fault-tolerant, highly available, and low cost data access operations, since a unique master copy can fail. Although the field of data replication is very well researched, the question of application-optimized replication strategies for specific scenarios still stands. There are many scenarios which cannot be satisfactorily managed by known replication strategies. Recent research has proposed the use of voting structures for generating new replication strategies from known ones, such that a wide range of scenarios can be addressed. However, unfortunately, voting structures cannot represent path-based replication strategies in an intuitive way. But path-based replication strategies have been proven to be very flexible and efficient in providing low operation costs and high availabilities. Thus, some very good characteristics cannot yet be covered by the above-sketched approach. In this paper, we present an extension to the concept of voting structures that allows the design of path-based replication strategies in an easy and intuitive way. Furthermore, we introduce a general design pattern that transforms each path-based replication strategy, given by a grid structure, to an efficient equivalent voting structure of the extended concept. The proposed approach is proven as well as its use demonstrated.

关键词： Fault tolerance Costs Fault tolerant systems distributed databases Transforms

来源：评论

学校读者我要写书评

暂无评论

An Improved parallel Strategy for Auxiliary Inverter without Control Interconnection in Metro Applications 10

An Improved Parallel Strategy for Auxiliary Inverter without...

引用

IEEE 10th international symposium on Power Electronics for distributed Generation systems (PEDG)

作者： Xu, Mingxia Wang, Zhiqiang Che, Xiangzhong Wang, Ninghui Dalian Univ Technol Sch Elect Engn Dalian Peoples R China CRRC Dalian R&D CO LTD Technol Ctr Dalian Peoples R China

ISBN: (纸本)9781728124551

This paper proposes an improved parallel control strategy which suits for the auxiliary inverter under different working conditions in metro. Firstly, differential droop coefficient and virtual impedance are introduced to improve the stability and dynamic response of the system. Meanwhile, the proportional-resonant control is introduced to enhance the ability of the auxiliary inverter under the sudden load change condition or with the non-linear load. Furthermore, mathematical modeling of the auxiliary inverters is carried out in the system. Finally, the improved droop control, virtual impedance and current resonant control strategies are applied to two paralleled inverters test platform of 120kVA. The experimental results show that the proposed control algorithm can greatly improve the voltage waveform and dynamic response of the parallel inverters, and improve the ability of the system under non-linear loads.

关键词： parallel control virtual impedance auxiliar inverters differential droop coefficient resonant control

来源：评论

学校读者我要写书评

暂无评论

It Can Understand the Logs, Literally 33

It Can Understand the Logs, Literally

引用

33rd IEEE international parallel and distributed Processing symposium (IPDPS)

作者： Pi, Aidi Chen, Wei Zeller, Will Zhou, Xiaobo Univ Colorado Dept Comp Sci Colorado Springs CO 80907 USA

ISBN: (纸本)9781538655559

Workflow reconstruction through logs is crucial for troubleshooting targeted distributed systems. It is also challenging to extract enough information from logs and keep a concise view, which makes manual log analysis hard to practice. However, currently popular tools rely on identifier-based log parsing, leaving a large amount of workflow information unexploited. In this paper, we propose a log extraction approach NLog, which utilizes a natural language processing based approach to obtain the key information from log messages and identify the same object in logs generated by different statements without any domain knowledge. We propose to use keyed message, a new log storage structure to store the parsed logs. We implement NLog and apply it to distributed data analytics frameworks Spark and MapReduce. Evaluation results show that NLog can accurately identify the objects in log messages even without explicit identifiers. By using keyed messages, users can have a concise as well as flexible view of the workflows.

关键词： distributed systems Profiling Information Extraction Troubleshooting

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：