检索结果-内蒙古大学图书馆

A Task-Oriented General-Purpose distributed computing System Based on CLTS Scheduling Algorithm

IEEE ACCESS 2023年 11卷 79176-79189页

作者： Huang, Min Zhao, Yunxiang Chen, Yazhou Army Engn Univ Shijiazhuang Campus Shijiazhuang 050003 Peoples R China Hebei Univ Sci & Technol Shijiazhuang 050018 Peoples R China

Most current research on commonly used distributed computing frameworks neglects the difficulty of learning these frameworks. These commonly used distributed computing frameworks are designed for professionals, and users must understand them well to use them for calculation tasks. In order to solve the challenging balance problem between versatility and user learning difficulty, a new distributed computing system is proposed. The design of this system is based on the idea of divide and conquer in distributed computing. The paper uses Netty, Zookeeper, Hadoop distributed File System (HDFS) and other tools to implement the system functions. Firstly, the paper analyzes the research status of distributed computing frameworks at home and abroad;Then, according to the idea of divide and conquer, the paper uses Netty to implement the basic architecture of the system, uses Zookeeper and Netty to implement relevant distributed mechanisms, uses HDFS as the distributed storage, designs and implements a Task-Oriented General-Purpose (TOGP) distributed computing system, TOGP;Finally, the paper intensely studies the task scheduling problem of the system, proposes a scheduling algorithm, Node Processing Capacity and distributed Lock Task Scheduling (CLTS) algorithm. The system scalability test proves that the TOGP has good horizontal scalability. In the comparative experiment, the processing capacity of the TOGP using the round robin is about 16% higher than that of Hadoop, which proves that the TOGP is available and efficient. A series of experiments prove that the CLTS scheduling algorithm can effectively adapt to the heterogeneous cluster environment and efficiently schedule tasks.

关键词： distributed computing load balance task-oriented task scheduling

来源：评论

学校读者我要写书评

暂无评论

Multi-User Linearly-Separable distributed computing

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2023年第10期69卷 6314-6339页

作者： Khalesi, Ali Elia, Petros EURECOM Commun Syst Dept F-06410 Sophia Antipolis France

In this work, we explore the problem of multi-user linearly-separable distributed computation, whereN servers help compute the desired functions (jobs) of K users, and where each desired function can be written as a linear combination of up to L (generally non-linear) subtasks (or sub-functions). Each server computes some of the subtasks, communicates a function of its computed outputs to some of the users, and then each user collects its received data to recover its desired function. We explore the computation and communication relationship between how many servers compute each subtask vs. how much data each user receives. For a matrix F representing the linearly-separable form of the set of requested functions, our problem becomes equivalent to the open problem of sparse matrix factorization F = DE over finite fields, where a sparse decoding matrix D and encoding matrix E imply reduced communication and computation costs respectively. This paper establishes a novel relationship between our distributed computing problem, matrix factorization, syndrome decoding and covering codes. To reduce the computation cost, the above D is drawn from covering codes or from a here-introduced class of so-called 'partial covering' codes, whose study here yields computation cost results that we present. To then reduce the communication cost, these coding-theoretic properties are explored in the regime of codes that have low-density parity check matrices. The work reveals first for the commonly used one-shot scenario - that in the limit of large N, the optimal normalized computation cost gamma is an element of (0, 1) is in the range gamma is an element of (H-q(-1) ( log(q)(L)/N), H-q(-1) (K/N))- where H-q is the q-ary entropy function- and that this can be achieved with normalized communication cost that vanishes as root log(q)(N)/N. The above reveals an unbounded coding gain over the uncoded scenario, as well as reveals the role of a certain functional rate log(q)(L)/N and functiona

关键词： distributed computing linearly separable functions coding theory sparse matrix factorization covering codes straggler mitigation distributed gradient coding

来源：评论

学校读者我要写书评

暂无评论

On distributed computing: A View, Physical Versus Logical Objects, and a Look at Fully Anonymous Systems 26th

On Distributed Computing: A View, Physical Versus Logical Ob...

引用

26th International Symposium on Stabilization, Safety, and Security of distributed Systems

作者： Raynal, Michel Univ Rennes INRIA CNRS IRISA F-35042 Rennes France

ISBN: (纸本)9783031744976;9783031744983

This article presents a short (and partial) history of synchronization in systems made up of asynchronous sequential processes (automata). Among other points, it shows that synchronization (which consists in ordering operations issued by processes on shared objects) has a different flavor according to the fact that the objects are physical objects (such as a printer or a disk) or logical objects (immaterial objects represented by sequences of bits). It then follows from this physical/logical nature of computing objects that mutual exclusion is to physical objects what consensus is to logical objects. The article also addresses recent results on process synchronization in fully anonymous systems (systems in which processes cannot be distinguished one from the other, and where there is a disagreement on the addresses of the memory registers.

关键词： Agreement Algorithm Anonymity Asynchrony Atomicity Concurrency Consensus distributed computing Informatics Liveness Logical (immaterial) object Memory anonymity Mutual exclusion Parallel computing Process anonymity Physical object Safety Sequential process Sequential specification Synchronization Total order

来源：评论

学校读者我要写书评

暂无评论

Healthcare framework for identification of strokes based on versatile distributed computing and machine learning (jul 2023,10.1007/s00500-023-09002-1)

引用

SOFT computing 2023年第20期27卷 15407-15407页

作者： Xiao, Yineng Liu, Zhao Nanjing Univ Global Intellectual Property Inst Suzhou Peoples R China Peking Univ Adv Inst Informat Technol Hangzhou Peoples R China Univ Chinese Acad Sci Sch Publ Policy & Management Beijing Peoples R China

This paper presents a novel healthcare services framework that leverages versatile distributed computing and mobile cloud computing to enhance the delivery of medical care data. The framework is designed to integrate with diverse cloud settings and distributed computing resources, utilizing a Virtual-Dedicated-Server with 5 VCPU and 32 GB storage of RAM to develop a prototype specifically tailored for stroke patients with cardioembolic and cryptogenic subtypes, using Android-based mobile phones as the primary devices. The proposed framework consists of two fundamental application components: flexible usage and server request. By employing a Convolutional Neural Network (CNN) module, the system effectively distinguishes between the two-stroke subtypes. Simultaneously, the server application securely stores patient data, ensuring accessibility, security, and adaptability for stroke patients. The CNN module performs computations using the Stroke dataset, providing valuable insights into subtype classification. Additionally, the GBRF (Gradient boosting random forest) algorithm has been employed for further analysis and accurate predictive modeling within the healthcare system. The research contributions of this work are significant. Firstly, it introduces a unique healthcare mechanism that harnesses the potential of distributed computing and mobile cloud computing in improving healthcare services. Secondly, the paper verifies the exceptional value of stroke-related data collected through smartphones, underscoring the uniqueness and reliability of such data sources. Lastly, the system enables the provision of health status information to patients through a CNN application programming interface (API), facilitating seamless communication and personalized healthcare services. By integrating machine intelligence based technologies, the framework enhances the efficiency and effectiveness of stroke identification and contributing to the overall well-being of patients in a

关键词： Deep neural networks distributed computing Healthcare Machine learning (ML) Strokes

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Data Management on distributed computing for Digital Healthcare

AI-Driven Data Management on Distributed Computing for Digit...

引用

IEEE International Conference on Pervasive computing and Communications (PerCom)

作者： Akdemir, Bilgehan Univ Oulu Ctr Wireless Commun Networks & Syst CWC NS Oulu Finland

ISBN: (纸本)9798350304367;9798350304374

This research aims to optimize the processing of medical data by developing and implementing an efficient distributed computing platform by leveraging machine learning and edge computing. By doing so, we seek to strike a balance between the computational requirements of machine learning models and the need to process medical data locally in many mobile medical imaging scenarios, thus addressing the challenges posed by volume, privacy, and security.

关键词： distributed computing digital healthcare edge computing federated learning

来源：评论

学校读者我要写书评

暂无评论

Traquest Model 2.0-A Model for Faster ACID distributed computing 21st

Traquest Model 2.0-A Model for Faster ACID Distributed Compu...

引用

21st International Symposium on distributed computing and Artificial Intelligence

作者： Ratai, Daniel B. Horvath, Zoltan Porkolab, Zoltan Toth, Melinda Eotvos Lorand Univ Fac Informat ELTE Budapest Hungary

ISBN: (纸本)9783031809453;9783031809460

The global state of a distributed system is most commonly stored in databases. Databases are responsible for ensuring that the data is available, durable, and correct at some level of consistency. However, this approach has its limitations. The computing nodes responsible for the application tier need to constantly communicate over the network to be able to interact with the global state and this comes with a performance limitation. Our Traquest model concept allows us to manage the data and even provide full ACID properties on the application tier level instead of the database level. In most cases, the data can be stored right next to the computation even in the same runtime environment. Our prototype measurements imply, that in some cases a Traquest model-based distributed system can provide even magnitudes larger throughput than the fastest in-memory databases today. The Traquest model also introduces a workaround for the famous CAP theorem by introducing temporary availability.

关键词： distributed computing ACID transaction fault tolerance CAP theorem

来源：评论

学校读者我要写书评

暂无评论

The topology of randomized symmetry-breaking distributed computing

引用

Journal of Applied and Computational Topology 2024年第4期8卷 909-940页

作者： Fraigniaud, Pierre Gelles, Ran Lotker, Zvi Université Paris Cité and CNRS Paris France Bar-Ilan University Ramat Gan Israel

Studying distributed computing through the lens of algebraic topology has been the source of many significant breakthroughs during the last 2 decades, especially in the design of lower bounds or impossibility results. Despite hundred of results considering deterministic algorithms, none apply to randomized algorithms. This paper aims at studying randomized synchronous distributed computing through the lens of algebraic topology. We do so by studying the wide class of (input-free) symmetry-breaking tasks, e.g., leader election, in synchronous fault-free anonymous systems. We design a topological framework, which allows analyzing such tasks and determining their solvability. The pivotal technical observation is that, unlike in deterministic algorithm, where solvability means that the topological complex describing the protocol can be globally mapped into an output protocol, in our framework the solvability is determined “locally”, i.e., for each simplex of the protocol complex individually, without requiring any global consistency. As an interesting application, we derive necessary and sufficient conditions for solving leader election in shared-memory and message-passing models in which there might be correlations between the randomness provided to the nodes. We find that solvability of leader election relates to the number of parties that possess correlated randomness, either directly or via their greatest common divisor, depending on the specific communication model. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： 68Q85 68W15 Correlated randomness distributed computing Eventual solvability Kolmogorov’s 0-1 law Leader election

来源：评论

学校读者我要写书评

暂无评论

High-Performance distributed computing with Smartphones

High-Performance Distributed Computing with Smartphones

引用

29th International Conference on Parallel and distributed computing (Euro-Par)

作者： Ishikawa, Nadeem Nomura, Hayato Yoda, Yuya Uetsuki, Osamu Fukunaga, Keisuke Nagoya, Seiji Sawara, Junya Ishihata, Hiroaki Senoguchi, Junsuke Tokyo Univ Technol 1404-1 Katakuramachi Hachioji Tokyo Japan ITOCHU Techno Solut Corp Kamiyacho Trust Tower4-1-1ToranomonMinato Ku Tokyo Japan

ISBN: (纸本)9783031488023;9783031488030

The demand for large-scale computing, such as the application of AI in big data analytics and engineering simulations, has been steadily increasing. Meanwhile, many companies and individuals now own smartphones and PCs, but a significant portion of these IT assets remains underutilised, especially overnight or utilised as computing resources. This paper solves these issues by proposing to use these resources in a distributed system. This system highlights the opportunities for cost-effective and resource-efficient high-performance computing(HPC) solutions by utilising underutilised resources. The original distributed computing system framework SMPDG will be described in this paper.

关键词： distributed computing Parallel computing High Performance computing

来源：评论

学校读者我要写书评

暂无评论

An Improved and Efficient distributed computing Framework with Intelligent Task Scheduling 20th

An Improved and Efficient Distributed Computing Framework wi...

引用

20th International Conference on distributed computing and Intelligent Technology (ICDCIT)

作者： Venkatesh, Pruthvi Raj Krishna, P. Radha Natl Inst Technol Dept Comp Sci & Engn Warangal Telangana India

ISBN: (纸本)9783031505829;9783031505836

distributed computing platforms involve multiple processing systems connected through a network and support the parallel execution of applications. They enable huge computational power and data processing with a quick response time. Examples of use cases requiring distributed computing are stream processing, batch processing, and client-server models. Most of these use cases involve tasks executed in a sequence on different computers to arrive at the results. Numerous distributed computing algorithms have been suggested in the literature, focusing on efficiently utilizing compute nodes to handle tasks within a workflow on on-premises setups. Industries that previously relied on on-premises setups for big data processing are shifting to cloud environments offered by providers such as Azure, Amazon, and Google. This transition is driven by the convenience of Platform-as-a-Service offerings scuh as Batch Services, Hadoop, and Spark. These PaaS services, coupled with auto-provisioning and auto-scaling, reduce costs through a Pay-As-You-Go model. However, a significant challenge with cloud services is configuring them with only a single type of machine for performing all the tasks in the distributed workflow, although each task has diverse compute node requirements. To address this issue in this paper, we propose an Intelligent task scheduling framework that uses a classifier-based dynamic task scheduling approach to determine the best available node for each task. The proposed framework improves the overall performance of the distributed computing workflow by optimizing task allocation and utilization of resources. Although Azure Batch Service is used in this paper to illustrate the proposed framework, our approach can also be implemented on other PaaS distributed computing platforms.

关键词： distributed computing Azure Batch Decision Tree PaaS CSP

来源：评论

学校读者我要写书评

暂无评论

Integrating Multi-FPGA Acceleration to OpenMP distributed computing 1

引用

20th International Workshop on OpenMP (IWOMP)

作者： Rosso, Pedro Henrique Petrica, Lucian Lisa, Nusrat Jahan Pereira, Marcio Rigo, Sandro Yviquel, Herve Bonato, Vanderlei Francesquini, Emilio Araujo, Guido Univ Estadual Campinas UNICAMP Campinas Brazil Univ Sao Paulo Sao Carlos Brazil Univ Fed ABC UFABC Santo Andre SP Brazil Adv Micro Devices AMD Dublin Ireland

ISBN: (数字)9783031725678

ISBN: (纸本)9783031725661;9783031725678

Designing high-performance scientific applications has become a time-consuming and complex task that requires developers to master multiple frameworks and toolchains. Although re-configurability and energy efficiency make FPGA a powerful accelerator, efficiently integrating multiple FPGAs into a distributed cluster is a complex and cumbersome task. Such complexity grows considerably when applications require partitioning execution among CPUs, GPUs, and FPGAs. This paper introduces FPGA offloading support to OpenMP cluster (OMPC), an OpenMP-only framework capable of transparently offloading computation across nodes in a cluster, which reduces developer effort and time to solution. In addition, OMPC enables true heterogeneity by allowing the programmer to assign program kernels to the most appropriate architecture (CPUs, GPUs, or FPGA), depending on their workload characteristics. This is achieved by adding only a few lines of standard OpenMP code to the application. The resulting framework was applied to the heterogeneous acceleration of an image recoloring application. Experimental results demonstrate speed-ups gains using different acceleration arrangements with CPU, GPU and FPGA. Measurements using Halstead metrics show that the proposed framework is faster to program. Furthermore, the solution enables transparently offloading OMPC communication tasks to multiple FPGAs, which results in speed-ups of up to 1.41x over the default communication mechanism (Message Passing Interface - MPI) on Task Bench, a synthetic benchmark for task parallelism.

关键词： distributed computing FPGA Acceleration Heterogeneous computing

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：