检索结果-内蒙古大学图书馆

Effects of network topology on the performance of consensus and distributed learning of SVMs using ADMM

PEERJ COMPUTER SCIENCE 2021年 7卷 e397页

作者： Tavara, Shirin Schliep, Alexander Chalmers Univ Technol Dept Comp Sci & Engn Data Sci & AI Div Gothenburg Sweden Univ Gothenburg Gothenburg Sweden

The Alternating Direction Method of Multipliers (ADMM) is a popular and promising distributed framework for solving large-scale machine learning problems. We consider decentralized consensus-based ADMM in which nodes may only communicate with one-hop neighbors. This may cause slow convergence. We investigate the impact of network topology on the performance of an ADMM-based learning of Support Vector Machine using expander, and mean-degree graphs, and additionally some of the common modern network topologies. In particular, we investigate to which degree the expansion property of the network influences the convergence in terms of iterations, training and communication time. We furthermore suggest which topology is preferable. Additionally, we provide an implementation that makes these theoretical advances easily available. The results show that the performance of decentralized ADMM-based learning of SVMs in terms of convergence is improved using graphs with large spectral gaps, higher and homogeneous degrees.

关键词： Machine learning parallel and distributed computing SVMs ADMM Expander graphs distributed optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Dynamic Load Balance for Hot-spot and Unbalance Region Problems in HBase 8

Dynamic Load Balance for Hot-spot and Unbalance Region Probl...

引用

8th IEEE International Conference on Big Data (Big Data)

作者： Chen, Yibo Xiang, Xing Ling, Xiao Zhang, Xiangchi Wu, Fan Gao, Jianliang State Grid Hunan Elect Power Co Ltd Informat & Commun Branch Changsha Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China

ISBN: (纸本)9781728162515

In distributed storage, dynamic loads usually cause a huge burden such as hot-spot and unblance region problems. In this paper, we focus on the problems of dynamic unbalance loads in distributed database HBase. Firstly, we propose a new intelligent load balance framework to support the collection and analysis of dynamic load information. Then, two efficient load balance strategies are proposed to solve hot-spot problem and unbalance region problem. Finally, we evaluate the strategies on HBase using real-world big data on distributed clusters. Compared to the existing balance strategies, the proposed load balance strategies can make more effective use of the resources and reduce the response time for large dynamic loads.

关键词： distributed storage parallel and distributed computing dynamic loads intelligent load balance

来源：评论

学校读者我要写书评

暂无评论

Teaching Modern Multithreading in CS2 with Actors 34

Teaching Modern Multithreading in CS2 with Actors

引用

34th IEEE International parallel and distributed Processing Symposium (IPDPS)

作者： Lewis, Mark C. Lacher, Lisa L. Trinity Univ Dept Comp Sci San Antonio TX 78212 USA Univ Houston Clear Lake Dept Comp Sci Houston TX USA

ISBN: (纸本)9781728174457

Explosive growth in multiprocessor computing and the pervasive nature of multicore processors has not only made multithreading and related topics such as parallelism, concurrency, synchronization, etc. an essential part of any undergraduate Computer Science curriculum, it has also lead to the addition of newer constructs to support multithreading in many languages. Not only is it important to motivate student interest in this topic, it is important that they are also educated in current methods used in industry. This can mean an increase in material that needs to be covered. Because of the increase in scope of a CS education, teaching topics in parallel and distributed computing in a hands-on manner is challenging, thus it is valuable for educators to explore different methods of educational delivery in order to best engage their students within the limits of curriculum timelines. The actor model is immensely popular in industry and runs some of the most important software today. In this paper, we describe how we are using Actors as a significant part of the multithreading coverage at the CS2 level, for first-year computer science majors. We also describe a semesterlong project that involves the use of these concepts to help solidify student understanding and present student feedback on the project and approach.

关键词： Computer Science Education parallel and distributed computing multithreading actors futures Scala

来源：评论

学校读者我要写书评

暂无评论

Helastic: On combining threshold-based and Serverless elasticity approaches for optimizing the execution of bioinformatics applications

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2021年 53卷 101407-101407页

作者： Aubin, Mateus Rauback Righi, Rodrigo da Rosa Valiati, Victor Hugo da Costa, Cristiano Andre Antunes, Rodolfo Stoffel Galante, Guilherme Univ Vale Rio dos Sinos UNISINOS Sao Leopoldo RS Brazil Univ Estadual Oeste Parana UNIOESTE Cascavel PR Brazil

Recent advances in Next Generation Gene Sequencing (NGS) technologies brought an abundance of bioinformatics and phylogenetics data. The available datasets create new opportunities for studies about the genetic relationships among organisms, which previously relied mainly on manual observations. The state-of-the-art shows that the software employed in this area is based on technologically outdated solutions with ample space for adopting modern computing techniques such as cloud resource elasticity and dynamic load balancing. This article aims to fill this gap with the proposal of Helastic, a model to explore cloud elasticity on jModelTest. The latter is a widely used software for performing statistical selection of nucleotide replacement models in phylogenetic analyzes. Helastic's contributions appear in a dual elasticity layer that combines the traditional threshold-based, reactive approach with Serverless (also referred to in the literature as Function-as-a-Service, or FaaS). Design decisions include interoperability as a requirement, enabling existing jModelTest applications to benefit from Helastic without significant code changes. We evaluate our proposal through a prototype, which was tested on both elastic and non-elastic scenarios. Data regarding execution time and resource usage are presented in this article. Results demonstrate our solution's feasibility and the benefits of working with a dual-elasticity approach rather than a single resource rearrangement technique.

关键词： parallel and distributed computing Cloud computing Elasticity Bioinformatics Phylogenetics

来源：评论

学校读者我要写书评

暂无评论

A novel framework for policy based on-chain governance of blockchain networks

引用

INFORMATION PROCESSING & MANAGEMENT 2021年第4期58卷 102556-102556页

作者： Dursun, Taner Ustundag, Burak Berk TUBITAK BILGEM Blockchain Res Lab Kocaeli Turkey Istanbul Tech Univ Comp Engn Dept Istanbul Turkey

Although blockchains are systems that are intended to survive on their own, they still may need human intervention like other parallel and distributed computing (PDC) architectures. The reasons for this intervention are twofold: management of blockchain nodes and governance of blockchain. The second focuses on sustaining blockchain unlike the first one concerning with operation of individual nodes. Proposed blockchain governance models so far include cumbersome processes in which deciding and deployment of changes rely on the involvement of multiple actors. They have been criticized from various aspects such as reducing the decentralized nature of blockchain. In this paper, we propose a novel on-chain governance model exploiting both policy-based management and decentralized identity technologies. Since it allows controlling the behavior of the system via higher level expressions that are easy to understand, the policy based management concept will fit in well with blockchain ecosystems having stakeholders from different knowledge levels. This model is not only more effective regarding existing off-chain governance models but also is simpler and more user friendly than other on-chain governance models. Besides, the emerging decentralized identity concept has the potential for solving many problems related to decision-making process of blockchain governance. By employing this concept, our approach fortifies decentralization, security and fairness while providing welldirected governance. The smart contract based modular design of our framework opens the door for adoption of its components by other governance models as well.

关键词： parallel and distributed computing Policy based management Blockchain governance On-chain governance Smart contract Decentralized identity

来源：评论

学校读者我要写书评

暂无评论

Introducing parallelism to First-Year CS Majors 20

Introducing Parallelism to First-Year CS Majors

引用

51st ACM SIGCSE Technical Symposium on Computer Science Education (SIGCSE)

作者： Anthony, Barbara M. Erdil, D. Cenk Glebova, Olga Montante, Robert Southwestern Univ Georgetown TX 78626 USA Sacred Heart Univ Fairfield CT 06825 USA Georgia State Univ Atlanta GA 30302 USA Bloomsburg Univ Bloomsburg PA 17815 USA

ISBN: (纸本)9781450367936

We propose to strengthen the computer science (CS) curriculum by embedding parallel concepts in a required first-semester seminar taken by all incoming declared CS majors. We introduce students to parallel computing concepts through a series of unplugged activities so that students see parallel approaches as a natural form of solution to a task. We describe a pilot offering of the class and activities, with measurements and analysis of what students self-report and their performance on assessments.

关键词： Unplugged activities parallel and distributed computing computing education

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Dependability for Voltage and Reactive Power Control by Modified Brain Storm Optimization using Individual and Sub-population based parallel Multi-Population

Comparative Evaluation of Dependability for Voltage and Reac...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Matsumoto, Kaichi Fukuyama, Yoshikazu Meiji Univ Grad Sch Adv Math Sci Tolyo Japan

ISBN: (纸本)9781728125473

Voltage and reactive power control (VRPC) is one of Mixed Integer Nonlinear Programming (MINLP) problems. Evolutionary computation (EC) based VRPC methods have been developed for solving VRPC problems. Since VRPC is an online control, it is necessary to solve a VRPC problem in a limited VRPC interval. Recently, high level of renewable energy penetration and progress of deregulation in power systems require to shorten the VRPC interval and to solve a large-scale VRPC problem in the VRPC interval. Namely, Fast calculation is required in VRPC. Application of parallel and distributed computing (PDC) is a practical option for solving this challenge. However, since power system is a social infrastructure, a dependable method is required for keeping quality of solutions even if several servers cannot return the calculation results due to various faults. When PDC is applied to an EC method using multi-population (MP), there are two ways for realization of parallel computation, namely sub-population based parallel multi-population (PMP) and individual based PMP. No papers have ever compared the two methods from a dependability point of view. This paper presents comparative evaluation of dependability for VRPC by modified brain storm optimization (MBSO) using the individual and the sub-population based PMP. Simulation results with an IEEE 118 bus bench mark system indicate higher dependability of the method using the individual based PMP than the method using sub-population based PMP.

关键词： voltage and reactive power control individual based multi-population parallel and distributed computing dependability modified brain storm optimization evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Multi-path Coverage of All Final States for Model-Based Testing Theory Using Spark In-memory Design 14th

Multi-path Coverage of All Final States for Model-Based Test...

引用

14th International Conference on Verification and Evaluation of Computer and Communication Systems (VECoS)

作者： Adoni, Wilfried Yves Hamilton Krichen, Moez Nahhal, Tarik Elbyed, Abdeltif Hassan II Univ Casablanca Casablanca Morocco Albaha Univ FCSIT Albaha Saudi Arabia Univ Sfax ReDCAD Lab Sfax Tunisia

ISBN: (纸本)9783030659554;9783030659547

This paper deals with an efficient and robust distributed framework for finite state machine coverage in the field model based testing theory. All final states coverage in large-scale automaton is inherently computing-intensive and memory exhausting with impractical time complexity because of an explosion of the number of states. Thus, it is important to propose a faster solution that reduces the time complexity by exploiting big data concept based on Spark RDD computation. To cope with this situation, we propose a parallel and distributed approach based on Spark in-memory design which exploits A* algorithm for optimal coverage. The experiments performed on multi-node cluster prove that the proposed framework achieves significant gain of the computation time.

关键词： Model-based testing Coverage Big data Big graphs Apache spark Apache hadoop parallel and distributed computing

来源：评论

学校读者我要写书评

暂无评论

Trying to do it all in a single course: a surprisingly good idea

Trying to do it all in a single course: a surprisingly good ...

引用

Workshop on Education for High Performance computing (EduHPC)

作者： Newhall, Tia Swarthmore Coll Comp Sci Dept Swarthmore PA 19081 USA

ISBN: (纸本)9780738143057

We present the curricular design and learning goals of an upper-level undergraduate course that covers a wide breadth of topics in parallel and distributed computing (PDC), while also providing students with depth of experience and development of problem solving, programming, and analysis skills. We discuss lessons learned from our experiences teaching this course over the past 10 years, and discuss changes and improvements we have made in its offerings, as well as choices and trade-offs we made to achieve a balance, in a single course, between breadth and depth of topic across these two huge fields. Evaluations from students support that our approach works well meeting the goals of exposing students to a broad range of PDC topics, building important PDC thinking and programming skills, and meeting other pedagogical goals of an advance upper-level undergraduate CS course. Although our single course design was created due to constraints common to smaller schools that have fewer faculty resources, smaller curricula, and often fewer required courses for their majors, our experiences with this course lead us to conclude that it is a good approach for an advanced undergraduate course on PDC at any institution.

关键词： parallel and distributed computing CS Education curriculum design

来源：评论

学校读者我要写书评

暂无评论

Towards distributed Software Resilience in Asynchronous Many-Task Programming Models 10

Towards Distributed Software Resilience in Asynchronous Many...

引用

IEEE/ACM 10th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)

作者： Gupta, Nikunj Mayo, Jackson R. Lemoine, Adrian S. Kaiser, Hartmut Indian Inst Technol Dept CSE Roorkee Uttar Pradesh India Sandia Natl Labs Livermore CA USA Louisiana State Univ Ctr Computat Technol Baton Rouge LA 70803 USA AMD Inc Austin TX USA STE AR Grp Noida India

ISBN: (纸本)9780738110806

Exceptions and errors occurring within mission critical applications due to hardware failures have a high cost. With the emerging Next Generation Platforms (NGPs), the rate of hardware failures will likely increase. Therefore, designing our applications to be resilient is a critical concern in order to retain the reliability of results while meeting the constraints on power budgets. In this paper, we discuss software resilience in AMTs at both local and distributed scale. We choose HPX to prototype our resiliency designs. We implement two resiliency APIs that we expose to the application developers, namely task replication and task replay. Task replication repeats a task n-times and executes them asynchronously. Task replay reschedules a task up to n-times until a valid output is returned. Furthermore, we expose algorithm based fault tolerance (ABFT) using user provided predicates (e.g., checksums) to validate the returned results. We benchmark the resiliency scheme for both synthetic and real world applications at local and distributed scale and show that most of the added execution time arises from the replay, replication or data movement of the tasks and not the boilerplate code added to achieve resilience.

关键词： software resilience parallel and distributed computing asynchronous many-task systems HPX

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：