检索结果-内蒙古大学图书馆

IEEE 24th Pacific Rim International symposium on Dependable computing (PRDC)

作者： Alhajaili, Sara Jhumka, Arshad Univ Warwick Dept Comp Sci Coventry W Midlands England Univ Jeddah Jeddah Saudi Arabia

ISBN: (纸本)9781728149615

there are various means of providing dependability, one of which is fault removal and debugging is one popular example of a fault removal technique. During debugging, the system is executed, and execution data is collected, to be analysed later, to determine if the execution has satisfied the system specification. In a distributed system, the data collection is done centrally via a monitor, and the assumption typically is that all the nodes are correct. However, in open distributed systems such as the Internet of things (IoT), there is no central authority to enforce this assumption and nodes may behave arbitrarily by violating protocol steps, making processes such as debugging very challenging. We call the data collection process for such processes auditing and a program that reliably records such data as being auditable. In this context, we make the following novel contributions towards auditability enforcement: (i) we define the auditability problem and (ii) identify a necessary condition for a program to be auditable. We then provide examples of auditable programs. Subsequently, (iii) we show an impossibility result for strong auditability. To circumvent this impossibility, we study a weaker problem and discuss the ramifications of certain implementations. Finally, we show that auditability is at least as difficult as the problem of fair exchange. this is the first formal work towards the design of reliable systems through audibility.

关键词： distributed Systems Fair exchange Impossibility Safety Specification

来源：评论

学校读者我要写书评

暂无评论

distributed Maintenance of a Spanning Tree of k-Connected Graphs 24

Distributed Maintenance of a Spanning Tree of k-Connected Gr...

引用

IEEE 24th Pacific Rim International symposium on Dependable computing (PRDC)

作者： Hamid, Brahim Rouland, Quentin Jaskolkat, Jason IRIT Univ Toulouse 118 Route Narbonne F-31062 Toulouse 9 France Carleton Univ Syst & Comp Engn 1125 Colonel By Dr Ottawa ON K1S 5B6 Canada

ISBN: (纸本)9781728149615

this work is devoted to the problem of spanning trees maintenance in the presence of crash failures in a distributed environment using only local knowledge. Using a pre-constructed spanning tree of a k-connected graph, we present a protocol to maintain a spanning tree in the presence of k - 1 consecutive failures. the contribution of this paper is threefold. First, the problem is formalized as an occurrence of Menger's theorem in a distributed setting. the second result shows an implementation of the protocol which is composed of a set of modules encoded using a graph relabeling systems model. the last contribution is the implementation of this protocol in the asynchronous message passing model. For a given graph G = (V, E), where M is the number of its edges, N is the number of its nodes, and Delta is its degree;After each failure occurrence, our algorithms need the following requirements: the first one uses O(Delta x N) steps and O(Delta) bits per node. the second one uses ON + M) messages and O(N) time and O(Delta) bits per node. In addition, we investigate the possible specification and verification of the presented algorithm using Alloy as a tooled formal language.

关键词： distributed computing failure detectors fault-tolerance graph relabeling systems local computations maintenance spanning tree vertex connectivity

来源：评论

学校读者我要写书评

暂无评论

Efficient randomized test-and-set implementations

引用

distributed computing 2019年第6期32卷 565-586页

作者： Giakkoupis, George Woelfel, Philipp INRIA Rennes France Univ Calgary Calgary AB Canada

We study randomized test-and-set (TAS) implementations from registers in the asynchronous shared memory model with n processes. We introduce the problem of group election, a natural variant of leader election, and propose a framework for the implementation of TAS objects from group election objects. We then present two group election algorithms, each yielding an efficient TAS implementation. the first implementation has expected max-step complexity O(log* k) in the location-oblivious adversary model, and the second has expected max-step complexity O(log log k) against any read/write-oblivious adversary, where k = n is the contention. these algorithms improve the previous upper bound by Alistarh and Aspnes (in: Proceedings of the 25th International symposium on distributed computing, 2011) of O(log log n) expected max-step complexity in the oblivious adversary model. We also propose a modification to a TAS algorithm devised by Alistarh, Attiya, Gilbert, Giurgiu, and Guerraoui (in: Proceedings of the 24th International symposium on distributed computing, DISC 2010) for the strong adaptive adversary, which improves its space complexity from super-linear to linear, while maintaining its O(log n) expected max-step complexity. We then describe how this algorithm can be combined with any randomized TAS algorithm that has expected max-step complexity T (n) in a weaker adversary model, so that the resulting algorithm has O(log n) expected max-step complexity against any strong adaptive adversary and O(T (n)) in the weaker adversary model. Finally, we prove that for any randomized 2-process TAS algorithm, there exists a schedule determined by an oblivious adversary such that with probability at least 1/4t one of the processes needs at least t steps to finish its TAS operation. this complements a lower bound by Attiya and Censor-Hillel (SIAM J Comput 39(8):3885-3904, 2010) on a similar problem for n = 3 processes.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

A new Julia-based parallel time-domain simulation algorithm for analysis of power system dynamics 20

A new Julia-based parallel time-domain simulation algorithm ...

引用

Proceedings of the IEEE/ACM 24th International symposium on distributed Simulation and Real Time Applications

作者： Michael Kyesswa Philipp Schmurr Hüseyin K. Çakmak Uwe Kühnapfel Veit Hagenmeyer Karlsruhe Institute of Technology Karlsruhe Germany

the present paper describes a new parallel time-domain simulation algorithm using a high performance computing environment - Julia - for the analysis of power system dynamics in large networks. the parallel algorithm adapts a parallel-in-space decomposition scheme to a previously sequential algorithm in order to develop a new parallelizable numerical solution of the power system equations. the parallel-in-space decomposition is based on the block bordered diagonal form, which reformulates the network admittance matrix into sub-blocks that can be solved in parallel. For the optimal spatial decomposition of the network, a new extended graph partitioning strategy is developed for load balancing and minimizing the communication between subnetworks. the new parallel simulation algorithm is tested using standard test networks of varying complexity. the simulation results are compared to those obtained from a sequential implementation in order to validate the solution accuracy and to determine the performance improvement in terms of computational speedup. Test simulations are conducted using the ForHLR II supercomputing cluster and show a huge potential in computational speedup with increasing network complexity.

关键词： time-domain simulation transient stability analysis parallel computing power systems graph partitioning

来源：评论

学校读者我要写书评

暂无评论

Uniform Consensus Prone to Omission Failures with Fault Knowledge 24

Uniform Consensus Prone to Omission Failures with Fault Know...

引用

IEEE 24th Pacific Rim International symposium on Dependable computing (PRDC)

作者： Cao, Xiao Chinese Acad Sci Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9781728149615

As for uniform consensus prone to omission failures, there are t+1 (t is the number of faulty nodes) round tight lower bound and left perpendicular1/2right perpendicular-1 fault tolerance tight upper bound [6,7]. However, the unreachable n/2 upper bound is based on a hidden condition that it's impossible for all the nodes to know whether they are faulty or not. Few papers focused on this issue. this paper asks two vital questions about it: can nodes know they are faulty or not and what will happen if they have such fault knowledge. Some new findings are made including: (1) this condition is true if only message passing is available;(2) With receive and send fault knowledge, the fault tolerance tight upper bound is n;(3) Still, with only receive fault knowledge, the fault tolerance tight upper bound is n-1;(4) Finally if only send fault knowledge is available, the fault tolerance upper bound is smaller than 2n/3.

关键词： uniform consensus omission failure fault knowledge impossibilities distributed algorithms

来源：评论

学校读者我要写书评

暂无评论

Model Checking Actor-based Cyber-Physical Systems

Model Checking Actor-based Cyber-Physical Systems

引用

International Workshop/symposium on distributed Simulation and Real-Time Applications (DS-RT)

作者： Franco Cicirelli Libero Nigro CNR - National Research Council of Italy - Institute for High Performance Computing and Networking (ICAR) Rende CS Italy University of Calabria Rende CS Italy

the following topics are dealt with: cloud computing; Internet of things; autonomous aerial vehicles; learning (artificial intelligence); parallel processing; virtualisation; formal verification; distributed processin... 详细信息

ISBN: (数字)9781728173436

ISBN: (纸本)9781728173443

关键词： Wheels Model checking Analytical models Java Brakes Computational modeling Delays

来源：评论

学校读者我要写书评

暂无评论

High Performance distributed Deep Learning: A Beginner's Guide 19

High Performance Distributed Deep Learning: A Beginner's Gui...

引用

24th ACM SIGPLAN symposium on principles and Practice of Parallel Programming (PPoPP)

作者： Panda, Dhabaleswar K. (DK) Awan, Ammar Ahmad Subramoni, Hari Ohio State Univ Dept Comp Sci & Engn Columbus OH 43210 USA

ISBN: (纸本)9781450362252

the current wave of advances in Deep Learning (DL) has led to many exciting challenges and opportunities for Computer Science and Artificial Intelligence researchers alike. Modern DL frameworks like Caffe2, TensorFlow, Cognitive Toolkit (CNTK), PyTorch, and several others have emerged that offer ease of use and flexibility to describe, train, and deploy various types of Deep Neural Networks (DNNs). In this tutorial, we will provide an overview of interesting trends in DNN design and how cutting-edge hardware architectures are playing a key role in moving the field forward. We will also present an overview of different DNN architectures and DL frameworks. Most DL frameworks started with a singlenode/single-GPU design. However, approaches to parallelize the process of DNN training are also being actively explored. the DL community has moved along different distributed training designs that exploit communication runtimes like gRPC, MPI, and NCCL. In this context, we will highlight new challenges and opportunities for communication runtimes to efficiently support distributed DNN training. We also highlight some of our co-design efforts to utilize CUDA-Aware MPI for large-scale DNN training on modern GPU clusters. Finally, we include hands-on exercises in this tutorial to enable the attendees to gain first-hand experience of running distributed DNN training experiments on a modern GPU cluster.

关键词： High-Performance Deep Learning Machine Learning DNN Training HPC MPI

来源：评论

学校读者我要写书评

暂无评论

CoSim: a simulator for co-scheduling of batch and on-demand jobs in HPC datacenters 20

CoSim: a simulator for co-scheduling of batch and on-demand ...

引用

Proceedings of the IEEE/ACM 24th International symposium on distributed Simulation and Real Time Applications

作者： Avinash Maurya Bogdan Nicolae Ishan Guliani M. Mustafa Rafique Rochester Institute of Technology Argonne National Laboratory

the increasing scale and complexity of scientific applications are rapidly transforming the ecosystem of tools, methods, and workflows adopted by the high-performance computing (HPC) community. Big data analytics and deep learning are gaining traction as essential components in this ecosystem in a variety of scenarios, such as, steering of experimental instruments, acceleration of high-fidelity simulations through surrogate computations, and guided ensemble searches. In this context, the batch job model traditionally adopted by the supercomputing infrastructures needs to be complemented with support to schedule opportunistic on-demand analytics jobs, leading to the problem of efficient preemption of batch jobs with minimum loss of progress. In this paper, we design and implement a simulator, CoSim, that enables on-the-fly analysis of the trade-offs arising between delaying the start of opportunistic on-demand jobs, which leads to longer analytics latency, and loss of progress due to preemption of batch jobs, which is necessary to make room for on-demand jobs. To this end, we propose an algorithm based on dynamic programming with predictable performance and scalability that enables supercomputing infrastructure schedulers to analyze the aforementioned trade-off and take decisions in near real-time. Compared with other state-of-art approaches using traces of the theta pre-Exascale machine, our approach is capable of finding the optimal solution, while achieving high performance and scalability.

关键词： high-performance computing job checkpointing batch job preemption

来源：评论

学校读者我要写书评

暂无评论

Accelerating distributed stochastic gradient descent with Adaptive Periodic Parameter Averaging 19

Accelerating distributed stochastic gradient descent with Ad...

引用

24th ACM SIGPLAN symposium on principles and Practice of Parallel Programming, PPoPP 2019

作者： Jiang, Peng Agrawal, Gagan Department of Computer Science and Engineering Ohio State University ColumbusOH United States

ISBN: (纸本)9781450362252

Communication overhead is a well-known performance bottleneck in distributed Stochastic Gradient Descent (SGD), which is a popular algorithm to perform optimization in large-scale machine learning tasks. In this work, we propose a practical and effective technique, named Adaptive Periodic Parameter Averaging, to reduce the communication overhead of distributed SGD, without impairing its convergence property. © 2019 Copyright held by the owner/author(s).

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Programming Quantum Computers: A Primer with IBM Q and D-Wave Exercises 19

Programming Quantum Computers: A Primer with IBM Q and D-Wav...

引用

24th ACM SIGPLAN symposium on principles and Practice of Parallel Programming (PPoPP)

作者： Mueller, Frank Byrd, Greg Dreher, Patrick North Carolina State Univ Raleigh NC 27695 USA

ISBN: (纸本)9781450362252

this tutorial provides a hands-on introduction to quantum computing. It will feature the three pillars, architectures, programming, and algorithms/applications of quantum computing. Its focus is on the applicability of problems to quantum computing from a practical point, with only the necessary foundational coverage of the physics and theoretical aspects to understand quantum computing. Simulation software will be utilized complemented by access to actual quantum computers to prototype problem solutions. this should develop a better understanding of how problems are transformed into quantum algorithms and what programming language support is best suited for a given application area. As a first of its kind, to the best of our knowledge, the tutorial includes hands-on programming experience with IBM Q and D-Wave hardware.

关键词： quantum 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：