2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum最新文献_第7页

Adaptive Resource Management for Service Workflows in Cloud Environments 云环境中服务工作流的自适应资源管理

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.151

Y. Wei, M. Blake, Iman Saleh

引用次数: 16

A unified approach for different tasks on rings in robot-based computing systems 机器人计算系统环上不同任务的统一方法

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.89

Gianlorenzo D'angelo, G. Stefano, A. Navarra, N. Nisse, Karol Suchan

{"title":"A unified approach for different tasks on rings in robot-based computing systems","authors":"Gianlorenzo D'angelo, G. Stefano, A. Navarra, N. Nisse, Karol Suchan","doi":"10.1109/IPDPSW.2013.89","DOIUrl":"https://doi.org/10.1109/IPDPSW.2013.89","url":null,"abstract":"A set of autonomous robots have to collaborate in order to accomplish a common task in a ring-topology where neither nodes nor edges are labeled. We present a unified approach to solve three important problems: the exclusive perpetual exploration, the exclusive perpetual search and the gathering problems. In the first problem, each robot aims at visiting each node infinitely often; in perpetual graph searching, the team of robots aims at clearing the whole network infinitely often; and in the gathering problem, all robots must eventually occupy the same node. We investigate these tasks in the Look-Compute-Move distributed computing model where the robots cannot communicate but can perceive the positions of other robots. Each robot is equipped with visibility sensors and motion actuators, and it operates in asynchronous cycles. In each cycle, a robot takes a snapshot of the current global configuration (Look), then, based on the perceived configuration, takes a decision to stay idle or to move to one of its adjacent nodes (Compute), and in the latter case it eventually moves to this neighbor (Move). Moreover, robots are endowed with very weak capabilities. Namely, they are anonymous, oblivious, uniform (execute the same algorithm) and have no common sense of orientation. In this setting, we devise algorithms that, starting from an exclusive rigid (i.e. a periodic and asymmetric) configuration, solve the three above problems in anonymous ring-topologies.","PeriodicalId":234552,"journal":{"name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121598242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16

Ninja Migration: An Interconnect-Transparent Migration for Heterogeneous Data Centers 忍者迁移:异构数据中心的互连透明迁移

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.114

Ryousei Takano, H. Nakada, Takahiro Hirofuchi, Yoshio Tanaka, T. Kudoh

{"title":"Ninja Migration: An Interconnect-Transparent Migration for Heterogeneous Data Centers","authors":"Ryousei Takano, H. Nakada, Takahiro Hirofuchi, Yoshio Tanaka, T. Kudoh","doi":"10.1109/IPDPSW.2013.114","DOIUrl":"https://doi.org/10.1109/IPDPSW.2013.114","url":null,"abstract":"A virtual machine (VM) migration is useful for improving flexibility and maintainability in cloud computing environments. However, the heterogeneity of the underlying software and hardware, including CPU and interconnect architectures, makes it hard to migrate a VM. In addition, VM monitor~(VMM)-bypass I/O technologies, which significantly reduce the overhead of I/O virtualization, also make VM migration impossible. Therefore, a VM assigned to an Infiniband device cannot migrate to an Ethernet machine, and vice versa. If we overcome the above barriers, we can increase the potential and possibilities of VM migration. In this paper, we propose an interconnect-transparent migration mechanism to simultaneously migrate multiple co-located VMs between data centers equipped with different interconnect devices. Our implementation of the proposed mechanism, called Ninja migration, is achieved by cooperation between a VMM and an MPI runtime system on the guest OS. We demonstrate fallback and recovery operations on a high performance computing workload using the proposed mechanism. We have confirmed that 1) the proposed mechanism has no performance overhead during normal operations, and 2) MPI processes running on distributed VMs can migrate between an Infiniband cluster and an Ethernet cluster without restarting the processes.","PeriodicalId":234552,"journal":{"name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121903596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Visualizing Parallelism in CS 2 可视化cs2中的并行性

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.65

Sean Massung, Cinda Heeren

引用次数: 3

An Image Management System Implemented on Open-Source Cloud Platform 基于开源云平台的图像管理系统

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.176

Jian Wan, S. Han, Jilin Zhang, Baojin Zhu, Li Zhou

引用次数: 5

Investigating the Feasibility of Making Contexts Explicit in Designing Cloud Workflow 探讨云工作流设计中上下文显化的可行性

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.42

Xiaoliang Fan, Ruisheng Zhang, P. Brézillon

{"title":"Investigating the Feasibility of Making Contexts Explicit in Designing Cloud Workflow","authors":"Xiaoliang Fan, Ruisheng Zhang, P. Brézillon","doi":"10.1109/IPDPSW.2013.42","DOIUrl":"https://doi.org/10.1109/IPDPSW.2013.42","url":null,"abstract":"Cloud workflow allows automating the workflow process through a compilation of known sequences of actions in cloud environment. Current Cloud workflows lack the ability, in the one hand, to capture the contexts during the design phase of Cloud workflows; and in the other hand, to deliver a real-time assistance to help a specific user interact with the system in the selection of the relevant cloud workflow components for his specific need. We propose a context-oriented approach to improve the design phase of cloud workflows. A user-oriented paradigm is presented to make contexts explicit in designing cloud workflows. Context will be made explicit due to the integration of BPEL and Contextual Graphs (CxGs) representation. CxGs representation is the formalism for representing uniformly all the ingredients of design process in cloud workflows, so that users could customize information, formalize their design strategies, and possibly interact with the system to model the cloud workflow. We illustrate our methodology through a case study in virtual screening to testify our investigation study. Finally, we conclude that the method we proposed for making contexts explicit in Cloud workflows could be considered as a successful attempt to address the social and human factors related to the design of Cloud workflows.","PeriodicalId":234552,"journal":{"name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122115232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Symmetric Comparison-Based Fault Diagnosis of Multiprocessor and Distributed Systems Using Nonlinear Support Vector Machines 基于非线性支持向量机的多处理器和分布式系统对称比较故障诊断

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.122

M. Elhadef

{"title":"Symmetric Comparison-Based Fault Diagnosis of Multiprocessor and Distributed Systems Using Nonlinear Support Vector Machines","authors":"M. Elhadef","doi":"10.1109/IPDPSW.2013.122","DOIUrl":"https://doi.org/10.1109/IPDPSW.2013.122","url":null,"abstract":"In this paper, the problem of identifying the set of permanent faulty nodes using partial syndromes, i.e., when not all the comparison outcomes are available prior to initiating the diagnosis phase, is considered. A new diagnosis approach, using nonlinear support vector machines (SVMs), is described. We consider the symmetric comparison diagnosis model which assumes that nodes are assigned a set of tasks and their outcomes are compared, and that at most t nodes can fail simultaneously. Based on the agreements and disagreements among the nodes' outputs, the diagnosis algorithm must identify all faulty nodes. The new nonlinear SVM-based fault identification algorithm is first trained using various syndromes with known fault sets. Then, it is extensively tested using randomly generated diagnosable systems of different sizes and under various fault scenarios. Simulations showed that the nonlinear SVM-based diagnosis performed efficiently, i.e. the diagnosis algorithm correctly identified almost all the faulty nodes even when at most half of the comparison outcomes are missing. In addition, results from the thorough simulation study demonstrate the effectiveness of the nonlinear SVM-based fault identification algorithm, in terms of diagnosis correctness, latency, and scalability.","PeriodicalId":234552,"journal":{"name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125367495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Capping Speculative Traces to Improve Performance in Simultaneous Multi-threading CPUs 封顶推测跟踪以提高同步多线程cpu的性能

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.27

Yilin Zhang, Wei-Ming Lin

{"title":"Capping Speculative Traces to Improve Performance in Simultaneous Multi-threading CPUs","authors":"Yilin Zhang, Wei-Ming Lin","doi":"10.1109/IPDPSW.2013.27","DOIUrl":"https://doi.org/10.1109/IPDPSW.2013.27","url":null,"abstract":"Simultaneous Multi-Threading (SMT) improves the overall performance of superscalar CPUs by allowing concurrent execution of multiple independent threads with sharing of key data path components in order to better utilize the resources. Speculative executions help modern processors to exploit more Instruction-Level Parallelism. However, the performance penalty from a miss speculation is much more prominent in an SMT environment than a traditional multi-threading system due to the resulted waste of shared resources at clock-cycle level, versus thread level. In this paper, we show that instructions fetched due to incorrect prediction can be more than 30% of all instructions, which results in a huge waste of resources that could have been better used by other non-speculative threads. To minimize this waste of resources, a technique is proposed in this paper to control the amount of speculative instructions dispatched into Issue Queue (IQ), the most critically shared resource in the SMT pipeline. Simulation result shows the proposed technique can reduce the waste of resource due to miss-speculated traces by 38% and improve overall throughput by up to 17% in IPC.","PeriodicalId":234552,"journal":{"name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130015873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

BOINC as a Service for the SlapOS Cloud: Tools and Methods BOINC作为SlapOS云的服务:工具和方法

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.59

C. Cérin, Alain Takoudjou

{"title":"BOINC as a Service for the SlapOS Cloud: Tools and Methods","authors":"C. Cérin, Alain Takoudjou","doi":"10.1109/IPDPSW.2013.59","DOIUrl":"https://doi.org/10.1109/IPDPSW.2013.59","url":null,"abstract":"In this article we introduce the problems and solutions related to the integration of desktop grid middleware in a cloud, in our case the open source SlapOS cloud. We focus on the issues that describe the integration of what we call a recipe (a description of a process related to the automatic deployment of applications) which is one aspect of systems design in service-oriented architecture and Cloud Computing. The context of our work is somehow orthogonal to what is done traditionally in the Cloud because we do not rely on virtual machines and there is no data center, in the common sense of the word. We also introduce our environment (IDE) for developing applications, designed for SlapOS. We demonstrate that from the initial deployment model we can take into account not only Web applications, B2B applications. . . but also grid applications; here a desktop grid middleware that constitutes a case study. Our first contribution focuses on the problems to automatically deploy and install a desktop grid application, on demand, with no administrator intervention. The second contribution focuses on the architectural design of an IDE for the SlapOS cloud and we illustrate our IDE's usage in the context of our use case.","PeriodicalId":234552,"journal":{"name":"2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128711869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Multi-segment Green Light Optimal Speed Advisory 多段绿灯最佳速度通知

2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum Pub Date : 2013-05-20 DOI: 10.1109/IPDPSW.2013.157

M. Seredynski, W. Mazurczyk, D. Khadraoui

引用次数: 56