检索结果-内蒙古大学图书馆

Predictive and Distributed Routing Balancing, an Application-Aware Approach

Procedia computer Science 2013年 18卷 179-188页

作者： Carlos Núñez Castillo Diego Lugones Daniel Franco Emilio Luque Martin Collier Computer Architecture and Operating Systems Department Universitat Auto‘noma de Barcelona Bellaterra Spain School of Electronic Engineering Dublin City University Glasnevin Dublin 9 Ireland

The interconnection design in computing clusters and data centers is expected to change significantly in the near future to sustain the increasing communication demand at controlled capitalization and operational cost. In particular, a shift from typ- ical and expensive full-bisection bandwidth interconnects (which safely cover the worst communication cases) to application oriented designs (which may provide cost-efficient data movement at larger system scales) is devised in academic research and industry initiatives. Having information of communication dynamics of applications (e.g. repetitiveness, computing and communication phases, traffic pattern and bandwidth, etc.) allows for efficiently managing and provisioning of network re- sources at reduced cost. This paper presents an Application-Aware Predictive and Distributed Routing Balancing technique (PR-DRB), a new method that controls network inefficiencies based on communication patterns of applications and speculative routing, PR-DRB monitors increments in the communication latency and, then, dynamically re-distributes the network traffic over multiple paths (path expansion) to deal with load unbalances. Additionally, PR-DRB stores the number of paths used to balance the traffic (solution) and links it to the application's pattern that caused the unbalance (problem). This information allows PR-DRB to respond to similar situations in repetitive patterns, quickly converging to a stable solution. Evaluation results show latency and completion time reductions of up to 37% for experiments conducted on 64 nodes executing the NAS benchmarks and the Lammps application.

关键词： Interconnection networks High performance computing Predictive routing Hpc clusters Parallel scientific applications Application-aware routing

来源：评论

学校读者我要写书评

暂无评论

Using an Agent-based Simulation for Predicting the Effects of Patients Derivation Policies in Emergency departments

引用

Procedia computer Science 2013年 18卷 641-650页

作者： Manel Taboada Eduardo Cabrera Francisco Epelde Ma Luisa Iglesias Emilio Luque Tomas Cerda Computer Science School University Autonoma of Barcelona(UAB) Spain Computer Architecture and Operating Systems Department (CAOS) UAB Spain Hospital of Sabadell Consorci Sanitari Parc Taulí Barcelona Spain

The increasing demand of urgent care, overcrowding of hospital emergency departments (ED) and limited economic resources are phenomena shared by health systems around the world. It is estimated that up to 50% of patients that are attended in ED have non complex conditions that could be resolved in ambulatory care services. The derivation of less complex cases from the ED to other health care devices seems an essential measure to allocate properly the demand of care service between the different care units. This paper presents the results of an experiment carried out with the objective of analyzing the effects on the ED (patients’ Length of Stay, the number of patients attended and the level of activity of ED Staff) of different derivation policies. The experiment has been done with data of the Hospital of Sabadell (a big hospital, one of the most important in Catalonia, Spain), making use of an Agent-Based model and simulation formed entirely of the rules governing the behaviour of the individual agents which populate the ED, and due to the great amount of data that should be computed, using High Performance Computing.

关键词： Healthcare operational management Agent-based modelling Individual oriented simulation Emergency department Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Transparent fault tolerance middleware at user level

Transparent fault tolerance middleware at user level

引用

2012 10th Annual International Conference on High Performance Computing and Simulation, HPCS 2012

作者： Castro, Marcela Rexachs, Dolores Luque, Emilio Computer Architecture and Operating Systems Department Universitat Autònoma de Barcelona Spain

ISBN: (纸本)9781467323598

We present a design of a transparent fault tolerance middleware for message passing applications. The approach consists in transforming the interconnections used by the application in reliable ones and support log-based rollback recovery protocol. When one of the nodes of the cluster fails, the processes are recovered in a new one and the connections are reestablished. All this work is made automatically and in a transparent way for the application. This service can be optionally activated at runtime at user level. The models used for protection and recovering application and detection of failures are based on RADIC architecture. We have tested this middleware by executing a master-worker (M/W) and SPMD applications which follow different communication patterns. © 2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Transparent fault tolerance solution at socket level based on RADIC

Transparent fault tolerance solution at socket level based o...

引用

2012 10th IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2012

作者： Castro, Marcela Rexachs, Dolores Luque, Emilio Computer Architecture and Operating Systems Department Universitat Autònoma de Barcelona Spain

ISBN: (纸本)9780769547015

We present a transparent middleware for fault tolerance based on RADIC, Redundant Array of Distributed Independent Controllers, a transparent and scalable fault tolerant architecture for parallel applications. It is designed at socket level and makes a secure tunnel connection able to keep the tcp sessions established by the application in spite of node failures. It is located at user level and is independent of the message-passing communication library being used. The protection gets through uncoordinated checkpoints and log message and the recovery are done in a automatic way so in case of node failures there is no need of intervention of the administrator. We have tested our fault tolerance system by executing a master-worker (M/W) and SPMD applications that follow different communication patterns. © 2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

An Innovative Teaching Strategy to Understand High-Performance systems through Performance Evaluation

引用

Procedia computer Science 2012年 9卷 1733-1742页

作者： Gonzalo Zarza Diego Lugones Daniel Franco Emilio Luque Computer Architecture and Operating Systems Department Universitat Autónoma de Barcelona Spain

Nowadays, the study of high-performance computing (HPC) is one of the essential aspects of postgraduate pro-grammes in Computational Science. However, university education in HPC often suffers from a significant gap between theoretical concepts and the practical experience of students. To face this challenge, we have implemented an innovative teaching strategy to provide students appropriate resources to ease the assimilation of theoretical con-cepts, while improving their practical experience through the use of teaching tools and resources specifically designed to promote active learning. We have used the proposed strategy to organize the module of Parallel computers and architectures of the Master's in High-Performance Computing, at the Universitat Aut‘onoma de Barcelona, obtaining very promising results. In particular, we have observed improvements of both the academic marks of students and the perception about their own expertise and skills in HPC, regarding the previous teaching approach.

关键词： University Education High-Performance Computing Simulation Management OPNET Modeler

来源：评论

学校读者我要写书评

暂无评论

Application of self-organizing systems in power systems control

Application of self-organizing systems in power systems cont...

引用

13th International Conference on Product-Focused Software Process Improvement, PROFES 2012

作者： Müller, Sven C. Häger, Ulf Rehtanz, Christian Wedde, Horst F. Institute of Energy Systems Energy Efficiency and Energy Economics TU Dortmund University of Technology Dortmund Germany Department of Operating Systems and Computer Architecture TU Dortmund University of Technology Dortmund Germany

ISBN: (纸本)9783642310621

The European electrical transmission network is operated increasingly close to its operational limits due to market integration and increased feed-in by renewable energies. For this reason, innovative solutions for a reliable, secure and efficient network operation are requested. The application of self-organizing systems promises significant potential in real-time control. This paper outlines the challenges of power system operation, gives a brief overview of relevant system characteristics and discusses the applicability of self-organizing systems for different fields of power system control. As a result of current research, the application of an agent-based decentralized power flow control system is presented and discussed in comparison to current practice based on central decision making. © 2012 Springer-Verlag.

关键词： Flexible AC transmission systems

来源：评论

学校读者我要写书评

暂无评论

Proximity Load Balancing for Distributed Cluster-based Individual-oriented Fish School Simulations

引用

Procedia computer Science 2012年 9卷 328-337页

作者： Roberto Solar Remo Suppi Emilio Luque Department of Computer Architecture & Operating Systems Universitat Autònoma de Barcelona Bellaterra 08193 Barcelona Spain

Partitioning and load balancing are highly important issues in distributed individual-oriented simulation. Choosing how to distribute individuals on the distributed environment can be a crucial factor at the moment of executing the simulation. Partitioning an individual-oriented system should be efficient in order to reduce communication involved in interaction between individuals belong to different logical processes. Furthermore, if the individual-oriented model exhibits mobility patterns, we should be able to maintain the load balancing in order to keep the global application performance. In this work, we present a proximity load balancing strategy for a distributed cluster-based individual-oriented fish school simulator. On one hand, we implement a robust cluster-based partitioning method by means of covering radius criterion and voronoi diagrams. We use a proximity criterion to distribute individuals on the distributed architecture. On the other hand, we propose a proximity load balancing strategy in order to maintain the application performance as the simulation progresses.

关键词： High-performance simulation individual-oriented models distributed simulation data clustering nearest-neighbor load balancing

来源：评论

学校读者我要写书评

暂无评论

Hierarchical MATE's approach for dynamic performance tuning of large-scale parallel applications

Hierarchical MATE's approach for dynamic performance tuning ...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Andrea Martínez Anna Sikora Eduardo César Joan Sorribes Computer Architecture and Operating Systems Department Universitat Autònoma de Barcelona Spain

Currently, performance analysis support tools are required to exploit the potential performance of large-scale computers. However, in this context, scalability becomes a major problem for this kind of tools. Nowadays, there are automatic performance analysis tools, such as Scalasca [1] or Periscope [2], capable of scaling and looking for performance problems of parallel applications. Nevertheless, if the behaviour of a parallel application varies during the execution according to the data evolution, then dynamic analysis and tuning of the application during its execution, such as that performed by MATE [3] tool, is necessary.

关键词： Tuning Performance analysis Scalability computer architecture Monitoring Instruments Prototypes

来源：评论

学校读者我要写书评

暂无评论

Coupling Wind Dynamics into a DDDAS Forest Fire Propagation Prediction System

引用

Procedia computer Science 2012年 9卷 1110-1118页

作者： Carlos Brun Tom‘as Artées Tom‘as Margalef Ana Cortées Computer Architecture and Operating Systems Department Escola d’Enginyeria Universitat Aut‘onoma de Barcelona Campus UAB Bellaterra 08193 Spain

Natural hazards are significant problems that every year cause important loses around the world. A good prediction of the behavior of the hazards is a crucial issue to fight against them and to minimize the damages. The models that represent these phenomena need several input parameters and in many cases, such parameters are diffcult to know or even to estimate in a real scenario. So, a methodology based on the DDDAS paradigm was developed to calibrate the input parameters according to real observations of the behavior and evolution of the hazard. Such calibrated parameters are then used to provide an improved prediction for the next time interval. This methodology was tested on Forest Fire Propagation Prediction with significant results. The developed methodology takes the fire behavior and propagation during a time interval and then searches for the values of the input parameters that best reproduce the propagation of the fire during that interval. Several Artificial Intelligence (AI) methods were applied to carry out this search as fast as possible. The values of the parameters that best reproduce the behavior of the fire were then used as input parameters to predict the propagation during the next time interval. These parameters were considered constant during both time intervals and a single value for each parameter was used for the calibrating process and for the prediction stage. This methodology fits on the DDDAS paradigm since the prediction is dynamically driven by the system evolution. However, there are several parameters that are not constant through time, but they may vary dynamically. In the case of forest fires, a typical example is the wind. In some cases, when the time interval is short an average value for the wind can be a feasible value, but when the time interval is longer, in most cases, a single value cannot represent the variability of the wind. We can estimate wind behavior applying some complementary model. In this work, we are going a ste

关键词： fire prediction DDDAS calibration wind simulation fire spread genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

On the Way of Applying Urgent Computing Solutions to Forest Fire Propagation Prediction

引用

Procedia computer Science 2012年 9卷 1657-1666页

作者： Andrés Cencerrado Ana Cortés Tom‘as Margalef Computer Architecture and Operating Systems Department. Escola d’Enginyeria Universitat Aut‘onoma de Barcelona. 08193 Bellaterra Barcelona (Spain)

A quick response becomes crucial in natural hazard management. When an emergency occurs, hazard evolution simulators are a very helpful tool for the teams in charge of making decisions. To perform the simulations, they rely on data which usually constitutes a big set of parameters, which have been previously recorded from observations, usually coming from remote sensors, images, etc. However, this data is frequently subject to a high degree of uncertainty. This data uncertainty also produces uncertainty in simulators’ results. To overcome this drawback, in previous works we developed a two-stage prediction method, which has been demonstrated to improve noticeably the quality of the predictions. The time incurred in performing this strategy, however, may vary signiﬁcantly depending on different factors. As it is well known, the execution time of a particular simulator depends on the speciﬁc setting of the input parameters. Moreover, decision control centers in charge of making decisions to ﬁght against the ongoing disaster require a certain degree of quality in the ﬁnal prediction. Depending on how demanding are the quality and time constraints, the two-stage strategy may need the support of Urgent Computing solutions, in order to meet the requirements. In this work, we focus on forest ﬁres spread prediction, as a real application case of study, and we expose our methodology to characterize both the time needed and the expected quality of the two-stage prediction method, so that we are able to determine the amount of computational resources needed to respond effciently to an eventual emergency. This way, we emphasize the need of Urgent Computing mechanisms to be able to put into practice this method at real time.

关键词： Forest Fire Simulation Data Uncertainty Urgent 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：