the paper exploits the interlayer coupling of a cross-layer design concept in grid computing environment. A joint application and fabric layer resource scheduling algorithm which combines both application-centric and ...
详细信息
ISBN:
(纸本)9780769531939
the paper exploits the interlayer coupling of a cross-layer design concept in grid computing environment. A joint application and fabric layer resource scheduling algorithm which combines both application-centric and system-centric scheduling benefits is proposed. We formulate the integrated design of resource allocation and user QoS satisfaction control into a constrained optimization problem. the application layer adaptively adjusts user's resource demand based on the current resource conditions, while the fabric layer adaptively allocates CPU, storage and bandwidth required by the upper layer.
distributed parallel computing, which uses generalpurpose workstations connected by a network as a large parallel computing resource, is one of the most promising trends in parallel computing. Over the last two decade...
详细信息
this paper proposes an open cooperative architecture for the integration of mobile networks. It is based on the Soft-switch idea which is the control functional entity of Next Generation Network (NGN) and fit for larg...
详细信息
ISBN:
(纸本)9781424424238
this paper proposes an open cooperative architecture for the integration of mobile networks. It is based on the Soft-switch idea which is the control functional entity of Next Generation Network (NGN) and fit for large scale nerworking. fit the architecture static routing combined with dynamic routing is adopted for globally connecting among network soft-switch centers (NSCs) withdistributed control mode, using this method, heterogeneous mobile networks (HMN) can be high efficiently and collaboratively interoperated in the architecture. through the use of backup and pool techniques, the bottleneck problem can be solved, and system security enhanced. through dynamic control by NSC in the networking architecture, we can get traffic assignments among HMN based on the qualify of service (QoS) and fairness, and can adopt optimal control strategies for each individual network. the algorithms for fair traffic assignment among HMN are addressed and analyzed.
An effective work-load distribution has a prime rule on reducing the total execution time of a parallel application on heterogeneous environments, such as computational grids and heterogeneous clusters. this paper pre...
详细信息
ISBN:
(纸本)9780769532578
An effective work-load distribution has a prime rule on reducing the total execution time of a parallel application on heterogeneous environments, such as computational grids and heterogeneous clusters. this paper presents two approaches to workload distribution based on analytical models developed to performance prediction of parallel applications, named VRP and VRP-SS. the work-load is distributed based on relative performance ratios, obtained by analytical models constructed according to the rides described in the PEMPIs methodology. In the experimental tests we evaluated the strategies and compared them using MPI applications. the results showed the efficiency of our strategies by reducing the total execution time and improving the workload balance.
During the last years a large number of research works has focused on problems related to multi-core processors. Due to the possibilities of many cores, the number of opportunities in High Performance computing (HPC) ...
详细信息
ISBN:
(纸本)9780769531939
During the last years a large number of research works has focused on problems related to multi-core processors. Due to the possibilities of many cores, the number of opportunities in High Performance computing (HPC) has grown a lot. In fact, new fields related to HPC and processor architecture increase the future possibilities of a Grid-on-Chip (GoC). the goal of this paper is to show a high-throughput MCNoC (Multi-Cluster Network-on-Chip) as an alternative architecture to support clusters of cores and Grid features. In this new scenario data throughput, flexibility, and scalability are very important. the results verify that MCNoC has a similar area occupation and a better data throughput than a traditional Network-on-Chip.
the proceedings contain 67 papers. the topics discussed include: an event-triggered time synchronization scheme for sensor networks;zigbee network for measurement of human vibration;a system for unobtrusive monitoring...
ISBN:
(纸本)9780769532578
the proceedings contain 67 papers. the topics discussed include: an event-triggered time synchronization scheme for sensor networks;zigbee network for measurement of human vibration;a system for unobtrusive monitoring of mobility in bed;extension of capture information in pervasive healthcare systems: a case study;dynamic code tuning aids the success of telemedicine;strategic planning of an integrated smart card fare collection system - challenges and solutions;formal modelling and analysis of a distributed database protocol in Maude;GUFI: a new algorithm for general updating of frequent itemsets;combining parallel self-organizing maps and K-means to cluster distributed data;collaborating mechanical design phases across a grid;an economic approach for scheduling dependent tasks in grid computing;and design and implementation of a virtual organization file system for dynamic VOs.
In the last ten years there were intensive researches to find new methods for handling internet distributed databases and image processing. One of these methods is the Mojette transform (MOT). this transform is an exa...
详细信息
ISBN:
(纸本)1424415446
In the last ten years there were intensive researches to find new methods for handling internet distributed databases and image processing. One of these methods is the Mojette transform (MOT). this transform is an exact discrete Radon transform defined for a set of specific projections. the MOT is used mainly in image processing applications. there were several implementation using personal computers [8] and [9], but these application were implemented only for locally stored images. there are some applications where real time computing is a must, but the implementations before referred can not accomplish this requirement. the Mojette transforms implemented under different operating systems and for different processors presented below helps the performance analyses of the MOT and also let to conclude the need for reconfigurable hardware implementation. there is also analyzed the implementation of Mojette transform and Inverse Mojette transform (IMOT) the implementation in Field Programmable Gate Arrays using reconfigurable platform. the paper tries to conclude the necessity for hardware implementation for real time processing. the paper outline the development work in order to create an embedded reconfigurable hardware based on FPGA board.
In many distributedcomputing paradigms, especially sensor networks and ubiquitous computing but also grid computing and web services, programmers commonly tie their application to a particular set of processors. this...
详细信息
ISBN:
(纸本)9783540787426
In many distributedcomputing paradigms, especially sensor networks and ubiquitous computing but also grid computing and web services, programmers commonly tie their application to a particular set of processors. this can lead to poor utilisation of resources causing increased compute time, wasted network bandwidth or poor battery life, particularly if later changes to the architecture or application render early decisions inappropriate. this paper describes a system which separates application code from the description of the resources available to execute it. Our framework and prototype compiler determines the best location to execute different parts of the distributed application. In addition, our language encourages the programmer to structure data, and the operations performed on it, as monoids and monoid homomorphisms. this approach enables the compiler to apply particular program transformations in a semantically-safe way, and therefore further increase the flexibility of the assignment of application tasks to available resources.
A number of recently proposed mobile sensor network architectures rely on uncontrolled, or weakly-controlled mobility to achieve sensing coverage over time at low cost, an opportunistic sensor networking approach. How...
详细信息
ISBN:
(数字)9783540691709
ISBN:
(纸本)9783540691693
A number of recently proposed mobile sensor network architectures rely on uncontrolled, or weakly-controlled mobility to achieve sensing coverage over time at low cost, an opportunistic sensor networking approach. However, this reliance on mobility also introduces a number of challenges. In this paper, we discuss the challenges inherent in this networking paradigm, and describe two composable techniques, sensor sharing and substitution, to make the system more robust in terms of data fidelity and delay. We present a numerical analysis of these techniques, separately and in combination, based on a simple Markov model of an opportunistic sensor network.
Many scientific applications exhibit high demands on memory storage and computing capability. Recent improvements in commodity processors and networks have provided an opportunity to support such scientific applicatio...
详细信息
ISBN:
(纸本)9780769531939
Many scientific applications exhibit high demands on memory storage and computing capability. Recent improvements in commodity processors and networks have provided an opportunity to support such scientific applications within an everyday computing infrastructure. Good applications need the ability to work in constantly changing environments. Adaptability and fault tolerance are essential. Based on simulation of relativistic particle transport, this paper proposes a data-level check-pointing scheme for common scientific applications. this scheme takes advantage of the regular program layout, dominant computing loops, and fine-grained iterations. Without handling stack and heap segments directly, only application data is saved and restored as the computation state. Checkpointing interval can be dynamically adjusted to satisfy sensitivity and efficiency requirements for feasible fault tolerance. Withthis periodic but fixed-location checkpointing scheme, the MPI-based simulation system can be reconfigured by being shut down first and then restarted on same or different computer clusters. Application data can be redistributed for the new configuration. Experimental results have demonstrated this scheme's efficiency and effectiveness.
暂无评论