Mobile IPv6 (MIPv6) provides an efficient solution to solve the wide-area host mobility problem. MIPv6's registration process introduces overhead in case of local-area mobility when coupled with a high rate of cha...
详细信息
ISBN:
(纸本)9781424419678
Mobile IPv6 (MIPv6) provides an efficient solution to solve the wide-area host mobility problem. MIPv6's registration process introduces overhead in case of local-area mobility when coupled with a high rate of change of the mobile node's point of attachment. Regional-aware router hierarchies along with a regional registration framework have been introduced to reduce binding update overhead for local-area mobility. In this paper, a framework which leverages IPv6 anycasting functionality is introduced to enhance MIPv6 regional registrations. the novel framework is designed to promote fault tolerance and improve the mobile node's reachability in the foreign domain. Roots of regional-aware router hierarchies are members of the same anycast group where the anycast address is the care-of-address for mobile nodes. Mobility management state is accessible from all hierarchies either through push data replication among roots of regional-aware router hierarchies or by deploying a mobility support service in the foreign domain Our framework enables the mobile node to be reachable, while moving across domain hierarchies, even if the domain suffers from n-1 failures of hierarchies' roots where n is the number of hierarchies in the domain.
this paper presents a comprehensive analysis of a novel temporal dataset of Shewanella oneidensis. Here we propose to cluster the temporal gene expression data of Shewanella oneidensis to define its molecular response...
详细信息
the emergence of new information system (IS) service technologies yields opportunities and challenges in identifying and monitoring quality of services that providers are delivering. Unfortunately, very few approaches...
详细信息
ISBN:
(纸本)9781605580234
the emergence of new information system (IS) service technologies yields opportunities and challenges in identifying and monitoring quality of services that providers are delivering. Unfortunately, very few approaches have applied accurate and unbiased views on service quality that takes into account the true value of the service provided. this paper poses the definition of quality of service for IS services (QoSIS) and examines how to discover and select high-quality IS services from the viewpoint of the service customers. this will be accomplished through the development of a QoSIS-based service acquisition model by introducing a quality assurance party (QAP) and two quality notions that are respectively referred for traditional customer/provider service and SaaS (software as a service). Copyright 2008 ACM.
this paper suggests a temporal multi-agent logic LDMA, (with interacting agents), to imitate decision-making of independent agents, supported by access to knowledge through interaction with other agents. the interacti...
详细信息
ISBN:
(纸本)9789898111371
this paper suggests a temporal multi-agent logic LDMA, (with interacting agents), to imitate decision-making of independent agents, supported by access to knowledge through interaction with other agents. the interaction is modeled by considering all possible communication paths between agents in temporal Kripke/Hintikka like models. the logic LDMA distinguishes local and global decision-making and is based on temporal Kripke/Hintikka models with agents accessibility relations defined between the states of time clusters. the main result provides a decision algorithm for LDMA (so, we prove that the set of theorems of LDMA is decidable), which also solves the satisfiability problem for LDMA.
the proceedings contain 47 papers. the topics discussed include: multiple stream prediction;enhanced loop coalescing: a compiler technique for transforming non-uniform iteration spaces;folding active list for high per...
详细信息
ISBN:
(纸本)3540777032
the proceedings contain 47 papers. the topics discussed include: multiple stream prediction;enhanced loop coalescing: a compiler technique for transforming non-uniform iteration spaces;folding active list for high performance and low power;reducing misspeculation penalty in trace-level speculative multithreaded architectures;exploiting execution locality with a decoupled kilo-instruction processor;decoupled state-execute architecture;a scalable methodology for computing fault-free paths in infiniband torus networks;using a way cache to improve performance of set-associative caches;design of fast collective communication functions on clustered workstations with Ethernet and myrinet;dynamic load balancing in MPI jobs;workload characterization of stateful networking applications;using recursion to boost ATLAS's performance and towards generic solver of combinatorial optimization problems with autonomous agents in P2P networks.
Industry and academia are exploring ways to exploit the services paradigm to assist in the challenges of software self-management. In this paper we present a novel approach which aims to bring these two fields closer ...
详细信息
ISBN:
(纸本)9783540896470
Industry and academia are exploring ways to exploit the services paradigm to assist in the challenges of software self-management. In this paper we present a novel approach which aims to bring these two fields closer by specifying the requirements and capabilities within a UML2 model architecture style and illustrating how these model elements are used to generate specifications for dynamic runtime service brokering given different modes of a software system. the approach is implemented in a tool suite integrated into the Eclipse IDE with a prototype runtime service broker engine.
MPI-Allgather is a collective communication operation that is intensively used in many scientific applications. Due to high data exchange volume in MPI-Allgather, efficient and scalable implementation of this operatio...
详细信息
ISBN:
(纸本)9780889867741
MPI-Allgather is a collective communication operation that is intensively used in many scientific applications. Due to high data exchange volume in MPI-Allgather, efficient and scalable implementation of this operation is critical to the performance of scientific applications running on emerging multi-core clusters. Mellanox ConnectX is a modern InfiniBand host channel adapter that is able to serve data communication over multiple simultaneously active connections in a scalable manner. In this work, we utilize this feature of the ConnectX architecture and propose novel multi-connection aware RDMA-based MPI-Allgather algorithms for different message sizes over multi-core clusters. Our algorithms also use shared-memory for intra-node communications. the performance results indicate that the proposed four-group multi-connection aware gather-based algorithm is the best algorithm up to 32B messages and gains up to 3.1 times improvement for 4B messages over the native MVAPICH implementation. the proposed single-group multi-connection aware algorithm is the algorithm of choice for 64B to 2KB messages, and outperforms the MVAPICH by a factor of 2.3 for 64B messages. the best algorithm for 4-64KB messages is the two-group multi-connection aware algorithm that achieves an improvement of up to 1.8 for 4KB messages over MVAPICH.
We present some results regarding utilizing Graphics Processing Unit (GPU) for computingthe deformation of two experimental objects. A suture simulation model with CPU and a 2D deformable cloth model with nVidia CUDA...
详细信息
ISBN:
(纸本)9783540690566
We present some results regarding utilizing Graphics Processing Unit (GPU) for computingthe deformation of two experimental objects. A suture simulation model with CPU and a 2D deformable cloth model with nVidia CUDA techniques are also proposed. We conducted experimental studies to compare the GPU-based suture models and withthe CPU implementation. We also experimented withthe implicit model of the 2D mesh which offer similar computational challenges associated with any Finite-Element modeling approaches. A method for computingthe inverse of a matrix with truncated Neumann series is also introduced.
Resource performance in the Computational Grid is not only heterogeneous, but also changing dynamically. However, scheduling algorithms designed for traditional parallel and distributed systems, such as clusters, only...
详细信息
ISBN:
(纸本)160132068X
Resource performance in the Computational Grid is not only heterogeneous, but also changing dynamically. However, scheduling algorithms designed for traditional parallel and distributed systems, such as clusters, only consider the heterogeneity of the resources. In this paper, a workflow scheduling algorithm is proposed. this algorithm uses given QoS guidance to allocate tasks to distributed computer resources whose performance is subject to dynamic change and can be described by predefined probability distribution functions. this new algorithm works in an offline way that allows it to be easily set up and run with less cost. Simulations have been done to test its performance with different workflow and resource settings. the new algorithm can also be easily expanded to accommodate Service Level Agreement (SLA) based workflows.
this paper presents a standards-based architecture for a complex and generic distributed multimedia scenario, which combines content search and retrieval, DRM, and context-based content adaptation together. the most i...
详细信息
ISBN:
(纸本)9780769532998
this paper presents a standards-based architecture for a complex and generic distributed multimedia scenario, which combines content search and retrieval, DRM, and context-based content adaptation together. the most innovative part of the proposed work comes from the integration of a flexible language for multimedia search based on MPEG Query Format (MPQF) standard withthe application of video analysis algorithms for the automatic extraction of low-level features.
暂无评论