Nowadays Internet users participate in different types of collaborative applications from different parts of the world. In these types of applications, users need to coordinate access to shared resources. This coordin...
详细信息
ISBN:
(纸本)9780889868113
Nowadays Internet users participate in different types of collaborative applications from different parts of the world. In these types of applications, users need to coordinate access to shared resources. This coordination is termed as floor control and researchers have proposed different types of floor control protocols in the literature. Certain types of collaborative applications require that a user with higher priority will be given preference over a user with lower priority at the time of floor assignment by the underlying protocol. This implies that the protocol needs to consider the priority of the user while assigning the floor. If two users are contending for the floor and their priorities are same, then the user who has requested the floor first will get the floor before the other user. These applications also require that this coordination should be performed without the help of any centralized controller. In this paper, we propose GPRIDE - a Generalized PRIority-based distributed floor control protocol for collaborative applications. We have implemented our proposed protocol using BSD Sockets API and tested the performance of the protocol on the PlanetLab network for different conditions. PlanetLab is an overlay testbed that connects several academic and research institutions all over the world in a virtual network.
Our objective is to provide location-, topology-, and administrative- transparent grid computing forMPI applications, while hiding the physical details of computing platforms and heterogeneous networks fromthe applica...
详细信息
ISBN:
(纸本)9780889868113
Our objective is to provide location-, topology-, and administrative- transparent grid computing forMPI applications, while hiding the physical details of computing platforms and heterogeneous networks fromthe application elopers and users. To achieve this objective, we introduced a new resource allocation model, workflow structures to specify MPI applications involving multiple tasks, and message relay to enable communication across different networks. We eloped the SGR framework, which integrates workflow scheduling, task grouping, and message relay services, while hiding resource allocation, heterogeneous networks, and decentralized resource management systems from application elopers and users. The SGR system has been implemented on a Globus-enabled computing grid. We created a simulation environment to investigate our model and various schedulers. Using the findings from simulation, we implemented the SGR framework and tested the model's implementation on a two-cluster grid. We observed that duplication can improve performance by more than 15%, which matches our simulation results. Moreover, we evaluated our new message relay service for cross-site message passing. The test results indicate that although the SGR's message relay service has some communication overhead, the system is scalable with respect to the number of processes and the message size.
We present an architecture using a dynamical deterministic unit ring decomposition to improve the balancing quality of an heterogeneous dynamic hashing scheme. This new approach, denoted by DhHHT, is capable to distri...
详细信息
ISBN:
(纸本)9780889868113
We present an architecture using a dynamical deterministic unit ring decomposition to improve the balancing quality of an heterogeneous dynamic hashing scheme. This new approach, denoted by DhHHT, is capable to distribute any subsetD' ⊆ D of uniformitems balanced among a dynamical node set V . Further, the capacity of a node, labeled as c(v)min v ∈ V , is allowed to change during runtime and causes no overhead. The challenge in this area is to assign to each v ∈ V approximately |D'| . c(v)/Σu∈V c(u) items, even if nodes are added or removed from V , where |D| denotes the cardinality of D. We will show that DhHHT reaches this without global knowledge about V nor by capacity normalization. Further, DhHHT has an improved model complexity of O(|V |), which is reduced by O(log n) compared to previous approaches. Its special design purpose is to manage limited resources with persistent allocation requests, where even slightly constant balancing iations are intolerable. We also present an uniform dynamical deterministic hash range decomposition, used to place nodes in the hash range, which provides a constant upper and lower iation of 1.118 = s = 1.809. The decomposition is embedded within the DhHHT architecture.
Cloud computing is attracting considerable attention as a paradigm shift in the way of supplying and using computing resources. To realize a platform of Cloud computing, large-scale data centers equipped with a huge n...
详细信息
ISBN:
(纸本)9780889868113
Cloud computing is attracting considerable attention as a paradigm shift in the way of supplying and using computing resources. To realize a platform of Cloud computing, large-scale data centers equipped with a huge number of physical resources have to be constructed and operated. One of the big concerns is then how to reduce the resource management and operational cost. Moreover, for reasons of security, users require isolation of their virtual systems running on a shared Cloud platform. Especially, business application systems need strong isolation to protect their private and confidential information. Accordingly, we have been developing new technologies to support the operation and management of such next-generation data centers. In this paper, we describe the design and implementation of ITcell system a platform for IaaS (Infrastructure as a Service) style Cloud computing. Our concept for ITcell is treating physical resources like cells in living organisms-numerous, easily replaceable and integrated in a larger whole. In the development of ITcell system, we addressed and solved the following issues: (1) efficient management of physical resources;(2) rapid integration of new physical servers;(3) managing a VAS (virtual application system) as a single unit;and (4) ensuring network isolation between VAS instances on a shared platform.
Recently, data storage systems with data deduplication have been introduced as a method of reducing storage space by eliminating redundant data. In a deduplication storage system, the collision-resistant fingerprint o...
详细信息
ISBN:
(纸本)9780889868113
Recently, data storage systems with data deduplication have been introduced as a method of reducing storage space by eliminating redundant data. In a deduplication storage system, the collision-resistant fingerprint of each data segment must be calculated using a hash algorithm. This paper presents a GPU based accelerator, called g-Dedu, for processing the hash computation of the deduplication system. The g-Dedu accelerator algorithm is especially designed for handling the variable and small size of the data used in a deduplication system, which cannot be processed efficiently by a GPU in a straightforward way. Our data organization approach uses a hierarchical data structure to organize the processing data. A scheduler manages these data for optimal GPU processing. Our patterned data segment approach overcomes some noticeable performance drops resulting from the GPU memory model. Furthermore, different from some previous GPU hash accelerator work, our approach strictly follows the hash processing standard. Using this new approach, g-Dedu achieves 6 times speedup on the SHA-1 computation, and 7.4 times speedup on the SHA-2 computation when compared with a CPU-based mplementation.
Recent investigations into resilience of large-scale high-performance computing (HPC) systems showed a continuous trend of decreasing reliability and availability. Newly installed systems have a lower mean-time to fai...
详细信息
ISBN:
(纸本)9780889867840
Recent investigations into resilience of large-scale high-performance computing (HPC) systems showed a continuous trend of decreasing reliability and availability. Newly installed systems have a lower mean-time to failure (MTTF) and a higher mean-time to recover (MTTR) than their predecessors. Modular redundancy is being used in many mission critical systems today to provide for resilience, such as for aerospace and command & control systems. The primary argument against modular redundancy for resilience in HPC has always been that the capability of a HPC system, and respective return on investment, would be significantly reduced. We argue that modular redundancy can significantly increase compute node availability as it removes the impact of scale from single compute node MTTR. We further argue that single compute nodes can be much less reliable, and therefore less expensive, and still be highly available, if their MTTR/MTTF ratio is maintained.
Since distributedparallelcomputing system offers users with more spread computing and storage resources, it provides us a prospect to propose new efficient and dynamic solvers for the numerical solutions of partial ...
详细信息
ISBN:
(纸本)9780889867901
Since distributedparallelcomputing system offers users with more spread computing and storage resources, it provides us a prospect to propose new efficient and dynamic solvers for the numerical solutions of partial differential equations (PDEs) in order to visualize breasts' cancerous cell. Partial differential equations (PDEs) can be classified as parabolic equation, elliptic equation and hyperbolic equation. Partial differential equations are used commonly as mathematical models for solving all of the science and engineering fields. This research will focus on the study of elliptic equations, particularly Helmholtz's wave equation and hyperbolic equations. The numerical finite-difference method is chosen as a platform for discretizating the elliptic equations and to solve the hyperbolic equations. The elliptic equation can be used as mathematical models for biological aspects of electromagnetic wave. Breast cancer is the commonest female malignancy in Malaysia as well as all over the world. The incidence of breast cancer in Malaysia is estimated to be around 27 per 100,000 populations, with close to 3,000 new cases annually. parallel Virtual Machine (PVM) is emphasized as communication open source software on distributedparallelcomputing system, which results in a performance gain. The parallel performance measurements of the parallelcomputing is analysed in this study.
In the modern business world, very often two parties collaborate with each other for their mutual benefit. Accordingly, transactions are processed between them, with one party processing a part of a transaction, and t...
详细信息
ISBN:
(纸本)9780889867840
In the modern business world, very often two parties collaborate with each other for their mutual benefit. Accordingly, transactions are processed between them, with one party processing a part of a transaction, and the other continuing with the remainder. Because of the mutual advantage it brings to the collaborators, to discover such a pattern relation becomes especially important that, a frequent pattern of one party is dependent upon, or associated with, a frequent pattern of the other party. Generally it is required that pattern relation mining should be conducted without disclosing private data to each other. And also, since any subpattern of a frequent pattern is also frequent, it is sufficient to mine only the maximal frequent patterns. In this paper we propose an effective privacy-preserving maximal pattern relation mining algorithm, called CMPRM.
暂无评论