The programming is still a challenging issue for the high performance distributed computing (HPDC) platform, and it is critical to the popularity of peer-to-peer (P2P) based HPDC systems. Therefore, this paper focuses...
详细信息
The programming is still a challenging issue for the high performance distributed computing (HPDC) platform, and it is critical to the popularity of peer-to-peer (P2P) based HPDC systems. Therefore, this paper focuses on the design and implementation of OMP, a one-sided message passing programming model for unstructured P2P computingsystem, P2HP. Based on taskspsila execution flow, P2HP provides a one-sided point-to-point message-passing communication library, and a software development kit with rich APIs for applicationspsila parallelization. Furthermore, a serial sequence alignment algorithm is parallelized with OMP in P2HP. The evaluation shows that OMP makes P2HP practical and efficient.
The heterogeneity, distribution and dynamicity of web services hamper WSRF (Web service resource framework) of grid to exert its excellences in resource integrations. In this paper, we propose our SOV (service orient ...
详细信息
The heterogeneity, distribution and dynamicity of web services hamper WSRF (Web service resource framework) of grid to exert its excellences in resource integrations. In this paper, we propose our SOV (service orient virtualization) model for medical image grid (MedImgrid), which creates a virtual middle layer for grid to simplify the transformation from users' business aims to executable web-service instances. The layer adopts semantic based cross clustering means to support approximate optimal service selection from WSS (Web service set) to break through the hard-encoded mode of web-service based applications. It provides service-independent composition mechanism and can adjust a service composition path even during runtime. SOV utilizes the web services as the joint-point of grid, semantic and virtualization technologies so as to conceal the heterogeneities of low-level resources and surpass the limits of tightly-coupled mode to service composition within grid environment.
The concept of green computing has attracted much attention recently in clustercomputing. However, previous local approaches focused on saving the energy cost of the components in a single workstation without a globa...
详细信息
The concept of green computing has attracted much attention recently in clustercomputing. However, previous local approaches focused on saving the energy cost of the components in a single workstation without a global vision on the whole cluster, so it achieved undesirable power reduction effect. Other cluster-wide energy saving techniques could only be applied to homogeneous workstations and specific applications. This paper describes the design and implementation of a novel approach that uses live migration of virtual machines to transfer load among the nodes on a multilayer ring-based overlay. This scheme can reduce the power consumption greatly by regarding all the cluster nodes as a whole. Plus, it can be applied to both the homogeneous and heterogeneous servers. Experimental measurements show that the new method can reduce the power consumption by 74.8% over base at most with certain adjustably acceptable overhead. The effectiveness and performance insights are also analytically verified.
To understand and predict electromagnetic behavior is one of the most important electrical engineering technologies. FDTD is the key algorithm for solving this kind of problems, which provides a direct, time domain so...
详细信息
To understand and predict electromagnetic behavior is one of the most important electrical engineering technologies. FDTD is the key algorithm for solving this kind of problems, which provides a direct, time domain solution to Maxwell's equations in differential form with relatively good accuracy and flexibility. In this paper, we propose a novel hybrid parallelization model for FDTD method, which combines the domain distribution scheme and the single instruction multiple data (SIMD) parallelization. This model is able to exploit the computing potential of a new generation parallel machine named cell broadband engine (CBE). The experiment results show that the algorithm obtains approximately linearly speedup with respect to the number of SPEs and has excellent scalability.
During the study of grid projects, a real grid environment or simulated grid is built up for development and experiment normally. But there are some disadvantages such as high cost, complex deployment and configuratio...
详细信息
During the study of grid projects, a real grid environment or simulated grid is built up for development and experiment normally. But there are some disadvantages such as high cost, complex deployment and configuration, hard management, even conflict among people. A novel virtual grid experiment method with HAL (Hardware Abstraction Level) virtualization technology is presented, which can conquer the disadvantages above and has been used in MedImgrid for the development of medical grid applications. The experiment shows that the method is feasible with low cost, easy configuration and convenient management, so as to increase research efficiency and shorten developing cycle. Furthermore, it can be applied not only in MedImgrid but also in some other grid projects.
Automated trust negotiation (ATN) is an important means to establish trust between strangers through the exchange of digital credentials and mobile access control policies specifying what combinations of credentials a...
详细信息
ISBN:
(纸本)9781424414895
Automated trust negotiation (ATN) is an important means to establish trust between strangers through the exchange of digital credentials and mobile access control policies specifying what combinations of credentials a stranger must submit. As a certificate may contain sensitive information, unlimited disclosure will leak valuable information or jeopardize individual privacy. In order to prevent information leakage, the negotiation protocol is designed so complicated that a requestor is hard to attain the access. In addition, if the encryption algorithm is short in security intensity, the transmitting message over the public channel is easy to be attacked. To solve these problems, an asymmetrical encryption based ATN model (AEBM) is proposed in this paper. AEBM adopts credentials with a flexible format to meet the requirements of access control policies, instead of disclosing the whole contents of a certificate. Further, AEBM uses asymmetric encryption technique to encrypt the transmitting message, which can prevent information from leaking. AEBM presents a new negotiation strategy to enhance the negotiation efficiency. A use case is studied to prove that AEBM is sound and reasonable.
It is very significant for the medical and health enterprises to develop an efficient medical information grid to achieve sufficient medical data share and integration. In order to access heterogeneous data resources ...
详细信息
It is very significant for the medical and health enterprises to develop an efficient medical information grid to achieve sufficient medical data share and integration. In order to access heterogeneous data resources transparently, front agent is built on heterogeneous databases or medical systems, the same as the unified data models and mapping rules with gridservices to communicate with upper grid middleware, so that users can query or access medical data conveniently. Two medical application instances, medical information integration and content-based image diagnosis or retrieval of emphysema disease, are introduced and realized with these technologies.
In gridcomputing, group communication is an important strategy to realize large-scale information resource sharing. However, it is very difficult to ensure the security of group communication in large-scale grid envi...
详细信息
In gridcomputing, group communication is an important strategy to realize large-scale information resource sharing. However, it is very difficult to ensure the security of group communication in large-scale grid environment. In this paper, based on the basic theories of threshold signature and the basic characteristics of group communication in grid, we present four algorithms, including keys generating, individual signature generating and verifying, group signature generating and encrypting, decrypting and group signature verifying, which constitute the authenticated encryption mechanism for group communication in grid. Finally, we validate the correctness of the authenticated encryption mechanism proposed in this paper and analyze its security. In addition, the validity of this mechanism is verified by the experiments. The results show that it is efficient to ensure the security of group communication in grid.
Cell broadband engine (Cell BE) is a state-of-the-art heterogeneous multi-core processor. It is an accelerator-based multi-core architecture, which contains a powerful 64-bit dual-threaded PowerPC core and eight high ...
详细信息
ISBN:
(纸本)9780769533063
Cell broadband engine (Cell BE) is a state-of-the-art heterogeneous multi-core processor. It is an accelerator-based multi-core architecture, which contains a powerful 64-bit dual-threaded PowerPC core and eight high efficient single-instruction-multiple-data (SIMD) cores. Apart from traditional parallel systems, the users must explicitly manage the communication, scheduling and load-balancing to achieve cellpsilas greatest performance. In this paper, a novel heterogeneous data parallel computational model on cell BE is proposed. This aggressive model could not only exploit computing power of SPE but also that of PPE and aggregate them together to achieve high performance. We investigate the performance of this model with naive ray tracing algorithm. The preliminary experimental results validate the efficiency of this model.
In the existing data fetching algorithms for P2P streaming systems, the peers usually fetch data independently, leading to huge inter-AS traffic (AS: autonomous system). This paper proposes CoFetch, a collaborative fe...
详细信息
In the existing data fetching algorithms for P2P streaming systems, the peers usually fetch data independently, leading to huge inter-AS traffic (AS: autonomous system). This paper proposes CoFetch, a collaborative fetching algorithm for P2P live streaming systems to decrease inter-AS traffic. In CoFetch, to avoid that all peers fetch the same data from inter-AS connection, instead of aggressively fetching data depending on the peers' own desires, the peers divide requests into multiple steps. In each step, peers mainly and locally share data fetched in previous steps by other collaborating peers and request subset data from inter-AS connections. The analytical results show that, inter-AS traffic in CoFetch is independent of the number of peers in AS but the number of collaborating peers in AS. Furthermore, in each overlay, when we limit the number of collaborating peers in one AS from 5 to 20, the inter-AS traffic is about 1.7-3 times of the streaming rate, regardless of the number of peers.
暂无评论