This article is an overview of the GIPSY Demand Migration System (DMS). This system brings a Demand Driven Execution Engine like the one used in the GIPSY to a high level of distributiveness and interoperability of op...
详细信息
ISBN:
(纸本)0769523331
This article is an overview of the GIPSY Demand Migration System (DMS). This system brings a Demand Driven Execution Engine like the one used in the GIPSY to a high level of distributiveness and interoperability of operational nodes, by mixing together advanced distributed technologies. The main Demand Migration System's artifacts are discussed, and their different distributions within the GIPSY are surveyed. The article concludes with a presentation of a successful GIPSY Demand Migration implementation, based on JINI. This paper describes only the aspects of the GIPSY Demand Migration, i.e. it does not deal with load balancing and efficiency aspects of the GIPSY, as these are to be tackled by other subsystems of the GIPSY.
Computer-generated Fresnel hologram (Fresnel CGH) for 3-D object can be made by calculation of Fresnel diffraction., However, since-diffraction computing is complicated, it is-required huge calculation time. In this p...
详细信息
ISBN:
(纸本)0819445967
Computer-generated Fresnel hologram (Fresnel CGH) for 3-D object can be made by calculation of Fresnel diffraction., However, since-diffraction computing is complicated, it is-required huge calculation time. In this paper, we propose the fast calculation method of Fresnel CGH utilizing distributed parallel processing.
Several load balancing schemes are recently proposed for distributed object computing systems, which are widely envisioned to be the desired distributed software development paradigm due to the higher modularity and t...
详细信息
ISBN:
(纸本)0769513727
Several load balancing schemes are recently proposed for distributed object computing systems, which are widely envisioned to be the desired distributed software development paradigm due to the higher modularity and the capability of handling machine and operating system heterogeneity. However, while the rationales and mechanisms employed are dramatically different, the relative strengths and weaknesses of these approaches are unknown, making it difficult for a practitioner to choose an appropriate approach for the problem at hand. In this paper, we describe in detail three representative approaches, which are all practicable, and present a quantitative comparison using our experimental distributed object computing platform. Among these three approaches, namely, javaspaces based, request redirection based, and fuzzy decision based, we find that the fuzzy decision based algorithm outperforms the other two considerably.
Processing astronomical images is an inherently resource intensive procedure that is typically time consuming as well. At the same time, first order reductions are particularly important during the observing process s...
详细信息
ISBN:
(纸本)0819454257
Processing astronomical images is an inherently resource intensive procedure that is typically time consuming as well. At the same time, first order reductions are particularly important during the observing process since they can provide key quality assessment information. To resolve this conflict, the Online Data Processing (OLDP) system being commissioned at the Gemini Observatory automatically maps reduction sequences onto a cluster of servers during observing, taking advantage of available concurrency where possible. The user constructs a visual representation of the sequence for an observation using the Gemini Observing Tool. No constraints are placed upon the series of steps that comprise the sequence. At runtime, the OLDP reads the reduction sequence from the Observing Database and splits it into smaller pieces for simultaneous execution on the cluster. Recipe steps can be implemented in IRAF, shell scripts, or Java, and other types can be plugged into the architecture without modifying the core of the code base. This paper will introduce the Gemini OLDP and demonstrate how it utilizes modern infrastructure technology like Jini and javaspaces to achieve its goals.
So that a military commander has precise command, control, and planning information available for a given mission, information must be tailored for a particular area of operation, for a specific level of command, and ...
详细信息
ISBN:
(纸本)0819442453
So that a military commander has precise command, control, and planning information available for a given mission, information must be tailored for a particular area of operation, for a specific level of command, and for a specific time period. The commander must be able to quickly understand the information, query related information, and analyze the information in collaboration with others to plan and control a military operation. To provide such tailored information, we envision an environment in which customized agents traverse a diverse, distributed, frequently changing information space to identify relevant data. Once aware of the data, visual interfaces facilitate understanding and navigation. Geographically separated users manipulate a customized view to access a common information framework in which they can interactively collaborate with other users. We propose an architecture for achieving this vision that is well suited to implementation with Jini networking technologies. As a first step toward achieving this architecture we have developed a collaborative visualization framework that enables multiple distributed users to interact using shared visual interface components while simultaneously communicating via a text-based chat window. Our framework provides communications management and messaging support and well-defined Java class interfaces for integrating visualization components. Initial results indicate significant benefits for application development through reuse and extensibility. We achieved interactive performance and synchronized collaboration using javaspaces as the underlying distributed technology.
The Linda tuplespace paradigm is increasingly being used in the design of large-scale Internet-based systems. However, centralized tuplespace implementations suffer from both availability and scalability limitations. ...
详细信息
ISBN:
(纸本)0819446424
The Linda tuplespace paradigm is increasingly being used in the design of large-scale Internet-based systems. However, centralized tuplespace implementations suffer from both availability and scalability limitations. GLOBE is a distributed and replicated tuplespace that combines high availability and scalability in such heterogeneous and loosely coupled systems. The level of availability and scalability of a GLOBE tuplespace can dynamically and independently be adjusted by modifying the number of replicas and partitions in the system. A tuplespace semantics is defined specifically tailored for large-scale, loosely coupled networks. The GLOBE replica update protocols are based on a combination of active operation propagation and anti-entropy propagation in the case of failures. A prototype of GLOBE has been implemented by extending a centralized javaspaces implementation. Evaluations of the prototype implementation indicate that a distributed and replicated GLOBE tuplespace can outperform a highly loaded centralized tuplespace.
What distinguishes e-commerce from ordinary commerce? What distinguishes it from distributed computation? In this paper we propose a performative theory of e-commerce, drawing on speech act theory, in which e-commerce...
详细信息
ISBN:
(纸本)9781581136838
What distinguishes e-commerce from ordinary commerce? What distinguishes it from distributed computation? In this paper we propose a performative theory of e-commerce, drawing on speech act theory, in which e-commerce exchanges are promises of future commercial actions, whose real-world meanings are constructed jointly and incrementally. We then define a computational model for this theory, called Posit Spaces, along with the syntax and semantics for an agent interaction protocol, the Posit Spaces Protocol or PSP. This protocol enables participants in a multi-agent commercial interaction to propose, accept, modify and revoke joint commitments. Our work integrates three strands of prior research: the theory of Tuple Spaces in distributed computation; formal dialogue games from argumentation theory; and the study of commitments in multi-agent systems.
The search for techniques to process growing mountains of data efficiently continues apace, nowhere more so than in the field of bioinformatics. Distributed processing represents a practical solution to the search for...
详细信息
ISBN:
(纸本)9780954414511
The search for techniques to process growing mountains of data efficiently continues apace, nowhere more so than in the field of bioinformatics. Distributed processing represents a practical solution to the search for more powerful architectures that can harness the power of multiple machines to solve a given *** this approach brings with it associated problems - selecting the most appropriate language to use in developing the software, development platform and system *** paper addresses some of these issues and also details observations gathered during the design and construction of one such distributed system [1] built using Java to solve a well-known bioinformatics problem [2] in a parallel processing environment using artificial neural networks. This paper does not provide a detailed discussion of the problem itself or results obtained, however the inquisitive reader will find further details in [1].
暂无评论