Proceedings International Phoenix Conference on Computers and Communications

28-31 March 1995

Filter Results

Displaying Results 1 - 25 of 110
  • Internetworking with ATM and legacy LAN networks

    Publication Year: 1995
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (25 KB)

    Summary form only given. To be truly successful, ATM network islands need to interoperate with today's LANs and WANs. In this talk we will examine alternatives for attaching routers and bridges to an ATM network as well as the issues associated with internetworking ATM networks with WAN network types such as SMDS and Frame Relay.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings International Phoenix Conference on Computers and Communications

    Publication Year: 1995
    Request permission for commercial reuse | PDF file iconPDF (30 KB)
    Freely Available from IEEE
  • Distributed simulation in a loosely coupled environment using the TCP/IP protocol

    Publication Year: 1995, Page(s):122 - 127
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    We investigate in this paper the feasibility and the performance of two distributed simulation schemes in a loosely coupled multi-computer environment supported by the TCP/IP protocol. We compare the results of conservative and optimistic approach of distributed simulation of a bus based computer network. The results show that both approaches are effective even when implemented on a set of worksta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effect of faulty network components on node availability

    Publication Year: 1995, Page(s):128 - 135
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    Failure of network hardware components in parallel systems results in deterioration of the communication support provided to various nodes. Limited communication capability may result in the unavailability of one or more nodes to users. In this paper, we develop a framework to study the effect of faulty network components on node availability. We use the framework to investigate the specific case ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • System-level testing assignment for hypercubes with lower fault bounds

    Publication Year: 1995, Page(s):136 - 142
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    The maximum allowed number of faulty processors in an n-dimensional hypercube system is n under PMC model for diagnosis. When the n fault bound is adopted, all links will be used to perform diagnosis. However, if the fault bound is lower than n, many links can be freed from the task of performing diagnosis. In this paper, we show that each drop of the fault bound by 1 can free 2n-1 link... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiences with high-level parallel programming systems

    Publication Year: 1995, Page(s):472 - 478
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (668 KB)

    A programmer developing software for parallel systems usually is responsible for the management of low level issues such as communication and synchronization. This is potentially problematic from the perspectives of correctness and portability. This paper considers an alternative approach, namely, the use of high level parallel programming systems. We report our experiences with implementing paral... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A practical overview of synchronization status messaging and its applicability to SONET networks

    Publication Year: 1995, Page(s):571 - 577
    Cited by:  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    The paper discusses synchronization status messaging and its applicability to SONET networks. The synchronization status messaging formats and requirements are first described from a standards perspective. The application of synchronization status messaging to SONET linear and ring architectures is then explained through step by step examples. The interworking between nonmessaging and messaging eq... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A top-down method for synthesizing optimized protocol converters

    Publication Year: 1995, Page(s):270 - 276
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (672 KB)

    In this paper, we propose a top-down method for constructing optimized protocol converters to achieve interoperability between heterogeneous computer networks. This method first generates a converter from a given service specification of the internetworking system and two protocol specifications, based on two important concepts: controllability and observability. The reduction relation is used to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient routing algorithms for folded-cube networks

    Publication Year: 1995, Page(s):143 - 151
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB)

    We consider the partial multinode broadcast, the total exchange, and several other prototype communication tasks in a folded-cube network of processors. In the partial multinode broadcast in a N-processor network, each one of M arbitrary nodes (M⩽N) broadcasts a packet to all the remaining N-1 nodes. In the total exchange task each processor sends a separate (personalized) packet to every othe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis of a dual bus reservation based fiber-optic network

    Publication Year: 1995, Page(s):479 - 486
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    In this paper, we present the performance of a dual bus reservation based (DBRB) access protocol, for high speed local and metropolitan area networks. The DBRB network consists of unidirectional dual bus topology of fiber optic cables. At each end there is a master station which generates a frame of slots. When a station wants to transmit, it has to make a reservation in a frame on one bus and wai... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Throughput analysis of interconnecting CSMA/CD LANs with switching hubs

    Publication Year: 1995, Page(s):522 - 528
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    In this paper, we study the throughput characteristics of carrier sense multiple access with collision detection (CSMA/CD) local area networks (LANs) interconnecting with switching hubs. The interconnection schemes considered here not only increase the performance of CSMA/CD LANs to meet the evolving bandwidth requirements of today's applications, but also reduce the overhead costs when updating e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ATM LAN interconnections with a cut-through nonblocking switch

    Publication Year: 1995, Page(s):578 - 584
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB)

    The paper presents a cut through ATM switch with shared buffers for LAN interconnections. The incoming ATM cells are not stored into shared buffers as long as the destination output port is available. In other words, an ATM cell is waiting at the input port. It will be passed through the switch using a cut through link, if the destination output port is available. On the other hand, it will be sto... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The RAPID transport protocol

    Publication Year: 1995, Page(s):277 - 282
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    Future networking environments are expected to provide more bandwidth and be more robust to bit errors. Such changes will pose new requirements for data transfer protocols. Rather than trying to adapt an existing transport protocol to this new environment, we decided to develop a new one called RAPID. The most important features of RAPID are its unidirectional data transfer capability and a clear ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A reconfigurable 1-factor hypercubic embedding interconnection network for parallel processing

    Publication Year: 1995, Page(s):152 - 158
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    A reconfigurable interconnection network based on a multi-ring architecture called REFINE is described. REFINE embeds a single 1-factor of the Boolean hypercube in any given configuration. The mathematical properties of the REFINE topology and the hardware for the reconfiguration switch are described. The REFINE topology is scalable in the sense that the number of interprocessor communication link... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • HyperPascal for architecture independent parallel programming

    Publication Year: 1995, Page(s):451 - 457
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    The design and implementation of a high-level parallel programming language interface for distributed-memory MIMD architectures is described. This interface is termed as HyperPascal and is based on a computation graph decomposition model of parallel programming. HyperPascal closely resembles the Pascal language but in addition provides constructs that allow for the high-level specification of proc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design issues in client/server systems

    Publication Year: 1995, Page(s):487 - 493
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (524 KB)

    In this paper we present a methodology to address design issues that relate to the client/server model of distributed processing. The design process consists of four phases, namely requirements specification, conceptual design, system design and analysis, and implementation. A case study is presented where the methodology is used to design a client/server computing environment that provides distri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive proportional rate control for ABR service in ATM networks

    Publication Year: 1995, Page(s):529 - 535
    Cited by:  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    The emergence of asynchronous transfer mode (ATM) technology has generated new challenging problems for computer network designers. One of these challenges lies in the efficient management of ATM traffic so that the communication bandwidth of the network can be optimally utilized. Considerable standardisation efforts in recent ATM Forum activities have been centered on the traffic management of av... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MPCBN: a high performance ATM switch

    Publication Year: 1995, Page(s):585 - 591
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (552 KB)

    It has been recognized that the main bottleneck of ATM networks is the switch itself. We propose using a multiple partitionable circular bus network (MPCBN) as an ATM switch. To achieve parallel execution of cell transfer requests, we use a graph coloring algorithm for conflict resolution. An approach of using finite projective places is then used to reduce the number of switch points from O(N View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing nonseries-parallel structures in multilevel logic minimization

    Publication Year: 1995, Page(s):95 - 101
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (540 KB)

    Traditional multilevel logic synthesis generally involves decomposing a given two-level sum-of-products expression into a series parallel network by factorization. There is a potential for greater savings if we can identify a nonseries-parallel network realizing the same function. Little work has been done in the area of recognition of nonseries-parallel structures. This paper introduces a new alg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Query-driven petri net reduction for analysis in Ada tasking

    Publication Year: 1995, Page(s):334 - 340
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    We have illustrated methods to address three types of problems in static analysis for Ada tasking: quantitative questions, safety problems and MAY-happen event problems. We have applied a two-phase methodology to automate analysis: first deriving a semantically rich model independent of any specific analysis issue, that is the original Ada nets, and then manipulating this model with algorithms tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formal verification of a commercial serial bus interface

    Publication Year: 1995, Page(s):378 - 382
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    A new technique for the analysis of sequential hardware designs is illustrated on a serial bus interface. A set of experiments using models of the bus interface and temporal logic formulae is discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • NView: a visual framework for network tool integration

    Publication Year: 1995, Page(s):283 - 289
    Cited by:  Papers (1)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (728 KB)

    Monitoring and managing distributed applications and networks present a number of problems. Tracking down the source of connection problems over a large area, such as the Internet, can be time-consuming and confusing, as one must deal with many small utilities. In this paper, we present NView a framework program for integrating network tools into a uniform visual interface with a minimum of effort... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An ATM protocol for local access and control of internal/external traffic

    Publication Year: 1995, Page(s):159 - 167
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (644 KB)

    A new protocol is proposed to regulate the local media access to a private asynchronous transfer mode (ATM) switch as well as to control the flow of traffic that is either internal or external to such a switch. A mechanism, which guarantees a certain bandwidth by providing a fixed number of credits per timeslot to competing terminals, is modified to permit intermediate resets for those unsatisfied... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • “Receiver makes right” data conversion in PVM

    Publication Year: 1995, Page(s):458 - 464
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (552 KB)

    Using a receiver makes it right (RMR) data conversion technique in PVM significantly improves the message-passing performance in heterogeneous environments. The improvements are due to two factors: (1). RMR reduces the need for conversions in a heterogeneous environment; (2). At most each message is converted, only once compared to twice for XDR used in public version of PVM, and our conversion ro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamically reconfigurable switch for high-speed networks

    Publication Year: 1995, Page(s):508 - 514
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (648 KB)

    We present a design for a dynamically reconfigurable switch for high-speed networks. The proposed switch will be used to build high-performance parallel/distributed systems. Switch reconfigurability is exploited to implement different interconnection topologies and support different application requirements. We discuss an FPGA implementation of such a switch where a new configuration can be attain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.