Proceedings of 1994 International Conference on Parallel and Distributed Systems

19-21 Dec. 1994

Filter Results

Displaying Results 1 - 25 of 121
  • Proceedings of 1994 International Conference on Parallel and Distributed Systems

    Publication Year: 1994
    Request permission for commercial reuse | PDF file iconPDF (569 KB)
    Freely Available from IEEE
  • Panel 1: Are We Providing The Right Education For Computer Science/engineering Students?

    Publication Year: 1994, Page(s): 14
    Request permission for commercial reuse | PDF file iconPDF (70 KB)
    Freely Available from IEEE
  • Panel 2: Is It Possible to Fairly Compare Interconnection Networks?

    Publication Year: 1994, Page(s):16 - 18
    Request permission for commercial reuse | PDF file iconPDF (284 KB)
    Freely Available from IEEE
  • Panel 3: Taiwan's Information Superhighway: Technical Issues And Social Impacts

    Publication Year: 1994, Page(s): 20
    Request permission for commercial reuse | PDF file iconPDF (47 KB)
    Freely Available from IEEE
  • Panel 4: What Types Of Research Papers Should We Be Writing?

    Publication Year: 1994, Page(s): 22
    Request permission for commercial reuse | PDF file iconPDF (78 KB)
    Freely Available from IEEE
  • Panel 5: Parallel Processing: What Have We Done Wrong?

    Publication Year: 1994, Page(s): 24
    Request permission for commercial reuse | PDF file iconPDF (43 KB)
    Freely Available from IEEE
  • Panel 6: Parallel And Distributed Processing Research In Some Asian Countries

    Publication Year: 1994, Page(s): 26
    Request permission for commercial reuse | PDF file iconPDF (50 KB)
    Freely Available from IEEE
  • Parallel block generalized WZ factorization

    Publication Year: 1994, Page(s):174 - 179
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (599 KB)

    In this paper we first present a block strategy for the generalized WZ factorization, which consists of block factorizing a matrix A in the form A=WZW/sup -1/. This study shows how a block strategy may be used to reduce a large eigenvalue problem into a number of smaller ones. Next, we develop a parallel multi-phase algorithm for this method, which requires processes such as matrices products, Gau... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient Hough transform algorithm on SIMD hypercube

    Publication Year: 1994, Page(s):236 - 241
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB)

    This paper presents a fast algorithm for computing the Hough transform on SIMD hypercube architectures. For an image with N/spl times/N pixels and n quantized /spl theta/ values, our algorithm computes the Hough transform in O(logN) time on a hypercube of size N/spl times/N/spl times/n. An efficient algorithm for large Hough transform problems on a smaller fixed-size hypercube is also given. On a ... View full abstract»

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

    Publication Year: 1994, Page(s):769 - 771
    Request permission for commercial reuse | PDF file iconPDF (178 KB)
    Freely Available from IEEE
  • On evaluating parallel sparse Cholesky factorizations

    Publication Year: 1994, Page(s):162 - 167
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    Though many parallel implementations of sparse Cholesky factorization with the experimental results accompanied have been proposed, it seems hard to evaluate the performance of these factorization methods theoretically because of the irregular structure of sparse matrices. This paper is an attempt to such research. On the basis of the criteria of parallel computation and communication time, we suc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CGIN: a modified Gamma interconnection network with multiple disjoint paths

    Publication Year: 1994, Page(s):366 - 372
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    To ensure high terminal reliability for the Gamma interconnection network (GIN), we propose a new modified GIN, referred to as CGIN (cyclic Gamma interconnection network) as its connecting patterns between stages exhibit a cyclic feature. The fact that there exist multiple disjoint paths between any communication pair for all types of CGINs makes it possible to tolerate any arbitrary single fault ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A discrete-event simulation model for characterizing parallel file transfers

    Publication Year: 1994, Page(s):154 - 160
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB)

    In this paper, we characterize the performance of parallel file transfers using the Zebra striped network file system by means of distributed discrete-event simulation model which uses a variation of the conservative timestamping-technique. The simulator is a powerful tool that can be adapted to model related systems such as multiprocessors and distributed shared memories. Preliminary simulation r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extracting the parallelism in program with unstructured control statements

    Publication Year: 1994, Page(s):264 - 270
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    Program parallelization is inhibited by unstructured control statements such as GOTOs, causing interacting and overlapping execution trajectories. In this contribution, a program restructuring method is proposed to convert unstructured control statements into block if statements and while loops. Furthermore, an algorithm is presented to transform a common type of while loops into do loops. The tec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multicast communication in 2-D mesh networks

    Publication Year: 1994, Page(s):63 - 68
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (608 KB)

    Multicast refers to the message delivery from a source node to an arbitrary number of destination nodes in a communication network. The 2D mesh topology has become increasingly popular as interconnection network for multicomputers and distributed systems. Two multicast algorithms are proposed for 2D mesh networks. The computational complexity of the algorithms is analyzed. The performance of the p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algorithms for node disjoint paths in incomplete star networks

    Publication Year: 1994, Page(s):296 - 303
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    We give efficient algorithms for node disjoint path problems in incomplete star graphs which are defined in this paper to reduce the large gaps in the size of systems based on star graph topologies. Four disjoint path paradigms in incomplete star graphs are discussed: (1) disjoint paths between a pair of nodes s and t, (2) disjoint paths from a node s to a set T of nodes, (3) disjoint paths from a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the development paradigm of distributed applications

    Publication Year: 1994, Page(s):736 - 741
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    We propose an ideal development paradigm facilitating the implementation of distributed applications. In this paradigm a developer focuses his mind only on the application itself and does not need to spend time on application-unrelated activities. The programming style is nearly consistent with that of centralized system. The mechanism of the general support environment to this paradigm is describ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of relaxed memory consistency models for multithreaded multiprocessors

    Publication Year: 1994, Page(s):474 - 480
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (648 KB)

    Stochastic timed Petri nets are developed to evaluate the relative performance of distributed shared memory models for scalable multithreaded multiprocessors. The shared memory models evaluated include the Sequential Consistency (SC), the Weak Consistency (WC), the Processor Consistency (PC) and the Release Consistency (RC) models. Under saturated conditions, we found that multithreading contribut... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extending Vienna Fortran with task parallelism

    Publication Year: 1994, Page(s):258 - 263
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    Vienna Fortran supports a wide range of data-parallel numerical problems. However, a significant number of scientific and engineering applications are of a multi-disciplinary and heterogeneous nature and thus do not fit well into the data parallel paradigm. In this paper we present new language extensions to fill this gap. Tasks can be spawned as asynchronous activities in a homogeneous or heterog... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pyramided hypercube: an extendable cubic network with fixed degree

    Publication Year: 1994, Page(s):690 - 697
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    The proposed network is a pyramid-like network of hypercubes, called pyramided hypercube. A pyramided hypercube containing m levels and having n-cube as basic configuration is denoted by PH(m,n). A PH(m,n) with fixed degree n+2, possesses logarithmic diameter, optimal fault tolerance, and capability of simple routing. The PH(m,n) can be extended smoothly with a constant predefined building block b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Group communications algorithm for dynamically updating in distributed systems

    Publication Year: 1994, Page(s):56 - 62
    Cited by:  Papers (8)  |  Patents (34)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    The paper proposes a novel updating technique, dynamically updating to achieve extension or modification of functions in a distributed system. Usual updating techniques require multiple processes to suspend simultaneously in order to avoid an unspecified reception caused by the conflict of different versions of processes. By using the proposed dynamically updating technique, the updating operation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance tuning of message passing programs through visual analysis

    Publication Year: 1994, Page(s):730 - 735
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (660 KB)

    Designing a parallel program to fully utilise the processing power of a multiprocessor machine requires a series of performance analysis and tuning. The paper describes a performance tuning tool for message passing parallel programs. The tool combines the advantages of relational databases and spreadsheets to organise the performance data and analyse the program performance through visualisation. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Storage design and retrieval of continuous multimedia using multi-disks

    Publication Year: 1994, Page(s):148 - 153
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (552 KB)

    In the domain of multimedia applications, continuous display is an important issue. In this paper, we present a practical method to allocate disk storage for multimedia data so that continuous requirement can be met. This technique explores data-transfer parallelism on a multidisk system. Moreover, in order to ensure that continuous retrieval can be achieved in a multiuser environment, we propose ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extracting multi-thread with data localities for vector computers

    Publication Year: 1994, Page(s):466 - 473
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    In this paper, we propose a source-to-source compilation strategy to partition vectorized loop programs into multithread execution form. Each partitioned thread consists of instances of statements with localities in vector registers. The multi-threading scheme gives a novel combination of loop unrolling, statement instances reordering, index shifting, vector register reuse exploiting, and multi-th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An improved characterization of 1-step recoverable embeddings: rings in hypercubes

    Publication Year: 1994, Page(s):508 - 514
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (548 KB)

    An embedding is 1-step recoverable if any single fault occurs, the embedding can be reconfigured in one reconfiguration step to maintain the structure of the embedded graph. In this paper we present an efficient scheme to construct this type of 1-step recoverable ring embeddings in the hypercube. Our scheme will guarantee finding a 1-step recoverable embedding of a length-k (even) ring in a d-cube... View full abstract»

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