By Topic

Proceedings of IEEE International Symposium on Parallel Algorithms Architecture Synthesis

17-21 March 1997

Filter Results

Displaying Results 1 - 25 of 49
  • Proceedings of IEEE International Symposium on Parallel Algorithms Architecture Synthesis

    Publication Year: 1997
    Request permission for commercial reuse | PDF file iconPDF (452 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 1997, Page(s):389 - 390
    Request permission for commercial reuse | PDF file iconPDF (90 KB)
    Freely Available from IEEE
  • Parallel rendering techniques for massively parallel visualization

    Publication Year: 1997, Page(s):276 - 281
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    As the resolution of simulation models increases, scientific visualization algorithms which take advantage of the large memory and parallelism of massively parallel processors (MPPs) are becoming increasingly important. For large applications, rendering on an MPP tends to be preferable to rendering on a graphics workstation, due to the MPP's abundant resources: memory, disk and numerous processors... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A load balancing algorithm using prediction

    Publication Year: 1997, Page(s):159 - 165
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (516 KB)

    The static task allocation problem and the dynamic load balancing problem are relevant issues when using a multiprocessor computer system to execute parallelized tasks. The paper presents an artificial intelligence (AI) strategy to resolve the above problems under the PVM (Parallel Virtual Machine). The AI technique is employed to accurately predict better allocation for PVM tasks in their initial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The stereo correspondence problem on a ring-based network

    Publication Year: 1997, Page(s):265 - 275
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1188 KB)

    A reconfigurable network called the “reconfigurable multi-ring network” (RMRN) is described. The RMRN is shown to be a truly scalable network in that each node in the network has a fixed degree of connectivity and the reconfiguration mechanism ensures a network diameter of O(log2N) for an N-processor network. Basic message passing and reconfiguration primitives for the SIMD/... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel algorithm for k-minimum spanning trees

    Publication Year: 1997, Page(s):384 - 388
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    A parallel algorithm to find k, 2⩽k⩽nn-2, spanning trees from a connected, weighted and undirected graph C(V, E, W) in the order of increasing weight is presented. It runs in O(T(n)+klogn) time with O(n2/log n) processors on a CREW PRAM, where n=|V|, m=|E| and T(n), O(log n)⩽T(n)⩽O(log2 n), is the time of the fastest parallel algorithms to find a m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A distributed environment for hypercube computing

    Publication Year: 1997, Page(s):256 - 263
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    Proposes a distributed computing environment, called the Virtual Cube (VC), to support arbitrarily large binary hypercube computing on a cluster of homogeneous workstations that are interconnected by an Ethernet LAN. The embedding concept between binary hypercube parallel architectures is introduced, and the concept of a cluster of computers interconnected through a computer network. In VC, a SIMD... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient processor allocation algorithm using two-dimensional packing

    Publication Year: 1997, Page(s):151 - 158
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB)

    The mesh is one of the most widely used interconnection networks for multiprocessor systems. We propose an approach to partition a given mesh into m submeshes which can be allocated to m tasks with grid structures. We adapt two dimensional packing to solve the submesh allocation problem. Due to the intractability of the two dimensional packing problem, finding an optimal solution is computationall... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Block-SVD algorithms and their adaptation to hypercubes and rings

    Publication Year: 1997, Page(s):175 - 181
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    The paper presents parallel algorithms for efficient solution of the SVD (singular value decomposition) problem by the block two sided Jacobi method. It is shown how the method could be applied to MIMD computers with the hypercube and ring topology. Three types of orderings for solving SVD on block structured submatrices are analysed from the point of view of communication requirements and suitabi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient parallel and distributed topological sort algorithms

    Publication Year: 1997, Page(s):378 - 383
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    In this paper, we give efficient parallel and distributed algorithms for the topological sort problem on acyclic graphs with n vertices. Our parallel algorithm solves the problem on a CREW PRAM in O(log2 n) time with O(M(n)/log n) processors, where M(n) denotes the number of processors needed to multiply two n×n integer matrices over the integer ring. The best known upper bound of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modular parallel programming in mpC for distributed memory machines

    Publication Year: 1997, Page(s):248 - 255
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (708 KB)

    The mpC language is an ANSI C superset supporting modular parallel programming for distributed memory machines. It allows the user to specify dynamically an application topology, and the mpC programming environment uses this information in run time to provide the most efficient execution of the program on any particular distributed memory machine. The paper describes the features of mpC and its pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An algorithmic approach on deadlock detection for enhanced parallelism in multiprocessing systems

    Publication Year: 1997, Page(s):233 - 238
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    This paper presents a non-blocking deadlock detection scheme with immediate knot detection in multiprocessing systems. We assume an expedient state and a special case where each request is limited to one resource unit at a time. Unlike the previous deadlock detection schemes, this new method, using some different data structures takes O(1) time for detecting a knot and O(nm) time for blocking or h... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • World-wide computing infrastructure: global and local partnership

    Publication Year: 1997, Page(s):25 - 30
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    The world wide computing infrastructure on the growing computer network technology is a leading technology to make a variety of information services accessible through the Internet for all types of users: from the high end, high performance computing users through to many personal computing users. One important feature of such services is location transparency; information can be obtained irrespec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An architecture-independent workload characterization model for parallel computer architectures

    Publication Year: 1997, Page(s):143 - 150
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (764 KB)

    A model is presented for representing and comparing workloads, based on the way they would exercise parallel machines. This workload characterization is derived from parallel instruction centroid and parallel workload similarity. The centroid is a simple measure that aggregates average parallelism instruction mix, and critical path length. When captured with abstracted information about communicat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Instruction-level parallel processors-dynamic and static scheduling tradeoffs

    Publication Year: 1997, Page(s):74 - 81
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    Recently, high performance computer architecture has focused on dynamic scheduling techniques to issue and execute multiple operations concurrently. These designs are complex and have frequently shown disappointing performance. A complementary approach is the use of static scheduling techniques to exploit the same parallelism. We describe some of the tradeoffs between the use of static and dynamic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shortcut interconnection: new multistage interconnection network for the locality of reference in shared memory multiprocessor system

    Publication Year: 1997, Page(s):216 - 224
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB)

    The traditional UPP MINs (Unique Path Property MIN)-Omega, baseline, Multistage Cube Network-have usually been designed for constructing N×N MIN using (N/2) log2N(O(Nlog2 N)) SEs. So far the multiple path MINs have been realized by adding additional hardware such as extra stages or duplicated data links. This paper presents a new Multistage interconnection Network (MIN)... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Introducing parallelism in multimedia database systems

    Publication Year: 1997, Page(s):348 - 355
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (800 KB)

    We discuss possibilities of parallelizing multimedia database systems, especially based on our experiences with our multimedia database system MultiMAP and our parallel database system MIDAS. We describe both initial systems in brief. Our main purpose is to examine when parallelism is of advantage and where sequential processing in multimedia databases is sufficient View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solver with the differential algebraic cubic interpolated propagation scheme on massively parallel computer

    Publication Year: 1997, Page(s):200 - 205
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (368 KB)

    A method for solving hydrodynamic equations with the differential algebraic-cubic interpolated propagation (DA-CIP) scheme on massively parallel computer is presented. The scheme uses a spatial profile interpolated with cubic polynomials within the grid cells; it is formulated straightforwardly from the equations of motion describing the system without algorithmically specific parameters, and appl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Portable multiprecision arithmetic package based on message passing interface

    Publication Year: 1997, Page(s):324 - 331
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (644 KB)

    Multiprecision arithmetic allows one to significantly reduce the influence of rounding errors in cases when the standard data representation does not support the required accuracy. In this paper, we discuss an effective programming technology for supporting a given accuracy of calculations in a suitable time by a complex method using multiprecision arithmetic, dynamically changeable operand length... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient submesh allocation scheme for 3D torus multicomputer systems

    Publication Year: 1997, Page(s):83 - 90
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (740 KB)

    Recently, the 3D torus has emerged as a new candidate interconnection topology for message-passing multicomputer systems. In this paper, we propose an efficient submesh allocation scheme for 3D tori based on a first-fit approach. The scheme minimizes the allocation and deallocation time complexity by employing an efficient mechanism for searching a free submesh based on 3D window sliding, and mani... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The shortest routing path in star graphs with faulty clusters

    Publication Year: 1997, Page(s):91 - 96
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    Given a graph G, a cluster C is a connected subgraph of G, and C is called a faulty cluster if all nodes in C are faulty. Given an n-dimensional star graph Gn with n-2 faulty clusters of diameter at most 2, it has been shown by the authors (1994) that any two non-faulty nodes s and t of Gn can be connected by a fault-free path of length at most d(Gn)+6 in O(n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new transformation method to generate optimized DO loop from FORALL construct

    Publication Year: 1997, Page(s):240 - 247
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    Data parallel language was suggested to solve programming problems of distributed memory machines in terms of programming language. Among data parallel languages, HPF is a standard data parallel language across a variety of high-performance architectures. Most HPF compilers are source-to-source translators because they can be easily implemented. However, these source-to-source compilers produce si... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Run-time reference clustering for cache performance optimization

    Publication Year: 1997, Page(s):42 - 49
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    We introduce a method for improving the cache performance of irregular computations in which data are referenced through run time defined indirection arrays. Such computations often arise in scientific problems. The presented method called Run-Time Reference Clustering (RTRC), is a run time analog of a compile time blocking used for dense matrix problems. RTRC uses the data partitioning and remapp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prefetching by self-contained variables-a generalization from array to recursive data structures

    Publication Year: 1997, Page(s):225 - 232
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (716 KB)

    Data prefetching has proven to be effective in hiding memory latency from the program execution time. Most current data prefetching schemes are targeted only for array references with constant strides; for array references with non-constant strides, they lose most of their effectiveness. In this paper, we propose a novel data prefetching scheme, based on a property called the self-containedness of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extraction and optimization of the implicit program parallelism by dynamic partial evaluation

    Publication Year: 1997, Page(s):332 - 339
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB)

    Much work has been done to implement declarative languages in parallel form. Most of them tend to resort to imperative features for some purposes, particularly for description of the parallelism. We propose parallel computation on associative networks, a machine independent parallel programming model, for automatic extraction of available inherent parallelism and optimization of declarative progra... View full abstract»

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