By Topic

Parallel Algorithms/Architecture Synthesis, 1997. Proceedings., Second Aizu International Symposium

Date 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
    Save to Project icon | Request Permissions | PDF file iconPDF (452 KB)  
    Freely Available from IEEE
  • Author index

    Publication Year: 1997 , Page(s): 389 - 390
    Save to Project icon | Request Permissions | PDF file iconPDF (90 KB)  
    Freely Available from IEEE
  • Memory hierarchy design for Jetpipeline: to execute scalar and vector instructions in parallel

    Publication Year: 1997 , Page(s): 66 - 73
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (632 KB)  

    Superscalar and VLIW architectures are based on instruction level parallelism (ILP), which ideally achieve high performance to execute multiple instructions in parallel. However, the system performance is restricted because of the Von Neumann bottleneck. Therefore, the memory hierarchy design is very important in this kind of architecture. We have proposed a computer architecture named Jetpipeline... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training neocognitron to recognize handwritten digits in the real world

    Publication Year: 1997 , Page(s): 292 - 298
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (512 KB)  

    Using a large-scale real-world database-the ETL-1 database of the Electrotechnical Laboratory in Japan-we show that a neocognitron trained by unsupervised learning with a winner-take-all process can recognize handwritten digits with a recognition rate higher than 97%. We use the technique of dual thresholds for feature-extracting S-cells, and higher threshold values are used in the learning than i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The program of grand challenge problems: expectations and results

    Publication Year: 1997 , Page(s): 2 - 7
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (544 KB)  

    The US high performance computing community still uses the term “Grand Challenge” for a variety of difficult problems in computational science. Though it was primarily a means of communicating computing goals to nonpractitioners, it also serves the useful purpose of letting practitioners focus on defining goals more carefully. For purposes of Grand Challenge computing, it is essential ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The use of feedback in scheduling parallel computations

    Publication Year: 1997 , Page(s): 124 - 132
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (804 KB)  

    Discusses the use of run-time feedback for optimizing the execution of parallel computations. Four levels of feedback are distinguished and the applicability and limitations of each are discussed. A two-part scheduling paradigm known as SEDIA (Static Exploration/Dynamic Instantiation and Activation) that addresses these limitations to perform robust scheduling in the presence of variant run-time b... 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
    Save to Project icon | Request Permissions | 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.
  • Discrete-event simulation of parallel machines

    Publication Year: 1997 , Page(s): 300 - 307
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (692 KB)  

    Presents a new approach for parallel machine simulation based on the discrete-event system specification (DEVS) formalism. Our simulation approach is directed toward parallel machine simulation at the concurrent threads level, and it is applicable for analysing the influence of internal algorithm/application concurrency on the performance characteristics of parallel machines. It uses as its modeli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Householder bidiagonalization on parallel computers with dynamic ring architecture

    Publication Year: 1997 , Page(s): 182 - 191
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (676 KB)  

    A parallel algorithm for Householder bidiagonalization on parallel computers with dynamic ring architecture is presented. The Householder bidiagonalization is the core for singular value decomposition (SVD) which has been found to be very useful as an analytical tool in the presence of roundoff error and inexact data. Two sided Householder reduction/expansion technique is applied for bidiagonaliza... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel genetic algorithms for communication network design

    Publication Year: 1997 , Page(s): 370 - 377
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (600 KB)  

    This paper is devoted to developing a genetic algorithm for a communication network design that minimizes total link cost, and subjects to some constraints like diameter and two-connectivity. Two parallel genetic algorithms on the level of partitioning requirements and the level of dividing population are proposed and implemented over a transputer based parallel network with various virtual networ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The architecture of massively parallel processor CP-PACS

    Publication Year: 1997 , Page(s): 31 - 40
    Cited by:  Patents (27)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (832 KB)  

    CP-PACS (Computational Physics by Parallel Array Computer System) is a massively parallel processor with 2048 processing units, built at the Center for Computational Physics, University of Tsukuba, Japan. The node processor of CP-PACS is a RISC microprocessor enhanced by pseudo vector processing, which can realize high performance vector processing. The interconnection network is the 3 dimensional... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mobile agents: the next generation in distributed computing

    Publication Year: 1997 , Page(s): 8 - 24
    Cited by:  Papers (12)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (1176 KB)  

    Mobile agents are programs that can move through a network under their own control, migrating from host to host and interacting with other agents and resources on each. We argue that these mobile, autonomous agents have the potential to provide a convenient, efficient and robust programming paradigm for distributed applications, particularly when partially connected computers are involved. Partial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new parallel algorithm for the parentheses-matching problem

    Publication Year: 1997 , Page(s): 364 - 369
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (440 KB)  

    The parentheses-matching problem is of crucial importance in the construction of expression tree in order to evaluate, for instance, arithmetic expressions. A new parallel algorithm is introduced in this paper to solve the parentheses-matching problem optimally (in O(log2 n) parallel time with O(n/log2 n) processors) on an EREW-PRAM model. An algorithm for an input string of ... 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
    Save to Project icon | Request Permissions | 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.
  • An efficient submesh allocation scheme for 3D torus multicomputer systems

    Publication Year: 1997 , Page(s): 83 - 90
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | 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.
  • Efficient parallel and distributed topological sort algorithms

    Publication Year: 1997 , Page(s): 378 - 383
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | 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.
  • Solver with the differential algebraic cubic interpolated propagation scheme on massively parallel computer

    Publication Year: 1997 , Page(s): 200 - 205
    Save to Project icon | Request Permissions | 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.
  • World-wide computing infrastructure: global and local partnership

    Publication Year: 1997 , Page(s): 25 - 30
    Save to Project icon | Request Permissions | 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.
  • Introducing parallelism in multimedia database systems

    Publication Year: 1997 , Page(s): 348 - 355
    Save to Project icon | Request Permissions | 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.
  • Using system state information for adaptive state polling policy in distributed load balancing

    Publication Year: 1997 , Page(s): 166 - 173
    Cited by:  Patents (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (828 KB)  

    The location policy in distributed load balancing schemes locates the destination nodes to or from which tasks will be transferred. It should evenly distribute workload to the entire nodes with minimal delay for transferring task. The traditional policies can be classified into dynamic selection, random selection, and state polling. However, the policies representatively cause unpredictable state,... 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
    Save to Project icon | Request Permissions | 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.
  • Portable multiprecision arithmetic package based on message passing interface

    Publication Year: 1997 , Page(s): 324 - 331
    Save to Project icon | Request Permissions | 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 processor allocation algorithm using two-dimensional packing

    Publication Year: 1997 , Page(s): 151 - 158
    Save to Project icon | Request Permissions | 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.
  • Dynamic access load balancing on the parallel secondary storage

    Publication Year: 1997 , Page(s): 316 - 323
    Cited by:  Patents (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (620 KB)  

    A massively parallel computer handles a massive amount of data with simultaneous access requests from multiple processors, and therefore it must have a large-capacity secondary storage system of very high concurrency. Such a storage system should consist of many disks that are connected in parallel. With such large-scale parallel disk systems, access load balancing is extremely important in order ... 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
    Save to Project icon | Request Permissions | 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.