Proceedings the First Aizu International Symposium on Parallel Algorithms/Architecture Synthesis

15-17 March 1995

Filter Results

Displaying Results 1 - 25 of 43
  • Proceedings the First Aizu International Symposium on Parallel Algorithms/Architecture Synthesis

    Publication Year: 1995
    Request permission for commercial reuse | |PDF file iconPDF (29 KB)
    Freely Available from IEEE
  • Massively parallel processing project of the Japanese Ministry of Education

    Publication Year: 1995, Page(s):30 - 37
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (376 KB)

    The Massively Parallel Processing Project started in 1992 as a priority area of research for the Ministry of Education in Japan. The objective of this research project is to establish the basic technology of massively parallel processing which is expected to be the fundamental tool to develop the high-level technologies of the 21st century. The main goal of this project is to build up a system pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Investigation of some hardware accelerators for relational algebra operations

    Publication Year: 1995, Page(s):308 - 314
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (436 KB)

    This paper is devoted to the application of specialized processors for speeding-up the realization of relational algebra operations on fine-grain SIMD computers. A short description of two processors is presented. By means of a special high level language STAR, the algorithms of implementation of relational algebra operations are described in a STARAN-like computer model, and then in the same mode... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • GRAPE project for a dedicated tera-flops computer

    Publication Year: 1995, Page(s):38 - 44
    Cited by:  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (504 KB)

    We are constructing a one tera-flops machine dedicated to astronomical many-body problems. It consists of parallelized GRAPE machines connected to a host workstation. The GRAPE machines only calculate forces between particles in the system by pipeline architecture. We designed and fabricated LSI chips for it, and about 2000 chips are being connected in parallel. The machine will be in operation by... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Garbage collection in message passing distributed systems

    Publication Year: 1995, Page(s):213 - 218
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (404 KB)

    Distributed systems use optimistic message logging for recovery from transient process failures. Such a recovery is facilitated by asynchronous message logging and check-pointing. It is also supported by garbage collection which requires identifying messages in stable storage that are no longer needed for the process of recovery. For this purpose, it is necessary to keep track of message dependenc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Supercompilers for massively parallel architectures

    Publication Year: 1995, Page(s):315 - 322
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (504 KB)

    We describe the design of a compilation system, which translates Fortran programs automatically into explicitly parallel programs for a massively parallel architecture. Such a compiler must automatically generate data distributions and derive program transformation strategies based on a combination of heuristics and analysis features. Programs are subjected to an iterative tuning process, involvin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Promising data parallel environment-ADEPS, ADETRAN and ADENA

    Publication Year: 1995, Page(s):45 - 53
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (776 KB)

    This paper compares some parallel computation schemes from view of simple usage, and proposes ADEPS as the most highly recommended. As shown, it produces simple programming language ADETRAN and also sophisticated machine architecture, called ADENA. Some established models of ADENAs are introduced as well as a new hopeful one as the next generation of supercomputers, called TFLOPS machines View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Task scheduling with locality consideration for a clustered parallel FL reduction system

    Publication Year: 1995, Page(s):234 - 240
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (500 KB)

    Multiprocessor systems provide us with high performance surpassing sequential computers. When constructing a multiprocessor system, task scheduling is one of the crucial issues affecting the system performance. The paper studies task scheduling for a clustered parallel reduction system of the functional language FL. We construct a shared memory multiprocessor system to realize parallel graph reduc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallelizing a PDE solver: experiences with PISCES-MP

    Publication Year: 1995, Page(s):287 - 293
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (600 KB)

    The paper presents a methodology for adapting dusty deck PDE solvers for parallel execution. Our approach minimizes changes to existing code and data structures, thereby preserving the value captured within dusty decks. This scheme uses the single program multiple data programming paradigm on message passing distributed memory architectures. To demonstrate the viability of our methodology the comm... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Non-blocking concurrency control in distributed database systems

    Publication Year: 1995, Page(s):192 - 198
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (464 KB)

    Concurrency control based on conventional techniques requires additional efforts for deadlock detection and elimination. The possibility of a deadlock is also connected to the introduction of delays, and repeated restarts of transactions in deadlock cycles. In the proposed approach, a technique for generation of data flow precedence graphs among transactions at data sites has been studied. The loc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cohesion: an efficient distributed shared memory system supporting multiple memory consistency models

    Publication Year: 1995, Page(s):146 - 152
    Cited by:  Papers (8)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (560 KB)

    This paper describes a prototype of DSM called Cohesion which supports two memory consistency models, namely Sequential consistency and Release consistency, within a single program to improve the performance and supports wide-variety of parallel programs for the system. Memory that is sequentially consistent is further divided into object-based and conventional (page-based) memory; where they are ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Aizu supercomputer: a massively parallel system for virtual reality problems

    Publication Year: 1995, Page(s):54 - 62
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (480 KB)

    The Aizu supercomputer is a massively parallel system suited to the solution of virtual reality problems and the support of multimedia applications. It employs a highly parallel MIMD architecture using a conflict-free internetwork system. The scalable communication system consists of two networks: a pyramid network and a reconfigurable network using optical links. The Aizu Supercomputer has a clus... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A scalable performance analysis tool for PowerPC based MPP systems

    Publication Year: 1995, Page(s):78 - 84
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (588 KB)

    This paper introduces a tool for optimizing programs on massively parallel computing systems. The tool has been implemented for a PowerPC based parallel computing platform. It is scalable with respect to its implementation and an the way it presents performance data. A major feature contributing to the scalable representation of performance data is the ability to focus measurements on points of in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel algorithms for extracting ridges and ravines

    Publication Year: 1995, Page(s):121 - 127
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (560 KB)

    This paper proposes two parallel algorithms called an even region parallel algorithm (ERPA) and an even strip parallel algorithm (ESPA) respectively for extracting ridge and ravine geometric features of a surface. The parallel programs were implemented on a GCcl-1/64 T805 transputer based parallel machine with maximum 64 transputers. The performance of these two algorithms are reported and analyze... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An experimental study of load balancing on Amoeba

    Publication Year: 1995, Page(s):220 - 226
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (552 KB)

    The paper presents the results of an experimental study of load balancing using job initiation and process migration, carried out on Amoeba (A.S. Tanenbaum et al., 1990). The results indicate the need for a load balancing facility in a distributed system to improve system performance, e.g., the average response time of processes. A number of load balancing algorithms, including the bidding and nei... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On finding optimal clusterings of task graphs

    Publication Year: 1995, Page(s):241 - 247
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (560 KB)

    Currently, many parallel algorithms are defined for shared memory architectures. The preferred machine model is the PRAM, but this model does not take into account properties of existing architectures that have a distributed memory and an asynchronous execution model. A transformation of PRAM programs into distributed, asynchronous ones is known. In order to produce not only correct but also effic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for visual parallel programming

    Publication Year: 1995, Page(s):294 - 300
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (504 KB)

    One of the difficulties of parallel programming is the gap between the desire of programmers to describe computations with manageable abstractions and the detailed description of parallelism, communication and synchronization required by most parallel programming languages. Since in a parallel program, activities are distributed across both space and time, pictures are much more meaningful than te... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of communication data: compression network

    Publication Year: 1995, Page(s):199 - 205
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (544 KB)

    The paper reports the effect of compressed message delivery (a compression network) on a parallel processing system such as workstation clusters. Compression network is simulated on a massively parallel processor, the Thinking Machines CM-5, using the parallel language Split-C. To examine the benefit of data compression to the system, profiles, including message pattern, number of messages, and me... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improvement of duplication scheduling heuristic algorithm with nonstrict triggering of program graph nodes

    Publication Year: 1995, Page(s):227 - 233
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (444 KB)

    The problem of multiprocessor scheduling can be stated as finding a schedule for a general task graph to be executed on a multiprocessor system so that the schedule length can be minimised. This scheduling problem is known to be NP-hard, and heuristic algorithms have been proposed to obtain optimal and suboptimal solutions. Duplication scheduling heuristic algorithm solves the max-min problem of p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visualization and sonification of methods

    Publication Year: 1995, Page(s):63 - 71
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (716 KB)

    An approach supporting a new programming philosophy and a way of developing the corresponding technology are presented. The idea behind the approach is making use of animation films as communication units for computer-human dialog. These films have their own sets of figures, sounds, colors and their own “shape” of the movement. Users recognize the units due to a combination of all thes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Aspects of a distributed solution of the Brusselator equation

    Publication Year: 1995, Page(s):114 - 120
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (488 KB)

    The spatial discretization of nonlinear partial differential equations (PDEs) results in large systems of nonlinear ordinary differential equations (ODEs). The discretization of the Brusselator equation is a characteristic example. For the parallel numerical solution of the Brusselator equation we use an iterated Runge-Kutta method. We propose modifications of the original method that exploit the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel algorithm for solving systems of linear equations with dynamically changed length of operands

    Publication Year: 1995, Page(s):100 - 106
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (456 KB)

    Peculiarity of the most direct algorithms for solving system of linear equations is the use of divisions for the elimination of unknowns. Division requires great time for its execution, when the multiprecision arithmetic is used because in this case it is realized by special programs. In this paper a parallel algorithm is described implementing the elimination procedure without divisions. Some res... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Software engineering techniques and tools for high performance parallel systems

    Publication Year: 1995, Page(s):85 - 91
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (656 KB)

    This paper considers the current state of software engineering for parallel systems. A review of existing approaches and techniques identifies inadequacies. Recent work on design, verification and automated support is outlined. The next generation of embedded and distributed technologies will compound the problems through increased demand and diversity. This paper discusses the implications for th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel polygon rendering on the graphics computer VC-1

    Publication Year: 1995, Page(s):2 - 9
    Cited by:  Papers (1)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (556 KB)

    This paper describes a parallel polygon rendering method on the graphics computer VC-1. The architecture of the VC-1 is a loosely-coupled array of general-purpose processors, each of which is equipped with a local frame buffer. The contents of the local frame buffers are merged into one in real time considering the visibility control based on screen depth. In our polygon rendering method, polygons... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel algorithms for maximal acyclic sets

    Publication Year: 1995, Page(s):169 - 175
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (528 KB)

    Given a graph G=(V, E), the classical spanning forest problem of G can be viewed as the problem of finding a maximal subset F of E inducing an acyclic subgraph. Although it is well known that this problem has efficient NC algorithms, its vertex counterpart, i.e., the problem of finding a maximal subset U of V inducing an acyclic subgraph, has not been shown to be in NC (or even in RNC) and is not ... View full abstract»

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