By Topic

Parallel Processing, 1996. Proceedings of the 1996 ICPP Workshop on Challenges for

Date 12-12 Aug. 1996

Filter Results

Displaying Results 1 - 19 of 19
  • Proceedings of the 1996 ICPP Workshop on Challenges for Parallel Processing

    Publication Year: 1996
    Request permission for commercial reuse | PDF file iconPDF (219 KB)
    Freely Available from IEEE
  • Introduction to the 1996 ICPP Workshop on Challenges for Parallel Processing

    Publication Year: 1996
    Request permission for commercial reuse | PDF file iconPDF (610 KB)
    Freely Available from IEEE
  • Models for parallel computation [Session Introduction]

    Publication Year: 1996
    Cited by:  Papers (4)
    Request permission for commercial reuse | PDF file iconPDF (291 KB)
    Freely Available from IEEE
  • Measuring the performance of parallel computations [Session Introduction]

    Publication Year: 1996
    Cited by:  Papers (1)
    Request permission for commercial reuse | PDF file iconPDF (250 KB)
    Freely Available from IEEE
  • Restructuring programs for high-speed computers with Polaris

    Publication Year: 1996, Page(s):149 - 161
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1140 KB)

    The ability to automatically parallelize standard programming languages results in program portability across a wide range of machine architectures. It is the goal of the Polaris project to develop a new parallelizing compiler that overcomes limitations of current compilers. While current parallelizing compilers may succeed on small kernels, they often fail to extract any meaningful parallelism fr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fortran: a modern standard programming language for parallel scalable high performance technical computing

    Publication Year: 1996, Page(s):140 - 148
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB)

    Fortran is often thought of as an old, archaic programming language that used to be adequate for technical computing but is rapidly being replaced by more modern languages such as C and, especially, C++. No perception could be less accurate. Fortran has been modernized by the standardization process that lead to Fortran 90, and further enhanced with features developed by the High Performance Fortr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The next frontier: interactive and closed loop performance steering

    Publication Year: 1996, Page(s):20 - 31
    Cited by:  Papers (10)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1124 KB)

    Software for a growing number of problem domains has complex, time varying behavior and unpredictable resource demands (e.g., WWW servers and parallel input/output systems). While current performance analysis tools provide insights into application dynamics and the causes of poor performance, with a posteriori analysis one cannot adapt to temporally varying application resource demands and system ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Let us build system-friendly networks-build them hierarchically

    Publication Year: 1996, Page(s):64 - 73
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (788 KB)

    Hierarchical systems address many hardware and software problems encountered by designers of large communication and computing systems; hence, interest in this field continues to grow. A diversity of hierarchical networks have been proposed in the literature. This paper introduces a framework for classifying hierarchical topologies. Using the framework, we survey existing topologies in an organize... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel I/O: a set of intertwined systems and applications issues

    Publication Year: 1996, Page(s):85 - 90
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    Historically, input/output (I/O) has been a bottleneck for many scientific and engineering applications. Sequential and vector supercomputers invested substantial resources into reducing that bottleneck. Now that high-performance computing is nearly synonymous with parallel computing, I/O has become more of a bottleneck and it is more difficult to eliminate it because of the complexity of data mov... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linguistic constructs for BSP style programming

    Publication Year: 1996, Page(s):96 - 102
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (392 KB)

    A necessary condition for the establishment, on a substantial basis, of a parallel software industry would appear to be the availability of technology for generating transportable software, i.e. architecture independent software which delivers scalable performance for a wide variety of applications on a wide range of multiprocessor computers. We are developing H-BSP-a general purpose parallel comp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On combining technology and theory in search of a parallel computation model

    Publication Year: 1996, Page(s):115 - 123
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (748 KB)

    A fundamental problem in parallel computing is to design high-level, architecture independent, algorithms that execute efficiently on general purpose parallel machines. The aim is to be able to achieve portability and high performance simultaneously. A key to accomplishing this is the existence of a computation model that can bridge the gap between the high level programming models and the underly... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Portable parallel programming in HPC++

    Publication Year: 1996, Page(s):132 - 139
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB)

    HPC++ is a C++ library and language extension framework that is being developed by the HPC++ consortium as a standard model for portable parallel C++ programming. This paper provides a brief introduction to HPC++ style programming and outlines some of the unresolved issues View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mechanisms for mapping high-level parallel performance data

    Publication Year: 1996, Page(s):10 - 19
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (864 KB)

    A primary problem in the performance measurement of high-level parallel programming languages is to map low-level events to high-level programming constructs. We discuss several aspects of this problem and present three methods with which performance tools can map performance data and provide accurate performance information to programmers. In particular, we discuss static mapping, dynamic mapping... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Commercially viable MPP networks

    Publication Year: 1996, Page(s):52 - 63
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (912 KB)

    Although an enormous variety of network topologies have been proposed, only a handful have been chosen for commercial machines. Of these, an even smaller number possess the characteristics adequate for the often conflicting set of requirements for robustness, efficiency, scalability, and modularity. In this paper we qualitatively examine network topologies based upon these and other issues, and co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Issues related to the structure and performance of parallel applications in a production environment

    Publication Year: 1996, Page(s):32 - 43
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1052 KB)

    The Perfect Benchmark suite was an attempt to assemble a realistic collection of application codes which could be used by computer scientists for performance evaluation, exploration of new architectural features, and testing compiler technologies. This paper surveys the origin, use, and inherent biases in the suite View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Issues in designing truly scalable interconnection networks

    Publication Year: 1996, Page(s):74 - 83
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (888 KB)

    Interconnection networks have been extensively studied in the computer architecture community as they are essential to the performance of parallel processing computing platforms. However, this research area has also been criticized for producing many practically useless research results, which hinder the needed progress in this area. This paper begins with a new classification of interconnection n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • What good are shared-memory models?

    Publication Year: 1996, Page(s):103 - 114
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1052 KB)

    Shared memory models have been criticized for years for failing to model essential realities of parallel machines. Given the current wave of popular message-passing and distributed memory models (e.g., BSP, LOGP), it is natural to ask whether shared memory models have outlived any usefulness they may have had. In this paper we discuss the continuing importance of shared memory models in the design... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Portable parallel programming languages

    Publication Year: 1996, Page(s):125 - 131
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    In this workshop session, three speakers present their viewpoints and contributions to the topic of portable parallel programming languages. They are Dennis Gannon from Indiana University, David Loveman from Digital Equipment Corporation, and David Padua from the University of Illinois. Their presentations discuss extensions to C++, Fortran, and compiler support for standard languages o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interconnection networks: dimensions in design

    Publication Year: 1996, Page(s):45 - 51
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    The interconnection network is the switching fabric responsible for providing communication between all processors in a parallel computer. Much research has been directed towards developing superior interconnection networks, but there is no general agreement that this problem is solved. The speakers for this panel session were asked to address the following question: for a given range of number of... View full abstract»

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