Parallel Computing Technologies: Third International Conference, Pact-95, St. Petersburg, Russia, September 12-15, 1995. Proceedings

ISBN-13: 9783540602224 / Angielski / Miękka / 1995 / 504 str.

Victor Malyshkin; V. E. Malyshkin

Opis

This book constitutes the proceedings of the Third International Conference on Parallel Computing Technologies, PaCT '95, held in St. Petersburg, Russia in September 1995.
The volume presents 45 revised full papers selected from a total of 98 submissions, including six invited presentations. The proceedings is organized in parts on theory, software, hardware and architecture, and applications to large-scale problems. Parallel processing technologies are shown to be the touchstone of parallel theories, models, languages, and programming systems.

Spis treści

Synchronous-asynchronous cellular computations.- Parallel computations and finite automata on semilattices.- Linear Fibonacci forms and parallel algorithms for high dimension arithmetic.- Cellular-Neural computations. Formal model and possible applications.- An efficient verifier of truly concurrent properties.- Optimal loop scheduling on multiprocessors: A pumping lemma for p-processor schedules.- Parallel and distributed processing of cellular hypergraphs.- Computer models of 3D cellular structures.- Comparison of two MST algorithms for associative parallel processors.- Petri net modelling of Estelle-specified communication protocols.- Dynamic scheduling of parallel applications.- A method for analyzing combinatorial properties of static connecting topologies.- cT: an imperative language with parallelizing features supporting the computation model “autotransformation of the evaluation network”.- Vienna fortran 90 — An advanced data parallel language.- Programming abstracts for synchronization and communication in parallel programs.- A program manipulation system for fine-grained architectures.- Compilation of CDL for different target architectures.- Performance evaluation and visualization with VISPAT.- Dataparallel programming with intelligent communication.- Optimization scheme on execution of logic program in a dataflow environment.- COVERS — A tool for the design of real-time concurrent systems.- Status and prospect of ZM4/SIMPLE/PEPP: An event-oriented evaluation environment for parallel and distributed programs.- The separating decomposition of discrete Fourier transform and vectorization of its calculation.- PFSLib — A parallel file system for workstation clusters.- Data structures, computational, and communication kernels for distributed memory sparse iterative solvers.- PARMA: A multiattribute file structure for parallel database machines.- T++: An object-oriented language to express task and data parallelism on Multi-SIMD computers.- mEDA-2: An extension of PVM.- Parallel iterative solution of systems of linear equations with dynamically changed length of operands.- Parallelization of computer code MASTAC three-dimensional finite elements method implementing.- New trends in simulation of distributed shared memory architectures.- Standard microprocessors versus custom processing elements for massively parallel architectures.- Further pipelining and multithreading to improve RISC processor speed. A proposed architecture and simulation results.- The massively parallel computer system MBC-100.- DFS-superMPx: Low-cost parallel processing system for machine vision and image processing.- Architectural issues of distributed workflow management systems.- Parallelization of the solution of 3D Navier-Stokes equations for fluid flow in a cavity with moving covers.- Distributing search and knowledge using a coordination language.- Design and evaluation of a multi-threaded architecture for parallel graph reduction.- Implementation of the multigrid method for solving the boundary-value problems for the Poisson and Helmholtz equations on the massively parallel computers.- Parallel seismic data processing method for MEMSY multiprocessor system.- Hardware and software platform for information processing.- Numerical simulation of reacting mixing layer with a parallel implementation.- Parallel computing in Russia.- Early approaches to parallel processing: Increasing performance and dependability.