Parallel Computation de Jens Volkert

Parallel Computation

Jens Volkert

en Limba Engleză Paperback – 27 sep 1993

The Austrian Center for Parallel Computation (ACPC) is acooperative research organization founded in 1989 to promoteresearch and education in the field of software for parallelcomputer systems. The areas in which the ACPC is activeinclude algorithms, languages, compilers, programmingenvironments, and applications for parallel andhigh-performance computing systems.This volume contains the proceedings of the SecondInternational Conference of the ACPC, held in Gmunden,Austria, October 1993. Authors from 17 countries submitted44 papers, of which 15 were selected for inclusion in thisvolume, which also includes 4 invited papers bydistinguished researchers. The volume is organized intoparts on architectures (2 papers), algorithms (7 papers),languages (6 papers), and programming environments (4papers).

Citește tot Restrânge

Cuprins

High-performance computing on a honeycomb architecture.- Refined local instruction scheduling considering pipeline interlocks.- Microscopic and macroscopic dynamics.- Further results of the relaxed timing model for distributed simulation.- Pipelining computations on processor arrays with reconfigurable bus systems.- An effective algorithm for computation of two-dimensional fourier transform for NxM matrices.- Rational number arithmetic by parallel p-adic algorithms.- Shortest non-synchronized motions parallel versions for shared memory crew models.- A pipeline algorithm for interactive volume visualization.- Data parallel programming: The promises and limitations of high performance fortran.- Foundations of practical parallel programming languages.- Prototyping parallel algorithms with proset-Linda.- Identifying the available parallelism using static analysis.- Automatic parallelization by pattern-matching.- Parallelization — A case study.- PVM 3 beyond network computing.- The design of the PACLIB kernel for parallel algebraic computation.- Generating parallel code from equations in the ObjectMath programming environments.- The paragon performance monitoring environment.