Parallel Computational Fluid Dynamics

Parallel Computational Fluid Dynamics '95

Implementations and Results Using Parallel Computers

Parallel Computational Fluid Dynamics(CFD) is an internationally recognised fast-growing field. Since 1989, the number of participants attending Parallel CFD Conferences has doubled.

In order to keep track of current global developments, the Parallel CFD Conference annually brings scientists together to discuss and report results on the utilization of parallel computing as a practical computational tool for solving complex fluid dynamic problems. This volume contains the results of research conducted during the past year.

Subject areas covered include: novel parallel algorithms, parallel Euler and Navier-Stokes solvers, parallel Direct Simulation Monte Carlo method and parallel multigrid techniques. The content of the book also demonstrates that considerable effort is being made to utilize parallel computing to solve a variety of fluid dynamics problems in topics such as climate modeling, consultation, aerodynamics and in many other areas.

Readers of this book will gain a valid insight into the exciting recent developments in Parallel CFD research.

,

Published: January 1996

Imprint: North-holland

ISBN: 978-0-444-82322-9

Contents

  • Due to space limitations, only a selection of the published papers are listed herewith. Preface. Invited Speakers. Multiblock structured algorithms in parallel CFD (C. de Nicola et al.). Using hundreds of workstations for production running of parallel CFD applications (C. Fischberg et al.). Parallel computation of frontal processes (M. Garbey, D. Tromeur-Dervout). Modelling the global ocean circulation on the T3D (C. Gwilliam). Concurrent distributed visualization and solution steering (R. Haimes). From R&D in parallel CFD to a tool for computer aided engineering (W. Loeve). Parallel computation of unsteady supersonic cavity flows (Y. Takakura et al.). Reacting Flows. A data-parallel LU relaxation method for reacting viscous flows (M. Wright, G. Candler). Distributed implementation of KIVA-3 on the Intel paragon (O. Yasar, T. Zacharia). Euler Solvers. Parallelization of a highly unstructured Euler-solver based on arbitrary polygonal control volumes (C. Helf et al.). Implementation and results of a time accurate finite-volume Euler code in the NWT parallel cComputer (L. Ruiz-Calavera, N. Hirose). Algorithms. Parallel computations of CFD problems using a new fast poisson solver (M. Obata, N. Satofuka). Spectral Methods. A commercial CFD application on a shared memory multiprocessor using MPI (P. Fischer, M. Venugopal). Large Scale Applications. Large scale simulations of flows about a space plane using NWT (K. Matsushima, S. Takanashi). Performance Issues. Benchmarking the FLOWer code on different parallel and vector machines (C. Oosterlee et al.). Flow Visualization. Runtime volume visualization for parallel CFD (K. Ma). Multigrid Methods. Application of parallel multigrid methods to unsteady flow: a performance evaluation (A. Degani, G. Fox). Applications. Cell-vertex multigrid solvers in the PARAGRID framework (S. Sibilla, M. Vitaletti). Implicit Navier-Stokes codes in parallel for aerospace applications (K. Badcock, B. Richards). Parallel computation of a tip vortex induced by a large aircraft wing (R. Ito, S. Takanashi). Towards an integrated CFD system in a parallel environment (M. Shih et al.). Turbulence. Parallel benchmarks of turbulence in complex geometries (C. Crawford et al.). A message-passing, distributed memory parallel algorithm for direct numerical simulation of turbulence with particle tracking (P. Yeung, C. Moseley). Adaptive Schemes. Parallel implementation of an adaptive scheme for 3D unstructured grids on a shared-memory multiprocessor (R. Biswas, L. Dagum). Climate Modeling. Semi-Lagrangian shallow water modeling on the CM-5 (B. Nadiga et al.). Application of a parallel Navier-Stokes model to ocean circulation (C. Hill, J. Marshall). Navier-Stokes Solvers. Towards modular CFD using the CERFACS parallel utilities (R. Choquet et al.). Space- and time-parallel Navier-Stokes solver for 3D block-adaptive Cartesian grids (V. Seidl et al.). A parallel implicit time accurate Navier-Stokes solver (C. Jenssen, K. Sørli). Distributing Computing. Dynamic load balancing in a 2D parallel Delaunay mesh generator (N. Verhoeven et al.). A dynamic load balancing technique for solving transonic and supersonic flows on networked workstations (N. Satofuka et al.). Mesh Partitioning Scalable parallel generation of partitioned, unstructured meshes (D. Hodgson et al.). Internal Flows Parallel computation of unsteady supersonic-inlet flows (S. Khandelwal et al.). Software Tools CPULib - A software library for parallel applications on arbitrary meshes (M. Rudgyard, T. Schönfeld).

Advertisement

advert image