Enhancing the Performance of a Parallel Solver for Turbulent Reacting Flow Simulations
- 3 March 2011
- journal article
- research article
- Published by Taylor & Francis in Numerical Heat Transfer, Part B: Fundamentals
- Vol. 59 (3) , 169-189
Abstract
This article describes results of an effort to improve the parallel efficiency of a solver for turbulent reacting flows on two computer architectures. The compact finite-difference scheme employed for the solution of the differential equations involves the inversion of multiple tridiagonal matrices at each time step. Detailed performance evaluation of the standard LU, parallel partition LU, and parallel diagonal dominant algorithms are presented. The speed-up and efficiencies of these parallel strategies are critically compared and evaluated based on both computation and communication complexities, on the CRAY XT4 and IBM Blue Gene/P architectures.Keywords
This publication has 31 references indexed in Scilit:
- Structure of hydrogen triple flames and premixed flames comparedCombustion and Flame, 2010
- A Computational Investigation of the Interaction of Pulses in Two-Pulse JetsNumerical Heat Transfer, Part A: Applications, 2008
- A Study of Flame-Vortex Interactions in the Presence of Residual GasesCombustion Science and Technology, 2008
- LARGE-EDDY SIMULATION OF TURBULENT COMBUSTIONAnnual Review of Fluid Mechanics, 2006
- A numerical study on the formation of diffusion flame islands in a turbulent hydrogen jet lifted flameProceedings of the Combustion Institute, 2005
- Exploring Velocity and Density Ratio Effects in a Mixing Layer Using DNSInternational Journal of Computational Fluid Dynamics, 1997
- Vector and parallel methods for the direct solution of Poisson's equationJournal of Computational and Applied Mathematics, 1989
- An Efficient Parallel Algorithm for the Solution of a Tridiagonal Linear System of EquationsJournal of the ACM, 1973
- A process for the step-by-step integration of differential equations in an automatic digital computing machineMathematical Proceedings of the Cambridge Philosophical Society, 1951
- Adjustment of an Inverse Matrix Corresponding to a Change in One Element of a Given MatrixThe Annals of Mathematical Statistics, 1950