Use of direct solvers in TFETI massively parallel implementation

  • Authors:
  • Václav Hapla;David Horák;Michal Merta

  • Affiliations:
  • Dep. of Applied Math., VSB-Tech. Univ. of Ostrava, Ostrava, 17. listopadu 15, Czech Republic,Centre of Excellence IT4Innovations, VSB-Tech. Univ. of Ostrava, Ostrava, Czech Republic;Dep. of Applied Math., VSB-Tech. Univ. of Ostrava, Ostrava, 17. listopadu 15, Czech Republic,Centre of Excellence IT4Innovations, VSB-Tech. Univ. of Ostrava, Ostrava, Czech Republic;Dep. of Applied Math., VSB-Tech. Univ. of Ostrava, Ostrava, 17. listopadu 15, Czech Republic,Centre of Excellence IT4Innovations, VSB-Tech. Univ. of Ostrava, Ostrava, Czech Republic

  • Venue:
  • PARA'12 Proceedings of the 11th international conference on Applied Parallel and Scientific Computing
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The FETI methods blend iterative and direct solvers. The dual problem is solved iteratively using e.g. CG method; in each iteration, the auxiliary problems related to the application of an unassembled system matrix (subdomain problems' solutions and projector application in dual operator) are solved directly. The paper deals with the comparison of the direct solvers available in PETSc on the Cray XE6 machine HECToR (PETSc, MUMPS, SuperLU) regarding their performance in the two most time consuming actions in TFETI --- the pseudoinverse application and the coarse problem solution. For the numerical experiments, our novel TFETI implementation in FLLOP (FETI Light Layer on top of PETSc) library was used.