High Performance Computing II
- Contents: Fast parallel
solvers for large (linear) systems of equations are investigated
by the student.
- direct solvers and approximative inverse
- iterative solvers and preconditioners
- presentation of the students on the investigated solvers
- comparison of the solvers above on various platforms as cluster
computers, shared memory computers,
distributed memory computers
- Final presentation and Tech-report on the results
- Lecturer:
- Prof.
Gundolf Haase, Heinrichstr. 36, Zi 506, Tel. 5178,
- Lecture Time:
- Wednesday 12:00 - 13.15 in SR 11.34
- Computers:
List
- Solver and other packages
(a selection from Arnold Neumaier's page):
-
- partitioners: METIS,
Chaco,
JOSTLE,
MESHPART
(Matlab Mesh Partitioning and Graph Separator Toolbox,
with Matlab interfaces to METIS and Chaco).
- direct solvers: MUMPS,
SuperLU,
- preconditioners: Hypre, AMG by Peter Arbenz;
approx. inverse: pARMS, SPAI,
ParaSails, AHMED, HLib
- iterative solvers: PETSc, Aztec, ParaSol,
- load balancing, parallel data management: Dune, Zoltan
- Projects/Talks:
- Stefan Fürtinger (PhD):
- Aurel Neic (PhD):
- March 17: Data partitioning with METIS and the parallel data handling with the Toolbox
- xxx: The direct solver MUMPS
- xxx: Hierachical matrices using AHMED
- Dmitry Nikolaenko (PhD):
- xxx: Load balancing/handling by Dune
- xxx: AMG-solver Hypre
- xxx: sparse approx. inverse by ParaSails
- Franz Pichler (M):
- Daniel Kraft (B):
- Patricia Walker (B):
- xxx: Load balancing/handling by Zoltan
- xxx: preconditioner pARMS
- Supporting documents/codes:
-
- 2 example matrices and read routine for it (129 MByte, thanks to Aurel Neic)
- 2 examples meshes (thanks to Aurel Neic):
- Compute-Server:
-
- MATH047016.uni-graz.at, Dual-Hexcore with 32GB Memory, Ubuntu 9.04
- last update: Oct 22, 2010