We describe some extensions to Parallel Sparse BLAS (PSBLAS), a library of routines providing basic Linear Algebra operations needed to build iterative sparse linear system solvers on distributed-memory parallel computers. We focus on the implementation of parallel Additive Schwarz preconditioners, widely used in the solution of linear systems arising from a variety of applications. We report a performance analysis of these PSBLAS-based preconditioners on test cases arising from automotive engine simulations. We also make a comparison with equivalent software from the well-known PETSc library.
Extending PSBLAS to Build Parallel Schwarz Preconditioners / Buttari, A.; D'Ambra, P.; di Serafino, D.; Filippone, S.. - 3732:(2006), pp. 593-602. (Intervento presentato al convegno PARA'04 Workshop "State of the Art in Scientific Computing" tenutosi a Lyngby, Denmark nel June 20-23, 2004) [10.1007/11558958_7].
Extending PSBLAS to Build Parallel Schwarz Preconditioners
di Serafino D.;
2006
Abstract
We describe some extensions to Parallel Sparse BLAS (PSBLAS), a library of routines providing basic Linear Algebra operations needed to build iterative sparse linear system solvers on distributed-memory parallel computers. We focus on the implementation of parallel Additive Schwarz preconditioners, widely used in the solution of linear systems arising from a variety of applications. We report a performance analysis of these PSBLAS-based preconditioners on test cases arising from automotive engine simulations. We also make a comparison with equivalent software from the well-known PETSc library.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.