Extending PSBLAS to Build Parallel Schwarz Preconditioners

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