Same ones. Why would the special case of one process be some different code?
Barry On Sep 18, 2013, at 8:38 PM, Jose David Bermeol <[email protected]> wrote: > Hi and for MATSEQAIJ > > Thanks > > ----- Original Message ----- > From: "Barry Smith" <[email protected]> > To: "Jose David Bermeol" <[email protected]> > Cc: [email protected] > Sent: Tuesday, September 17, 2013 8:48:59 AM > Subject: Re: [petsc-dev] Petsc test > > > I would suggest src/snes/examples/tutorials/ex19.c as a two dimensional > mesh problem. You can run with -da_refine n where n is 2, 3, 4, … etc to > create larger problems. > > For three dimensions you can use src/ksp/ksp/examples/tutorials/ex45.c again > -da_refine 1,2,3,… increases the problem size > > Barry > > On Sep 16, 2013, at 8:23 PM, Jose David Bermeol <[email protected]> wrote: > >> Hi, I'm testing my Matsolver that uses pardico for MATMPIAIJ matrices, I >> want to know if you have a set of test for solvers and tests for >> scalability(to do benchmarking). >> >> Thanks
