Is the matrix changing in the for loop? Are the number of iterations increasing for each KSP? run with -ksp_monitor
> On Jul 20, 2015, at 8:01 PM, Matthew Knepley <[email protected]> wrote: > > It sounds like you are allocating memory each time. You can check using > -malloc_dump > after a few iterates. > > Matt > > On Mon, Jul 20, 2015 at 7:35 PM, Orxan Shibliyev <[email protected]> > wrote: > I am solving a non-linear problem. Basically I do the following: > > ... Allocate A, x, b, ksp ... > > for_loop > ... call myFunction ... > > where, > > myFunction: > ... > startTime > KSPSolve > stopTime > .... > > I record time for KSPSolve. It takes more each time until it becomes > impossible to wait. I put the code on a cluster with (14 x 1) processors. Any > idea? > > > > -- > What most experimenters take for granted before they begin their experiments > is infinitely more interesting than any results to which their experiments > lead. > -- Norbert Wiener
