I think the first thing that I need to do is get ASM working on the CPU in
my code as a direct solver.

FieldSplit was mentioned the way to do this. How would I do that?

Thanks,
Mark

On Wed, Dec 30, 2020 at 11:11 PM Jed Brown <[email protected]> wrote:

> Barry Smith <[email protected]> writes:
>
> >   I was assuming the triangular systems were all solvable and setup in
> the correct format so the triangular solver would not be the place to first
> detect problems with the factor. Though not completely generally that seems
> to cover most cases.
>
> You could write a solver that way, but that doesn't appear to be what
> cusparse has done. Perhaps it's because the function takes the raw arrays
> as inputs (rather than an opaque structure that can only be created by an
> analysis phase that confirms validity). For all we know, they might do 90%
> of the work synchronously and just leave the last kernel in the stream.
>

Reply via email to