That is superlu_dist and hypre.
Yes, but both backends are rather primitive and will be a little struggle to
use.
For superlu_dist you need to get the branch
barry/fix-superlu_dist-py-for-gpus and rebase it against master
I only recommend trying them if you are adventuresome.
Dear Developers,
>From the online documentation, both superlu and hypre have some gpu
functionalities. Can we use these gpu features through PETSc's interface?
Thank you.
Best,
Xiangdong
It seems the problem is triggered by DMSetUp. You can write a small test
creating the DMDA with the same size as your code, to see if you can reproduce
the problem. If yes, it would be much easier for us to debug it.
--Junchao Zhang
On Thu, Jan 16, 2020 at 7:38 AM Anthony Jourdon
Are you increasing your problem size with the number of ranks or same size
problem?
It could also be out of memory issues.
No error message is printed; which is not standard. It should print first a
message why it failed.
Are you sure all the libraries were rebuilt.
> On Jan 16, 2020, at 3:18 AM, Timothée Nicolas
> wrote:
>
> Actually, for the main solver it works. I'm thinking, could it be due to the
> fact that the second SNES instance is defined in a routine that is called
> somewhere inside the FormFunction of the main SNES? We are improving our
>
On Thu, Jan 16, 2020 at 4:18 AM Timothée Nicolas
wrote:
> Actually, for the main solver it works. I'm thinking, could it be due to
> the fact that the second SNES instance is defined in a routine that is
> called somewhere inside the FormFunction of the main SNES? We are improving
> our boundary
Actually, for the main solver it works. I'm thinking, could it be due to
the fact that the second SNES instance is defined in a routine that is
called somewhere inside the FormFunction of the main SNES? We are improving
our boundary condition, which becomes quite complex, and we have a small