[petsc-dev] 3rd party GPU AMG solvers

[Karl Rupp]

Hi Mark,

> A lot of this is driven by desires of DOE programs -- not your monkey 
> not your circus -- but I think that we need to have a story for how to 
> use GPUs, or whatever apps in our funding community want to do, and tell 
> it dispassionately. We don't commit resources nor commit to design 
> changes but just say this how one could do it.

it will nonetheless require a lot of convincing that at best they get 
moderate speed-ups, not the 580+x claimed in some of those early GPU 
papers...


> The fusion folks that I work with, and I assume other DOE offices, are 
> just looking at their codes, subroutine by subroutine, and having 
> postdocs look at GPUising them. We just need intelligent answers to 
> their questions. Even if we as sentient and passionate human being have 
> opinions on the approach that is implied by their questions, it is part 
> of my job to just give them a professional answer.

In the past ~18 months I've worked with applications that wanted to use 
GPUs in just that manner. Needless to say that you end up with touching 
almost everything to actually beat an existing (efficient) CPU-based 
application by less than a factor of 2. This involves MPI-parallel 
applications; it's much easier to get higher speedups if you don't need 
to communicate across ranks.


> I have enough now (thanks Jed and Lorena, et al!) to answer the AMGx 
> question sufficiently, and if you could give me a quick assessment of 
> where we are with hypre's GPU solver that would be great.

does "work in progress" suffice? ;-)

Best regards,
Karli




> 
> On Thu, Jul 13, 2017 at 11:16 PM, Karl Rupp <rupp at iue.tuwien.ac.at 
> <mailto:rupp at iue.tuwien.ac.at>> wrote:
> 
>     Hi Mark,
> 
>         I hear Hypre has support for GPUs in a May release. Any word on
>         the status of using it in PETSc?
> 
> 
>     as far as I know, it is currently not supported in PETSc. I'll have
>     a look at it and see what needs to be done to enable it.
> 
> 
>         And we discussed interfacing to AMGx, which is complicated
>         (precluded?) by not releasing source. Anything on the potential
>         of interfacing to AMGx?  I think it would be great to make this
>         available. It is on a lot of checkboxes. I would love to be able
>         to say, yea you can use it.
> 
> 
>     Lorena Barba's group actually interfaced PETSc to AMGx at some point
>     (presented at GTC 2016 if I'm not mistaken). I'll reach out to them,
>     maybe they have something to contribute.
> 
>     Best regards,
>     Karli
> 
>