[J3] Performance Portability and Fortran: Making Fortran cool again

[Ondřej Čertík]

On Thu, Jan 17, 2019, at 11:39 AM, Gary Klimowicz wrote:
> > On 1/17/19, 12:11 PM, "J3 on behalf of Ondřej Čertík via J3" <j3-bounces at mailman.j3-fortran.org on behalf of j3 at mailman.j3-fortran.org> wrote:
> 
>    >  
>     
>     > On Thu, Jan 17, 2019, at 9:21 AM, Tom Clune via J3 wrote:
>     > > A colleague just shared a link that seems relevant to one of 
> the 
>     > > subthreads of this discussion:
>     > > 
>     > > 
> https://www.nextplatform.com/2019/01/16/burying-the-openmp-versus-openacc-hatchet/
>     > > 
>     > > Note - I think the author has stated things exactly backwards 
> in 
>     > > several places, but I think the committee will generally like 
> the 
>     > > conclusion at the end.
>     
>     
>     > This is a very good article, thanks for sharing it. I am 
> wondering which things you think are stated backwards?
>     
>     > I discussed the "do concurrent" approach with several people at 
> work and we arrived at the same conclusion as this article, that the 
> compiler should simply offload "do concurrent" to a GPU and the GPU 
> specific options that you currently specify in the OpenACC pragma, such 
> as:
>     
>     > !$acc kernels loop gang(32), vector(16)
>     
>     > should become compiler options, that the user specifies when 
> compiling for a given GPU. This is equivalent to how Kokkos works: you 
> specify these options at configure time, they are not part of the 
> source code.
>     
>     > This answers my question for an email above how it should be designed.
>     
>     > Ondrej
>     
> PGI had a demo at Supercomputing in November showing exactly that: 
> undecorated DO CONCURRENT with GPU offload. It was just a demo, but 
> it's clearly an important implementation direction.

I searched, but wasn't able to find any information about this online. Is there something that I can read about this, or try it out? I was only able to find a few general words in the section "THE FUTURE OF GPU PROGRAMMING" here:

https://www.nvidia.com/en-us/events/supercomputing/

> 
> And if I understand Ondrej's comment correctly, I agree that the 
> optimization hints belong at configure time or runtime, and not be part 
> of source code itself.

Yes.

Ondrej