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

[Tom Clune]

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/ <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.

- Tom


> On Jan 17, 2019, at 7:16 AM, Gary Klimowicz via J3 <j3 at mailman.j3-fortran.org> wrote:
> 
> On 1/16/19, 11:29 AM, "J3 on behalf of Bill Long via J3" <j3-bounces at mailman.j3-fortran.org on behalf of j3 at mailman.j3-fortran.org> wrote:
> 
>> On Jan 16, 2019, at 12:55 AM, Damian Rouson via J3 <j3 at mailman.j3-fortran.org> wrote:
>> 
>> Tread lightly in this territory -- especially in the DOE community.  There are very influential people who will have daggers drawn the minute you try to say anything positive about Fortran.  It gets religious quickly
> 
>    Absolutely. Some have invested their whole career and reputation on making C++ the only acceptable option.  It is a very sensitive issue.
> 
>    Cheers,
>    Bill
> 
>> and most in the community are unaware of the latest developments in Fortran but are very aware that the compilers have not kept up with the standards.   Citing fancy new features that your compiler doesn't support won't get you very far in the DOE community.  They know that story all too well and it's at least one of the reasons so much of the DOE community has moved away from Fortran.  They had work to get done and couldn't wait for compiler support to come along. 
> 
> 
> I'll reply to this thread, but this applies to all the comments you all have taken the time to post.
> 
> Thank you very much for your time and attention.
> 
> It seems that there is a natural tension between getting the most "performant portability" and getting the most "portable performance". This is especially true if we are concerned with portability over *time* as well as *place*.
> 
> Having the solid stability of Fortran as a standard supports "time" and "portable performance", I think. But that also means that quality of implementation in the compilers can improve programs without changing the programs themselves.
> 
> (PGI did a demo at SC 2018 where we GPU offload DO CONCURRENT. As Ondrej points out, this may not get you *optimal* performance. But the performance you do get is likely to be portable.)
> 
> Really, thank you all for your insights (and references).
> 
> Gary
> 
> 
> -----------------------------------------------------------------------------------
> This email message is for the sole use of the intended recipient(s) and may contain
> confidential information.  Any unauthorized review, use, disclosure or distribution
> is prohibited.  If you are not the intended recipient, please contact the sender by
> reply email and destroy all copies of the original message.
> -----------------------------------------------------------------------------------

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.j3-fortran.org/pipermail/j3/attachments/20190117/ea4a3bba/attachment.html>