(j3.2006) (SC22WG5.5141) [ukfortran] image selectors

[Bill Long]

On 12/10/13 2:01 PM, Van Snyder wrote:
> On Tue, 2013-12-10 at 09:23 +0000, N.M. Maclaren wrote:
>> On Dec 10 2013, Tom Clune wrote:
>>> On Dec 9, 2013, at 6:52 PM, Van Snyder <Van.Snyder at jpl.nasa.gov> wrote:
>>>
>>>> Better yet would be to specify the mapping from parent team to subteam.
>>>> If NEW_INDEX is not specified, is there really a difficulty with
>>>> specifying, for example, that the image indices for the subteam are in
>>>> the same order as the image indices in the parent team, so that image
>>>> index 1 for the subteam applies to the image with the smallest image
>>>> index in the parent team that becomes part of the subteam, etc.?
>>>
>>> I'll second that. ince many applications will be ported from MPI, the
>>> principle of "least surprise" should be invoked here. Unless there is a
>>> reason to the contrary, the MPI convention for subcommunicator ranks
>>> should apply to subteam image indices. MPI allows redefining ranks as
>>> well, but I've only used that once (maybe) in 20+ years of coding in MPI.
>>
>> Yes, but I do NOT agree with that specification!  It should simply be
>> explicitly stated to be unspecified, thus permitting an implementation
>> to optimise.  Few will, but so what?
>
> It is explicitly stated to be unspecified, but not using the term
> "processor dependent."
>
> I don't see how there are opportunities for optimization by not
> specifying the mapping from parent team cosubscripts to subteam
> subscripts.
>

I would expect the optimization to be in the computation of the new 
image index inside FORM TEAM.   If FORM TEAM is rarely executed in a 
program (a reasonable expectation) this might not be that important.

Do you intend that, "if NEW_INDEX is not specified, the image index 
values shall be in the same numerical order as in the parent team" 
should be part of your ballot response?

Cheers,
Bill


-- 
Bill Long                                           longb at cray.com
Fortran Technical Support    &                 voice: 651-605-9024
Bioinformatics Software Development            fax:   651-605-9142
Cray Inc./Cray Plaza, Suite 210/380 Jackson St./St. Paul, MN 55101