Hi!
On 2026-07-16T19:17:30+0200, Paul-Antoine Arras <[email protected]> wrote:
> On 16/07/2026 16:27, Tobias Burnus wrote:
>> Regarding the documentation (current version at ...)
>> https://gcc.gnu.org/onlinedocs/gcc/OpenMP-and-OpenACC-
>> Options.html#index-fopenmp-ompt
>>
>>
>> First, I find the second part/clause of the first sentence in
>> -fopenmp-ompt-detail in particular confusing:
>>
>> Like @option{-fopenmp-ompt}, and additionally emit calls into
>> libgomp, enabling
>> OMPT dispatch callbacks that get called at the beginning of each
>> workshare chunk
>> for statically scheduled @code{for} and @code{distribute}. Requires
>> @option{-fopenmp}.
>>
>> Maybe: "On top of -fopenmp-ompt, emit additional calls into libgomp,"
>> as minimal change - or even smaller change:
>> "Like -fopenmp-ompt, emit additional calls into libgomp,"
>>
>>
>> However, I wonder whether the whole should be completely differently
>> worded;
>> for instance:
>>
>> -fopenmp-ompt
>>
>> For some OpenMP constructs
Maybe 'certain' instead of 'some'?
>> generate calls before and after the
I like in the current text that we say "calls [into libgomp]", which
intends to help the user understand what kind of calls these are?
Or, even better, as you have it below: "calls into the OpenMP runtime",
to avoid implementor-speak?
>> region instead of only on region entry. This improves the OMPT
>> tracing
Is "OMPT tracing" the correct term to use?
>> at expense of additional calls. In particular, the
>> additional calls will be added for static worksharing loops,
>> static worksharing @code{dispatch}
Shoud this probably be 'distribute' instead of 'dispatch'?
>> and the @code{single},
>> @code{masked}, and @code{master} construct.
>> Requires @option{-fopenmp}.
>>
>> -fopenmp-ompt-details
>>
>> Add additional calls into the OpenMP runtime that might affect
>> the performance
Maybe "might negatively affect performance"?
>> but further improves OMPT tracing. In particular,
>> dispatch callbacks
Should 'dispatch' get some mark-up here? Or, prefix with "OMPT"?
>> are generated at the beginning of each workshare
>> chunk for static worksharing loops and
>> static worksharing @code{dispatch}.
Again, probably 'distribute' instead of 'dispatch'?
>> This option implies
>> @option{-fopenmp-ompt}. Requires @option{-fopenmp}.
>> What do you think?
>
> I am happy to rephrase as you suggest but would like to hear from Thomas
> (who approved the original patch)
I've got no strong attachment to the current text, so if that's to be
improved, then please go ahead.
Grüße
Thomas
> and possibly from Sandra (who you
> already CC'd).
>
> Thanks,
> --
> PA
