Re: [PATCH 0/4] openacc: Async fixes

[Thomas Schwinge <thomas@codesourcery.com>]

Hi Julian!

On 2021-06-29T16:42:00-0700, Julian Brown <julian@codesourcery.com> wrote:
> This patch series contains fixes for various problems with async support
> for OpenACC at present:

Thanks, I shall be looking into these in detail, "soonish".

Some quick comments.


>  - Asynchonous host-to-device copies invoked from within libgomp
>    (target.c) could copy bad data to the target -- and the workaround
>    for that currently used in the AMD GCN target plugin could lead to
>    a different problem (a race condition).

As per discussion on Monday, I like to you moved (back?) the "ephemeral"
handling into 'libgomp/target.c:gomp_copy_host2dev'.


>  - The OpenACC profiling-interface implementation did not measure
>    asynchronous operations properly.

We'll need to be careful: (possibly, an older version of) that one we
internally had identified to be causing some issues; see the
"acc_prof-parallel-1.c intermittent failure on og10 branch" emails,
2020-07.


>  - Several test cases misuse OpenACC asynchronous support (more race
>    conditions).

Mostly ACK, but some more changes may be necessary; please see
<http://mid.mail-archive.com/87sg1s9s9l.fsf@euler.schwinge.homeip.net>
(you were CCed).

>  .../libgomp.oacc-c-c++-common/deep-copy-10.c  |  14 +-

Please provide some detail about that one ("Fix async behaviour").  It's
not obvious to me what's wrong with the current version (but I haven't
really spent time on that yet).


Grüße
 Thomas
-----------------
Mentor Graphics (Deutschland) GmbH, Arnulfstrasse 201, 80634 München Registergericht München HRB 106955, Geschäftsführer: Thomas Heurung, Frank Thürauf