From: Thomas Schwinge <thomas@codesourcery.com>
To: Julian Brown <julian@codesourcery.com>
Cc: <gcc-patches@gcc.gnu.org>, Jakub Jelinek <jakub@redhat.com>,
"Chung-Lin Tang" <cltang@codesourcery.com>
Subject: Re: [PATCH 0/4] openacc: Async fixes
Date: Wed, 30 Jun 2021 10:28:00 +0200 [thread overview]
Message-ID: <87pmw3ycxb.fsf@euler.schwinge.homeip.net> (raw)
In-Reply-To: <cover.1624987598.git.julian@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
next prev parent reply other threads:[~2021-06-30 8:28 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-29 23:42 Julian Brown
2021-06-29 23:42 ` [PATCH 1/4] openacc: Async fix for lib-94 testcase Julian Brown
2021-06-29 23:42 ` [PATCH 2/4] openacc: Fix async bugs in several OpenACC test cases Julian Brown
2021-06-29 23:52 ` Julian Brown
2021-06-29 23:42 ` [PATCH 3/4] openacc: Fix asynchronous host-to-device copies in libgomp runtime Julian Brown
2021-07-27 10:01 ` Thomas Schwinge
2023-03-10 15:22 ` Allow libgomp 'cbuf' buffering with OpenACC 'async' for 'ephemeral' data (was: [PATCH 3/4] openacc: Fix asynchronous host-to-device copies in libgomp runtime) Thomas Schwinge
2021-06-29 23:42 ` [PATCH 4/4] openacc: Profiling-interface fixes for asynchronous operations Julian Brown
2021-06-30 8:28 ` Thomas Schwinge [this message]
2021-06-30 10:40 ` [PATCH 0/4] openacc: Async fixes Julian Brown
2021-07-02 13:51 ` Julian Brown
2023-03-10 11:38 ` Thomas Schwinge
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87pmw3ycxb.fsf@euler.schwinge.homeip.net \
--to=thomas@codesourcery.com \
--cc=cltang@codesourcery.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jakub@redhat.com \
--cc=julian@codesourcery.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).