From: Tobias Burnus <tobias@codesourcery.com>
To: Thomas Schwinge <thomas@codesourcery.com>,
Gerald Pfeifer <gerald@pfeifer.com>,
Julian Brown <julian@codesourcery.com>,
Andrew Stubbs <andrew_stubbs@mentor.com>
Cc: <gcc-patches@gcc.gnu.org>
Subject: Re: [wwwdocs] gcc-12/changes.html (GCN): >1 workers per gang
Date: Tue, 10 Aug 2021 12:10:30 +0200 [thread overview]
Message-ID: <69870f64-b4e2-2f4c-8431-cff45c631cb2@codesourcery.com> (raw)
In-Reply-To: <87o8a6pube.fsf@euler.schwinge.homeip.net>
Hi all,
On 09.08.21 20:53, Gerald Pfeifer wrote:
> (Is "CU" a sufficiently established term, or might it make sense
> to spell it out?)
I don't know – but we could use "per compute unit (CU)".
On 09.08.21 16:27, Thomas Schwinge wrote:
> On 2021-08-09T15:55:07+0200, Tobias Burnus<tobias@codesourcery.com> wrote:
>> +++ b/htdocs/gcc-12/changes.html
>> + <li>When used as OpenACC device: the limitation of 1 worker per gang, 2 gangs
>> + per CU has been lifted; now up to 16 workers per gang and 40 gangs per CU
>> + are supported. (Except that the hardware limit of 40 workers total may
>> + not be exceeded.)</li>
> I haven't changed anything related to a "limitation of [...] 2 gangs per
> CU has been lifted". Maybe that has already been done earlier, maybe
> that still has to be done? I don't know -- Julian?
Looking at the current code, it has:
if (dims[0] == 0) dims[0] = get_cu_count (kernel->agent); /* Gangs. */
Thus at least when nothing else has been specified, it uses #CUs of gangs,
running on #CUs CUs, i.e. 1 gang per CU.
[OG11 – but not mainline] What's needed is something like:
dims[0] = get_cu_count (kernel->agent) * (32 / dims[1]);
which I see in OG11 – oddly, I also see there code like:
def->gdims[0] = get_cu_count (agent); // * (40 / gcn_threads);
In other words: For gangs > #CUs or >1 gang per CU, the following patch
is needed:
[OG11] https://gcc.gnu.org/g:4dcd1e1f4e6b451aac44f919b8eb3ac49292b308
[email] https://gcc.gnu.org/pipermail/gcc-patches/2020-July/550102.html
"not suitable for mainline until the multiple-worker support is merged there"
@Andrew + @Julian: Do you intent to commit it relatively soon?
Regarding the wwwdocs patch, I can hold off until that commit or reword
it to only cover the workers part.
Thanks Thomas & Gerald for the comments!
Tobias
-----------------
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634 München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht München, HRB 106955
next prev parent reply other threads:[~2021-08-10 10:10 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-09 13:55 Tobias Burnus
2021-08-09 14:27 ` Thomas Schwinge
2021-08-10 10:10 ` Tobias Burnus [this message]
2021-08-16 8:34 ` Stubbs, Andrew
2021-08-16 9:28 ` Thomas Schwinge
2021-08-09 18:53 ` Gerald Pfeifer
2022-02-02 15:39 ` Tobias Burnus
2022-02-02 16:23 ` Andrew Stubbs
2022-02-02 17:54 ` Tobias Burnus
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=69870f64-b4e2-2f4c-8431-cff45c631cb2@codesourcery.com \
--to=tobias@codesourcery.com \
--cc=andrew_stubbs@mentor.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=gerald@pfeifer.com \
--cc=julian@codesourcery.com \
--cc=thomas@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).